Multi-vehicle cooperative lane-changing method

Abstract

This specification discloses a multi-vehicle cooperative lane-changing method. The method may include: acquiring traffic participant information within a preset range of a target vehicle sent by a roadside sensing device; the target vehicle being the vehicle to be changed lanes; determining, based on the traffic participant information, whether a cooperative vehicle exists; the cooperative vehicle and the target vehicle being located in different lanes; the cooperative vehicle being a vehicle that needs to adjust its speed to ensure the target vehicle safely enters the lane it is about to enter; if a cooperative vehicle exists, determining its vehicle information; generating a cooperative driving instruction based on the target vehicle's vehicle information and the cooperative vehicle's vehicle information; and sending the cooperative driving instruction to the cooperative vehicle so that the cooperative vehicle can leave lane-changing space for the target vehicle to change lanes.

Description

Technical Field

[0001] This application relates to the field of intelligent driving, and in particular to a multi-vehicle cooperative lane-changing method. Background Technology

[0002] Cloud-based control systems for autonomous driving are complex systems comprised of vehicles and other traffic participants, roadside infrastructure, cloud control platforms, related support platforms, and communication networks. They can eliminate information silos between traffic management and vehicle management, improve the utilization rate of road infrastructure, enhance traffic management optimization, increase road traffic efficiency, reduce traffic accidents, and decrease energy consumption. Simultaneously, their development will promote cross-sectoral integration and collaborative development among the automotive, transportation, communication, and cloud computing industries, forming a comprehensive high-tech industrial cluster effect.

[0003] Existing autonomous vehicles typically determine the appropriate lane-changing opportunity based on the surrounding environment and plan lane changes autonomously. However, when autonomous vehicles are driving on roads with high penetration rates, they are prone to conflicts with other vehicles during lane-changing, and may even fail to find a suitable opportunity to change lanes, making it impossible for them to change lanes safely and in a timely manner. Summary of the Invention

[0004] This specification provides a multi-vehicle cooperative lane-changing method to solve the problem that existing lane-changing methods for autonomous vehicles cannot change lanes safely and in a timely manner.

[0005] To solve the above-mentioned technical problems, the embodiments in this specification are implemented as follows:

[0006] This specification provides an embodiment of a multi-vehicle cooperative lane-changing method, which may include:

[0007] Acquire traffic participant information within a preset range of the target vehicle sent by the roadside sensing device; the target vehicle is a vehicle waiting to change lanes.

[0008] Based on the traffic participant information, it is determined whether a cooperating vehicle exists; the cooperating vehicle is located in a different lane from the target vehicle; the cooperating vehicle is a vehicle that needs to adjust its speed to ensure that the target vehicle safely enters the lane it is about to enter.

[0009] If a cooperating vehicle exists, then determine the vehicle information of the cooperating vehicle;

[0010] Based on the vehicle information of the target vehicle and the vehicle information of the cooperating vehicle, a cooperative driving instruction is generated.

[0011] The cooperative driving instruction is sent to the cooperative vehicle so that the cooperative vehicle can leave lane-changing space for the target vehicle to change lanes.

[0012] At least one embodiment in this specification can achieve the following beneficial effects: by acquiring traffic participant information within a preset range of the target vehicle sent by the roadside sensing device; determining whether there is a cooperating vehicle based on the traffic participant information; if there is a cooperating vehicle, determining the vehicle information of the cooperating vehicle; generating a cooperative driving instruction based on the vehicle information of the target vehicle and the vehicle information of the cooperating vehicle; sending the cooperative driving instruction to the cooperating vehicle so that the cooperating vehicle leaves lane-changing space for the target vehicle to change lanes, enabling the target vehicle to safely and timely complete the lane change with the cooperation of other vehicles. Attached Figure Description

[0013] To more clearly illustrate the technical solutions in the embodiments or prior art of this specification, the drawings used in the description of the embodiments or prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0014] Figure 1 This is a schematic diagram of the overall scheme architecture of a multi-vehicle cooperative lane-changing method provided in the embodiments of this specification in a practical application scenario;

[0015] Figure 2 This is a flowchart illustrating a multi-vehicle cooperative lane-changing method provided in the embodiments of this specification;

[0016] Figure 3 This is a schematic diagram illustrating how to resolve lane-changing conflicts involving multiple vehicles, as provided in the embodiments of this specification.

[0017] Figure 4 This is a vehicle speed planning system provided in the embodiments of this specification. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of one or more embodiments of this specification clearer, the technical solutions of one or more embodiments of this specification will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this specification, and not all of them. Based on the embodiments in this specification, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of one or more embodiments of this specification.

[0019] The technical solutions provided in the various embodiments of this specification are described in detail below with reference to the accompanying drawings.

[0020] In existing technologies, autonomous vehicles typically determine the appropriate time to change lanes based on the surrounding environment and plan lane changes autonomously. However, when autonomous vehicles are driving on roads with high penetration rates, they are prone to conflicts with other vehicles during lane changes, and may even be unable to find a suitable time to change lanes, thus preventing them from changing lanes in a timely manner.

