CN117826825B - Unmanned mining card local path planning method and system based on artificial potential field algorithm - Google Patents
Unmanned mining card local path planning method and system based on artificial potential field algorithm Download PDFInfo
- Publication number
- CN117826825B CN117826825B CN202410224077.0A CN202410224077A CN117826825B CN 117826825 B CN117826825 B CN 117826825B CN 202410224077 A CN202410224077 A CN 202410224077A CN 117826825 B CN117826825 B CN 117826825B
- Authority
- CN
- China
- Prior art keywords
- potential field
- obstacle
- path
- path planning
- vehicle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000005065 mining Methods 0.000 title claims abstract description 49
- 230000004888 barrier function Effects 0.000 claims abstract description 7
- 230000007613 environmental effect Effects 0.000 claims abstract description 6
- 230000006870 function Effects 0.000 claims description 21
- 238000010276 construction Methods 0.000 claims description 16
- 238000005457 optimization Methods 0.000 claims description 13
- 230000009471 action Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 239000002245 particle Substances 0.000 claims description 3
- 230000033001 locomotion Effects 0.000 abstract description 7
- 230000000694 effects Effects 0.000 abstract description 4
- 238000004364 calculation method Methods 0.000 abstract description 3
- 239000003795 chemical substances by application Substances 0.000 description 7
- 230000008569 process Effects 0.000 description 4
- 230000037237 body shape Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 241000408659 Darpa Species 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000005381 potential energy Methods 0.000 description 1
- 230000007115 recruitment Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an unmanned mining card local path planning method and system based on an artificial potential field algorithm, and relates to the technical field of unmanned mining card control, wherein the unmanned mining card local path planning method comprises the steps of configuring a data sensor to collect environmental data, vehicle running state data and barrier information; establishing an obstacle elliptical potential field based on an improved artificial potential field algorithm, and completing target modeling of a target point based on an obstacle point; and introducing lane keeping constraint, a shortest path principle, an optimal curvature principle and path heading constraint to carry out path planning. According to the unmanned mining card local path planning method based on the artificial potential field algorithm, the influence of the shape of the vehicle body is considered, the effect of the elliptical potential field in the whole obstacle vehicle potential field is selected, the method for establishing the symmetrical point obstacle model ensures that local target points are on a symmetrical axis, the calculation result is more accurate and is fit with reality, and the mining card movement is more flexible and safer. The invention has better effects in the aspects of safety, flexibility and applicability.
Description
Technical Field
The invention relates to the technical field of unmanned mining card control, in particular to an unmanned mining card local path planning method and system based on an artificial potential field algorithm.
Background
The mining truck is an important carrier for transportation in a mining area, under normal conditions, when the mining truck runs on a mining area lane, a relatively stable distance is kept, the vehicle speed is in a safe interval, but the mining area is complex and various in weather, severe in working environment and frequent in accidents, the road state is greatly influenced by the factors, the problem of deviation from a normal channel is possibly caused, the vehicle speed is unstable, traffic accidents are easily caused, the mining area safety, the worker safety and the driving safety are negatively influenced, and a certain difficulty is caused for traffic dispersion. Therefore, along with the annual promotion of national requirements for intelligent and safe construction of mines, in order to ensure the running safety of vehicles, the errors of manual driving mine cards are reduced, and the unmanned system is introduced, so that the personnel safety risk caused by transportation can be effectively reduced, and the problem of difficulty in recruitment can be thoroughly solved. Because mine roads are poor in road conditions, unstructured barriers are more, and the requirements of a road surface tracking obstacle avoidance algorithm are different from structured road scenes, the method has great significance in considering unmanned mining card local path planning. The path planning function is the basis of autonomous driving of the intelligent automobile, and the common path planning algorithm for the automatic driving automobile mainly comprises a planning algorithm based on searching, a planning algorithm based on random sampling, a planning algorithm based on curve interpolation and a planning algorithm based on numerical optimization. Montemerlo M et al describe an improved Hybrid a algorithm based on the a algorithm, which generates a four-dimensional vector set of vehicle coordinates, vehicle heading angle and vehicle movement direction to describe the vehicle state, solving the discrete problem that the conventional a algorithm does not meet the vehicle driving requirement. The PRM algorithm is used for sampling, the point which is farthest from the obstacle in each sampling is reserved, the subsequent path connection and search are carried out, the path generated by the algorithm can be effectively far away from the obstacle, and the path safety is improved. Kuwata Y et al analyzed the motion planning subsystem in DARPA race and proposed an improved RRT algorithm that keeps the vehicle running safely with uncertainty and limited perception. The curve interpolation adopts different methods to carry out path smoothing and curve generation, but the problems of boundary constraint and the like are difficult to process. The numerical optimization-based method takes motion planning as a mathematical optimization problem, and the planning result is continuous, optimal and space-time. However, since the vehicle kinematic model is nonlinear and the collision avoidance constraints are non-convex, the solution of the optimization problem is very difficult and inefficient, while the algorithm lacks global.
