CN116798232B - A multi-vehicle collaborative decision-making system that combines vehicle priority and artificial fish schools - Google Patents
A multi-vehicle collaborative decision-making system that combines vehicle priority and artificial fish schools Download PDFInfo
- Publication number
- CN116798232B CN116798232B CN202310998816.7A CN202310998816A CN116798232B CN 116798232 B CN116798232 B CN 116798232B CN 202310998816 A CN202310998816 A CN 202310998816A CN 116798232 B CN116798232 B CN 116798232B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- vehicles
- force
- priority
- distance
- 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
- 241000251468 Actinopterygii Species 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000004458 analytical method Methods 0.000 claims abstract description 16
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 16
- 230000008859 change Effects 0.000 claims abstract description 14
- 230000008569 process Effects 0.000 claims abstract description 8
- 230000000694 effects Effects 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 7
- 230000015572 biosynthetic process Effects 0.000 claims description 37
- 238000004364 calculation method Methods 0.000 claims description 12
- 230000009466 transformation Effects 0.000 claims description 9
- 238000011156 evaluation Methods 0.000 claims description 7
- 230000001133 acceleration Effects 0.000 claims description 6
- 230000007246 mechanism Effects 0.000 claims description 3
- 230000004044 response Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 238000012423 maintenance Methods 0.000 claims description 2
- 230000005484 gravity Effects 0.000 claims 3
- 238000004891 communication Methods 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 6
- 230000003993 interaction Effects 0.000 abstract description 3
- 238000005755 formation reaction Methods 0.000 description 25
- 238000011160 research Methods 0.000 description 8
- 230000009471 action Effects 0.000 description 5
- 230000006399 behavior Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012617 force field calculation Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 230000000116 mitigating effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000004043 responsiveness Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000002195 synergetic effect Effects 0.000 description 1
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention relates to a multi-vehicle collaborative decision-making system combining vehicle priority and artificial fish shoals, and belongs to the field of traffic informatization. The system is divided into three parts: the workshop force field analysis subsystem, the vehicle-vehicle cooperative relation analysis subsystem and the multi-vehicle cooperative planning decision-making subsystem. Aiming at the problem of poor modeling effect of the traditional dynamic environment of force field processing, a potential field model considering the vehicle speed is designed, the workshop acting force based on the distance relation and the interaction force in the vehicle speed change process are considered, and the modeling accuracy of the interaction force between the vehicle groups in the dynamic environment is improved. A priority algorithm is designed in the single vehicle processing, and three cooperative schemes are designed aiming at the multi-vehicle situation. According to the invention, the intelligent road side sensing and V2X communication technology at the road end is fully utilized to acquire real-time traffic data, the data processing is mainly concentrated in the high-performance computing equipment at the road side, and the multi-vehicle collaborative decision model at the road side is optimized, so that the traffic efficiency of the road junction can be effectively improved, and the road junction congestion is reduced.
Description
Technical Field
The invention belongs to the field of traffic informatization, and relates to a multi-vehicle collaborative decision-making system combining vehicle priority and artificial fish shoals.
Background
In recent years, with the increasing prominence of traffic jam problems and the increasing traffic safety requirements, vehicle group collaborative planning becomes one of research hotspots in the intelligent traffic field. The cooperative planning of the vehicle group aims at improving the running efficiency of the road and the throughput capacity of traffic flow by optimizing the running strategy of the vehicle, thereby reducing traffic jam and providing safer and more efficient traffic environment.
The current research methods focus mainly on the following aspects: sensor technology, communication technology, traffic models, and cooperative control strategies. These methods attempt to achieve synergistic travel and mitigation of traffic congestion between clusters of vehicles by collecting and analyzing data of vehicles and roads. However, these methods also have some important research drawbacks.
First, current research methods tend to ignore the effect of priority differences between vehicles and the manner of manual intervention on efficiency. In actual traffic, different types of vehicles (such as emergency vehicles, public transportation vehicles, large and medium-sized vehicles) have different priorities and need to be specially treated. However, most research methods employ the same rules and strategies for all vehicles, and do not take into account well the individual characteristics of the vehicle and the behavior habits of humans. This results in that the planning result may not be flexible and reliable enough to meet the changes of the actual traffic situation.