[0021] To address the shortcomings of existing technologies, this solution provides the following embodiments:

[0022] Figure 1 This is a schematic diagram of the overall architecture of a multi-vehicle cooperative lane-changing method in a practical application scenario, as described in the embodiments of this specification.

[0023] like Figure 1 As shown, the scheme mainly includes: a roadside sensing device 1, a server 2, a cooperating vehicle 3, and a target vehicle 4. In practical applications, the roadside sensing device 1 can sense the vehicle information of each vehicle on the road and the road environment information, and send this vehicle information and road environment information to the server 2. The target vehicle 4 can also report its own vehicle information to the server 2. The server 2 can determine whether the target vehicle 4 needs to cooperate in lane changing based on the vehicle information of the target vehicle 4 and the information sent by the roadside sensing device. When it is determined that the target vehicle 4 needs to cooperate in lane changing, the server 2 plans for both the cooperating vehicle 3 and the target vehicle 4, and sends the planning results to the cooperating vehicle 3 and the target vehicle 4 respectively, so that the cooperating vehicle 3 can cooperate with the target vehicle 4 to complete the lane change.

[0024] Figure 2 This is a flowchart illustrating a multi-vehicle cooperative lane-changing method provided in an embodiment of this specification. From a programming perspective, the entity executing the process can be a program or application client mounted on an application server or cloud control system.

[0025] like Figure 2 As shown, the process may include the following steps:

[0026] Step 202: Obtain traffic participant information within a preset range of the target vehicle sent by the roadside sensing device; the target vehicle is a vehicle waiting to change lanes.

[0027] In the embodiments of this specification, the target vehicle can be a vehicle that the server determines needs to change lanes based on the driving plan contained in the vehicle, or it can be a vehicle whose uploaded vehicle information contains a lane-change request. Based on the location information contained in the vehicle information uploaded by the target vehicle and the location information contained in the vehicle information uploaded by the roadside sensing device, the corresponding traffic participant information, such as vehicles, within a preset range of the target vehicle can be found. This preset range information can be a search for vehicles within a 100-meter radius forward and backward from the target vehicle on the road where the target vehicle is located. The value of the range can be set according to the specific road conditions and is not specifically limited here.

[0028] Step 204: Based on the traffic participant information, determine whether there is a cooperating vehicle; the cooperating vehicle is located in a different lane from the target vehicle; the cooperating vehicle is a vehicle that needs to adjust its speed to ensure that the target vehicle safely enters the lane it is about to enter.

[0029] In this embodiment, the cooperating vehicle is a vehicle located in the target lane that the target vehicle is about to enter and which may obstruct the target vehicle from changing lanes. This cooperating vehicle needs to adjust its speed so that the target vehicle can safely and smoothly enter the lane. Determining whether a cooperating vehicle exists primarily involves determining if there is space available for the target vehicle to change lanes. This can be done by determining whether the distance between the traffic participants and the target vehicle is greater than a set distance, based on the positions of the traffic participants and the target vehicle. If it is greater than a set threshold, it means that the target vehicle does not need to cooperate when changing lanes, and therefore no other vehicle cooperation is required; that is, no cooperating vehicle exists. Alternatively, it can be determined whether there are vehicles within the space available for the target vehicle to change lanes, based on the target vehicle's position information. If no vehicles exist, no cooperation is needed, and therefore no other vehicle cooperation is required; that is, no cooperating vehicle exists.

[0030] Step 206: If there is a cooperating vehicle, determine the vehicle information of the cooperating vehicle.

[0031] In the embodiments of this specification, if a cooperating vehicle is present, it indicates that there is no space for the target vehicle to change lanes in the target lane, and other vehicles are needed to cooperate in order to enter smoothly and in a timely manner. Alternatively, it could mean that the distance between the traffic participant and the target vehicle is less than or equal to a set threshold, or that other vehicles exist within the target vehicle's lane-changing space. The vehicle closest to the target vehicle among the other vehicles is identified as the cooperating vehicle, and its vehicle information is obtained. There can also be multiple cooperating vehicles; the cooperating vehicles that need to cooperate with the target vehicle to change lanes can be determined based on the actual vehicle distribution.

[0032] Step 208: Generate a cooperative driving instruction based on the vehicle information of the target vehicle and the vehicle information of the cooperating vehicle.

[0033] In the embodiments described in this specification, the coordination vehicle can be determined to accelerate or decelerate based on its positional relationship with the target vehicle, in order to provide lane-changing space for the target vehicle. Considering that the target vehicle may decelerate and turn when changing lanes, vehicles located behind the target vehicle and in the lane to be entered are generally considered as coordination vehicles. Deceleration planning can be implemented for coordination vehicles behind the target vehicle, causing them to slow down and increase the distance between them, leaving lane-changing space for the target vehicle. Based on this deceleration planning, the target speed of the coordination vehicle is determined, and a coordination driving command is generated based on the target speed.

[0034] In practical applications, a vehicle positioned in front of the target vehicle and in the lane it is about to enter can be designated as the first cooperating vehicle, and a vehicle positioned behind the target vehicle and in the same lane can be designated as the second cooperating vehicle. In this case, the distance between the first cooperating vehicle and the target vehicle is extremely close, typically within 10 meters. For the first cooperating vehicle, acceleration planning can be implemented; for the second cooperating vehicle, deceleration planning can be implemented, allowing both vehicles sufficient space for lane changing for the target vehicle. The target speeds of the corresponding cooperating vehicles are determined based on the acceleration and deceleration plans, thereby generating the corresponding cooperative driving instructions.

[0035] Step 210: Send the cooperative driving instruction to the cooperative vehicle so that the cooperative vehicle can leave lane-changing space for the target vehicle to change lanes.

[0036] In the embodiments described in this specification, a cooperative driving command can be sent to the corresponding cooperative vehicle. The control system in the cooperative vehicle can control the cooperative vehicle to drive as expected according to the cooperative driving command, so that the cooperative vehicle can leave lane-changing space for the target vehicle to change lanes.

[0037] It should be understood that the order of some steps in the methods described in one or more embodiments of this specification may be interchanged according to actual needs, or some steps may be omitted or deleted.

[0038] Figure 2 The method involves acquiring traffic participant information within a preset range of the target vehicle sent by roadside sensing devices; determining whether a cooperating vehicle exists based on the traffic participant information; if a cooperating vehicle exists, determining its vehicle information; generating a cooperative driving instruction based on the target vehicle's vehicle information and the cooperating vehicle's vehicle information; and sending the cooperative driving instruction to the cooperating vehicle so that the cooperating vehicle can leave lane-changing space for the target vehicle to change lanes, enabling the target vehicle to safely and timely complete the lane change with the cooperation of other vehicles.

[0039] based on Figure 2In addition to the method described herein, this specification also provides some specific implementation methods of this method, which will be described below.

[0040] Optionally, the determination of whether a cooperating vehicle exists based on the traffic participant information, as described in the embodiments of this specification, may specifically include:

[0041] The coordination range is determined based on the speed of the target vehicle and the preset duration.

[0042] Based on the location of the target vehicle and the traffic participant information, determine whether there are any vehicles within the cooperative range behind the target vehicle in the target lane to be entered;

[0043] If there is a vehicle within the cooperative range located behind the target vehicle in the target lane, then that vehicle is identified as a cooperative vehicle.

[0044] In the embodiments of this specification, a preset travel distance can be obtained by calculating the preset travel time of the target vehicle at its current constant speed. The target vehicle is projected onto the corresponding position of the lane to be entered, and this position is taken as the projection position. Taking the prescribed travel direction of the target vehicle as the positive direction, and the projection position as the origin, the preset travel distance is extended backward along the lane to be entered to obtain the cooperation range. For example: the target vehicle is currently at position A in lane 1 and needs to enter lane 2. The target vehicle's current travel speed is 90 km / h, and the preset travel time is 4 seconds. The calculated preset travel distance = 90 km / h * 4 seconds = 100 meters. The target vehicle is projected onto the corresponding position in lane 2, that is, the target vehicle is translated to lane 2, obtaining the projected vehicle position A1. The lane range 100 meters after A1, which is opposite to the travel direction, is set as the cooperation range. It can be determined whether there is a vehicle within the cooperation range. If there is a vehicle, it is determined to be a cooperation vehicle; if there is no vehicle, it is determined that the vehicle does not need cooperation.

[0045] To ensure greater accuracy in identifying the cooperating vehicle, the method of identifying the vehicle as a cooperating vehicle in the embodiments of this specification may specifically include:

[0046] If there are multiple vehicles within the cooperative range located behind the target vehicle in the target lane, the vehicle closest to the target vehicle will be designated as the cooperative vehicle.

[0047] In the embodiments described in this specification, if the target vehicle is within a queue, the vehicle closest to the target vehicle within the coordination range, as well as all subsequent vehicles belonging to the same queue, are considered as cooperating vehicles. This ensures that the cooperating vehicles can maintain queue movement and reserve lane-changing space for the target vehicle. Regardless of whether there is a queue, only the vehicle closest to the target vehicle within the coordination range can be considered as a cooperating vehicle.

[0048] To enable the cooperating vehicle to reserve space for lane changing, the generation of cooperative driving instructions described in this specification embodiment may specifically include:

[0049] Based on the speed information of the cooperating vehicle and the speed information of the target vehicle, the first target speed of the cooperating vehicle is calculated using a cooperative decision-making algorithm.

[0050] The cooperative driving command is generated based on the first target speed.

[0051] The cooperative decision-making algorithm in the embodiments of this specification can calculate the first target acceleration of the cooperative vehicle based on the speed information of the target vehicle, the speed information of the cooperative vehicle, the position information of the target vehicle, and the speed information of the cooperative vehicle. The first target speed of the cooperative vehicle can be calculated based on the first target acceleration, and a cooperative driving command can be generated based on the first target speed. Alternatively, the first target speed of the cooperative vehicle can be calculated based on other existing cooperative decision-making algorithms.

[0052] The collaborative decision-making algorithm in this embodiment can plan the driving trajectories of the target vehicle and the collaborating vehicles, simulate the planned driving trajectories of the target vehicle and the collaborating vehicles, select the best simulation result (i.e., the highest score) based on the simulation results, and determine the first target driving state of the collaborating vehicles and the second target driving state of the target vehicle based on the selected plan. The target driving state may include the target speed and the corresponding driving action, such as going straight, turning left, and turning right.

[0053] In order to enable the target vehicle to successfully complete the lane change, the method described in the embodiments of this specification may further include:

[0054] Based on the target vehicle's current driving lane and the target lane it is about to enter, a lane change instruction is generated using a collaborative decision-making algorithm; the lane change instruction is used to indicate that the target vehicle should adjust its driving direction.

[0055] Based on the speed information of the target vehicle, the second target speed of the target vehicle is calculated using the collaborative decision-making algorithm;

[0056] Based on the lane change instruction and the second target speed information, a lane change driving command is generated so that the target vehicle can complete the lane change according to the lane change driving command.

[0057] The cooperative decision-making algorithm in the embodiments of this specification can preset the target vehicle's driving trajectory based on the target vehicle information and the cooperative vehicle information, and calculate the target vehicle's second target speed based on the position information contained in the target vehicle's driving trajectory, the target vehicle information, and the cooperative vehicle information. The lane-changing instruction can include a command prompting the target vehicle to adjust its driving direction. The lane-changing instruction is generated when the target vehicle is eligible to change lanes, i.e., when the cooperative vehicle has cooperated to create space for the target vehicle to change lanes. The second target speed can be the speed the target vehicle needs to reach when changing lanes, or the speed the target vehicle needs to reach when completing the lane change. A lane-changing driving command can be generated based on the lane-changing instruction and the second target speed, so that the target vehicle's control system can control the target vehicle to safely and smoothly complete the lane change according to the lane-changing driving command.

[0058] Given that there may be multiple lane-changing needs and lane-changing conflicts, in order to ensure the safety of lane changing, in the embodiments of this specification, if there are two vehicles to enter the target lane, the distance between the two vehicles is less than a preset distance, the first vehicle is located in the adjacent lane on one side of the target lane, and the second vehicle is located in the adjacent lane on the other side.

[0059] Before acquiring the traffic participant information within a preset range of the target vehicle sent by the roadside sensing device, the process may further include:

[0060] Based on the collaborative decision-making algorithm, the timing of the first vehicle and the second vehicle completing the lane change is determined;

[0061] Based on the aforementioned timing sequence, the vehicle that has priority in changing lanes is identified as the target vehicle.

[0062] In the embodiments of this specification, when multiple vehicles are waiting to change lanes and lane-changing conflicts exist, it is necessary to determine their lane-changing order so that they can complete the lane changes sequentially, ensuring timely and smooth completion. Lane-changing conflicts can be understood as follows: the middle lane is the lane to be entered, and vehicles needing to change lanes to the middle lane exist at similar or corresponding positions on both sides of the lane. The collaborative decision-making algorithm can determine the lane-changing order of conflicting vehicles based on vehicle information. If the first vehicle changes lanes first, it becomes the target vehicle during its lane-changing process; after the first lane-changing is completed, the second vehicle becomes the target vehicle for its lane-changing.

[0063] Figure 3 This is a schematic diagram illustrating an embodiment of the present specification for resolving lane-changing conflicts involving multiple vehicles. Figure 3 As shown, 1, 2, and 3 can represent lanes, vehicles A and B can represent disabled vehicles that are prohibited from driving, and vehicles C and D can represent two vehicles that need to change lanes and have a lane-changing conflict. Figure 3The upper half of the diagram represents the distribution of vehicles before lane changes. Since both lanes 1 and 3 have disabled vehicles and are impassable, vehicle C in lane 1 and vehicle D in lane 3 need to change lanes to lane 2 to avoid collisions. According to the collaborative decision-making algorithm, vehicle C can change lanes first. After vehicle C completes its lane change, vehicle D then begins its lane change, resolving the lane-changing conflict between the two vehicles. Figure 3 The lower half of the diagram can represent the distribution of vehicles when vehicle C has completed lane changing and vehicle D is changing lanes.

[0064] To reduce the probability of accidents, the method described in this specification, which uses a collaborative decision-making algorithm to determine the timing of lane changes for the first and second vehicles, may specifically include:

[0065] Based on the Markov decision method and the vehicle information of each vehicle, multiple driving decisions are determined for the vehicle to be driven into the target lane.

[0066] Based on the Monte Carlo tree search method and the driving status of each vehicle, the multiple driving decisions are simulated to obtain the simulation results corresponding to the multiple driving decisions.

[0067] Based on the simulation results, the decision value of the multiple driving decisions is determined;

[0068] The driving decision with the highest decision value among the multiple driving decisions is taken as the target driving decision;

[0069] The lane-changing sequence of the first vehicle and the second vehicle is determined based on the target driving decision.

[0070] The Markov decision method in the embodiments of this specification can be an optimal decision process for stochastic dynamic systems based on Markov process theory. It can be a rule provided to the decision-maker to select actions at various times, denoted as π = (π0, π1, π2, ..., πn, πn+1...), where πn is the rule for selecting actions at time n. Theoretically, to find the optimal strategy πn over a wide range, it is best to select the optimal strategy based on history before time n, or even randomly. When the Markov decision method determines multiple optimal decisions, a Monte Carlo tree search method can be used to simulate each decision, and the value of each decision can be determined based on the simulation results. If a conflict occurs during the simulation, a negative score is given; if the decision can complete the target action and reach the target speed, a positive score is given. Positive scores can be divided according to the degree of alignment between the completed action and the target; higher alignment results in higher scores, and lower alignment results in lower scores. Finally, the scores corresponding to each time step in each decision are integrated and calculated, and the decision with the highest score, i.e., the highest decision value, is determined as the target decision. The timing of lane changes is determined based on the result of the target decision.

[0071] To facilitate the determination of the lane-changing needs of the target vehicle, the method described in the embodiments of this specification may further include:

[0072] Obtain the expected exit from the vehicle's driving plan;

[0073] Determine whether the distance between the expected exit and the target vehicle is less than or equal to a first distance threshold;

[0074] If the distance between the expected exit and the target vehicle is less than or equal to a first distance threshold, then the lane corresponding to the expected exit is determined as the lane the target vehicle is to enter.

[0075] In the embodiments of this specification, the vehicle driving plan can be a driving route determined before the autonomous vehicle departs, or a driving route replanned by the autonomous vehicle when it deviates from the expected plan during driving. The expected exit of the target vehicle can be determined based on this driving route. This expected exit can be an exit from a highway or an intersection where the vehicle needs to enter a road. If the lane currently being driven by the target vehicle is inconsistent with the lane corresponding to the expected exit, it can be determined whether the distance between the target vehicle and the expected exit is less than or equal to a first distance threshold, such as 200 meters, to determine whether the target vehicle needs to change lanes.

[0076] In practical applications, the target vehicle can also be a vehicle that needs to change lanes when lane-level allocation is performed using dynamic programming methods. Alternatively, it can be a vehicle that needs to change lanes during autonomous driving when there is a treacherous area ahead of its current lane. Treacherous areas can be caused by traffic accidents or abnormal road conditions. Lane-level allocation aims to increase the average vehicle speed and road throughput (the number of vehicles passing through per unit time), thereby improving the logistics efficiency of unmanned logistics vehicles in trunk line logistics.

[0077] To improve the traffic efficiency of target vehicles, before acquiring road condition information within a preset range of the target vehicle sent by the roadside sensing device as described in the embodiments of this specification, the following may also be included:

[0078] Obtain the positions of multiple vehicles in the target road segment where the target vehicle is located;

[0079] Based on the positions of the multiple vehicles, determine whether the distance between two adjacent vehicles is less than a second distance threshold;

[0080] If the distance between two adjacent vehicles is less than a second distance threshold, then the two adjacent vehicles are divided into the same queue; the target vehicle is a vehicle in the same queue.

[0081] In this embodiment of the specification, to improve vehicle traffic efficiency and logistics efficiency, vehicles on the road segment where the target vehicle is located can be platooned. This allows vehicles within a platoon to maintain a small distance (e.g., 20 meters) and vehicles between platoons to maintain a larger distance (e.g., 100 meters), thereby improving fuel efficiency and road throughput, and avoiding traffic congestion. In practical applications, the distance between two vehicles can be used to determine whether they belong to the same platoon.

[0082] In the embodiments of this specification, one of the two adjacent vehicles is a vehicle in a queue; before dividing the two adjacent vehicles into the same queue, the following may also be included:

[0083] Determine whether the number of vehicles in the queue to which the vehicle belongs is less than a preset number;

[0084] The step of dividing the two adjacent vehicles into the same queue specifically includes:

[0085] If the number of vehicles in the queue of a vehicle is less than a preset number, then the two adjacent vehicles will be assigned to the same queue.

[0086] In the embodiments of this specification, if one of the two vehicles is already in a queue, it is first necessary to determine whether the queue containing the vehicle already in the queue has reached its maximum number of vehicles. If it has not reached the maximum number and the distance between the two vehicles meets the requirements, they are assigned to the same queue. Otherwise, the other vehicle not in a queue is designated as the lead vehicle of the new queue. In practical applications, it is best to keep the number of vehicles in a queue to within 15 to avoid lane changes being hindered by excessively long queues. The lead vehicle in the queue can determine its target speed using an adaptive cruise control algorithm, while other vehicles in the queue can determine their target speeds using a fixed-distance following algorithm, so that a large distance is maintained between queues and a small distance is maintained between vehicles within the same queue.

[0087] In practical applications, when a target vehicle changes lanes, it has already left the queue. However, the target vehicle that has completed the lane change still needs to be re-entered into the queue. For cooperating vehicles, either the cooperating vehicle and the vehicles behind it that belong to the same queue can travel according to the same cooperative driving instruction to maintain the queue, or they can all be treated as vehicles that have left the queue, and then re-entered into the queue after the target vehicle has completed the lane change.

[0088] Figure 4 This specification provides a vehicle speed planning system according to its embodiments. The system may include three service modules: a multi-vehicle lane allocation service module, a cooperative adaptive cruise control service module, and a cooperative lane changing service module. The multi-vehicle lane allocation service module can calculate the vehicle's target lane based on road environment information and vehicle information, and calculate the vehicle's target speed based on the target lane and vehicle information, so that the vehicle can travel to the allocated target lane at the target speed.

[0089] The cooperative adaptive cruise service module can be used to platoon vehicles within a preset distance range, such as 200 meters. Then, it calculates the target speed for the vehicles in the platoon. For the lead vehicle in the platoon or vehicles outside the platoon, the adaptive cruise algorithm is used to calculate the target speed. For the following vehicles in the platoon, the fixed-distance following algorithm is used to calculate the target speed, so that each vehicle in the platoon can drive according to the corresponding target speed.

[0090] The cooperative lane-changing service module can be used to match cooperative vehicles when a vehicle seeking a lane change has no available space. Based on a cooperative decision-making algorithm, it plans the speeds of both the cooperative vehicle and the target vehicle, enabling them to travel according to the speed planning results so that the target vehicle can complete the lane change. It should be understood that when the target vehicle needs to change lanes, some vehicles may need to leave the platoon. After completing the lane change, they can be re-formed using the cooperative adaptive cruise control service.

[0091] The system's operation status is as follows: Figure 4 As shown, it may include:

[0092] Step 402: Use thread 0 to assign lanes to the vehicle; the vehicle is an autonomous vehicle.

[0093] In the embodiments of this specification, if a vehicle is in a lane-assignment pending state, thread 0 can be used with a multi-vehicle lane allocation service module to calculate the vehicle's target lane based on road environment information and vehicle information. The lane-assignment pending state can include at least one of the following: a vehicle that has just entered a preset length range and has not yet been assigned a lane; a vehicle that needs to avoid impassable areas; or a vehicle that needs to exit or enter a road from a predetermined intersection. Road environment image information can include road throughput, the distribution of vehicles on the road, and road condition information. This allows vehicles to be assigned to the target lane through the multi-vehicle lane allocation service module, guiding vehicles to change lanes or maintain their current lane, optimizing average traffic speed, and improving road throughput.

[0094] Step 404: When the vehicle does not require lane allocation, use thread 1 to determine the following mode of the vehicle based on the queue construction result.

[0095] In the embodiments described in this specification, when lane assignment is not required, the cooperative adaptive cruise service module, using thread 1, can queue vehicles, enabling them to travel according to the queue, reducing traffic congestion and improving fuel efficiency. Once a vehicle is queued, the queue construction result can determine whether the vehicle belongs to a following vehicle, the lead vehicle, or is outside the queue. If it belongs to a following vehicle, its driving mode is determined to be a fixed-distance following mode; if it belongs to the lead vehicle or is outside the queue, its driving mode is determined to be adaptive cruise mode. In the cooperative adaptive cruise service module, considering that excessively long queues can cause lane-changing obstacles, a maximum of 15 vehicles are allowed in a single queue.

[0096] Step 406: Using thread A, determine the necessity of single-vehicle lane-changing coordination for the vehicle.

[0097] In the embodiments of this specification, the cooperative lane-changing service module can be used at least to determine the necessity of single-vehicle lane-changing coordination. This includes determining whether the vehicle to be changed lanes can change lanes according to the target lane, whether there is lane-changing space in the lane the vehicle is about to enter, and whether the vehicle will be obstructed by other autonomous vehicles or face a collision risk when changing lanes. If no lane-changing space exists, lane-changing coordination is required. When lane-changing space exists, the vehicle to be changed lanes does not need coordination. The multi-vehicle lane allocation service module can perform speed planning for the vehicle to be changed, obtain a target speed, generate instructions based on the target speed and target lane, and complete the lane change according to the instructions.

[0098] Step 408: Using thread A, perform speed planning for the vehicle according to the following mode.

[0099] In the embodiments of this specification, the cooperative adaptive cruise service module can at least be used to calculate the target speed of a vehicle based on the following mode. If the vehicle is in adaptive cruise mode (i.e., it is outside the queue or the lead vehicle in the queue), the target speed can be calculated according to the adaptive cruise algorithm. If the vehicle is in fixed-distance following mode (i.e., it is following another vehicle in the queue), the target speed can be calculated according to the fixed-distance following algorithm. This allows vehicles in the queue to travel at a set distance, improving fuel efficiency and road throughput.

[0100] Step 410: If the vehicle needs to cooperate, send a cooperation request to thread 2; use thread 2 to match a cooperating vehicle.

[0101] In the embodiments of this specification, the cooperative lane-changing service module can be used to match cooperative vehicles. The cooperative request may include information such as the vehicle's identification information, speed information, location information, current lane information, and target lane information. Thread 2 searches for vehicles that obstruct the lane-changing of the vehicle to be changed based on the cooperative request information, and selects the autonomous vehicle closest to the vehicle to be changed in the target lane as the cooperative vehicle. Alternatively, the autonomous vehicle closest to the vehicle to be changed in the target lane, as well as other vehicles behind it belonging to the same queue, can also be selected as cooperative vehicles.

[0102] Step 412: Calculate the target speed of the vehicle using a collaborative decision-making algorithm based on the vehicle information of the cooperative vehicle and the vehicle information of the vehicle.

[0103] The cooperative lane-changing service module in the embodiments of this specification can at least be used to determine the lane-changing decision of a vehicle based on a cooperative decision-making algorithm. This lane-changing decision can at least include the vehicle's target speed.

[0104] Step 414: Generate an instruction based on the target speed of the vehicle and send the instruction to the vehicle.

[0105] In the embodiments of this specification, if the autonomous vehicle is part of a queuing, the cooperative adaptive cruise service module can generate a command based on the target speed calculated by the following algorithm and send the command to the autonomous vehicle so that it can follow the queuing at the target speed. If the autonomous vehicle is a vehicle that can change lanes automatically without coordination, the multi-vehicle lane allocation service module can calculate the target speed based on the single-vehicle lane change planning algorithm and generate a command based on the target speed and target lane so that the autonomous vehicle can complete the lane change automatically. If the autonomous vehicle is a vehicle waiting to change lanes with coordination, the cooperative lane change service module can calculate the target speed of the vehicle waiting to change lanes based on the cooperative decision algorithm and generate a command based on the target speed and target lane so that the autonomous vehicle waiting to change lanes can complete the lane change with the coordination of other vehicles. It can be understood that if the autonomous vehicle is a cooperating vehicle, the cooperative decision algorithm can calculate the target speed of the cooperating vehicle and generate a command based on the target speed so that the cooperating autonomous vehicle can drive according to the command, reserving lane change space for the vehicle waiting to change lanes.

[0106] The above methods can accelerate the logistics efficiency and fuel efficiency of trunk logistics by constructing queues, improve the average driving speed and road throughput of vehicles by lane-level allocation of vehicles, and enable vehicles to change lanes in a timely manner through coordinated lane changing.

[0107] Based on the same idea, embodiments of this specification also provide an apparatus corresponding to the above method. This apparatus may include:

[0108] The traffic participant information acquisition module is used to acquire traffic participant information within a preset range of the target vehicle sent by the roadside sensing device; the target vehicle is a vehicle waiting to change lanes.

[0109] The cooperative vehicle determination module is used to determine whether a cooperative vehicle exists based on the traffic participant information; the cooperative vehicle and the target vehicle are located in different lanes; the cooperative vehicle is a vehicle that needs to adjust its speed to ensure that the target vehicle can safely enter the lane it is about to enter;

[0110] The collaborative vehicle information determination module is used to determine the vehicle information of the collaborative vehicle if a collaborative vehicle exists.

[0111] The cooperative driving instruction generation module is used to generate cooperative driving instructions based on the vehicle information of the target vehicle and the vehicle information of the cooperative vehicle.

[0112] The instruction sending module is used to send the cooperative driving instruction to the cooperative vehicle so that the cooperative vehicle can leave lane-changing space for the target vehicle to change lanes.

[0113] Following the same approach, embodiments of this specification also provide a device corresponding to the above-described method. The device may include:

[0114] At least one processor; and,

[0115] A memory communicatively connected to the at least one processor; wherein,

[0116] The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to:

[0117] Acquire traffic participant information within a preset range of the target vehicle sent by the roadside sensing device; the target vehicle is a vehicle waiting to change lanes.

[0118] Based on the traffic participant information, it is determined whether a cooperating vehicle exists; the cooperating vehicle is located in a different lane from the target vehicle; the cooperating vehicle is a vehicle that needs to adjust its speed to ensure that the target vehicle safely enters the lane it is about to enter.

[0119] If a cooperating vehicle exists, then determine the vehicle information of the cooperating vehicle;

[0120] Based on the vehicle information of the target vehicle and the vehicle information of the cooperating vehicle, a cooperative driving instruction is generated.

[0121] The cooperative driving instruction is sent to the cooperative vehicle so that the cooperative vehicle can leave lane-changing space for the target vehicle to change lanes.

[0122] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0123] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A multi-vehicle cooperative lane-changing method, characterized in that, include: Obtain the positions of multiple vehicles in the target road segment where the target vehicle is located; Based on the positions of the multiple vehicles, determine whether the distance between two adjacent vehicles is less than a second distance threshold; If the distance between two adjacent vehicles is less than a second distance threshold, then the two adjacent vehicles are divided into the same queue; the target vehicle is a vehicle in the same queue. Acquire traffic participant information within a preset range of the target vehicle sent by roadside sensing devices; The target vehicle is the vehicle waiting to change lanes; Based on the traffic participant information, determine whether there are any cooperating vehicles; The cooperating vehicle and the target vehicle are located in different lanes; the cooperating vehicle is a vehicle that needs to adjust its speed to ensure that the target vehicle safely enters the lane it is about to enter; If a cooperating vehicle exists, then determine the vehicle information of the cooperating vehicle; Based on the vehicle information of the target vehicle and the vehicle information of the cooperating vehicle, a cooperative driving instruction is generated. The cooperative driving instruction is sent to the cooperative vehicle so that the cooperative vehicle can leave lane-changing space for the target vehicle to change lanes; Vehicles that have completed the lane change will still be included in the queue; For cooperative vehicles, control the cooperative vehicle and the vehicles behind it that belong to the same queue to drive according to the same cooperative driving instruction; or treat the cooperative vehicle and the vehicles behind it that belong to the same queue as vehicles that have left the queue, and then regroup the vehicles that have left the queue after the target vehicle has completed the lane change.

2. The method according to claim 1, characterized in that, The step of determining whether a cooperating vehicle exists based on the traffic participant information specifically includes: The coordination range is determined based on the speed of the target vehicle and the preset duration. Based on the location of the target vehicle and the traffic participant information, determine whether there are any vehicles within the cooperative range behind the target vehicle in the target lane to be entered; If there is a vehicle within the cooperative range located behind the target vehicle in the target lane, then that vehicle is identified as a cooperative vehicle.

3. The method according to claim 2, characterized in that, The step of identifying the vehicle as a cooperative vehicle specifically includes: If there are multiple vehicles within the cooperative range located behind the target vehicle in the target lane, the vehicle closest to the target vehicle will be designated as the cooperative vehicle.

4. The method according to claim 1, characterized in that, The generation of cooperative driving instructions specifically includes: Based on the speed information of the cooperating vehicle and the speed information of the target vehicle, the first target speed of the cooperating vehicle is calculated using a cooperative decision-making algorithm. The cooperative driving command is generated based on the first target speed.

5. The method according to claim 1, characterized in that, The method further includes: Based on the target vehicle's current driving lane and the target lane it is about to enter, a lane change instruction is generated using a collaborative decision-making algorithm; the lane change instruction is used to indicate that the target vehicle should adjust its driving direction. Based on the speed information of the target vehicle, the second target speed of the target vehicle is calculated using the collaborative decision-making algorithm; Based on the lane change instruction and the second target speed information, a lane change driving command is generated so that the target vehicle can complete the lane change according to the lane change driving command.

6. The method according to claim 1, characterized in that, If there are two vehicles waiting to enter the target lane, and the distance between the two vehicles is less than the preset distance, the first vehicle is located in the adjacent lane on one side of the target lane, and the second vehicle is located in the adjacent lane on the other side. Before acquiring the traffic participant information within a preset range of the target vehicle sent by the roadside sensing device, the method further includes: Based on the collaborative decision-making algorithm, the timing of the first vehicle and the second vehicle completing the lane change is determined; Based on the aforementioned timing sequence, the vehicle that has priority in changing lanes is identified as the target vehicle.

7. The method according to claim 6, characterized in that, The step of determining the timing of the lane change by the first vehicle and the second vehicle according to the collaborative decision-making algorithm specifically includes: Based on the Markov decision method and the vehicle information of each vehicle, multiple driving decisions are determined for the vehicle to be driven into the target lane. Based on the Monte Carlo tree search method and the driving status of each vehicle, the multiple driving decisions are simulated to obtain the simulation results corresponding to the multiple driving decisions. Based on the simulation results, the decision value of the multiple driving decisions is determined; The driving decision with the highest decision value among the multiple driving decisions is taken as the target driving decision; The lane-changing sequence of the first vehicle and the second vehicle is determined based on the target driving decision.

8. The method according to claim 1, characterized in that, The method further includes: Obtain the expected exit from the vehicle's driving plan; Determine whether the distance between the expected exit and the target vehicle is less than or equal to a first distance threshold; If the distance between the expected exit and the target vehicle is less than or equal to a first distance threshold, then the lane corresponding to the expected exit is determined as the lane the target vehicle is to enter.

9. The method according to claim 1, characterized in that, One of the two adjacent vehicles is a vehicle in a queue; before dividing the two adjacent vehicles into the same queue, the process further includes: Determine whether the number of vehicles in the queue to which the vehicle belongs is less than a preset number; The step of dividing the two adjacent vehicles into the same queue specifically includes: If the number of vehicles in the queue of a vehicle is less than a preset number, then the two adjacent vehicles will be assigned to the same queue.

Images