The artificial potential field method is a traditional classical path planning algorithm, has the characteristics of simple implementation, small calculated amount, smoother planned path and the like, integrates all environment information into different force sources, guides the actions of an intelligent agent through the resultant force of the different force sources, and leads the intelligent agent to be easy to fall into a minimum extreme point when the resultant force is 0, thereby causing path planning failure. The local path planning of the unmanned mining card is used for sensing road environment information through a vehicle-mounted sensor, the behavior planning of the vehicle is carried out through system decision, the path planning from the target starting point to the target ending point is completed, and the estimated tracking is completed through a vehicle controller.
The invention plans the local path of the unmanned mining card based on the improved artificial potential field algorithm, so that the shape of the planned path is smooth and natural as much as possible, and meanwhile, the planned path is ensured to be kept on a road with a certain distance from the central line, thereby laying a foundation for the control research of the unmanned mining card. The innovation aims at improving the path planning performance of the mine card, so that the mine card can safely and efficiently run in a mining area, and further development of mine intellectualization and safety is promoted.
Disclosure of Invention
The present invention has been made in view of the above-described problems.
Therefore, the technical problems solved by the invention are as follows: the existing unmanned mining card local path planning method is difficult to adapt to complex and changeable terrains, has insufficient accuracy and flexibility of a circular potential field, and can avoid the problem that the intelligent agent is easy to fall into the minimum extreme point when the resultant force is 0 when the action of the intelligent agent is guided through the resultant force of different force sources, so that the path planning failure is caused.
In order to solve the technical problems, the invention provides the following technical scheme: an unmanned mining card local path planning method based on an artificial potential field algorithm comprises the steps of configuring a data sensor to collect environment data, vehicle running state data and obstacle information; establishing an obstacle elliptical potential field based on an improved artificial potential field algorithm, and completing target modeling of a target point based on an obstacle point; and introducing lane keeping constraint, a shortest path principle, an optimal curvature principle and path heading constraint to carry out path planning.
As a preferable scheme of the unmanned mining card local path planning method based on the artificial potential field algorithm, the invention comprises the following steps: the acquisition of the environmental data, the vehicle running state data and the obstacle information comprises the steps of configuring a laser radar to acquire the position of an obstacle vehicle, configuring a vehicle-mounted camera to collect road width and lane marks, and configuring an inertia measurement unit to collect the speed, acceleration and course angle of a mine card.
As a preferable scheme of the unmanned mining card local path planning method based on the artificial potential field algorithm, the invention comprises the following steps: the establishment of the obstacle elliptical potential field based on the improved artificial potential field algorithm comprises the steps of setting a controlled mine card as a particle in a two-dimensional space, setting coordinates as X= (X, y) and setting coordinates as X g＝(xg,yg), and determining the distance from the controlled mine card to a target point, wherein the distance is expressed as:
the gravitational potential field is expressed as:
Wherein ρ g (t) represents the distance from the controlled mine card to the target point at time t, γ represents the gravitational adjustment coefficient, and k represents the gravitational field coefficient; the attraction of the controlled mine card is expressed as:
Fatt(X)＝-▽Uatt(X)＝kVg
wherein V g represents a unit vector of the controlled mine card pointing to the target point.