Secondly, the existing research method lacks a unified optimization framework in the vehicle group collaborative planning. The driving strategies between vehicles are often independently formulated and adjusted, and the behaviors of the vehicles cannot be well coordinated and integrated. This results in an inability to maximize traffic flow efficiency and throughput, with problems of traffic congestion and delays.
In addition, the existing methods have some limitations in terms of traffic information acquisition and processing. Although sensor technology and communication technology are evolving and abundant traffic data is available, how to efficiently process and utilize such data remains a challenge. The current research method only considers static traffic model and historical data, and lacks full utilization of dynamic traffic condition and real-time data. This limits the adaptability and responsiveness of the research methods so that the traffic system cannot cope with complex traffic environments and emergencies in time.
Therefore, in order to solve the insufficient multi-vehicle cooperation and the need of vehicle-road cooperation, a safe and efficient multi-vehicle cooperation decision service is provided, travel safety and propulsion cooperation development are guaranteed, and a unidirectional multi-lane vehicle group cooperation planning method combining vehicle priority and group intelligence is needed, so that a safe and reliable multi-vehicle cooperation driving scheme is provided for a smart traffic scene under the internet of vehicles, and vehicle-road cooperation and subsequent unmanned driving are realized.
Disclosure of Invention
In view of the above, the present invention is directed to a multi-vehicle collaborative decision-making system combining vehicle priority and artificial fish school.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a multi-vehicle collaborative decision-making system combining vehicle priority and artificial fish shoals comprises a workshop force field analysis subsystem, a vehicle-vehicle collaborative relation analysis subsystem and a multi-vehicle collaborative planning decision-making subsystem.
The vehicle-to-vehicle virtual action force field is constructed according to the position and speed change based on the relation between vehicles analyzed by the workshop force field analysis subsystem;
the vehicle-vehicle cooperative relationship analysis subsystem adopts an artificial fish swarm algorithm to carry out multi-vehicle cooperative planning, and in the searching process of the fish swarm, the mutual attraction and repulsion between individuals are calculated through the potential field relationship between vehicles to simulate the fish swarm behavior; carrying out iterative computation by considering the specificities of different vehicle types in an artificial fish swarm algorithm to obtain an optimal result;
the multi-vehicle collaborative planning decision making subsystem combines the results obtained by the fish swarm algorithm and designs three multi-vehicle collaborative planning decision schemes of vehicle formation control, vehicle obstacle avoidance control and vehicle formation transformation control according to the common situations of traffic roads.
Optionally, the workshop force field analysis subsystem acquires vehicle information from the RSU, including position, speed and acceleration information of the vehicle and the obstacle, extracts the vehicle information, sets a virtual force field for the vehicle group, and performs force field modeling according to the position information and the speed information between the vehicles to obtain a relative acting force relationship between the vehicles; wherein, the gravitational field formula is:k in the formula a 、K av For the position gain coefficient and the speed gain coefficient, q and v are the current position and speed of the individual, q g 、v g For the position and velocity of the target point, the attraction force is calculated as: f (F) a ＝-grad|U a (q)|＝-K a |q-q g |-K av V-vg |; the repulsive field is: />K in the formula r 、K rv For the position gain coefficient and the velocity gain coefficient, ρ (q, q g ) For the distance of the individual from the obstacle ρ 0 To calculate the influence distance of the repulsive force potential field, the repulsive force is calculated as: />
Optionally, in the process of searching the artificial fish shoal, calculating mutual attraction force and repulsive force among individuals by using a formula obtained by the workshop force field analysis subsystem to simulate the fish shoal behavior, and performing specific treatment on the fish shoal according to the types of different vehicles when calculating the fitness evaluation of each fish, wherein the specific treatment comprises the following steps: when calculating the fitness evaluation of each fish, the volume parameters of different vehicle types are included into calculation; meanwhile, a priority mechanism is introduced for improving the response speed of the algorithm to the emergency vehicle, and three priorities of high, medium and low are set for vehicles of different vehicle types; the gravitation formula and the repulsion formula of the vehicle volume are respectively:and->Wherein V represents the volume of the vehicle, V g Representing the volume of another vehicle; if the vehicle body exceeds a certain volume, the attraction force between the two vehicles becomes smaller, and the repulsive force becomes larger; comprehensively setting priority according to the influence degree of vehicles on traffic jam and the passing priority of vehicles, setting emergency vehicles of emergency ambulances or police vehicles as high priority, setting buses or buses of schools as medium priority, and setting the emergency vehicles or emergency vehicles as medium priorityThe medium-sized vehicle or truck dangerous vehicle is set as a secondary medium priority, and the common sedan is set as a low priority for processing; and finally, carrying out multiple iterations on the artificial fish swarm algorithm to obtain the calculated optimal result.
