[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
You seem to have javascript disabled. Please note that many of the page functionalities won't work as expected without javascript enabled.
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.6
Journals
WEVJ
Special Issues
Research on Intelligent Vehicle Path Planning Algorithm
share announcement

Research on Intelligent Vehicle Path Planning Algorithm

A special issue of World Electric Vehicle Journal (ISSN 2032-6653).

Deadline for manuscript submissions: 31 October 2025 | Viewed by 34729

Special Issue Editors

Dr. Liguo Zang

E-Mail Website
Guest Editor
School of Automobile and Rail Transportation, Nanjing Institute of Technology, Nanjing 211167, China
Interests: vehicle dynamics; new energy vehicles and intelligent technology
Special Issues, Collections and Topics in MDPI journals
Dr. Leilei Zhao

E-Mail Website
Guest Editor
School of Transportation and Vehicle Engineering, Shandong University of Technology, Zibo 255000, China
Interests: vehicle engineering; vibration mechanics
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

To solve various problems such as traffic congestion, traffic safety and environmental pollution on urban roads, path planning algorithms have gradually become an important research direction in the field of intelligent transportation, receiving considerable scholarly attention. In recent years, the application and popularity of intelligent transportation has provided a rich variety of research topics for path planning algorithms. Currently, research in this are focuses on various path planning algorithms such as traditional algorithms, intelligent optimization algorithms, algorithms based on reinforcement learning, and hybrid algorithms. In order to promote academic exchanges in related technology directions and the development of advanced technologies for intelligent transportation, we are launching a Special Issue of the World Electronic Vehicle Journal on “Research on Intelligent Vehicle Path Planning” to call for papers. We encourage authors to submit research discussing the core key technical problems, the future research trends and methods of path planning algorithms in intelligent transportation.

Dr. Liguo Zang
Dr. Leilei Zhao
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. World Electric Vehicle Journal is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • intelligent vehicle
  • path planning algorithm
  • algorithmic optimization
  • obstacle avoidance
  • lane change

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (20 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