As a preferable scheme of the unmanned mining card local path planning method based on the artificial potential field algorithm, the invention comprises the following steps: the building of the obstacle elliptical potential field based on the improved artificial potential field algorithm further comprises the steps that if the coordinate position in the European space of the obstacle vehicle is X ob＝(xob,yob under the condition that the obstacle vehicle exists, a repulsive potential field is built by combining a harmonic function, and the repulsive potential field is expressed as:
Wherein eta and rho o are the action coefficient and the distance range of the repulsive force potential field, and rho ob represents the distance between the controlled mine card and the obstacle point; according to the repulsive potential field function, when ρ ob≤ρo, the repulsive force of the control object is expressed as:
Wherein V ob is a direction vector of the controlled mine card pointing to the obstacle point, and m represents a repulsive potential field influence parameter; when n effective obstacles exist in the space, the resultant force of the controlled mine cards is expressed as:
After the resultant force of the controlled mine cards is determined, an elliptical potential field of the obstacle truck is constructed, and the construction of the potential field is completed.
As a preferable scheme of the unmanned mining card local path planning method based on the artificial potential field algorithm, the invention comprises the following steps: the object modeling based on the obstacle point comprises the steps of performing controlled object modeling based on an improved artificial potential field algorithm, establishing an obstacle elliptical potential field, completing object modeling based on the obstacle point of a target point, taking the geometric center of an obstacle vehicle as the circle center of the elliptical potential field, and respectively taking a long axis and a short axis as a and b, wherein the obstacle potential field U truck is expressed as:
Wherein k truck is the barrier vehicle potential field stiffness, Representing the geometric center coordinates of the ith obstacle.
As a preferable scheme of the unmanned mining card local path planning method based on the artificial potential field algorithm, the invention comprises the following steps: the path planning comprises the steps of introducing lane keeping constraint, a shortest path principle, an optimal curvature principle and path heading constraint; the lane keeping constraint is expressed as a road constraint by constraining the vehicle to travel at a distance from the lane centerline:
Wherein L i represents the vehicle position of the i-th control point, L d represents the position of the lane center line, and N represents the total number of control nodes; the shortest path principle calculates the shortest path by calculating the path length variation of the adjacent control nodes, expressed as:
Where Deltax i and Deltay i represent the path length variation of the ith control point, deltax c,i and Deltay c,i represent the position variation between control nodes, A vector representation representing the path length, T representing the transpose; the optimal curvature principle simplifies the path into a path formed by connecting control nodes by a sectional natural cubic spline curve, and the path curvature is calculated in a quadratic manner, which is expressed as:
Wherein, Representing the square of the curvature of the ith path, s representing the path parameters, s * representing the normalized path parameters, x ri(s*) and y ri(s*), the position function of the ith path in the x-axis and y-axis, represented as a natural cubic spline curve, a 0i,a1i,a2i,a3i representing the coefficient controlling the shape of the ith spline curve in the x-axis, b 0i,b1i,b2i,b3i representing the coefficient controlling the shape of the ith spline curve in the y-axis, s i0 representing the starting parameter value of the ith path, Δs representing the total length of the ith path; the path course constraint is realized by controlling the course angle between adjacent nodes, and the course angle between the adjacent control nodes is expressed as:
after the constraint construction is completed, the four constraints are converted into a multi-objective optimization function.
As a preferable scheme of the unmanned mining card local path planning method based on the artificial potential field algorithm, the invention comprises the following steps: the path planning further comprises the step of converting four constraints into a multi-objective optimization function after the constraint construction is completed, wherein the four constraints are expressed as:
Wherein I is a control variable, including four constrained variation parameters, λ 1、λ2 and λ 3 represent weight coefficients.
Another object of the present invention is to provide an unmanned mining card local path planning system based on an artificial potential field algorithm, which can adjust a potential field action area of a vehicle by adopting an elliptical potential field area and take a geometric center of an obstacle vehicle as a circle center of the elliptical potential field, thereby more accurately reflecting actual conditions of the obstacle, providing a more accurate and flexible potential field adjustment mechanism for path planning, and solving the problem that the existing artificial potential field technology cannot completely fit the actual vehicle due to the fact that the potential field is not completely fit by adopting a circular potential field.
As a preferable scheme of the unmanned mining card local path planning system based on the artificial potential field algorithm, the invention comprises the following steps: the system comprises a data acquisition module, a potential field construction module and a path planning module; the data acquisition module is used for configuring the data sensor to acquire environment data, vehicle running state data and obstacle information; the potential field construction module is used for establishing an obstacle elliptical potential field based on an improved artificial potential field algorithm, and completing target modeling of a target point based on an obstacle point; the path planning module is used for introducing lane keeping constraint, a shortest path principle, an optimal curvature principle and path heading constraint to carry out path planning.