Optionally, the vehicle formation control simulates a fish swarm model to establish a vehicle induction area, analyzes the resultant force between vehicles to reach an equilibrium state, adjusts the movement direction of the vehicles and the distance between the vehicles according to a potential force field formula, and obtains the optimal holding speed of the vehicles based on a headway formula and combining the optimal holding distance between the vehicles;
the vehicle obstacle avoidance control requires that the relative distance between vehicles is not changed as much as possible so as to ensure the balance state between the vehicles; meanwhile, the obstacle is regarded as a repulsive field, and under the action of the target vehicle and the obstacle, the obstacle avoidance effect is realized by performing angle offset in the vertical direction;
the vehicle formation transformation control realizes transformation of the triangular vehicle formation into a linear formation by carrying out cooperative lane change so as to ensure the safety among vehicle groups; during running, the vehicle groups are uniformly distributed on a plurality of lanes and are expressed as triangular formations; when encountering an obstacle or avoiding a lane for a high-priority vehicle, the vehicle team is changed into a straight line formation through cooperative lane changing.
Optionally, after the vehicle formation control meeting, a vehicle maintenance control scheme is proposed; the vehicle formation control firstly calculates the magnitudes of two forces according to an attraction force calculation formula and a repulsion force calculation formula respectively, and the vehicle F a ＝F r Calculating an optimal holding distance between vehicles by stress balance, and then calculating a formula s=t according to a headstock distance formula h * v calculating an optimal holding speed of the vehicle; wherein S is the longitudinal distance between two vehicle heads, v is the real-time speed of the vehicle, T h The time interval is the time interval of the head of two continuous vehicles passing through a certain section time interval in a vehicle queue running on the same lane; the vehicle formation retention is achieved when the vehicle formation is not subjected to external forces but only internal forces.
Optionally, in the vehicle obstacle avoidance control, in order to ensure the stress balance in the fleet, it is required to keep the vehicleThe resultant force of the distance and the speed of the vehicle group of the vehicle and the nearby vehicle counteracts to zero, meanwhile, the obstacle is regarded as a repulsive field, and the repulsive force and the obstacle avoidance rotation angle of the vehicle are calculated according to the distance between the vehicle and the obstacle; the vehicle can move to the inner lane when avoiding the obstacle, so that the distance between vehicles is reduced, and the speed of the vehicles is changed according to a resultant force formula to ensure the stress balance; between the vehicle and the obstacle, the relative components of the X and Y axes of the repulsive force between the vehicle and the obstacle are calculated according to the GPS positioning information of the vehicle and the obstacle: (F) r .x，F r Y) = (x_car-x_obstacle, y_car-y_obstacle), the obstacle avoidance rotation angle of the vehicle is obtained by the following formula: θ=atan2 (F) r .y，F r X); finally, the vehicle rotates according to the calculated angle theta to achieve the obstacle avoidance effect.
Optionally, in the vehicle formation transformation control, the control is set at time t 1 The real-time speed of the time neighbor vehicle is v 0 A term is additionally introduced into the calculation of the repulsive force to characterize the influence of the speed of the neighbor lane on the repulsive force: f (F) rnew ＝F r *(1/dis tan ce)*(1+v 0 ) Wherein distance represents the distance between the vehicle and the vehicle behind the adjacent vehicle, and then the formula of the rotation angle of the updated vehicle to the adjacent lane is as follows: θ avoid ＝atan2(F rnew .y，F rnew X); and the vehicles change lanes to the neighbor lanes according to the rotation angle, and finally, the formation change of the vehicles is realized.
The invention has the beneficial effects that: according to the invention, the intelligent road side sensing and V2X communication technology at the road end is fully utilized to acquire real-time traffic data, the data processing is mainly concentrated in the high-performance computing equipment at the road side, and the multi-vehicle collaborative decision model at the road side is optimized, so that the traffic efficiency of the road junction can be effectively improved, and the road junction congestion is reduced.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objects and other advantages of the invention may be realized and obtained by means of the instrumentalities and combinations particularly pointed out in the specification.
Drawings
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in the following preferred detail with reference to the accompanying drawings, in which:
FIG. 1 is a system frame diagram of the present invention;
FIG. 2 is a flow chart of the multi-vehicle collaborative planning scheme formulation of the present invention;
FIG. 3 is a schematic view of a multi-vehicle cooperative obstacle avoidance system according to the present invention;
FIG. 4 is a schematic diagram of a vehicle formation transformation of the present invention.
Detailed Description
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the illustrations provided in the following embodiments merely illustrate the basic idea of the present invention by way of illustration, and the following embodiments and features in the embodiments may be combined with each other without conflict.
Wherein the drawings are for illustrative purposes only and are shown in schematic, non-physical, and not intended to limit the invention; for the purpose of better illustrating embodiments of the invention, certain elements of the drawings may be omitted, enlarged or reduced and do not represent the size of the actual product; it will be appreciated by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numbers in the drawings of embodiments of the invention correspond to the same or similar components; in the description of the present invention, it should be understood that, if there are terms such as "upper", "lower", "left", "right", "front", "rear", etc., that indicate an azimuth or a positional relationship based on the azimuth or the positional relationship shown in the drawings, it is only for convenience of describing the present invention and simplifying the description, but not for indicating or suggesting that the referred device or element must have a specific azimuth, be constructed and operated in a specific azimuth, so that the terms describing the positional relationship in the drawings are merely for exemplary illustration and should not be construed as limiting the present invention, and that the specific meaning of the above terms may be understood by those of ordinary skill in the art according to the specific circumstances.
The method comprises the steps of firstly acquiring vehicle information from an RSU, including information such as positions, speeds, accelerations, course angles, road conditions and the like of vehicles and obstacles, extracting relevant information of the vehicles, setting a virtual force field for a vehicle group, and carrying out force field modeling according to the position information and the speed information among the vehicles to obtain a relative acting force relation among the vehicles. According to the actual road condition, constructing a potential field of a workshop by combining a distance relation and a speed change relation between vehicles, wherein the formula of the potential field is as follows:
k in the formula a 、K av For the position gain coefficient and the speed gain coefficient, q and v are the current position and speed of the individual, q g 、v g For the position and velocity of the target point, the attraction force is calculated as:
F a ＝-grad|U a (q)|＝-K a |q-q g |-K av |v-v g |
similarly, the resulting repulsive force field formula is:
k in the formula r 、K rv For the position gain coefficient and the velocity gain coefficient, ρ (q, q g ) For the distance of the individual from the obstacle ρ 0 As the influence distance of the repulsive force potential field, the repulsive force is calculated as:
and the vehicle-vehicle cooperative relationship analysis subsystem is combined with an artificial fish swarm algorithm to carry out multi-vehicle cooperative planning decision. Referring to the flow chart of the multi-vehicle collaborative planning scheme of fig. 2, the influence of the volumes and the urgency of different vehicles on the multi-vehicle collaborative planning is considered in the initialization of individual parameters of the fish shoal. In calculating the fitness evaluation for each fish, the volume parameters for the different vehicle classes are included in the calculation. Meanwhile, in order to improve the response speed of the algorithm to the emergency vehicle, a priority mechanism is introduced, and three priorities of high, medium and low are set for vehicles of different vehicle types. In addition, in the searching process of the shoal of fish, the mutual attraction force and the repulsive force among individuals are calculated through the workshop potential force field obtained by the workshop force field analysis subsystem so as to simulate the shoal of fish.