18 pages, 5255 KiB  
Article
Research on Vertical Parking Path Planning Based on Circular Arcs, Straight Lines, and Multi-Objective Evaluation Function
by Junpeng Ma and Yubin Qian
World Electr. Veh. J. 2025, 16(3), 152; https://doi.org/10.3390/wevj16030152 - 5 Mar 2025
Viewed by 90
Abstract
In the vertical parking process, the issue of turning in place due to discontinuities in path curvature is addressed by proposing an optimal reference path planning method based on circular arcs, straight lines, and a multi-objective evaluation function. This method first analyzes the [...] Read more.
In the vertical parking process, the issue of turning in place due to discontinuities in path curvature is addressed by proposing an optimal reference path planning method based on circular arcs, straight lines, and a multi-objective evaluation function. This method first analyzes the obstacle avoidance constraints between the vehicle’s outer contour and the parking space, as well as the vehicle’s kinematic constraints. The feasible driving region’s upper and lower boundaries are determined by tangent circular arcs and straight lines. Subsequently, a multi-objective evaluation function is designed, which integrates path curvature, adjustable margins at any given moment, and path length, to obtain the optimal circular arc and straight line combination within the feasible region. Finally, the path is fitted using a polynomial curve to form the optimal reference path. Simulation results demonstrate that the planned path satisfies both the continuity of path curvature and the vehicle’s kinematic constraints. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>Vehicle kinematic model.</p> Full article ">Figure 2
<p>Simplified model of a vertical parking space.</p> Full article ">Figure 3
<p>(<b>a</b>) Schematic of left boundary collision; (<b>b</b>) schematic of right boundary collision; (<b>c</b>) schematic of upper parking boundary collision; (<b>d</b>) schematic of the feasible region for vertical parking.</p> Full article ">Figure 4
<p>Analysis of the first limit value of the radius of the arc of the lower boundary of the vertical parking feasible region <math display="inline"><semantics> <mrow> <msubsup> <mrow> <mi>R</mi> </mrow> <mrow> <mn>1</mn> <mi>m</mi> <mi>i</mi> <mi>n</mi> <mn>1</mn> </mrow> <mrow> <mi>l</mi> </mrow> </msubsup> </mrow> </semantics></math>. In the path planning process, the vehicle’s pose is defined based on the coordinates of the rear axle center point, the red dash line represents the motion trajectory of the rear axle center point.</p> Full article ">Figure 5
<p>Analysis of the second limit value of the radius of the arc of the lower boundary of the vertically parked drivable area <math display="inline"><semantics> <mrow> <msubsup> <mrow> <mi>R</mi> </mrow> <mrow> <mn>1</mn> <mi>m</mi> <mi>i</mi> <mi>n</mi> <mn>2</mn> </mrow> <mrow> <mi>l</mi> </mrow> </msubsup> </mrow> </semantics></math>. In the path planning process, the vehicle’s pose is defined based on the coordinates of the rear axle center point, the red dash line represents the motion trajectory of the rear axle center point.</p> Full article ">Figure 6
<p>Vertical parking drivable area upper boundary arc radius <math display="inline"><semantics> <mrow> <msubsup> <mrow> <mi>R</mi> </mrow> <mrow> <mn>1</mn> <mi>m</mi> <mi>a</mi> <mi>x</mi> </mrow> <mrow> <mi>u</mi> </mrow> </msubsup> </mrow> </semantics></math> analysis.</p> Full article ">Figure 7
<p>Comparison of parking path lengths generated by different methods.</p> Full article ">Figure 8
<p>Comparison of computation times for parking paths generated by different methods.</p> Full article ">Figure 9
<p>Comparison of curvature smoothness of parking paths generated by different methods.</p> Full article ">Figure 10
<p>Drivable area and optimal circular arc and straight line combination for vertical parking.</p> Full article ">Figure 11
<p>Rear axle center trajectory for vertical parking after smoothing.</p> Full article ">Figure 12
<p>(<b>a</b>) The derivative of the vertical parking path curve; (<b>b</b>) the curvature of the vertical parking path curve; (<b>c</b>) the equivalent steering angle of the front wheels of the path curve; (<b>d</b>) the equivalent steering angle speed of the front wheels of the path curve.</p> Full article ">Figure 13
<p>Simulation results of vertical parking path planning.</p> Full article ">Figure 14
<p>Vertical parking path planning framework diagram.</p> Full article ">
18 pages, 2017 KiB  
Article
A Hybrid Dynamic Path-Planning Method for Obstacle Avoidance in Unmanned Aerial Vehicle-Based Power Inspection
by Zheng Huang, Chengling Jiang, Chao Shen, Bin Liu, Tao Huang and Minghui Zhang
World Electr. Veh. J. 2025, 16(1), 22; https://doi.org/10.3390/wevj16010022 - 2 Jan 2025
Viewed by 630
Abstract
Path planning for Unmanned Aerial Vehicles (UAVs) plays a critical role in power line inspection. In complex inspection environments characterized by densely distributed and dynamic obstacles, traditional path-planning algorithms struggle to ensure both efficiency and safety. To address these challenges, this study proposes [...] Read more.
Path planning for Unmanned Aerial Vehicles (UAVs) plays a critical role in power line inspection. In complex inspection environments characterized by densely distributed and dynamic obstacles, traditional path-planning algorithms struggle to ensure both efficiency and safety. To address these challenges, this study proposes a dynamic path-planning method that integrates an improved Rapidly exploring Random Tree Star (RRT*) algorithm with the Dynamic Window Approach (DWA). The proposed method includes key components such as sampling-point search, random tree growth, global path-node optimization, and local dynamic obstacle avoidance. In the sampling-point search, a target-biased search strategy is introduced to guide the random tree growth toward the target point, while an attractive function is added to enhance search efficiency. Based on a breadth-first search strategy, the path obtained is optimized to reduce path complexity. To address the RRT* algorithm’s limitation in dynamic obstacle avoidance, a local path-planning method combining the improved DWA algorithm is proposed, improving efficiency in areas with dense obstacles. Simulation results show that, compared to traditional algorithms, the proposed method achieves an 8% to 12% optimization in path length, more than 50% in node optimization, and over 95% in planning time optimization. Furthermore, in dynamic obstacle avoidance across different motion directions, the proposed method ensures effective local dynamic obstacle avoidance while minimizing global path fluctuations. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>Flowchart of TANR*-DWA algorithm.</p> Full article ">Figure 2
<p>Octree-based maps of the electric tower environment. The maps in panels (<b>a</b>–<b>c</b>) have resolutions of 3.2 m, 0.08 m, and 0.05 m, respectively.</p> Full article ">Figure 3
<p>Schematic diagram of the RRT algorithm.</p> Full article ">Figure 4
<p>Flowchart of random sampling points based on target-biased strategy.</p> Full article ">Figure 5
<p>Random tree sub-node update based on gravitational field. The different colors represent: gray for sub-nodes, purple for the starting point, green for the new sub-node, pink for the target point, and yellow for obstacles.</p> Full article ">Figure 6
<p>UAV dynamic window sampling trajectory.</p> Full article ">Figure 7
<p>Scene delineation based on octree map.</p> Full article ">Figure 8
<p>Comparison of the TANR*, RRT*, and APF-RRT* algorithms. Subplots (<b>a</b>–<b>c</b>) show the simulation results of the TANR* algorithm across the three scenarios, subplots (<b>d</b>–<b>f</b>) show the simulation results of the RRT* algorithm across the three scenarios, and subplots (<b>g</b>–<b>i</b>) show the simulation results of the APF-RRT* algorithm across the three scenarios.</p> Full article ">Figure 9
<p>Comparison of DWA and improved DWA path trajectories. Subplots (<b>a</b>–<b>c</b>) show the path trajectories planned by the DWA algorithm, while subplots (<b>d</b>–<b>f</b>) show the paths planned by the improved DWA algorithm.</p> Full article ">Figure 10
<p>Global path-planning and local dynamic path-planning trajectories of the TANR*-DWA algorithm. Subplot (<b>a</b>) represents the simple scenario, subplot (<b>b</b>) represents the complex scenario, and subplot (<b>c</b>) represents the mixed scenario.</p> Full article ">
13 pages, 3378 KiB  
Article
Research on Improved YOLOv7 for Traffic Obstacle Detection
by Yifan Yang, Song Cui, Xuan Xiang, Yuxing Bai, Liguo Zang and Hongshan Ding
World Electr. Veh. J. 2025, 16(1), 1; https://doi.org/10.3390/wevj16010001 - 24 Dec 2024
Viewed by 1205
Abstract
Object detection and recognition algorithms are widely used in applications such as real-time monitoring and autonomous driving. However, there is limited research on traffic obstacle detection in complex scenarios involving road construction and sudden accidents. This gap results in low accuracy and difficulties [...] Read more.
Object detection and recognition algorithms are widely used in applications such as real-time monitoring and autonomous driving. However, there is limited research on traffic obstacle detection in complex scenarios involving road construction and sudden accidents. This gap results in low accuracy and difficulties in recognizing occluded targets, thereby hindering the further development and widespread adoption of intelligent transportation systems. To address these issues, this paper proposes an improved algorithm based on YOLOv7, incorporating a lightweight coordinate attention mechanism to focus on small objects at long distances and capture target location information. The use of a high receptive field enhances the feature hierarchy within the detection network. Additionally, we introduce the focal efficient intersection over union loss function to address sample imbalance, which accelerates the model’s convergence speed, reduces loss values, and improves overall model stability. Our model achieved a detection accuracy of 98.1%, reflecting a 1.4% increase, while also enhancing detection speed and minimizing missed detections. These advancements significantly bolster the model’s performance, demonstrating advantages for real-world applications. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>YOLOv7 Network Structure.</p> Full article ">Figure 2
<p>Improved YOLOv7 Network Structure.</p> Full article ">Figure 3
<p>Coordinate Attention Mechanism.</p> Full article ">Figure 4
<p>P-R Curve of Different Algorithm: (<b>a</b>) Original, (<b>b</b>) Improved YOLOv7.</p> Full article ">Figure 5
<p>Heat Map Evaluation Indexes of Different Algorithms (<b>a</b>) Original; (<b>b</b>) Detection; (<b>c</b>) Thermal map; (<b>d</b>) Thermal map + CAttention.</p> Full article ">Figure 5 Cont.
<p>Heat Map Evaluation Indexes of Different Algorithms (<b>a</b>) Original; (<b>b</b>) Detection; (<b>c</b>) Thermal map; (<b>d</b>) Thermal map + CAttention.</p> Full article ">Figure 6
<p>Comparison of Loss Function Curves of Various Models.</p> Full article ">Figure 7
<p>Visualization Comparison of Detection Results (<b>a</b>) Original; (<b>b</b>) Improved.</p> Full article ">
13 pages, 498 KiB  
Article
Path Planning for Unmanned Aerial Vehicles in Dynamic Environments: A Novel Approach Using Improved A* and Grey Wolf Optimizer
by Ali Haidar Ahmad, Oussama Zahwe, Abbass Nasser and Benoit Clement
World Electr. Veh. J. 2024, 15(11), 531; https://doi.org/10.3390/wevj15110531 - 18 Nov 2024
Cited by 1 | Viewed by 1389
Abstract
Unmanned aerial vehicles (UAVs) play pivotal roles in various applications, from surveillance to delivery services. Efficient path planning for UAVs in dynamic environments with obstacles and moving landing stations is essential to ensure safe and reliable operations. In this study, we propose a [...] Read more.