A computer device comprising a memory storing a computer program and a processor executing the computer program is the step of implementing an unmanned mining card local path planning method based on a manual potential field algorithm.
A computer readable storage medium having stored thereon a computer program which when executed by a processor implements the steps of an unmanned mining card local path planning method based on an artificial potential field algorithm.
The invention has the beneficial effects that: the unmanned mining card local path planning method based on the artificial potential field algorithm effectively performs vehicle path planning by adopting an improved artificial potential energy method so as to better adapt to complex and changeable mining area environments, and provides new possibility for improving the accuracy and adaptability of path planning. The influence of the vehicle body shape is considered, the effect of an elliptical potential field whole obstacle vehicle potential field is selected, the method for establishing the symmetric point obstacle model ensures that a local target point is on a symmetric axis, and further, path planning is carried out on the basis of a natural cubic spline curve and global optimization on the premise of meeting lane keeping constraint, shortest path principle, optimal curvature principle and path heading constraint, so that a calculation result is more accurate and is fit with reality, and movement of a mine card is more flexible and safer. The invention has better effects in the aspects of safety, flexibility and applicability.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is an overall flowchart of an unmanned mining card local path planning method based on an artificial potential field algorithm according to a first embodiment of the present invention.
Fig. 2 is a 20km/h actual motion path diagram of an unmanned mining card local path planning method based on an artificial potential field algorithm according to a second embodiment of the present invention.
Fig. 3 is a diagram of an actual motion path of 35km/h of an unmanned mining card local path planning method based on an artificial potential field algorithm according to a first embodiment of the present invention.
Fig. 4 is an overall flowchart of an unmanned mining card local path planning system based on an artificial potential field algorithm according to a third embodiment of the present invention.
Detailed Description
So that the manner in which the above recited objects, features and advantages of the present invention can be understood in detail, a more particular description of the invention, briefly summarized above, may be had by reference to the embodiments, some of which are illustrated in the appended drawings. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
Example 1
Referring to fig. 1, for one embodiment of the present invention, there is provided an unmanned mining card local path planning method based on an artificial potential field algorithm, including:
s1: the configuration data sensor collects environmental data, vehicle running state data, and obstacle information.
Furthermore, collecting the environmental data, the vehicle running state data and the obstacle information comprises configuring a laser radar to collect the position of the obstacle vehicle, configuring a vehicle-mounted camera to collect road width and lane marks, and configuring an inertial measurement unit to collect the speed, acceleration and course angle of the mine truck.
S2: and establishing an obstacle elliptical potential field based on an improved artificial potential field algorithm to complete target modeling of the target point based on the obstacle point.
Furthermore, the artificial potential field method is a traditional classical path planning algorithm, which integrates all environmental information into different force sources, and guides actions of the intelligent agent through resultant force of the different force sources, when the resultant force is 0, the intelligent agent is easy to fall into a minimum extreme point, so that path planning failure is caused. For this problem, solutions can be divided into three categories: optimizing potential field functions, escaping minimum extrema, and blending with other algorithms to solve the problem. The invention adopts the optimized potential field function to avoid the intelligent agent from sinking into the minimum extreme point, so as to better carry out path planning.
It should be noted that, the establishment of the obstacle elliptical potential field based on the improved artificial potential field algorithm includes setting the controlled mine card as the particle in the two-dimensional space and setting the coordinate as x= (X, y) and the target point coordinate as X g＝(xg,yg), determining the distance from the controlled mine card to the target point, expressed as:
the gravitational potential field is expressed as:
Wherein ρ g (t) represents the distance from the controlled mine card to the target point at time t, γ represents the gravitational adjustment coefficient, and k represents the gravitational field coefficient. The attraction of the controlled mine card is expressed as:
Fatt(X)＝-▽Uatt(X)＝kVg
wherein V g represents a unit vector of the controlled mine card pointing to the target point.
It should be further noted that, the establishment of the obstacle elliptical potential field based on the improved artificial potential field algorithm further includes if in the presence of an obstacle vehicle, the coordinate position in the European space of the obstacle vehicle is X ob＝(xob,yob), constructing a repulsive potential field in combination with the harmonic function, where the repulsive potential field is expressed as:
wherein eta and rho o are the action coefficient and the distance range of the repulsive force potential field, and rho ob represents the distance between the controlled mine truck and the obstacle point.