The vehicle priority weight is calculated by adding a value representing the priority of the vehicle to the basic safety information of the vehicle, the priority being set according to the influence of the vehicle on the road traffic jam and the degree of urgency of the vehicle. Emergency vehicles such as emergency vehicles, police vehicles and the like are generally set to be high in priority, and the priority weight is recorded as 4; vehicles with more passengers, such as buses, buses in schools and the like, are medium priority, and the priority weight is recorded as 3; the large-volume dangerous vehicles such as medium-sized vehicles, trucks and the like are secondary medium priority, and the priority weight is recorded as 2; the ordinary car is marked as low priority, and the priority weight is marked as 1. The own vehicle message filling module of the OBU recognizes the vehicle type and sets the corresponding priority weight, and then fills the BSM message to send to the roadside device and other vehicles.
The multi-vehicle cooperative control algorithm flow based on the fish swarm effect is as follows:
first, initializing a vehicle group system to use a vehicle Car leaders Centrally, a vehicle group instruction is issued according to the same destination conditions. In the initialization of the vehicle information, the corresponding priority is also set according to the kind of the vehicle.
Second, if the individual vehicle Car followers(i) Meets the group conditions by Car leaders To get the dynamic target point close to it, car leaders Detecting vehicles in the perception range, and according to the number of detected vehiclesThe road environment conditions determine the vehicle sports formation. The force of the force field between vehicles is considered in the formation setting. Meanwhile, through vehicle-to-vehicle communication and vehicle-to-road communication, if vehicles with high and medium priority are found in the vehicle group, the vehicles are avoided and pass preferentially.
And thirdly, if the vehicle group reaches the destination, finishing the multi-vehicle collaborative planning control, otherwise, turning to a fourth step.
And fourthly, the motorcade vehicle advances towards the destination, and if the motorcade vehicle encounters an obstacle, the motorcade enters an obstacle avoidance state, and an obstacle avoidance control method is adopted.
Fifth step, if Car leaders The obstacle is met, and the overall obstacle avoidance of the vehicle group is considered under two conditions. Car when the vehicle is in the form of a line followers(i) Will keep the formation unchanged, follow Car leaders Exercise, car leaders The method comprises the steps that an obstacle is avoided in a lane changing mode, and a rear slave vehicle follows a front vehicle to cooperatively avoid the obstacle; when the vehicles are in a nonlinear queue, the neighboring lanes have vehicles to run at the moment, and Car leaders Requesting merging travel from a neighboring lane, if the number of vehicles in the lane where the obstacle is located is small, the following slave vehicle follows Car leaders Motion; if the number of vehicles in the lane where the obstacle is located is large, the rear sub-vehicle is decomposed into a plurality of small vehicle queues, and the vehicle queues apply for the merging driving to the adjacent lanes at proper time respectively. Referring to the multi-vehicle collaborative obstacle avoidance schematic diagram of fig. 3, when applying for merging traveling to a neighboring vehicle, the steering angle and the time for merging steering into the neighboring lane are obtained by calculating the potential occasion force of the vehicle and the vehicle behind the neighboring lane and combining the current speed.
If only Car followers(i) When encountering an obstacle, car followers(i) The obstacle avoidance breaks away from the motorcade and enters an individual obstacle avoidance state.
And (3) finishing obstacle avoidance of the obstacle avoidance vehicle, finishing an obstacle avoidance state by the vehicle team, entering a third step if the formation is unchanged, otherwise, recovering the original formation to enter the third step.
In the process of the movement of the vehicle, three movement cooperative control methods among the vehicles are defined:
vehicle formation control: knot(s)Establishing a sensing area of the vehicle by combining with an artificial fish swarm algorithm model, specifically, establishing a sensing range L of the periphery of the vehicle according to the vehicle info Influence distance L of repulsive force potential field between vehicles safe And a vehicle sensing area is jointly formed. Wherein the distance between the balance points of the two vehicles is represented by r, the distance between the two vehicles is represented by L, and when s is more than or equal to 0 and less than or equal to L safe When the two vehicles are in collision, the two vehicles are gradually far away until reaching the balance distance under the action of repulsive force; when L safe When s is more than or equal to r, the resultant force born by the two vehicles is counteracted, and the two vehicles are kept relatively balanced; when r is not less than s is not less than L info When the two vehicles are under the action of the force of attraction, the two vehicles are gradually close, and the closing speed is in direct proportion to the magnitude of the resultant force.
The fleet obstacle avoidance control refers to a multi-vehicle collaborative obstacle avoidance schematic diagram of fig. 3. When Car i Car when the distance between the vehicle and the obstacle is smaller than the range of the repulsive force of the obstacle when the obstacle is hit during movement i Will move away from the obstacle under the action of the repulsive force, provided however that Car i And Car j The distance between the two vehicles remains unchanged, and the distance refers to the balance distance between the two vehicles. Under this condition, the resultant force between the vehicles is unchanged, and the vehicle Car i Is affected only by the obstacle.
Formation change control referring to the vehicle formation change schematic of fig. 4. When a vehicle team encounters the conditions of obstacles, narrowing of a road surface and the like, the original vehicle team cannot pass through the road surface, and the vehicle team needs to be changed, so that the vehicles can pass smoothly. The transformation of the linear queue formation and the nonlinear queue formation is a lane change decision taking into account the balance of force fields between vehicles. In general, a part of the shop force is derived from the interaction force generated by the distance between vehicles, and the other part of the force is derived from the force generated by the change in the vehicle speed. When the host vehicle considers the neighboring lane, the relative distance between the host vehicle and the neighboring vehicle is shortened, and in order to ensure reasonable balance, the vehicle speed needs to be increased, and the specific calculation is referred to the potential force field calculation formula. When the rectangular team changes the line shape, the Car leaders Planning individual vehicle online formationsThe location is based on the principle of shortest arrival time. After the position of the vehicle is determined, the distance L between the vehicles is kept unchanged, the angle between the two vehicles is gradually reduced, and the distance L is formed by alpha 1 Becomes alpha 2 And when the angles of the multiple workshops are the same, finishing transformation, and when the line type rectangle is changed, reversing.
And the multi-vehicle collaborative planning based on the fish swarm algorithm establishes the motion planning of the vehicle swarm on the basis of overall optimization, and broadcasts through RSU road side equipment. The intelligent network-connected automobile plans the local path of the automobile according to the received broadcast signals. And determining a reference track or path according to the result of the global path planning or the current target. And setting reasonable maximum acceleration, maximum rotation angle and other parameters according to the dynamics constraint of the vehicle. Based on these parameters, a drivable region in the vicinity of the vehicle is generated for describing a possible range of motion of the vehicle. In this area, a local path satisfying the condition is searched based on evaluation indexes such as a distance to a target, a distance to an obstacle, and a limit of the maximum value of the speed and the acceleration of the vehicle. And selecting the optimal path as a local path planning result by comparing the evaluation index scores of different paths. And generating corresponding vehicle control instructions including steering angles, accelerations and the like according to the optimal local path planning result so as to realize motion control of the vehicle.
Finally, it is 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 modifications and equivalents may be made thereto without departing from the spirit and scope of the present invention, which is intended to be covered by the claims of the present invention.
Claims (2)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310998816.7A CN116798232B (en) | 2023-08-09 | 2023-08-09 | A multi-vehicle collaborative decision-making system that combines vehicle priority and artificial fish schools |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310998816.7A CN116798232B (en) | 2023-08-09 | 2023-08-09 | A multi-vehicle collaborative decision-making system that combines vehicle priority and artificial fish schools |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116798232A CN116798232A (en) | 2023-09-22 |
| CN116798232B true CN116798232B (en) | 2024-03-26 |
Family
ID=88038641
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310998816.7A Active CN116798232B (en) | 2023-08-09 | 2023-08-09 | A multi-vehicle collaborative decision-making system that combines vehicle priority and artificial fish schools |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116798232B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118736881B (en) * | 2024-08-30 | 2024-11-29 | 大连理工大学 | Dynamic cooperative control method of connected vehicles based on A-star algorithm and gravitational field model |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108216236A (en) * | 2017-12-25 | 2018-06-29 | 东软集团股份有限公司 | Control method for vehicle, device, vehicle and storage medium |
| CN109903551A (en) * | 2019-04-12 | 2019-06-18 | 北京航空航天大学 | A method, storage medium and device for driving and formation control of unmanned vehicles on expressway ramps based on artificial fish school |
| CN112026786A (en) * | 2020-09-09 | 2020-12-04 | 深圳技术大学 | Cooperative driving control system of intelligent car and multi-vehicle cooperative driving control system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106114507B (en) * | 2016-06-21 | 2018-04-03 | 百度在线网络技术（北京）有限公司 | Local path planning method and device for intelligent vehicle |
| CN111735466B (en) * | 2020-01-02 | 2021-11-12 | 北京京东乾石科技有限公司 | A multi-vehicle cooperative trajectory planning method, device, equipment and storage medium |
-
2023
- 2023-08-09 CN CN202310998816.7A patent/CN116798232B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108216236A (en) * | 2017-12-25 | 2018-06-29 | 东软集团股份有限公司 | Control method for vehicle, device, vehicle and storage medium |
| CN109903551A (en) * | 2019-04-12 | 2019-06-18 | 北京航空航天大学 | A method, storage medium and device for driving and formation control of unmanned vehicles on expressway ramps based on artificial fish school |
| CN112026786A (en) * | 2020-09-09 | 2020-12-04 | 深圳技术大学 | Cooperative driving control system of intelligent car and multi-vehicle cooperative driving control system |
Non-Patent Citations (1)
| Title |
|---|
| 基于鱼群效应的多车协同行驶控制方法;来磊 等;《西北工业大学学报》;20120630;第30卷(第3期);第373-377页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116798232A (en) | 2023-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11651240B2 (en) | Object association for autonomous vehicles | |
| CN112789481B (en) | Trajectory prediction for top-down scenarios | |
| CN112242069B (en) | A method and device for determining vehicle speed | |
| US20210094539A1 (en) | Blocking object avoidance | |
| JP2022163098A (en) | Operation management of autonomous traveling vehicle | |
| US12296849B2 (en) | Method and system for feasibility-based operation of an autonomous agent | |
| EP3814867A1 (en) | Orientation-adjust actions for autonomous vehicle operational management | |
| US11801864B1 (en) | Cost-based action determination | |
| CN109727490B (en) | Peripheral vehicle behavior self-adaptive correction prediction method based on driving prediction field | |
| CN112577506B (en) | Automatic driving local path planning method and system | |
| CN110288835A (en) | A Real-time Recognition Method of Surrounding Vehicle Behavior Based on Kinematics Prediction and Compensation Mechanism | |
| CN104732066B (en) | The modeling method of vehicle behavior temporal-spatial evolution and its application under path constraints | |
| CN116798232B (en) | A multi-vehicle collaborative decision-making system that combines vehicle priority and artificial fish schools | |
| CN114043984A (en) | Intelligent automobile lane change control system and method based on Internet of vehicles environment | |
| Ren et al. | Self-learned intelligence for integrated decision and control of automated vehicles at signalized intersections | |
| WO2024006115A1 (en) | Determining right of way | |
| Guo et al. | Self-defensive coordinated maneuvering of an intelligent vehicle platoon in mixed traffic | |
| CN118212808A (en) | Method, system and equipment for planning traffic decision of signalless intersection | |
| US20240067195A1 (en) | Transfer Learning with Experience Filter for Vehicle Operation | |
| Delp et al. | Classifying and passing 3d obstacles for autonomous driving | |
| Tsu-Tian | Research on intelligent transportation systems in Taiwan | |
| Zheng et al. | Traffic-aware autonomous driving with differentiable traffic simulation | |
| Yoneda et al. | Supervised vehicle trajectory prediction using orthogonal image map for urban automated driving | |
| Santana et al. | Platoon driving intelligence. A survey | |
| Wei et al. | A lane changing model based on imitation learning and Gaussian velocity Fields |
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 | ||
| GR01 | Patent grant |