Unmanned aerial vehicles (UAVs) play pivotal roles in various applications, from surveillance to delivery services. Efficient path planning for UAVs in dynamic environments with obstacles and moving landing stations is essential to ensure safe and reliable operations. In this study, we propose a novel approach that combines the A* algorithm with the grey wolf optimizer (GWO) for path planning, referred to as GW-A*. Our approach enhances the traditional A algorithm by incorporating weighted nodes, where the weights are determined based on the distance from obstacles and further optimized using GWO. A simulation using dynamic factors such as wind direction and wind speed, which affect the quadrotor UAV in the presence of obstacles, was used to test the new approach, and we compared it with the A* algorithm using various heuristics. The results showed that GW-A* outperformed A* in most scenarios with high and low wind speeds, offering more efficient paths and greater adaptability. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>GWO calculation algorithm.</p> Full article ">Figure 2
<p>The flowchart of the proposed approach (GW-A*).</p> Full article ">Figure 3
<p>Grid layout code snippet.</p> Full article ">Figure 4
<p>Visual representation of the grid layout.</p> Full article ">Figure 5
<p>Performance comparison between GW-A* and A* across incremental wind speed ranges from 0 to 6 m/s, with an impact angle of 45°.</p> Full article ">
32 pages, 5678 KiB  
Article
Anti-Collision Path Planning and Tracking of Autonomous Vehicle Based on Optimized Artificial Potential Field and Discrete LQR Algorithm
by Chaoxia Zhang, Zhihao Chen, Xingjiao Li and Ting Zhao
World Electr. Veh. J. 2024, 15(11), 522; https://doi.org/10.3390/wevj15110522 - 14 Nov 2024
Viewed by 1567
Abstract
This paper introduces an enhanced APF method to address challenges in automatic lane changing and collision avoidance for autonomous vehicles, targeting issues of infeasible target points, local optimization, inadequate safety margins, and instability when using DLQR. By integrating a distance adjustment factor, this [...] Read more.
This paper introduces an enhanced APF method to address challenges in automatic lane changing and collision avoidance for autonomous vehicles, targeting issues of infeasible target points, local optimization, inadequate safety margins, and instability when using DLQR. By integrating a distance adjustment factor, this research aims to rectify traditional APF limitations. A safety distance model and a sub-target virtual potential field are established to facilitate collision-free path generation for autonomous vehicles. A path tracking system is designed, combining feed-forward control with DLQR. Linearization and discretization of the vehicle’s dynamic state space model, with constraint variables set to minimize control-command costs, aligns with DLQR objectives. The aim is precise steering angle determination for path tracking, negating lateral errors due to external disturbances. A Simulink–CarSim co-simulation platform is utilized for obstacle and speed scenarios, validating the autonomous vehicle’s dynamic hazard avoidance, lane changing, and overtaking capabilities. The refined APF method enhances path safety, smoothness, and stability. Experimental data across three speeds reveal reasonable steering angle and lateral deflection angle variations. The controller ensures stable reference path tracking at 40, 50, and 60 km/h around various obstacles, verifying the controller’s effectiveness and driving stability. Comparative analysis of visual trajectories pre-optimization and post-optimization highlights improvements. Vehicle roll and sideslip angle peaks, roll-angle fluctuation, and front/rear wheel steering vertical support forces are compared with traditional LQR, validating the optimized controller’s enhancement of vehicle performance. Simulation results using MATLAB/Simulink and CarSim demonstrate that the optimized controller reduces steering angles by 5 to 10°, decreases sideslip angles by 3 to 5°, and increases vertical support forces from 1000 to 1450 N, showcasing our algorithm’s superior obstacle avoidance and lane-changing capabilities under dynamic conditions. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>Principle of autonomous collision avoidance.</p> Full article ">Figure 2
<p>APF three-dimensional potential field. Figure (<b>a</b>) shows the attractive potential field of the target point. Figure (<b>b</b>) shows the repulsive potential field of the static obstacle. Figure (<b>c</b>) shows the repulsive potential field of the dynamic obstacle.</p> Full article ">Figure 3
<p>Sub-target virtual potential field.</p> Full article ">Figure 4
<p>Contour maps of potential fields and collision-free trajectories.</p> Full article ">Figure 5
<p>Principles of vehicle dynamics.</p> Full article ">Figure 6
<p>Framework of DLQR tracking control algorithm.</p> Full article ">Figure 7
<p>Optimizing APF for overtaking and collision avoidance. (<b>a</b>) Changing lanes with combined force; (<b>b</b>) changing lanes to overtake; (<b>c</b>) lane change and passing complete; (<b>d</b>) return to main lane; (<b>e</b>) drive smoothly to the target point.</p> Full article ">Figure 7 Cont.
<p>Optimizing APF for overtaking and collision avoidance. (<b>a</b>) Changing lanes with combined force; (<b>b</b>) changing lanes to overtake; (<b>c</b>) lane change and passing complete; (<b>d</b>) return to main lane; (<b>e</b>) drive smoothly to the target point.</p> Full article ">Figure 8
<p>Body dimensions.</p> Full article ">Figure 9
<p>CarSim parameter configuration and Simulink algorithm module co-simulation platform.</p> Full article ">Figure 10
<p>Comparison of obstacle avoidance trajectories of artificial potential field method before and after optimization.</p> Full article ">Figure 11
<p>Simulation analysis of obstacle avoidance in different obstacle scenarios.</p> Full article ">Figure 12
<p>The results of lateral angle data of vehicle before optimization.</p> Full article ">Figure 12 Cont.
<p>The results of lateral angle data of vehicle before optimization.</p> Full article ">Figure 13
<p>The results of lateral angle data of vehicle after optimization.</p> Full article ">Figure 13 Cont.
<p>The results of lateral angle data of vehicle after optimization.</p> Full article ">Figure 14
<p>Vehicle lateral slip angle data before optimization.</p> Full article ">Figure 14 Cont.
<p>Vehicle lateral slip angle data before optimization.</p> Full article ">Figure 15
<p>Vehicle lateral slip angle data following optimization.</p> Full article ">Figure 15 Cont.
<p>Vehicle lateral slip angle data following optimization.</p> Full article ">Figure 16
<p>Numerical analysis of the vertical support force data of the front and rear wheels of the vehicle before optimization.</p> Full article ">Figure 16 Cont.
<p>Numerical analysis of the vertical support force data of the front and rear wheels of the vehicle before optimization.</p> Full article ">Figure 17
<p>Numerical analysis of the vertical support force data of the front and rear wheels of the vehicle after optimization.</p> Full article ">Figure 17 Cont.
<p>Numerical analysis of the vertical support force data of the front and rear wheels of the vehicle after optimization.</p> Full article ">
14 pages, 3069 KiB  
Article
An Improved RRT Path-Planning Algorithm Based on Vehicle Lane-Change Trajectory Data
by Jianlong Li, Bingzheng Liu, Dong Guo, Xianjie Gao and Pengwei Wang
World Electr. Veh. J. 2024, 15(11), 481; https://doi.org/10.3390/wevj15110481 - 23 Oct 2024
Cited by 1 | Viewed by 1313
Abstract
The Rapidly-exploring Random Tree (RRT) algorithm faces issues in path planning, including low search efficiency, high randomness, and suboptimal path quality. To overcome these issues, this paper proposes an improved RRT planning algorithm based on vehicle lane change trajectory data. This algorithm dynamically [...] Read more.
The Rapidly-exploring Random Tree (RRT) algorithm faces issues in path planning, including low search efficiency, high randomness, and suboptimal path quality. To overcome these issues, this paper proposes an improved RRT planning algorithm based on vehicle lane change trajectory data. This algorithm dynamically adjusts the sampling area based on road environment and trajectory change laws, allowing the random tree to sample within an effective area, thereby improving the algorithm’s sampling efficiency. After determining the sampling area, a sampling point optimization strategy is used to enhance sampling quality, resulting in a smoother and more executable path. Finally, the vehicle is processed in a standardized manner to further improve path safety. Simulation results indicate that, compared to the original RRT algorithm, the improved version reduces nodes, planning time, and path length by 12.77%, 64.79%, and 12.87%, respectively. It also improves path smoothness and more closely aligns with actual lane-change trajectories, demonstrating the effectiveness and executability of the improved algorithm. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>Lane change diagram.</p> Full article ">Figure 2
<p>Comparison chart of lateral and longitudinal coordinates before and after smoothing.</p> Full article ">Figure 3
<p>Diagram of sampling area Adjustment. (<b>a</b>) Schematic diagram of the variation of the sampling area; (<b>b</b>) sampling area.</p> Full article ">Figure 4
<p>Diagram of sampling point optimization strategy.</p> Full article ">Figure 5
<p>Comparison of trajectory clusters.</p> Full article ">Figure 6
<p>Vehicle normalization. (<b>a</b>) Envelope circle regularization; (<b>b</b>) Elliptical regularization.</p> Full article ">Figure 7
<p>Parameter comparison. (<b>a</b>,<b>b</b>) The simulation experiments under Scenario 1; (<b>c</b>,<b>d</b>) The simulation experiments under Scenario 2.</p> Full article ">Figure 8
<p>Sampling boundary comparison.</p> Full article ">Figure 9
<p>Path Planning simulation comparison. (<b>a</b>) Left lane change; (<b>b</b>) Right lane change.</p> Full article ">Figure 10
<p>Comparison of iteration counts between two algorithms.</p> Full article ">Figure 11
<p>Trajectory comparison chart.</p> Full article ">
17 pages, 1679 KiB  
Article
Vehicle Route Planning of Diverse Cargo Types in Urban Logistics Based on Enhanced Ant Colony Optimization
by Lingling Tan, Kequan Zhu and Junkai Yi
World Electr. Veh. J. 2024, 15(9), 405; https://doi.org/10.3390/wevj15090405 - 4 Sep 2024
Viewed by 1126
Abstract
In the realm of urban logistics, optimizing vehicle routes for varied cargo types—including refrigerated, fragile, and standard cargo—poses significant challenges amid complex urban infrastructures and heterogeneous vehicle capacities. This research paper introduces a novel model for the multi-type capacitated vehicle routing problem (MT-CVRP) [...] Read more.
In the realm of urban logistics, optimizing vehicle routes for varied cargo types—including refrigerated, fragile, and standard cargo—poses significant challenges amid complex urban infrastructures and heterogeneous vehicle capacities. This research paper introduces a novel model for the multi-type capacitated vehicle routing problem (MT-CVRP) that harnesses an advanced ant colony optimization algorithm, dubbed Lévy-EGACO. This algorithm integrates Lévy flights and elitist guiding principles, enhancing search efficacy and pheromone update processes. The primary objective of this study is to minimize overall transportation costs while optimizing the efficiency of intricate route planning for vehicles with diverse load capacities. Through rigorous simulation experiments, we corroborated the validity of the proposed model and the effectiveness of the Lévy-EGACO algorithm in optimizing urban cargo transportation routes. Lévy-EGACO demonstrated a consistent reduction in transportation costs, ranging from 1.8% to 2.5% compared to other algorithms, across different test scenarios following base data modifications. These findings reveal that Lévy-EGACO substantially improves route optimization, presenting a robust solution to the challenges of MT-CVRP within urban logistics frameworks. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>Vehicle addition and site relocation.</p> Full article ">Figure 2
<p>Lévy flight trajectory image.</p> Full article ">Figure 3
<p>Lévy flight and elitist guidance process.</p> Full article ">Figure 4
<p>Schematic diagram of distribution sites.</p> Full article ">
19 pages, 1384 KiB  
Article
Energy-Aware 3D Path Planning by Autonomous Ground Vehicle in Wireless Sensor Networks
by Omer Melih Gul
World Electr. Veh. J. 2024, 15(9), 383; https://doi.org/10.3390/wevj15090383 - 24 Aug 2024
Cited by 2 | Viewed by 1018
Abstract
Wireless sensor networks are used to monitor the environment, to detect anomalies or any other problems and risks in the system. If used in the transportation network, they can monitor traffic and detect traffic risks. In wireless sensor networks, energy constraints must be [...] Read more.