According to the repulsive potential field function, when ρ ob≤ρo, the repulsive force of the control object is expressed as:
Wherein V ob is the direction vector of the controlled mine card pointing to the obstacle point, and m represents the repulsive potential field influence parameter.
When n effective obstacles exist in the space, the resultant force of the controlled mine cards is expressed as:
After the resultant force of the controlled mine cards is determined, an elliptical potential field of the obstacle truck is constructed, and the construction of the potential field is completed.
Furthermore, the controlled target modeling is performed based on an improved artificial potential field algorithm, firstly, the barrier elliptical potential field is established, and the target modeling of the target point based on the barrier point is completed. By establishing an "elliptical potential field" at a conventional circular potential field in consideration of the vehicle body shape to adjust the region of action of the obstacle vehicle potential field, it is possible to distinguish from the conventional circular potential field in consideration of the obstacle vehicle body shape. The method comprises the steps of carrying out controlled target modeling based on an improved artificial potential field algorithm, establishing an obstacle elliptical potential field, completing target modeling of a target point based on an obstacle point, taking the geometric center of an obstacle vehicle as the center of the elliptical potential field, respectively taking a long axis and a short axis as a and b, and expressing an obstacle potential field U truck as:
Wherein k truck is the barrier vehicle potential field stiffness, Representing the geometric center coordinates of the ith obstacle.
S3: and introducing lane keeping constraint, a shortest path principle, an optimal curvature principle and path heading constraint to carry out path planning.
Still further, path planning includes introducing lane keeping constraints, shortest path principles, optimal curvature principles, and path heading constraints.
Lane keeping constraints are a primary consideration in path planning and are critical constraint indicators that ensure that the planned path does not deviate excessively from the lane. The constraint is introduced to effectively prevent the deviation between the path planning result and the lane from exceeding an acceptable range, so that the unmanned mine truck can be stably and safely kept in a specified lane range in the driving process. Lane keeping constraints are expressed as road constraints by constraining the vehicle to travel a distance from the lane centerline:
Where L i denotes the vehicle position of the i-th control point, L d denotes the position of the lane center line, and N denotes the total number of control nodes.
The planned path should be as safe as possible to reduce the transportation costs by reducing the path length to increase the truck transportation efficiency. The shortest path principle calculates the shortest path by calculating the path length variation of the adjacent control nodes, expressed as:
Where Deltax i and Deltay i represent the path length variation of the ith control point, deltax c,i and Deltay c,i represent the position variation between control nodes, The vector representing the path length represents the transpose, T.
A large curvature means that the vehicle needs to undergo a large change in steering angle while running, which is quite dangerous in running the vehicle. Therefore, in the path planning process, the optimal curvature principle must be followed, so that the change trend of the curvature is ensured to be gentle, and the steering in the vehicle driving process is more natural and stable. The following of the principle is helpful for reducing driving risk, improving driving safety and enabling the vehicle to finish transition more surely when the path turns. The principle of optimal curvature simplifies the path into a path formed by connecting control nodes by a sectional natural cubic spline curve, and the path curvature is calculated in a quadratic manner, which is expressed as:
Wherein, Representing the square of the curvature of the ith path, s representing the path parameters, s * representing the normalized path parameters, x ri(s*) and y ri(s*), the position function of the ith path in the x-axis and y-axis, represented as a natural cubic spline curve, a 0i,a1i,a2i,a3i representing the coefficient controlling the shape of the ith spline curve in the x-axis, b 0i,b1i,b2i,b3i representing the coefficient controlling the shape of the ith spline curve in the y-axis, s i0 representing the starting parameter value of the ith path, deltas representing the total length of the ith path.
The path heading constraint refers to path planning to ensure that the heading angle is consistent with the centerline of the lane as the vehicle travels along the centerline. This helps prevent the vehicle from deviating from the lane, ensures that the vehicle travels in a given direction, and improves the safety and stability of traveling. The path course constraint is realized by controlling the course angle between adjacent nodes, and the course angle between the adjacent control nodes is expressed as:
after the constraint construction is completed, the four constraints are converted into a multi-objective optimization function.
It should be noted that the path planning should satisfy these four constraints to ensure the rationality and safety of the planned path. Thus, the problem can be translated into a multi-objective optimization problem. The optimization objective is to make the planned path shape as smooth and natural as possible, while also ensuring that the planned path length is as short as possible and that the path orientation is as consistent as possible with the centre line of the road. In other words, it is desirable that the sum of the curvature changes of the path be minimal at the corresponding planning node, while the remaining three constraints also have minimal changes. After the constraint construction is completed, converting four constraints into a multi-objective optimization function, and expressing the four constraints as:
Wherein I is a control variable, including four constrained variation parameters, λ 1、λ2 and λ 3 represent weight coefficients.
Example 2
Referring to fig. 2-3, for one embodiment of the present invention, an unmanned mining card local path planning method based on an artificial potential field algorithm is provided, and in order to verify the beneficial effects of the present invention, scientific demonstration is performed through economic benefit calculation and simulation experiments.
And constructing a test environment by utilizing SCANeR software, and simultaneously improving the programming control of the path planning algorithm based on the artificial potential field by combining Matlab/Simulink software to finish the performance verification of the path planning method based on the artificial potential field. The setting of relevant road information is performed and corresponding context-aware sensors are added to the autonomous vehicle control and dynamic model at SCANeR.
And (3) setting an unmanned mining truck to run at a constant speed for 20km/h and 35km/h, and detecting the obstacle through a vehicle-mounted sensing sensor. After detecting that an obstacle is encountered, carrying out path planning and lane change through a local path planning system, and completing obstacle avoidance of the vehicle to obtain simulation results of the paths shown in fig. 2 and 3.
The result shows that the planned moving path of the autonomous vehicle is basically consistent with the target path, the curvature of the vehicle track is very smooth, and the phenomenon of a large curvature path does not occur.
Example 3
Referring to fig. 4, for one embodiment of the present invention, an unmanned mining card local path planning system based on an artificial potential field algorithm is provided, which includes a data acquisition module, a potential field construction module, and a path planning module.
The data acquisition module is used for configuring the data sensor to acquire environment data, vehicle running state data and obstacle information. The potential field construction module is used for establishing an obstacle elliptical potential field based on an improved artificial potential field algorithm, and target modeling of a target point based on an obstacle point is completed. The path planning module is used for introducing lane keeping constraint, a shortest path principle, an optimal curvature principle and path heading constraint to carry out path planning.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method of the embodiments of the present invention. And the aforementioned storage medium includes: a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium may even be paper or other suitable medium upon which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like. It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
It should be noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention may be modified or substituted without departing from the spirit and scope of the technical solution of the present invention, which is intended to be covered in the scope of the claims of the present invention.
Claims (7)
1. The unmanned mining card local path planning method based on the artificial potential field algorithm is characterized by comprising the following steps of:
the configuration data sensor collects environment data, vehicle running state data and obstacle information;
establishing an obstacle elliptical potential field based on an improved artificial potential field algorithm, and completing target modeling of a target point based on an obstacle point;
introducing lane keeping constraint, a shortest path principle, an optimal curvature principle and path heading constraint to carry out path planning;
The establishment of the obstacle elliptical potential field based on the improved artificial potential field algorithm comprises the following steps: setting the controlled ore card as a particle in a two-dimensional space, setting the coordinate as X= (X, y), setting the coordinate of a target point as X g＝(xg,yg), and determining the distance from the controlled ore card to the target point, wherein the distance is expressed as:
the gravitational potential field is expressed as:
Wherein, The distance from the controlled mine card to the target point at the moment t is represented, gamma represents the gravitational force adjustment coefficient, and k represents the gravitational field coefficient;
the attraction of the controlled mine card is expressed as:
Wherein V g represents a unit vector of the controlled mine card pointing to the target point;
The lane keeping constraint is expressed as a road constraint by constraining the vehicle to travel at a distance from the lane centerline:
Wherein L i represents the vehicle position of the i-th control point, L d represents the position of the lane center line, and N represents the total number of control nodes;
The shortest path principle calculates the shortest path by calculating the path length variation of the adjacent control nodes, expressed as:
Where Deltax i and Deltay i represent the path length variation of the ith control point, deltax c,i and Deltay c,i represent the position variation between control nodes, A vector representation representing the path length, T representing the transpose;
The optimal curvature principle simplifies the path into a path formed by connecting control nodes by a sectional natural cubic spline curve, and the path curvature is calculated in a quadratic form and expressed as:
Wherein, Representing the square of the curvature of the ith path, s representing the path parameters, s * representing the normalized path parameters, x ri(s*) and y ri(s*), the position function of the ith path in the x-axis and y-axis, represented as a natural cubic spline curve, a 0i,a1i,a2i,a3i representing the coefficient controlling the shape of the ith spline curve in the x-axis, b 0i,b1i,b2i,b3i representing the coefficient controlling the shape of the ith spline curve in the y-axis, s i0 representing the starting parameter value of the ith path, Δs representing the total length of the ith path;
the path course constraint is realized by controlling the course angle between adjacent nodes, and the course angle between the adjacent control nodes is expressed as:
After the constraint construction is completed, converting the four constraints into a multi-objective optimization function;
the path planning further comprises the step of converting four constraints into a multi-objective optimization function after the constraint construction is completed, wherein the four constraints are expressed as:
Wherein I is a control variable, including four constrained variation parameters, λ 1、λ2 and λ 3 represent weight coefficients.