Wireless sensor networks are used to monitor the environment, to detect anomalies or any other problems and risks in the system. If used in the transportation network, they can monitor traffic and detect traffic risks. In wireless sensor networks, energy constraints must be handled to enable continuous environmental monitoring and surveillance data gathering and communication. Energy-aware path planning of autonomous ground vehicle charging for sensor nodes can solve energy and battery replacement problems. This paper uses the Nearest Neighbour algorithm for the energy-aware path planning problem with an autonomous ground vehicle. Path planning simulations show that the Nearest Neighbour algorithm converges faster and produces a better solution than the genetic algorithm. We offer robust and energy-efficient path planning algorithms to swiftly collect sensor data with less energy, allowing the monitoring system to respond faster to anomalies. Positioning communicating sensors closer minimizes their energy usage and improves the network lifetime. This study also considers the scenario in which it is recommended to avoid taking direct travelling pathways between particular node pairs for a variety of different reasons. To address this more challenging scenario, we provide an Obstacle-Avoided Nearest Neighbour-based approach that has been adapted from the Nearest Neighbour approach. Within the context of this technique, the direct paths that connect the nodes are restricted. Even in this case, the Obstacle-Avoided Nearest Neighbour-based approach achieves almost the same performance as the the Neighbour-based approach. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>In this wireless sensor network (WSN), an automated guided vehicle (AGV) is utilized to collect data from all fifteen sensors (S1, S2,…, S15) that are monitoring the environment with the purpose of identifying anomalies and dangers in order to decrease the likelihood of accidents occurring. Following the completion of the compilation of all of the data, they should be transmitted to the data sink, which is the entity that is accountable for collecting all of the data and evaluating them.</p> Full article ">Figure 2
<p>Locations of sensors.</p> Full article ">Figure 3
<p>Achieved path planning solution by Nearest Neighbour.</p> Full article ">Figure 4
<p>Achieved path planning solution with GA in 1000 iterations.</p> Full article ">Figure 5
<p>Achieved path planning solution with GWO in 1000 iterations.</p> Full article ">Figure 6
<p>Achieved path lengths for visiting 100 nodes with NN-based approach, GWO-based approach, and GA-based approach in 1000 iterations.</p> Full article ">Figure 7
<p>The coordinates of the 100 sensor nodes.</p> Full article ">Figure 8
<p>Achieved path planning solution with NN-based approach.</p> Full article ">Figure 9
<p>The achieved (10,803 m) path planning solution for visiting the 100 nodes with the GA in 1000 iterations.</p> Full article ">Figure 10
<p>The achieved (17,794 m) path planning solution for visiting the 100 nodes with the GWO in 1000 iterations.</p> Full article ">Figure 11
<p>The achieved path lengths for visiting the 100 nodes by all the algorithms (NN-based approach, GWO-based approach, and GA-based approach) in 1000 iterations.</p> Full article ">Figure 12
<p>Achieved path planning solution for visiting the 50 nodes by AUV with OANN under limitations.</p> Full article ">Figure 13
<p>Achieved path planning solution for visiting the 100 nodes by AUV with OANN under limitations.</p> Full article ">
30 pages, 9113 KiB  
Article
Research on Unmanned Vehicle Path Planning Based on the Fusion of an Improved Rapidly Exploring Random Tree Algorithm and an Improved Dynamic Window Approach Algorithm
by Shuang Wang, Gang Li and Boju Liu
World Electr. Veh. J. 2024, 15(7), 292; https://doi.org/10.3390/wevj15070292 - 30 Jun 2024
Cited by 3 | Viewed by 1379
Abstract
Aiming at the problem that the traditional rapidly exploring random tree (RRT) algorithm only considers the global path of unmanned vehicles in a static environment, which has the limitation of not being able to avoid unknown dynamic obstacles in real time, and that [...] Read more.
Aiming at the problem that the traditional rapidly exploring random tree (RRT) algorithm only considers the global path of unmanned vehicles in a static environment, which has the limitation of not being able to avoid unknown dynamic obstacles in real time, and that the traditional dynamic window approach (DWA) algorithm is prone to fall into a local optimum during local path planning, this paper proposes a path planning method for unmanned vehicles that integrates improved RRT and DWA algorithms. The RRT algorithm is improved by introducing strategies such as target-biased random sampling, adaptive step size, and adaptive radius node screening, which enhance the efficiency and safety of path planning. The global path key points generated by the improved RRT algorithm are used as the subtarget points of the DWA algorithm, and the DWA algorithm is optimized through the design of an adaptive evaluation function weighting method based on real-time obstacle distances to achieve more reasonable local path planning. Through simulation experiments, the fusion algorithm shows promising results in a variety of typical static and dynamic mixed driving scenarios, can effectively plan a path that meets the driving requirements of an unmanned vehicle, avoids unknown dynamic obstacles, and shows higher path optimization efficiency and driving stability in complex environments, which provides strong support for an unmanned vehicle’s path planning in complex environments. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>Schematic diagram of the search path of the RRT algorithm.</p> Full article ">Figure 2
<p>Obstacle regularization.</p> Full article ">Figure 3
<p>Vehicle kinematics modeling.</p> Full article ">Figure 4
<p>Nodal angle diagram.</p> Full article ">Figure 5
<p>Before and after corner restraints. (<b>a</b>) Pre-restraint; (<b>b</b>) post-restraint.</p> Full article ">Figure 6
<p>Schematic diagram of collision detection.</p> Full article ">Figure 7
<p>Schematic diagram of the numerical differentiation method.</p> Full article ">Figure 8
<p>Adaptive radius node schematic.</p> Full article ">Figure 9
<p>Greedy strategy schematic.</p> Full article ">Figure 10
<p>Flowchart of the enhanced RRT algorithm.</p> Full article ">Figure 11
<p>Simulation results of intersection turnaround experiment. (<b>a</b>) Traditional RRT algorithm; (<b>b</b>) RRT* algorithm; (<b>c</b>) RRT-connect algorithm; (<b>d</b>) improved algorithm in this paper.</p> Full article ">Figure 12
<p>Schematic representation of the results search space.</p> Full article ">Figure 13
<p>Global path critical point extraction process.</p> Full article ">Figure 14
<p>Schematic diagram of the dynamic window algorithm.</p> Full article ">Figure 15
<p>These are maps showing a “C”-shaped obstacle. (<b>a</b>) Traditional DWA planning failure; (<b>b</b>) improved DWA planning success.</p> Full article ">Figure 16
<p>This is a static simulation of the scenarios. (<b>a</b>) Parking lot scenario; (<b>b</b>) roundabout U-turn scenario; (<b>c</b>) intersection left-turn scenario; (<b>d</b>) obstacle-avoidance lane-change scenario.</p> Full article ">Figure 17
<p>This is the simulation result of the parking lot exit tracking scenario. (<b>a</b>) RRT and DWA fusion algorithms. (<b>b</b>) Improvement of the DWA algorithm. (<b>c</b>) This paper improves the fusion algorithm.</p> Full article ">Figure 18
<p>These are graphs of linear velocity, angular velocity, and time. (<b>a</b>) Comparison of linear velocity changes; (<b>b</b>) comparison of angular velocity changes.</p> Full article ">Figure 19
<p>This is the simulation result of the roundabout turning scenario. (<b>a</b>) RRT and DWA fusion algorithms. (<b>b</b>) Improvement of the DWA algorithm. (<b>c</b>) This paper improves the fusion algorithm.</p> Full article ">Figure 20
<p>These are graphs of linear velocity, angular velocity, and time. (<b>a</b>) Comparison of linear velocity changes; (<b>b</b>) comparison of angular velocity changes.</p> Full article ">Figure 21
<p>This is the simulation result of the intersection left-turn scenario. (<b>a</b>) RRT and DWA fusion algorithms. (<b>b</b>) Improvement of the DWA algorithm. (<b>c</b>) This paper improves the fusion algorithm.</p> Full article ">Figure 22
<p>These are graphs of linear velocity, angular velocity, and time. (<b>a</b>) Comparison of linear velocity changes; (<b>b</b>) comparison of angular velocity changes.</p> Full article ">Figure 23
<p>This is the simulation result of the lane-change avoidance scenario. (<b>a</b>) RRT and DWA fusion algorithms. (<b>b</b>) Improvement of the DWA algorithm. (<b>c</b>) This paper improves the fusion algorithm.</p> Full article ">Figure 24
<p>This is a graph of linear velocity, angular velocity, and time. (<b>a</b>) Comparison of linear velocity changes; (<b>b</b>) comparison of angular velocity changes.</p> Full article ">
23 pages, 15041 KiB  
Article
Research on Obstacle Avoidance Trajectory Planning for Autonomous Vehicles on Structured Roads
by Yunlong Li, Gang Li and Kang Peng
World Electr. Veh. J. 2024, 15(4), 168; https://doi.org/10.3390/wevj15040168 - 17 Apr 2024
Cited by 2 | Viewed by 2156
Abstract
This paper focuses on the obstacle avoidance trajectory planning problem for autonomous vehicles on structured roads. The objective is to design a trajectory planning algorithm that can ensure vehicle safety and comfort and satisfy the rationality of traffic regulations. This paper proposes a [...] Read more.
This paper focuses on the obstacle avoidance trajectory planning problem for autonomous vehicles on structured roads. The objective is to design a trajectory planning algorithm that can ensure vehicle safety and comfort and satisfy the rationality of traffic regulations. This paper proposes a path and speed decoupled planning method for non-split vehicle trajectory planning on structured roads. Firstly, the path planning layer adopts the improved artificial potential field method. The obstacle-repulsive potential field, gravitational potential field, and fitting method of the traditional artificial potential field are improved. Secondly, the speed planning aspect is performed in the Frenet coordinate system. Speed planning is accomplished based on S-T graph construction and solving convex optimization problems. Finally, simulation and experimental verification are performed. The results show that the method proposed in this paper can significantly improve the safety and comfortable riding of the vehicle. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>Schematic graph of structured roads.</p> Full article ">Figure 2
<p>Left-turn road map of the total potential field.</p> Full article ">Figure 3
<p>Planned path guided by a single-point gravitational potential field.</p> Full article ">Figure 4
<p>Schematic of global gravitational point distribution.</p> Full article ">Figure 5
<p>Planned path guided by the global gravitational potential field.</p> Full article ">Figure 6
<p>Distribution of obstacle-repulsive potential field for different parameters: (<b>a</b>) <math display="inline"><semantics> <mrow> <mi>H</mi> <mo>=</mo> <mn>30</mn> <mo>,</mo> <msub> <mi>σ</mi> <mrow> <mi>x</mi> <mi>g</mi> </mrow> </msub> <mo>=</mo> <mn>5</mn> <mo>,</mo> <msub> <mi>σ</mi> <mrow> <mi>y</mi> <mi>g</mi> </mrow> </msub> <mo>=</mo> <mn>5</mn> </mrow> </semantics></math>. (<b>b</b>) <math display="inline"><semantics> <mrow> <mi>H</mi> <mo>=</mo> <mn>30</mn> <mo>,</mo> <msub> <mi>σ</mi> <mrow> <mi>x</mi> <mi>g</mi> </mrow> </msub> <mo>=</mo> <mn>10</mn> <mo>,</mo> <msub> <mi>σ</mi> <mrow> <mi>y</mi> <mi>g</mi> </mrow> </msub> <mo>=</mo> <mn>10</mn> </mrow> </semantics></math>. (<b>c</b>) <math display="inline"><semantics> <mrow> <mi>H</mi> <mo>=</mo> <mrow> <mn>50</mn> <mo>,</mo> </mrow> <msub> <mi>σ</mi> <mrow> <mi>x</mi> <mi>g</mi> </mrow> </msub> <mo>=</mo> <mn>5</mn> <mo>,</mo> <msub> <mi>σ</mi> <mrow> <mi>y</mi> <mi>g</mi> </mrow> </msub> <mo>=</mo> <mn>5</mn> </mrow> </semantics></math>. (<b>d</b>) <math display="inline"><semantics> <mrow> <mi>H</mi> <mo>=</mo> <mn>50</mn> <mo>,</mo> <msub> <mi>σ</mi> <mrow> <mi>x</mi> <mi>g</mi> </mrow> </msub> <mo>=</mo> <mn>10</mn> <mo>,</mo> <msub> <mi>σ</mi> <mrow> <mi>y</mi> <mi>g</mi> </mrow> </msub> <mo>=</mo> <mn>10</mn> </mrow> </semantics></math>.</p> Full article ">Figure 7
<p>Schematic graph of the safety ellipse.</p> Full article ">Figure 8
<p>The planning results for different repulsive potential fields, which include the following: (<b>a</b>) the range is a circle; (<b>b</b>) the range is an ellipse.</p> Full article ">Figure 9
<p>The obstacle-repulsive potential field range is a deformed ellipse.</p> Full article ">Figure 10
<p>Path fitting before and after comparison.</p> Full article ">Figure 11
<p>Schematic S-T graph.</p> Full article ">Figure 12
<p>Schematic graph of dynamic planning.</p> Full article ">Figure 13
<p>Dynamic and static obstacle avoidance simulation flowchart.</p> Full article ">Figure 14
<p>Schematic graph of the Panosim platform setup scenario and road patching.</p> Full article ">Figure 15
<p>The results of different algorithmic planning: (<b>a</b>) Potential field distribution of the C-APF algorithm. (<b>b</b>) Path planned by the E-APF algorithm. (<b>c</b>) Path planned by the DE-APF algorithm.</p> Full article ">Figure 16
<p>Paths planned by different algorithms.</p> Full article ">Figure 17
<p>Trend graphs of the paths planned by different algorithms: (<b>a</b>) Curvature and curvature ratio change rate of the paths. (<b>b</b>) Yaw angle and rate of change in the yaw angle of the paths.</p> Full article ">Figure 18
<p>The process of avoiding moving and static obstacles.</p> Full article ">Figure 19
<p>The results of planning under dynamic and quadratic planning: (<b>a</b>) S−T graph. (<b>b</b>) Speed of planning. (<b>c</b>) The state of acceleration. (<b>d</b>) The state of the first−order derivative of the acceleration–jerk.</p> Full article ">Figure 20
<p>Schematic graph of experimental scenes and working condition.</p> Full article ">Figure 21
<p>Schematic graph of the ROS intelligent microvehicle.</p> Full article ">Figure 22
<p>Planning results for the different algorithms.</p> Full article ">Figure 23
<p>Trend graphs of the paths planned by the different algorithms: (<b>a</b>) Curvature and curvature change rate of the paths. (<b>b</b>) Yaw angle and rate of change in the yaw angle of the paths.</p> Full article ">Figure 24
<p>Intelligent microvehicle status information: (<b>a</b>) The state of speed. (<b>b</b>) The state of acceleration. (<b>c</b>) The state of the first-order derivative of the acceleration–jerk.</p> Full article ">Figure 24 Cont.
<p>Intelligent microvehicle status information: (<b>a</b>) The state of speed. (<b>b</b>) The state of acceleration. (<b>c</b>) The state of the first-order derivative of the acceleration–jerk.</p> Full article ">
21 pages, 15213 KiB  
Article
Omnidirectional AGV Path Planning Based on Improved Genetic Algorithm
by Qinyu Niu, Yao Fu and Xinwei Dong
World Electr. Veh. J. 2024, 15(4), 166; https://doi.org/10.3390/wevj15040166 - 16 Apr 2024
Cited by 4 | Viewed by 1631
Abstract
To address the issues with traditional genetic algorithm (GA) path planning, which often results in redundant path nodes and local optima, we propose an Improved Genetic Algorithm that incorporates an ant colony algorithm (ACO). Firstly, a new population initialization method is proposed. This [...] Read more.
To address the issues with traditional genetic algorithm (GA) path planning, which often results in redundant path nodes and local optima, we propose an Improved Genetic Algorithm that incorporates an ant colony algorithm (ACO). Firstly, a new population initialization method is proposed. This method adopts a higher-quality random point generation strategy to generate random points centrally near the start and end of connecting lines. It combines the improved ACO algorithm to connect these random points quickly, thus greatly improving the quality of the initial population. Secondly, path smoothness constraints are proposed in the adaptive function. These constraints reduce the large-angle turns and non-essential turns, improving the smoothness of the generated path. The algorithm integrates the roulette and tournament methods in the selection stage to enhance the searching ability and prevent premature convergence. Additionally, the crossover stage introduces the edit distance and a two-layer crossover operation based on it to avoid ineffective crossover and improve convergence speed. In the mutation stage, we propose a new mutation method and introduce a three-stage mutation operation based on the idea of simulated annealing. This makes the mutation operation more effective and efficient. The three-stage mutation operation ensures that the mutated paths also have high weights, increases the diversity of the population, and avoids local optimality. Additionally, we added a deletion operation to eliminate redundant nodes in the paths and shorten them. The simulation software and experimental platform of ROS (Robot Operating System) demonstrate that the improved algorithm has better path search quality and faster convergence speed. This effectively prevents the algorithm from maturing prematurely and proves its effectiveness in solving the path planning problem of AGV (automated guided vehicle). Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>Genetic algorithm robot motion trajectory.</p> Full article ">Figure 2
<p>Population initialization.</p> Full article ">Figure 3
<p>Flowchart of cross-operations based on edit distance.</p> Full article ">Figure 4
<p>Improved variant operation.</p> Full article ">Figure 5
<p>Improved variant operation flowchart.</p> Full article ">Figure 6
<p>Delete the road map before and after the operation is processed.</p> Full article ">Figure 7
<p>Flowchart for improving the algorithm.</p> Full article ">Figure 8
<p>GA algorithm planning path under 30 × 30 map.</p> Full article ">Figure 9
<p>Ref. [<a href="#B2-wevj-15-00166" class="html-bibr">2</a>] algorithm planning path under 30 × 30 map.</p> Full article ">Figure 10
<p>IGA algorithm path planning under 30 × 30 map.</p> Full article ">Figure 11
<p>Comparison of path length iterations under 30 × 30 map.</p> Full article ">Figure 12
<p>Iterative comparison chart of the number of turns under 30 × 30 map.</p> Full article ">Figure 13
<p>Smoothness iteration comparison chart under 30 × 30 map.</p> Full article ">Figure 14
<p>Fitness iteration comparison chart under 30 × 30 map.</p> Full article ">Figure 15
<p>The GA algorithm plans the path under 40 × 40 map.</p> Full article ">Figure 16
<p>Ref. [<a href="#B2-wevj-15-00166" class="html-bibr">2</a>] algorithm planning path under 40 × 40 map.</p> Full article ">Figure 17
<p>IGA algorithm path planning under 40 × 40 map.</p> Full article ">Figure 18
<p>Path length iteration comparison chart under 40 × 40 map.</p> Full article ">Figure 19
<p>Iteration comparison chart of the number of turns under 40 × 40 map.</p> Full article ">Figure 20
<p>Smoothness iteration comparison chart under 40 × 40 map.</p> Full article ">Figure 21
<p>Fitness iteration comparison chart under 40 × 40 map.</p> Full article ">Figure 22
<p>Omnidirectional AGV experimental platform.</p> Full article ">Figure 23
<p>Experimental scene.</p> Full article ">Figure 24
<p>GA algorithm planning path1.</p> Full article ">Figure 25
<p>IGA algorithm planning path2.</p> Full article ">Figure 26
<p>GA algorithm planning path3.</p> Full article ">Figure 27
<p>IGA algorithm planning path4.</p> Full article ">
16 pages, 2311 KiB  
Article
Adaptive MPC-Based Lateral Path-Tracking Control for Automatic Vehicles
by Shaobo Yang, Yubin Qian, Wenhao Hu, Jiejie Xu and Hongtao Sun
World Electr. Veh. J. 2024, 15(3), 95; https://doi.org/10.3390/wevj15030095 - 4 Mar 2024
Cited by 3 | Viewed by 2394
Abstract
For continuously changing road conditions and vehicle operating states, the exactitude of vehicle path tracking has not been secured by model predictive control based on linear lateral stiffness. An amended square root cubature Kalman filter method based on the minimization of a new [...] Read more.
For continuously changing road conditions and vehicle operating states, the exactitude of vehicle path tracking has not been secured by model predictive control based on linear lateral stiffness. An amended square root cubature Kalman filter method based on the minimization of a new covariance of interest is proposed to calculate the tire lateral deflection force in real time. The ratio of the estimated tire force to the linear tire force was used as a ratio to adjust the lateral deflection stiffness, and an adaptive model predictive controller was built based on the vehicle path-tracking error model to correct the tire lateral deflection stiffness. Finally, an analysis based on the joint CarSim and Simulink simulation platform shows that compared to a conventional model predictive control (MPC) controller, a trajectory-following controller built based on this method can effectively reduce the lateral distance error and heading error of an autonomous vehicle. Especially under low adhesion conditions, the conventional MPC controllers will demonstrate large instability during trajectory tracking due to the deviation of the linear tire force calculation results, whereas the adaptive model predictive control (AMPC) controllers can correct the side deflection stiffness by estimating the tire force and still achieve stable and effective tracking of the target trajectory. This suggests that the proposed algorithm can improve the effectiveness of trajectory tracking control for autonomous vehicles, which is an important reference value for the optimization of autonomous vehicle control systems. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>2-DOF vehicle dynamics model.</p> Full article ">Figure 2
<p>Path-tracking model that considers trajectory curvature.</p> Full article ">Figure 3
<p>Schematic diagram of tire lateral force.</p> Full article ">Figure 4
<p>Results of tire lateral force estimation. (<b>a</b>) Front axle lateral force. (<b>b</b>) Rear axle lateral force.</p> Full article ">Figure 5
<p>Architecture of the path-tracing AMPC controller.</p> Full article ">Figure 6
<p>Control effect of high-attachment double-shift line condition. (<b>a</b>) Trajectory tracking of vehicles; (<b>b</b>) lateral position error; (<b>c</b>) heading angle error; (<b>d</b>) yaw rate.</p> Full article ">Figure 7
<p>Control effect of low-attachment double-shift line condition. The notes for (<b>a</b>–<b>d</b>) are the same as in <a href="#wevj-15-00095-f006" class="html-fig">Figure 6</a>.</p> Full article ">Figure 8
<p>Time spent on each step of the solution.</p> Full article ">
23 pages, 744 KiB  
Article
Heuristic Algorithms for Heterogeneous and Multi-Trip Electric Vehicle Routing Problem with Pickup and Delivery
by Li Wang, Yifan Ding, Zhiyuan Chen, Zhiyuan Su and Yufeng Zhuang
World Electr. Veh. J. 2024, 15(2), 69; https://doi.org/10.3390/wevj15020069 - 15 Feb 2024
Cited by 2 | Viewed by 2143
Abstract
In light of the widespread use of electric vehicles for urban distribution, this paper delves into the electric vehicle routing problem (EVRP): specifically addressing multiple trips per vehicle, diverse vehicle types, and simultaneous pickup and delivery. The primary objective is to minimize the [...] Read more.
In light of the widespread use of electric vehicles for urban distribution, this paper delves into the electric vehicle routing problem (EVRP): specifically addressing multiple trips per vehicle, diverse vehicle types, and simultaneous pickup and delivery. The primary objective is to minimize the overall cost, which encompasses travel expenses, waiting times, recharging costs, and fixed vehicle costs. The focal problem is formulated as a heterogeneous and multi-trip electric vehicle routing problem with pickup and delivery (H-MT-EVRP-PD). Additionally, we introduce two heuristic algorithms to efficiently approximate solutions within a reasonable computational time. The variable neighborhood search (VNS) algorithm and the adaptive large neighborhood search (ALNS) algorithm are presented and compared based on our computational experiences with both. Through solving a series of large-scale real-world instances for the H-MT-EVRP-PD and smaller instances using an exact method, we demonstrate the efficacy of the proposed approaches. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>Graph of size and cost.</p> Full article ">Figure 2
<p>Iteration time and cost trend of optimal solution.</p> Full article ">Figure 3
<p>Variance of the algorithm.</p> Full article ">Figure 4
<p>Partition optimization comparison results.</p> Full article ">Figure 5
<p>The time series diagram of partitioning and non-partitioning experiments.</p> Full article ">Figure 6
<p>Sequence diagram of partitioning experiment cost and number of iterations.</p> Full article ">Figure 7
<p>Customer service time and cost diagram.</p> Full article ">Figure 8
<p>Bar chart of the relationship between vehicle range and electricity costs.</p> Full article ">Figure 9
<p>Vehicle average charging time diagram.</p> Full article ">
21 pages, 6890 KiB  
Article
Obstacle Avoidance Trajectory Planning for Autonomous Vehicles on Urban Roads Based on Gaussian Pseudo-Spectral Method
by Zhenfeng Li, Xuncheng Wu, Weiwei Zhang and Wangpengfei Yu
World Electr. Veh. J. 2024, 15(1), 7; https://doi.org/10.3390/wevj15010007 - 26 Dec 2023
Cited by 2 | Viewed by 2551
Abstract
Urban autonomous vehicles on city roads are subject to various constraints when changing lanes, and commonly used trajectory planning methods struggle to describe these conditions accurately and directly. Therefore, generating accurate and adaptable trajectories is crucial for safer and more efficient trajectory planning. [...] Read more.
Urban autonomous vehicles on city roads are subject to various constraints when changing lanes, and commonly used trajectory planning methods struggle to describe these conditions accurately and directly. Therefore, generating accurate and adaptable trajectories is crucial for safer and more efficient trajectory planning. This study proposes an optimal control model for local path planning that integrates dynamic vehicle constraints and boundary conditions into the optimization problem’s constraint set. Using the lane-changing scenario as a basis, this study establishes environmental and collision avoidance constraints during driving and develops a performance metric that optimizes both time and turning angle. The study employs the Gauss pseudo-spectral method to continuously discretize the state and control variables, converting the optimal control problem into a nonlinear programming problem. Using numerical solutions, variable control and state trajectories that satisfy multiple constraint conditions while optimizing the performance metric are generated. The study employs two weights in the experiment to evaluate the method’s performance, and the findings demonstrate that the proposed method guarantees safe obstacle avoidance, is stable, and is computationally efficient at various interpolation points compared to the Legendre pseudo-spectral method (LPM) and the Shooting method. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>Vehicle kinematic model (The red part represents the simplified bicycle model).</p> Full article ">Figure 2
<p>Minimum longitudinal safety distance.</p> Full article ">Figure 3
<p>Minimum lateral safety distance.</p> Full article ">Figure 4
<p>Intersection over Union (IoU) based object classification ((<b>a</b>) shows a vertex of the red car invading the blue car contour line, (<b>b</b>) shows a vertex of the blue car invading the red contour line, and (<b>c</b>) shows all vertices of the vehicles invading each other, covering all initial collisions).</p> Full article ">Figure 5
<p>Construction of contour and vertex position relation diagram based on coordinate system.</p> Full article ">Figure 6
<p>Collision constraint model diagram for vehicle and roadside edges (1) <math display="inline"><semantics> <mrow> <mi>y</mi> <mo>=</mo> <mi>L</mi> <mi>A</mi> </mrow> </semantics></math>. (The green part represents the edge of the road, and the red dashed line represents the mapping of the four vertices of the vehicle to the edge of the road).</p> Full article ">Figure 7
<p>Collision constraint model diagram for vehicle and roadside edges (2) <math display="inline"><semantics> <mrow> <mi>x</mi> <mo>=</mo> <mi>L</mi> <mi>O</mi> </mrow> </semantics></math>. (The green part represents the edge of the road, and the red dashed line represents the mapping of the four vertices of the vehicle to the edge of the road).</p> Full article ">Figure 8
<p>Illustration of urban road setup and obstacle avoidance for autonomous vehicles. (Red represents lane changing vehicles, blue represents normal driving vehicles, and above is information on the vehicles changing lanes in the time domain).</p> Full article ">Figure 9
<p>Main categories of solutions to optimal control problems. (The red arrow represents the optimal control using the direct method, which discretizes the state variables and control variables in the problem. The Gaussian pseudospectral method in the point matching method is used for point matching, transforming the discretized problem into a nonlinear programming problem, and then using numerical solutions).</p> Full article ">Figure 10
<p>Trajectory Planning Based on Gaussian Pseudo-spectral Method.</p> Full article ">Figure 11
<p>The generated trajectory map of the test 1.</p> Full article ">Figure 12
<p>The generated trajectory map of the test 2.</p> Full article ">Figure 13
<p>Image (<b>A</b>) displays the variation in the x-coordinate of the position beneath test 1 and test 2; Image (<b>B</b>) displays the variation in the Y-coordinate of the position beneath test 1 and test 2; Image (<b>C</b>) displays the variation in the heading angle state of the test 1 and test 2; Image (<b>D</b>) displays the variation in the yaw angle state of the test 1 and test 2; Image (<b>E</b>) displays the variation in the linear velocity of the test 1 and test 2. All of the above are state variables.</p> Full article ">Figure 14
<p>Image (<b>A</b>) displays the variation in the angular control of the test 1 and test 2, Image (<b>B</b>) displays the variation in the linear acceleration of the test 1 and test 2. All of the above are control variables.</p> Full article ">Figure 15
<p>A comparison of minimum distance quantization is presented.</p> Full article ">Figure 16
<p>Presents a comparison of the velocity for LPM, GPM, and DSSSM at 17 and 31 interpolation points.</p> Full article ">
26 pages, 4313 KiB  
Article
Utilizing Probabilistic Maps and Unscented-Kalman-Filtering-Based Sensor Fusion for Real-Time Monte Carlo Localization
by Wael A. Farag and Julien Moussa H. Barakat
World Electr. Veh. J. 2024, 15(1), 5; https://doi.org/10.3390/wevj15010005 - 21 Dec 2023
Cited by 2 | Viewed by 2191
Abstract
An autonomous car must know where it is with high precision in order to maneuver safely and reliably in both urban and highway environments. Thus, in this paper, a reliable and relatively precise position estimation (localization) technique for autonomous vehicles is proposed and [...] Read more.
An autonomous car must know where it is with high precision in order to maneuver safely and reliably in both urban and highway environments. Thus, in this paper, a reliable and relatively precise position estimation (localization) technique for autonomous vehicles is proposed and implemented. In dealing with the obtained sensory data or given knowledge about the vehicle’s surroundings, the proposed method takes a probabilistic approach. In this approach, the involved probability densities are expressed by keeping a collection of samples selected at random from them (Monte Carlo simulation). Consequently, this Monte Carlo sampling allows the resultant position estimates to be represented with any arbitrary distribution, not only a Gaussian one. The selected technique to implement this Monte-Carlo-based localization is Bayesian filtering with particle-based density representations (i.e., particle filters). The employed particle filter receives the surrounding object ranges from a carefully tuned Unscented Kalman Filter (UKF) that is used to fuse radar and lidar sensory readings. The sensory readings are used to detect pole-like static objects in the egocar’s surroundings and compare them to the ones that exist in a supplied detailed reference map that contains pole-like landmarks that are produced offline and extracted from a 3D lidar scan. Comprehensive simulation tests were conducted to evaluate the outcome of the proposed technique in both lateral and longitudinal localization. The results show that the proposed technique outperforms the other techniques in terms of smaller lateral and longitudinal mean position errors. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>The RTMCL workflow.</p> Full article ">Figure 2
<p>Workflow of the UKF.</p> Full article ">Figure 3
<p>The motion model of an arbitrarily moving road object.</p> Full article ">Figure 4
<p>The workflow of the UK for lidar and radar fusion.</p> Full article ">Figure 5
<p>Overview and a flowchart of the particle filter algorithm.</p> Full article ">Figure 6
<p>Egocar localization outcomes in the shown test track.</p> Full article ">Figure 7
<p>Egocar orientation (yaw angle) estimation and ground truth in the testing track.</p> Full article ">Figure 8
<p>Performance of the yaw rate and speed of the egocar through a 3 − lap driving on the testing track (blue is the yaw rate and red is the speed).</p> Full article ">Figure 9
<p>Errors decay throughout the PF start-up phase.</p> Full article ">Figure 10
<p>The distribution of particles’ weights during a single-lap tour by the egocar.</p> Full article ">Figure 11
<p>The distribution of detected poles (red dots) during a single-lap touring by the egocar.</p> Full article ">
21 pages, 752 KiB  
Article
A GRASP Approach for the Energy-Minimizing Electric Vehicle Routing Problem with Drones
by Nikolaos A. Kyriakakis, Themistoklis Stamadianos, Magdalene Marinaki and Yannis Marinakis
World Electr. Veh. J. 2023, 14(12), 354; https://doi.org/10.3390/wevj14120354 - 18 Dec 2023
Cited by 2 | Viewed by 2276
Abstract
This study addresses the Electric Vehicle Routing Problem with Drones (EVRPD) by implementing and comparing two variants of the Greedy Randomized Adaptive Search Procedure (GRASP). The primary objective of the EVRPD is to optimize the routing of a combined fleet of ground and [...] Read more.
This study addresses the Electric Vehicle Routing Problem with Drones (EVRPD) by implementing and comparing two variants of the Greedy Randomized Adaptive Search Procedure (GRASP). The primary objective of the EVRPD is to optimize the routing of a combined fleet of ground and aerial vehicles, with the aim of improving delivery efficiency and minimizing energy consumption, which is directly influenced by the weight of the packages. The study assumes a standardized packing system consisting of three weight classes, where deliveries are exclusively performed by drones, while ground vehicles function as mobile depots. The two employed GRASP variants vary in their methods of generating the Restricted Candidate List (RCL), with one utilizing a cardinality-based RCL and the other adopting a value-based RCL. To evaluate their performance, benchmark instances from the existing EVRPD literature are utilized, extensive computational experiments are conducted, and the obtained computational results are compared and discussed. The findings of the research highlight the considerable impact of RCL generation strategies on solution quality. Lastly, the study reports four new best-known values. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>Route example of the EVRPD (<span class="html-italic">d</span> is the arc distance, <span class="html-italic">f</span> is the arc payload weight, <span class="html-italic">p</span> is the package’s weight class, <span class="html-italic">s</span>, <math display="inline"><semantics> <msup> <mi>s</mi> <mo>′</mo> </msup> </semantics></math> are the starting and ending nodes, respectively and 1, 2, 3 are the intermediate nodes).</p> Full article ">Figure 2
<p>An example of the EVRPD solution.</p> Full article ">Figure 3
<p>Gap% of solutions to the best solution found for each instance with different parameter settings.</p> Full article ">Figure 4
<p>Gap% of best solution obtained to the best previously known solution for each instance.</p> Full article ">Figure 5
<p>Gap% of average solution obtained to the best previously known solution for each instance.</p> Full article ">Figure 6
<p>Average computational time required for each instance per algorithm variant.</p> Full article ">
19 pages, 4083 KiB  
Article
Research on Intelligent Vehicle Motion Planning Based on Pedestrian Future Trajectories
by Pan Liu, Guoguo Du, Yongqiang Chang and Minghui Liu
World Electr. Veh. J. 2023, 14(12), 320; https://doi.org/10.3390/wevj14120320 - 23 Nov 2023
Viewed by 2056
Abstract
This work proposes an improved pedestrian social force model for pedestrian trajectory prediction to prevent intelligent vehicles from colliding with pedestrians while driving on the road. In this model, the intelligent vehicle performs motion planning on the basis of predicted pedestrian trajectory results. [...] Read more.
This work proposes an improved pedestrian social force model for pedestrian trajectory prediction to prevent intelligent vehicles from colliding with pedestrians while driving on the road. In this model, the intelligent vehicle performs motion planning on the basis of predicted pedestrian trajectory results. A path is planned by using the fifth-order Bezier curve, the optimal coordinate is acquired by adjusting the weight coefficient of each optimisation goal, and the optimal driving trajectory curve is planned. In speed planning, the pedestrian collision boundary is proposed to ensure pedestrian safety. The initial speed planning is performed by a dynamic programming algorithm, and then the optimal speed curve is obtained by quadratic programming. Finally, the front pedestrian deceleration or uniform speed scene is set for simulation verification. Simulation results show that the vehicle speed reaches a maximum value of 6.39 m/s under the premise of ensuring safety and that the average speed of the intelligent vehicle is 4.6 m/s after a normal start process. The maximum and average speed values obtained with trajectory prediction indicate that the intelligent vehicle ensures pedestrian and vehicle safety as well as the intelligent vehicle’s economy. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>Schematic diagram of self-driving force.</p> Full article ">Figure 2
<p>Schematic diagram of the force between pedestrians.</p> Full article ">Figure 3
<p>Schematic diagram of pedestrian anisotropy.</p> Full article ">Figure 4
<p>Schematic diagram of pedestrian–vehicle interaction force.</p> Full article ">Figure 5
<p>Road boundary constraints.</p> Full article ">Figure 6
<p>The fifth-order Bezier curve trajectory diagram.</p> Full article ">Figure 7
<p>The schematic diagram of local path planning.</p> Full article ">Figure 8
<p>Diagram of the pedestrian collision boundary.</p> Full article ">Figure 9
<p>S–T diagram and speed planning diagram.</p> Full article ">Figure 10
<p>Dynamic programming discretisation schematic diagram.</p> Full article ">Figure 11
<p>Diagram of intelligent vehicle motion planning in the scenario of forward pedestrian deceleration or uniform speed.</p> Full article ">Figure 12
<p>Pedestrian trajectory prediction diagram.</p> Full article ">Figure 13
<p>Optimal motion trajectory curve.</p> Full article ">Figure 14
<p>Speed curve.</p> Full article ">Figure 15
<p>Longitudinal acceleration curve.</p> Full article ">Figure 16
<p>Lateral acceleration curve.</p> Full article ">Figure 17
<p>Heading angle curve.</p> Full article ">
21 pages, 9112 KiB  
Article
Study on Lane-Change Replanning and Trajectory Tracking for Intelligent Vehicles Based on Model Predictive Control
by Yaohua Li, Dengwang Zhai, Jikang Fan and Guoqing Dong
World Electr. Veh. J. 2023, 14(9), 234; https://doi.org/10.3390/wevj14090234 - 24 Aug 2023
Cited by 2 | Viewed by 2096
Abstract
When an intelligent vehicle changes lanes, the state of other vehicles may change, which increases the risk of collision. Therefore, real-time local path replanning is needed at this time. Based on model predictive control (MPC), a lane-change trajectory replanning strategy was proposed, which [...] Read more.
When an intelligent vehicle changes lanes, the state of other vehicles may change, which increases the risk of collision. Therefore, real-time local path replanning is needed at this time. Based on model predictive control (MPC), a lane-change trajectory replanning strategy was proposed, which was divided into a lane-change trajectory correction strategy, a lane-change switchback strategy and forward active collision avoidance strategy according to collision risk. Based on the collision risk function of the rectangular safety neighborhood, the objective functions were designed according to the specific requirements of different strategies. The vehicle lateral controller based on MPC and the vehicle longitudinal motion controller were established. The longitudinal velocity was taken as the joint point to establish the lateral and longitudinal integrated controller. The trajectory planning module, trajectory replanning module and trajectory tracking module were integrated in layers, and the three trajectory replanning strategies of lane-change trajectory correction, lane-change switchback and forward active collision avoidance were respectively simulated and verified. The simulation results showed the trajectory replanning strategy achieves collision avoidance under different scenarios and ensures the vehicle’s driving stability. The trajectory tracking layer achieves accurate tracking of the conventional lane-change trajectory and has good driving stability and comfort. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>Schematic diagram of vehicle lane-change environment model.</p> Full article ">Figure 2
<p>Lane-change trajectory correction diagram.</p> Full article ">Figure 3
<p>Diagram showing trajectory when changing lanes to turn back.</p> Full article ">Figure 4
<p>Forward active collision avoidance diagram.</p> Full article ">Figure 5
<p>Lane-change replanning strategy.</p> Full article ">Figure 6
<p>Three-degrees-of-freedom dynamics model.</p> Full article ">Figure 7
<p>Longitudinal velocity controller.</p> Full article ">Figure 8
<p>Integrated lateral and longitudinal controller.</p> Full article ">Figure 9
<p>Integrated control of lane change.</p> Full article ">Figure 10
<p>The original lane-change trajectory vehicle location relationship diagram.</p> Full article ">Figure 11
<p>(<b>a</b>) Original planning trajectory and actual replanning trajectory. (<b>b</b>) Side slip angle. (<b>c</b>) Yaw velocity. (<b>d</b>) <math display="inline"><semantics> <mrow> <mi>β</mi> <mo>−</mo> <mover accent="true"> <mi>β</mi> <mo>˙</mo> </mover> </mrow> </semantics></math> Phase plane.</p> Full article ">Figure 12
<p>Vehicle position relationship diagram after lane-change trajectory correction.</p> Full article ">Figure 13
<p>Vehicle position relationship diagram before lane-change trajectory correction.</p> Full article ">Figure 14
<p>The simulation results of changing lanes and turning back. (<b>a</b>) Original planning trajectory and actual replanning trajectory. (<b>b</b>) Side slip angle. (<b>c</b>) Yaw velocity. (<b>d</b>) <math display="inline"><semantics> <mrow> <mi>β</mi> <mo>−</mo> <mover accent="true"> <mi>β</mi> <mo>˙</mo> </mover> </mrow> </semantics></math> Phase plane.</p> Full article ">Figure 15
<p>The simulation results of the deceleration and turnback conditions. (<b>a</b>) Original planning trajectory and actual replanning trajectory. (<b>b</b>) Side slip angle. (<b>c</b>) Yaw velocity. (<b>d</b>) <math display="inline"><semantics> <mrow> <mi>β</mi> <mo>−</mo> <mover accent="true"> <mi>β</mi> <mo>˙</mo> </mover> </mrow> </semantics></math> Phase plane. (<b>e</b>) Longitudinal velocity deviation. (<b>f</b>) Frictional circle constraint.</p> Full article ">Figure 16
<p>The simulation results of forward active collision avoidance conditions. (<b>a</b>) Original planning trajectory and actual replanning trajectory. (<b>b</b>) Side slip angle. (<b>c</b>) Yaw velocity. (<b>d</b>) <math display="inline"><semantics> <mrow> <mi>β</mi> <mo>−</mo> <mover accent="true"> <mi>β</mi> <mo>˙</mo> </mover> </mrow> </semantics></math> Phase plane. (<b>e</b>) Longitudinal velocity deviation. (<b>f</b>) Frictional circle constraint.</p> Full article ">
17 pages, 2561 KiB  
Article
Electric Logistics Vehicle Path Planning Based on the Fusion of the Improved A-Star Algorithm and Dynamic Window Approach
by Mengxue Yu, Qiang Luo, Haibao Wang and Yushu Lai
World Electr. Veh. J. 2023, 14(8), 213; https://doi.org/10.3390/wevj14080213 - 10 Aug 2023
Cited by 9 | Viewed by 1916
Abstract
The study of path-planning algorithms is crucial for an electric logistics vehicle to reach its target point quickly and safely. In light of this, this work suggests a novel path-planning technique based on the improved A-star (A*) fusion dynamic window approach (DWA). First, [...] Read more.
The study of path-planning algorithms is crucial for an electric logistics vehicle to reach its target point quickly and safely. In light of this, this work suggests a novel path-planning technique based on the improved A-star (A*) fusion dynamic window approach (DWA). First, compared to the A* algorithm, the upgraded A* algorithm not only avoids the obstruction border but also removes unnecessary nodes and minimizes turning angles. Then, the DWA algorithm is fused with the enhanced A* algorithm to achieve dynamic obstacle avoidance. In addition to RVIZ of ROS, MATLAB simulates and verifies the upgraded A* algorithm and the A* fused DWA. The MATLAB simulation results demonstrate that the approach based on the enhanced A* algorithm combined with DWA not only shortens the path by 4.56% when compared to the A* algorithm but also smooths the path and has dynamic obstacle-avoidance capabilities. The path length is cut by 8.99% and the search time is cut by 16.26% when compared to the DWA. The findings demonstrate that the enhanced method in this study successfully addresses the issues that the A* algorithm’s path is not smooth, dynamic obstacle avoidance cannot be performed, and DWA cannot be both globally optimal. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>Schematic of the three distance formulas.</p> Full article ">Figure 2
<p>(<b>a</b>) Diagram of an unoptimized approach; (<b>b</b>) Primary path optimization diagram; (<b>c</b>) Secondary path optimization diagram; (<b>d</b>) Tertiary path optimization diagram.</p> Full article ">Figure 3
<p>(<b>a</b>) Motion trajectory analysis diagram of electric logistics vehicle; (<b>b</b>) Speed sampling space.</p> Full article ">Figure 4
<p>Flow chart of path planning using an enhanced A* algorithm and DWA.</p> Full article ">Figure 5
<p>Simulation validation of the improved A* algorithm (The figure references the 2017 article by Cheng et al. for comparison [<a href="#B5-wevj-14-00213" class="html-bibr">5</a>]): (<b>a</b>) 20 × 20 map scene 1; (<b>b</b>) 20 × 20 map scene 2 (<b>c</b>) 20 × 20 map scene 3.</p> Full article ">Figure 6
<p>Comparison Chart of Path Planning using DWA (The figure references the 2020 article by Wu et al. for comparison [<a href="#B27-wevj-14-00213" class="html-bibr">27</a>]): (<b>a</b>) Process for improving the A* fusion DWA algorithm; (<b>b</b>) Static obstacle path-planning diagram; (<b>c</b>) Dynamic obstacle path-planning diagram.</p> Full article ">Figure 7
<p>Comparing the linear velocity, angular velocity, and attitude angle of various algorithms (unknown static and dynamic obstacles. (The figure references the 2020 article by Wu et al. for comparison [<a href="#B27-wevj-14-00213" class="html-bibr">27</a>]): (<b>a</b>) Angular velocity diagram of four algorithms electric logistics vehicle; (<b>b</b>) Linear velocity diagram of four algorithms electric logistics vehicle; (<b>c</b>) Attitude angle diagram of four algorithms electric logistics vehicle.</p> Full article ">Figure 7 Cont.
<p>Comparing the linear velocity, angular velocity, and attitude angle of various algorithms (unknown static and dynamic obstacles. (The figure references the 2020 article by Wu et al. for comparison [<a href="#B27-wevj-14-00213" class="html-bibr">27</a>]): (<b>a</b>) Angular velocity diagram of four algorithms electric logistics vehicle; (<b>b</b>) Linear velocity diagram of four algorithms electric logistics vehicle; (<b>c</b>) Attitude angle diagram of four algorithms electric logistics vehicle.</p> Full article ">Figure 8
<p>Three algorithms path-planning diagram: (<b>a</b>) A* algorithm path-planning diagram; (<b>b</b>) Improved A* algorithm path-planning diagram; (<b>c</b>) Improved A* algorithm fused with DWA algorithm path-planning diagram.</p> Full article ">Figure 9
<p>SLAM mapping path-planning map: (<b>a</b>) Unimproved algorithm path-planning map; (<b>b</b>) Improved algorithm path-planning map.</p> Full article ">

Review

Jump to: Research

27 pages, 5099 KiB  
Review
Path Planning Algorithms for Smart Parking: Review and Prospects
by Zhonghai Han, Haotian Sun, Junfu Huang, Jiejie Xu, Yu Tang and Xintian Liu
World Electr. Veh. J. 2024, 15(7), 322; https://doi.org/10.3390/wevj15070322 - 20 Jul 2024
Cited by 3 | Viewed by 2093
Abstract
Path planning algorithms are crucial components in the process of smart parking. At present, there are many path planning algorithms designed for smart parking. A well-designed path planning algorithm has a significant impact on the efficiency of smart parking. Firstly, this paper comprehensively [...] Read more.
Path planning algorithms are crucial components in the process of smart parking. At present, there are many path planning algorithms designed for smart parking. A well-designed path planning algorithm has a significant impact on the efficiency of smart parking. Firstly, this paper comprehensively describes the principles and steps of four types of path planning algorithms: the Dijkstra algorithm (including its optimized derivatives), the A* algorithm (including its optimized derivatives), the RRT (Rapidly exploring Random Trees) algorithm (including its optimized derivatives), and the BFS (Breadth First Search) algorithm. Secondly, the Dijkstra algorithm, the A* algorithm, the BFS algorithm, and the Dynamic Weighted A* algorithm were utilized to plan the paths required for the process of smart parking. During the analysis, it was found that the Dijkstra algorithm had the drawbacks of planning circuitous paths and taking too much time in the path planning for smart parking. Although the traditional A* algorithm based on the Dijkstra algorithm had greatly reduced the planning time, the effect of path planning was still unsatisfactory. The BFS (Breadth First Search) algorithm had the shortest planning time among the four algorithms, but the paths it plans were unstable and not optimal. The Dynamic Weighted A* algorithm could achieve better path planning results, and with adjustments to the weight values, this algorithm had excellent adaptability. This review provides a reference for further research on path planning algorithms in the process of smart parking. Full article
(This article belongs to the Special Issue Research on Intelligent Vehicle Path Planning Algorithm)
►▼ Show Figures

Figure 1

Figure 1
<p>Path planning algorithm classification diagram.</p> Full article ">Figure 2
<p>Dijkstra algorithm directed graph.</p> Full article ">Figure 3
<p>Dijkstra algorithm flowchart.</p> Full article ">Figure 4
<p>Node expansion directions.</p> Full article ">Figure 5
<p>A* algorithm flowchart.</p> Full article ">Figure 6
<p>The three-dimensional A* algorithm flowchart.</p> Full article ">Figure 7
<p>RRT algorithm schematic diagram.</p> Full article ">Figure 8
<p>Bi-RRT algorithm schematic diagram.</p> Full article ">Figure 9
<p><math display="inline"><semantics> <mrow> <mi>θ</mi> <mo>−</mo> <mi>c</mi> <mi>u</mi> <mi>t</mi> </mrow> </semantics></math> mechanism.</p> Full article ">Figure 10
<p>Shortest path finding process.</p> Full article ">Figure 11
<p>The time results of five runs of the four path planning algorithms.</p> Full article ">Figure 12
<p>The distance results of five runs of the four path planning algorithms.</p> Full article ">Figure 13
<p>The distributions of the max, min, and avg values in terms of time.</p> Full article ">Figure 14
<p>The distributions of the max, min, and avg values in terms of distance.</p> Full article ">Figure 15
<p>Paths planned by the Dijkstra.</p> Full article ">Figure 16
<p>Paths planned by the A*.</p> Full article ">Figure 17
<p>Paths planned by the Dynamic Weighted A*.</p> Full article ">Figure 18
<p>Paths planned by the BFS.</p> Full article ">
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-20
Back to TopTop