2. The unmanned mining card local path planning method based on the artificial potential field algorithm as claimed in claim 1, wherein the method comprises the following steps: the collecting environmental data, vehicle running state data and obstacle information includes: the method comprises the steps of configuring a laser radar to collect the position of an obstacle vehicle, configuring a vehicle-mounted camera to collect road width and lane marks, and configuring an inertial measurement unit to collect the speed, acceleration and course angle of a mine truck.
3. The unmanned mining card local path planning method based on the artificial potential field algorithm as claimed in claim 2, wherein: the method for establishing the obstacle elliptical potential field based on the improved artificial potential field algorithm further comprises the following steps: if the coordinate position in the European space of the obstacle-setting vehicle is X ob＝(xob,yob) under the condition that the obstacle-setting vehicle exists, constructing a repulsive potential field by combining the harmonic function, wherein the repulsive potential field is expressed as:
wherein eta and rho o are the action coefficient and the distance range of the repulsive force potential field, and rho ob represents the distance between the controlled mine card and the obstacle point;
According to the repulsive potential field function, when ρ ob≤ρo, the repulsive force of the control object is expressed as:
wherein V ob is a direction vector of the controlled mine card pointing to the obstacle point, and m represents a repulsive potential field influence parameter;
when n effective obstacles exist in the space, the resultant force of the controlled mine cards is expressed as:
After the resultant force of the controlled mine cards is determined, an elliptical potential field of the obstacle truck is constructed, and the construction of the potential field is completed.
4. The unmanned mining card local path planning method based on the artificial potential field algorithm of claim 3, wherein: the obstacle point-based target modeling includes: the method comprises the steps of carrying out controlled target modeling based on an improved artificial potential field algorithm, establishing an obstacle elliptical potential field, completing target modeling of a target point based on an obstacle point, taking the geometric center of an obstacle vehicle as the center of the elliptical potential field, respectively taking a long axis and a short axis as a and b, and expressing an obstacle potential field U truck as:
Wherein k truck is the barrier vehicle potential field stiffness, Representing the geometric center coordinates of the ith obstacle.
5. A system employing the unmanned mining card local path planning method based on artificial potential field algorithm as claimed in any one of claims 1 to 4, characterized in that: the system comprises a data acquisition module, a potential field construction module and a path planning module;
The data acquisition module is used for configuring the data sensor to acquire environment data, vehicle running state data and obstacle information;
The potential field construction module is used for establishing an obstacle elliptical potential field based on an improved artificial potential field algorithm, and completing target modeling of a target point based on an obstacle point;
the path planning module is used for introducing lane keeping constraint, a shortest path principle, an optimal curvature principle and path heading constraint to carry out path planning.
6. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the unmanned mining card local path planning method based on artificial potential field algorithm of any one of claims 1 to 4.
7. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of the artificial potential field algorithm based unmanned mining card local path planning method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410224077.0A CN117826825B (en) | 2024-02-29 | 2024-02-29 | Unmanned mining card local path planning method and system based on artificial potential field algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410224077.0A CN117826825B (en) | 2024-02-29 | 2024-02-29 | Unmanned mining card local path planning method and system based on artificial potential field algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117826825A CN117826825A (en) | 2024-04-05 |
| CN117826825B true CN117826825B (en) | 2024-06-07 |
Family
ID=90513677
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410224077.0A Active CN117826825B (en) | 2024-02-29 | 2024-02-29 | Unmanned mining card local path planning method and system based on artificial potential field algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117826825B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107063280A (en) * | 2017-03-24 | 2017-08-18 | 重庆邮电大学 | A kind of intelligent vehicle path planning system and method based on control sampling |
| CN114740864A (en) * | 2022-05-07 | 2022-07-12 | 南京信息工程大学 | Mobile robot path planning method based on improved PRM and artificial potential field |
| CN115071686A (en) * | 2022-06-15 | 2022-09-20 | 北京踏歌智行科技有限公司 | Parking method for unmanned mining vehicle in long and narrow area |
| CN115328152A (en) * | 2022-09-05 | 2022-11-11 | 北京理工大学 | Unmanned vehicle local real-time obstacle avoidance path planning method based on improved artificial potential field method |
| CN116300866A (en) * | 2022-12-28 | 2023-06-23 | 智新控制系统有限公司 | Vehicle obstacle avoidance method, device and medium based on artificial potential field method |
-
2024
- 2024-02-29 CN CN202410224077.0A patent/CN117826825B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107063280A (en) * | 2017-03-24 | 2017-08-18 | 重庆邮电大学 | A kind of intelligent vehicle path planning system and method based on control sampling |
| CN114740864A (en) * | 2022-05-07 | 2022-07-12 | 南京信息工程大学 | Mobile robot path planning method based on improved PRM and artificial potential field |
| CN115071686A (en) * | 2022-06-15 | 2022-09-20 | 北京踏歌智行科技有限公司 | Parking method for unmanned mining vehicle in long and narrow area |
| CN115328152A (en) * | 2022-09-05 | 2022-11-11 | 北京理工大学 | Unmanned vehicle local real-time obstacle avoidance path planning method based on improved artificial potential field method |
| CN116300866A (en) * | 2022-12-28 | 2023-06-23 | 智新控制系统有限公司 | Vehicle obstacle avoidance method, device and medium based on artificial potential field method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117826825A (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7150067B2 (en) | Vehicle control system, method for controlling vehicle, and non-transitory computer readable memory | |
| Li et al. | Real-time trajectory planning for autonomous urban driving: Framework, algorithms, and verifications | |
| Zhao et al. | Dynamic motion planning for autonomous vehicle in unknown environments | |
| CN112888612A (en) | Autonomous vehicle planning | |
| US20210373566A1 (en) | Trajectory generation using lateral offset biasing | |
| JP2021524410A (en) | Determining the drive envelope | |
| CN112639849A (en) | Route selection method and route selection device | |
| Berntorp et al. | Motion planning of autonomous road vehicles by particle filtering | |
| CN112577506B (en) | Automatic driving local path planning method and system | |
| CN107664993A (en) | A kind of paths planning method | |
| CN111397622A (en) | Intelligent automobile local path planning method based on improved A-algorithm and Morphin algorithm | |
| CN112327888B (en) | Path planning method and device, electronic equipment and storage medium | |
| CN117885764B (en) | Vehicle track planning method and device, vehicle and storage medium | |
| CN115230729A (en) | Automatic driving obstacle avoidance method and system and storage medium | |
| CN116069037A (en) | Unmanned vehicle formation track planning control method, device, equipment and storage medium | |
| Cai et al. | Rule‐constrained reinforcement learning control for autonomous vehicle left turn at unsignalized intersection | |
| CN115079699A (en) | Model prediction control-based motion planning method for man-machine co-driving automobile | |
| CN114715193A (en) | Real-time trajectory planning method and system | |
| CN117826825B (en) | Unmanned mining card local path planning method and system based on artificial potential field algorithm | |
| CN116653963B (en) | Vehicle lane change control method, system and intelligent driving domain controller | |
| Xing et al. | Lane change strategy for autonomous vehicle | |
| CN116448134B (en) | Vehicle path planning method and device based on risk field and uncertain analysis | |
| WO2024118997A1 (en) | Prediction model with variable time steps | |
| WO2024118765A1 (en) | Vehicle trajectory tree search for off-route driving maneuvers | |
| CN115454085B (en) | Automatic driving control method and automatic driving control device based on navigation map |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |