Vehicle lane-changing decision-making methods, devices, computer equipment, and storage media

Abstract

This application relates to a vehicle lane-changing decision-making method, apparatus, computer device, and storage medium. The method includes: acquiring surrounding environmental information of the vehicle; determining a trajectory evaluation result for switching to a target lane based on the surrounding environmental information; and determining a lane-changing decision result based on the trajectory evaluation result, user instructions, and preset navigation information. This method, by evaluating the trajectory of the target lane and comprehensively considering lane-changing demands from multiple sources, can output a safer optimal trajectory result based on real-time traffic conditions. This improves the safety, rationality, and real-time performance of the trajectory results generated from lane-changing intention decisions and lane-changing implementation decisions, and reduces the adverse impact of lane changing on traffic.

Description

Technical Field

[0001] This application relates to the field of autonomous driving technology, and in particular to a vehicle lane-changing decision-making method, apparatus, computer device, and storage medium. Background Technology

[0002] With the rise of the concept of autonomous driving, the core of the entire field's development is the autonomous driving system. As we all know, the autonomous driving system is the function of using onboard sensor systems to perceive the road environment and, based on the perceived road, vehicle position, and obstacle information, control the vehicle's steering, lane-changing trajectory, and speed, thereby enabling the vehicle to drive safely and reliably on the road and reach the predetermined destination.

[0003] At present, lane change decision-making in Baidu Apollo platform is the mainstream in autonomous driving research and application. The lane change intention in the decision-making scheme is basically obtained by parsing high-precision map navigation information. A series of trajectories are generated by sampling the end state, and then the trajectory is evaluated. This decision-making algorithm is more like a trajectory selector, which selects the trajectory with the highest ranking through different evaluation functions.

[0004] In traditional technical solutions for lane-changing decisions, the lane-changing trajectory is usually selected after successful calculation, lacking comprehensive evaluation, which directly leads to low safety and poor real-time performance of the output trajectory. Summary of the Invention

[0005] Therefore, it is necessary to provide a vehicle lane-changing decision-making method, device, computer equipment, and storage medium to address the aforementioned technical problems.

[0006] Firstly, this application provides a vehicle lane-changing decision-making method, the method comprising:

[0007] Obtain information about the vehicle's surrounding environment;

[0008] Based on the surrounding environment information, the trajectory evaluation result for switching to the target lane is determined;

[0009] The lane-changing decision is determined based on the trajectory evaluation results, user instructions, and preset navigation information.

[0010] In one embodiment, obtaining the vehicle's surrounding environment information includes:

[0011] Obtain at least one of the following: road information, vehicle driving information, and surrounding obstacle information.

[0012] In one embodiment, the process of determining the trajectory evaluation result for switching to the target lane based on the surrounding environment information includes:

[0013] The lane change request and target lane are determined based on at least one of the user's lane change command, preset navigation information, and vehicle driving status.

[0014] In one embodiment, determining the lane-changing requirement and the target lane based on the vehicle's driving status includes:

[0015] Get the vehicle's speed;

[0016] If the vehicle's speed is less than a preset threshold, the expected lane-changing behavior in the adjacent lanes is evaluated.

[0017] The target lane is determined based on the assessment results.

[0018] In one embodiment, the trajectory evaluation result for switching to the target lane based on the surrounding environment information includes:

[0019] Multiple candidate trajectories are determined based on the target lane;

[0020] Trajectory stability is determined based on the number of times each candidate trajectory is identified as the optimal trajectory within a preset time period;

[0021] The lane-changing efficiency of each candidate trajectory is determined based on the estimated lane-changing time.

[0022] The impact of each candidate trajectory is determined based on the area occupied by the target lane during the lane change process;

[0023] The risk level of each candidate trajectory is determined based on the probability of collision with the vehicle in front during lane changing.

[0024] The trajectory evaluation result for each candidate trajectory is determined based on trajectory stability, lane-changing efficiency, impact level, and risk level.

[0025] In one embodiment, the trajectory evaluation result for each candidate trajectory, based on trajectory stability, lane-changing efficiency, impact level, and risk level, further includes:

[0026] The trajectory stability, lane-changing efficiency, impact degree, and risk degree are weighted and summed to obtain the evaluation value of each candidate trajectory;

[0027] The optimal trajectory is determined based on the evaluation value and is used as the trajectory evaluation result.

[0028] In one embodiment, determining the lane-changing decision result based on the trajectory evaluation result, user instructions, and preset navigation information includes:

[0029] If any of the trajectory evaluation results, user instructions, and preset navigation information does not meet the preset conditions, the lane change decision result is no lane change.

[0030] Secondly, this application also provides a vehicle lane-changing decision-making device. The device includes:

[0031] The acquisition module is used to acquire information about the vehicle's surrounding environment.

[0032] The evaluation module is used to determine the trajectory evaluation result for switching to the target lane based on the surrounding environmental information;

[0033] The decision module is used to determine the lane-changing decision result based on the trajectory evaluation result, user instructions, and preset navigation information.

[0034] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0035] Obtain information about the vehicle's surrounding environment;

[0036] Based on the surrounding environment information, the trajectory evaluation result for switching to the target lane is determined;

[0037] The lane-changing decision is determined based on the trajectory evaluation results, user instructions, and preset navigation information.

[0038] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0039] Obtain information about the vehicle's surrounding environment;

[0040] Based on the surrounding environment information, the trajectory evaluation result for switching to the target lane is determined;

[0041] The lane-changing decision is determined based on the trajectory evaluation results, user instructions, and preset navigation information.

[0042] The aforementioned vehicle lane-changing decision-making method, device, computer equipment, and storage medium acquire information about the vehicle's surrounding environment; determine a trajectory evaluation result for switching to the target lane based on the surrounding environment information; and determine the lane-changing decision result based on the trajectory evaluation result, user instructions, and preset navigation information. This allows for the output of a safer optimal trajectory result based on real-time traffic conditions, improving the safety, rationality, and real-time performance of the final lane-changing trajectory. Attached Figure Description

[0043] Figure 1 This is a diagram illustrating the application environment of a vehicle lane-changing decision-making method in one embodiment.

[0044] Figure 2This is a flowchart illustrating a vehicle lane-changing decision-making method according to an embodiment of the present invention.

[0045] Figure 3 This is a schematic diagram illustrating the lane-changing requirements and target lane determination of the vehicle lane-changing decision method in one embodiment of the present invention.

[0046] Figure 4 This is a schematic diagram of the trajectory stability evaluation process in one embodiment of the present invention;

[0047] Figure 5 This is a schematic diagram illustrating the implementation of the lane-changing decision result of the vehicle lane-changing decision method in one embodiment of the present invention.

[0048] Figure 6 This is a structural block diagram of a vehicle lane-changing decision device according to one embodiment of the present invention;

[0049] Figure 7 This is an internal structural diagram of a computer device according to one embodiment of the present invention. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0051] An autonomous driving system is a function that uses onboard sensor systems to perceive the road environment and, based on the perceived information about the road, vehicle position, and obstacles, controls the vehicle's steering, lane-changing trajectory, and speed, thereby enabling the vehicle to travel safely and reliably on the road and reach a predetermined destination.

[0052] At present, lane change decision-making in Baidu Apollo platform is the mainstream in autonomous driving research and application. The lane change intention in the decision-making scheme is basically obtained by parsing high-precision map navigation information. A series of trajectories are generated by sampling the end state, and then the trajectory is evaluated. This decision-making algorithm is more like a trajectory selector, which selects the trajectory with the highest ranking through different evaluation functions.

[0053] The vehicle lane-changing decision method provided in this application embodiment can be applied to, for example, Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located in the cloud or on other network servers. When a user performs a current action on terminal 102, terminal 102 transmits the current action data to server 104. Server 104 obtains information about the vehicle's surrounding environment; based on the surrounding environment information, it determines the trajectory evaluation result for switching to the target lane; and based on the trajectory evaluation result, user instructions, and preset navigation information, it determines the lane-changing decision result. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, and smart in-vehicle devices. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted devices. Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0054] In one embodiment, such as Figure 2 As shown, a vehicle lane-changing decision method is provided. This embodiment uses the application of this method to a terminal as an example for illustration. It can be understood that this method can also be applied to a server, and can also be applied to a system including a terminal and a server, and can be implemented through the interaction between the terminal and the server.

[0055] In this embodiment, the method includes the following steps:

[0056] Step S201: Obtain information about the vehicle's surrounding environment.

[0057] Among them, the surrounding environment information of the vehicle refers to the environmental information that affects the target vehicle's decisions such as driving, changing lanes, and turning in autonomous driving.

[0058] Specifically, the vehicle generates various data during its operation, including data about the vehicle itself and data about obstacles around it. Optionally, data about the vehicle and its surroundings can be acquired using sensors such as GPS, IMU, cameras, and LiDAR, and then artificial intelligence and other technologies can be used to identify the type, location, speed, and other information of the obstacles based on this data.

[0059] Step S202: Determine the trajectory evaluation result for switching to the target lane based on the surrounding environment information.

[0060] Specifically, once the surrounding environment information of the vehicle is determined, if a lane change is to be performed, there are multiple trajectories to choose from. Based on the environmental information, the result of lane change based on each trajectory can be predicted to determine the feasibility of each trajectory. For the trajectory clusters in the scenario within a preset time period, further trajectory scoring estimation is performed to determine the feasibility of each target lane.

[0061] Step S203: Determine the lane change decision result based on the trajectory evaluation result, user instructions, and preset navigation information.

[0062] It is understandable that determining the final lane change result based solely on one of the trajectory evaluation results, the user instructions, and the preset navigation information is very one-sided, and the output result itself may not meet the needs of real-time lane changing. Combining the trajectory evaluation results, real-time user instructions, and preset navigation information for analysis can comprehensively consider the real-time situation before the final lane change, which is conducive to improving the accuracy of the final output lane change decision result.

[0063] In the above-mentioned vehicle lane-changing decision-making method, the surrounding environment information of the vehicle is obtained, and the trajectory evaluation result for switching to the target lane is determined based on the surrounding environment information. The trajectory evaluation result is an evaluation of the target lane trajectory cluster generated within a preset time period. Subsequently, the trajectory evaluation result is combined and analyzed with the lane-changing demand with target trajectory generated based on real-time user commands and real-time preset navigation information, and finally the lane-changing decision result is output. It can output the optimal trajectory result with higher safety based on real-time traffic conditions, thereby improving the safety, rationality and real-time performance of the final lane-changing trajectory.

[0064] In one embodiment, obtaining the vehicle's surrounding environment information includes the following steps:

[0065] Obtain at least one of the following: road information, vehicle driving information, and surrounding obstacle information.

[0066] Understandably, this involves obtaining road information such as the vehicle's current location in the specified lane and adjacent lanes, lane markings, and speed limits.

[0067] Acquire vehicle driving information such as vehicle position, speed, maximum and minimum acceleration and deceleration, and user commands;

[0068] Acquire information about surrounding obstacles, such as their location, speed, and predicted trajectory.

[0069] In other embodiments, other environmental information may be obtained, as long as it affects vehicle driving; no specific limitations are made here.

[0070] The above embodiments acquire at least one of the following: surrounding environmental information of the vehicle, such as road information, vehicle driving information, and surrounding obstacle information. Targeted collection of environmental data that affects lane-changing decision results helps to realistically recreate the actual driving environment of the vehicle, thereby ensuring the accuracy of trajectory evaluation results.

[0071] In one embodiment, before determining the trajectory evaluation result for switching to the target lane based on the surrounding environment information, the following steps are included:

[0072] The lane change request and target lane are determined based on at least one of the user's lane change command, preset navigation information, and vehicle driving status.

[0073] Among them, the lane change request generated based on the user's lane change instruction and the preset navigation information is an external lane change request in the vehicle's lane change scenario and is classified as a passive lane change intention; while the lane change request generated based on the vehicle's driving state is classified as an active lane change intention.

[0074] Specifically, autonomous driving is not completely driverless driving. Therefore, lane-changing requests during driving come from two sources. One is the lane-changing request generated autonomously by the autonomous driving system itself based on the current vehicle driving status. For example, when the current lane is extremely congested, the autonomous driving system itself generates a lane-changing request. The other is not generated by the autonomous driving system itself, but comes from the user's lane-changing command or from the path planning of the navigation system. In specific embodiments, the user's lane-changing command is taken as the first priority of lane-changing requests.

[0075] Understandably, the above embodiments take into account various lane-changing needs, which can effectively reduce lane-changing decision conflicts and improve the safety of lane-changing decision results.

[0076] In another embodiment, determining the lane-changing requirement and the target lane based on the vehicle's driving status includes:

[0077] Get the vehicle's speed;

[0078] If the vehicle's speed is less than a preset threshold, the expected lane-changing behavior in the adjacent lanes is evaluated.

[0079] The target lane is determined based on the assessment results.

[0080] Specifically, the system acquires the vehicle's speed in the current lane. If the vehicle speed is within a preset threshold range, it indicates that the traffic efficiency meets expectations, and no lane-changing request is generated; the vehicle continues to travel in the current lane. If the vehicle speed is less than the preset threshold, it indicates that the traffic efficiency of this lane is not high. Therefore, the system assesses the lane-changing expectations for adjacent lanes, including lane collision risk, lane violation risk, and obstacle risk. For example, regarding lane collision risk, if the assessment indicates no collision risk in the lane, a lane-changing request including the target lane is generated. If the assessment indicates collision risk in all lanes, no lane-changing request is generated, and the vehicle continues to travel in the current lane. For example, if the preset speed threshold is 30-60 km / h, if the actual acquired vehicle speed is within the 30-60 km / h range, the vehicle continues to travel in the current lane. If the vehicle speed is less than 30 km / h, the system assesses the lane-changing expectations for adjacent lanes. If the assessment indicates no collision risk in the lane, a lane-changing request including the target lane is generated. If the assessment indicates collision risk in all lanes, no lane-changing request is generated, and the vehicle continues to travel in the current lane. For example, the driving speed mentioned above can be the real-time speed at the current moment or the average speed over a preset time period. It can be set by the user according to actual needs, and no specific limitation is made here.

[0081] In other embodiments, the method further includes acquiring the vehicle's traffic efficiency and determining whether to evaluate lane-changing expectations for adjacent lanes based on whether the traffic efficiency meets a preset threshold. The traffic efficiency refers to the degree of matching between the vehicle's forward space and a preset target speed during its travel. The forward space during the vehicle's travel refers to the relative distance between the front of the vehicle and the rear of the vehicle in front.

[0082] See Figure 3 , Figure 3 This is a schematic diagram illustrating the lane-changing requirements and target lane determination process of the vehicle lane-changing decision-making method in one embodiment of the present invention.

[0083] In this embodiment, the process of determining the lane change requirement and the target lane includes:

[0084] Step 1: Identify user lane change requests or preset navigation information.

[0085] In this embodiment, step one specifically includes identifying and confirming the user's lane change request or preset navigation information based on the acquired vehicle surrounding environment information. When it is identified as a user's lane change request or preset navigation information, the system verifies "Condition 1: The target lane change lane exists and the road edge type allows lane change". If the verification is successful, proceed to step four.

[0086] Understandably, in condition 1, the existence of the target lane change means that the target lane change is passable and there are no situations where it is impassable due to traffic control, road construction, or other reasons; the road edge type allows lane changing, meaning that lane changing is allowed when the road edge line is dashed, but not when it is solid.

[0087] Step 2: Determine the vehicle's driving status.

[0088] In this embodiment, step two specifically includes obtaining the vehicle's speed in the current lane, verifying "condition 2, the vehicle's speed is within a preset threshold range, which means that the traffic efficiency meets expectations". If the verification is successful, no lane-changing request is generated, and the vehicle continues to travel in the current lane. If the vehicle's speed is less than the preset threshold, it indicates that the traffic efficiency of the current lane is not high, and then proceeds to step three, adjacent lane traffic efficiency assessment.

[0089] Under the understandable condition 2, the efficiency of lane passage is judged based on the vehicle speed. The longer the distance a vehicle travels in the current lane per unit time, the higher the lane passage efficiency. Alternatively, the passage efficiency can be judged based on the degree of matching between the forward space and the preset target speed during the vehicle's travel.

[0090] Step 3: Adjacent road trafficability assessment.

[0091] In this embodiment, step three specifically includes evaluating the lane-changing driving expectations of the left and right adjacent lanes of the current driving lane, obtaining the optimal lane-changing direction, and acquiring the adjacent lane trafficability evaluation results.

[0092] The adjacent lane trafficability assessment result refers to the prediction of the driving situation when changing lanes to adjacent lanes. For example, the driving situation when changing lanes to the left adjacent lane and the right adjacent lane is predicted, and the feasibility of changing lanes is determined based on the prediction results. If the prediction result is that changing lanes to the left adjacent lane is not possible, then the left adjacent lane is not suitable for changing lanes; if changing lanes to the right adjacent lane is possible, then the right adjacent lane is suitable for changing lanes, and the final lane change direction is chosen to be the right lane.

[0093] Step 4: Target lane recommendation.

[0094] In this embodiment, step four specifically includes verifying "condition 3, the adjacent lane is passable" based on the user lane change command in step one, the lane change request obtained from the preset navigation information, and the adjacent lane passability assessment result obtained in step three. If condition 3 is met, a lane change request containing the target lane is generated; if the verification fails, no lane change request is generated, and the current lane driving continues.

[0095] Understandably, condition 3, "adjacent lane assessment lane is passable," means that the lane has no risk of collision, no risk of lane changing violations, and no risk of obstacles.

[0096] In another embodiment, the trajectory evaluation result for switching to the target lane based on the surrounding environment information includes:

[0097] Multiple candidate trajectories are determined based on the target lane;

[0098] Trajectory stability is determined based on the number of times each candidate trajectory is identified as the optimal trajectory within a preset time period;

[0099] The lane-changing efficiency of each candidate trajectory is determined based on the estimated lane-changing time.

[0100] The impact of each candidate trajectory is determined based on the area occupied by the target lane during the lane change process;

[0101] The risk level of each candidate trajectory is determined based on the probability of collision with the vehicle in front during lane changing.

[0102] The trajectory evaluation result for each candidate trajectory is determined based on trajectory stability, lane-changing efficiency, impact level, and risk level.

[0103] Trajectory stability refers to the traversability of the candidate trajectory over a continuous period of time.

[0104] See Figure 4 Specifically, determining trajectory stability based on the number of times each candidate trajectory is identified as the optimal trajectory within a preset time period includes the following steps:

[0105] It is understandable that there will be multiple moments within the preset time period, and each moment will have an optimal trajectory. For the trajectory being evaluated, the more times it becomes the optimal trajectory within the preset time period, the better the stability of the evaluated trajectory.

[0106] Step 1, calculate the current k i The set of all lane-changing trajectories and the trajectory of the current driving lane at any given moment.

[0107] Step 2: Obtain the optimal trajectory L at the current moment based on relevant indicators. m .

[0108] The relevant indicators include lane-changing efficiency, impact on the target lane, and lane-changing risk level.

[0109] Step 3, up to the current k i At any given moment, obtain the number of times K has been used to calculate the lane change trajectory in steps 1 and 2.

[0110] Specifically, the number of times K has been obtained when the lane change trajectory calculations for steps 1 and 2 have been performed is retrieved. Here, the number K includes the current k. i In terms of timing, step 3 can effectively calculate the current k up to the present. iThe cumulative number of times at the moment when the lane-changing trajectory calculation has been performed.

[0111] Step 4, determine whether K < N is satisfied, where N is a preset number; when K < N is satisfied, obtain the pre-evaluated trajectory L k As the best trajectory L within N moments m The number of times n k ; when K < N is not satisfied, assign K = K + 1, and re-perform the loop calculation of Step 1.

[0112] Among them, Step 4 can effectively control the moments for which trajectory calculations need to be performed within a preset range, that is, ensure that the calculated trajectory time segment always remains from the k i moment to the k i before the i -N moment.

[0113] Step 5, calculate the stability value J k of each pre-evaluated trajectory L sta , and the specific calculation formula is

[0114] Among them, the pre-evaluated trajectory L k As the best trajectory L within N moments m The number of times n k , divide n k by the total number of moments, and the ratio can intuitively reflect the stability of the pre-evaluated trajectory L k .

[0115] Among them, the lane-changing efficiency refers to calculating the time required to change lanes from the current position to a specified position on the target lane based on a preset same distance. The longer the time, the lower the lane-changing efficiency.

[0116] Specifically, determining the lane-changing efficiency of each candidate trajectory based on the estimated lane-changing time includes the following steps:

[0117]

[0118] J eff represents the lane-changing efficiency.

[0119] is the time required for the trajectory that takes the longest time among all candidate trajectories to change lanes from the current position to a specified position on the target lane at a preset same distance within the time period from t0 to t n .

[0120] is the time required for the trajectory that takes the shortest time among all candidate trajectories to change lanes from the current position to a specified position on the target lane at a preset same distance within the time period from t0 to t n .

[0121] Δ t It is the time required for the current evaluation trajectory to change lanes from the current position to the designated position in the target lane when the same preset distance is reached.

[0122] The time taken for evaluating the track is normalized to the longest and shortest times to obtain the final track-switching efficiency J. eff .

[0123] The degree of impact refers to the extent to which a vehicle affects other vehicles. In other words, it refers to the area of ​​the target lane occupied by a vehicle during the entire lane-changing process. The larger the area occupied, the greater the impact on other vehicles.

[0124] Specifically, determining the impact of each candidate trajectory on the target lane's occupied area during lane changing includes the following steps:

[0125]

[0126]

[0127] J inf This represents the impact on other vehicles.

[0128] S k It is the area occupied by the target lane during the entire lane change process from the current position to the designated position of the target lane when the current evaluation trajectory is at the same preset distance.

[0129] S max It is the lane area of ​​the lane-changing trajectory with the largest lane area among all candidate trajectories, based on the same preset distance, which changes lanes from the current position to the specified position of the target lane.

[0130] S min It is the lane area of ​​the lane-changing trajectory with the smallest lane-occupying area among all candidate trajectories, based on the same preset distance, from the current position to the designated position of the target lane.

[0131] The road area occupied by the assessed trajectory is normalized with the maximum and minimum road areas to calculate the final impact J on other vehicles. inf .

[0132] The risk level refers to the risk of the vehicle colliding with the vehicle in front, given the current assessed trajectory.

[0133] Specifically, determining the risk level of each candidate trajectory based on the probability of collision with the vehicle in front during lane changing includes the following steps:

[0134] The collision probability assessment index is calculated based on the current assessment trajectory, taking into account the time when the vehicle collides with the vehicle in front while traveling at a constant speed and the time when the vehicle collides with the vehicle in front while driving at maximum acceleration. The closer the time ratio is to 1, the greater the collision probability, and thus the greater the collision risk.

[0135]

[0136] J risk This represents uncertainty and risk.

[0137] S is the relative distance between this vehicle and the vehicle in front in the current evaluation trajectory.

[0138] This is the time during which the vehicle collided with the vehicle in front while traveling at a constant speed in the current assessment trajectory.

[0139] In the current evaluation trajectory, this vehicle is at its maximum acceleration a max The time of collision with the vehicle in front under certain circumstances.

[0140] The collision time under the current assessment of the least risk lane collision. Collision time compared to the current assessment of the highest lane collision risk By dividing, we can obtain the information about the uncertainty risk J. risk The evaluation results.

[0141] In addition to factors affecting lane changing such as trajectory stability, lane changing efficiency, degree of impact, and degree of risk, the influencing factors also include vehicle fuel or electricity consumption, natural disaster warnings, etc. In other embodiments, other influencing factors may also be included, as long as they affect the vehicle's lane changing, without being specifically limited here.

[0142] In another embodiment, the trajectory evaluation result for each candidate trajectory, based on trajectory stability, lane-changing efficiency, impact level, and risk level, further includes:

[0143] The trajectory stability, lane-changing efficiency, impact degree, and risk degree are weighted and summed to obtain the evaluation value of each candidate trajectory;

[0144] The optimal trajectory is determined based on the evaluation value and is used as the trajectory evaluation result.

[0145] Specifically, the calculation process is as follows:

[0146] J tra =w1J sta +w2J eff +w3J inf +w4J risk

[0147] Among them, J tra J is the reward value for the vehicle's lane-changing trajectory. sta To assess the stability of the trajectory over a continuous period of time, J eff For evaluating the lane-changing efficiency of the trajectory to the target lane, J inf To assess the impact of the lane-changing trajectory on other vehicles in the target lane, J risk For the assessment of the risk of the vehicle's lane-changing trajectory, w1, w2, w3, and w4 are the weighting coefficients of the above four indicators, and w1+w2+w3+w4=1. The weighting coefficients are customized according to user needs.

[0148] Understandably, by weighting and summing the trajectory stability, lane-changing efficiency, impact level, and risk level, an evaluation value for each candidate trajectory is obtained. Based on the evaluation scores, the trajectories are sorted, and finally, the optimal trajectory can be determined. This comprehensive evaluation is highly accurate.

[0149] In one embodiment, determining the lane-changing decision result based on the trajectory evaluation result, user instructions, and preset navigation information includes:

[0150] If any of the trajectory evaluation results, user instructions, and preset navigation information does not meet the preset conditions, the lane change decision result is no lane change.

[0151] Understandably, the feedback of the trajectory evaluation result will affect the issuance of the user command. Therefore, if any of the trajectory evaluation result, user command, or preset navigation information does not meet the preset conditions, that is, if the trajectory evaluation result shows that there is no suitable lane-changing trajectory, or the user indicates that no lane change is allowed, or the navigation information shows that no lane change is allowed, the lane-changing decision result will be output as no lane change.

[0152] The above embodiments can comprehensively evaluate the lane change decision results from three aspects: trajectory evaluation results, user instructions, and preset navigation information. Based on real-time traffic conditions, they can output the optimal trajectory result with higher safety, thereby improving the safety, rationality, and real-time performance of the final lane change trajectory.

[0153] For example, see Figure 5 To explain, Figure 5 This is a schematic diagram illustrating the implementation process of the lane-changing decision-making method for vehicles in this embodiment.

[0154] In this embodiment, the lane-changing decision-making method is implemented based on the HFSM hierarchical finite state machine theory. The state machine includes four main states: lane-changing completed, lane-changing cancelled, lane-changing failed, and lane-changing in progress. The lane-changing completed main state is the default state of the state machine, and the lane-changing in progress main state includes three sub-states: preparing to change lanes, executing lane-changing, and completion pending confirmation.

[0155] The main state after lane change is the default state of the state machine. It verifies "Condition A: the lane change decision result is received and there is no collision risk within a certain time and space in the target lane". If the verification is successful, the preparation lane change sub-state in the main state during the lane change process is started.

[0156] The lane change preparation state not only provides functions such as adjusting the vehicle speed and illuminating the turn signals and providing voice prompts based on the road conditions of the target lane, but also determines whether to initiate the next lane change state based on the trajectory evaluation results of the target lane.

[0157] In the preparation for lane changing sub-state, when "condition D1, the lane changing trajectory evaluation result differs significantly from the expectation or there is no lane changing requirement within a continuous period of time" is met, the lane changing cancellation main state is initiated; when "condition E1, the lane changing decision result fails to be generated continuously within a period of time" is met, the main state of lane changing process is exited and the lane changing failure main state is initiated; when "condition G, the lane changing requirement remains unchanged and the lane changing trajectory evaluation result is consistent with the expected difference" is met, the execution lane changing sub-state is initiated.

[0158] The execution of the lane-changing sub-state is the process of defining the actual lane-changing trajectory of the vehicle.

[0159] In the lane-changing sub-state, when "Condition D2, lane-changing demand changes or disappears" is met, the lane-changing cancellation state is activated; when "Condition E2, lane-changing decision generation fails" is met, the lane-changing failure state is activated. When "Condition H, vehicle travels to target lane according to lane-changing decision result" is met, the completion pending confirmation sub-state is activated.

[0160] The completed pending confirmation sub-state is divided into two stages. In stage one, after the vehicle crosses the edge line, it completes stable driving in the target lane. If "condition E3 is met, the vehicle cannot complete driving in the target lane due to control, positioning, actuator or collision risk", then the lane change failure main state is activated. In stage two, if "condition B is met, the lane change request is issued by the user", then the vehicle waits for user confirmation. After confirmation, the lane change completion state is activated.

[0161] In the lane change cancellation main state, if condition C is met, the time for which lane change requests are continuously and stably received exceeds the threshold T. cancel When the lane-changing process is initiated, the current state is activated; otherwise, it remains in the current state.

[0162] T cancel =T intent +T silence

[0163] In the formula T cancel T is the time threshold in condition C. intentThe determination time for lane change intention stability is T, where the lane change request time based on the vehicle's driving state is much longer than the lane change request time based on the user's lane change command and the preset navigation information. silence Silence period for lane change;

[0164] In the main state of lane change failure, the source of failure for condition E that led to this state is recorded. For example, if condition F is met, the source of failure has been confirmed to have disappeared for more than T seconds. fail Upon receiving a lane change request, the lane change process status is activated, where T... fail Greater than T cancel If the conditions are not met, the state will remain unchanged.

[0165] Among them, condition E contains three sub-conditions: condition E1, condition E2, and condition E3.

[0166] T fail =T clear +T silence

[0167] In the formula T fail T is the time threshold in condition F. clear T is the time it takes for the source of failure to disappear stably. silence Silence period for lane change.

[0168] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0169] Based on the same inventive concept, this application also provides a vehicle lane-changing decision-making device for implementing the vehicle lane-changing decision-making method described above. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more vehicle lane-changing decision-making device embodiments provided below can be found in the limitations of the vehicle lane-changing decision-making method above, and will not be repeated here.

[0170] In one embodiment, such as Figure 6As shown, a vehicle lane-changing decision-making device is provided, including: an acquisition module 610, an evaluation module 620, and a decision-making module 630, wherein:

[0171] The acquisition module 610 is used to acquire information about the vehicle's surrounding environment.

[0172] The acquisition module 610 is also used to acquire at least one of road information, vehicle driving information, and surrounding obstacle information.

[0173] The evaluation module 620 is used to determine the trajectory evaluation result of switching to the target lane based on the surrounding environment information.

[0174] The evaluation module 620 is also used to determine multiple candidate trajectories based on the target lane; determine trajectory stability based on the number of times each candidate trajectory is determined as the optimal trajectory within a preset time period; determine the lane-changing efficiency of each candidate trajectory based on the expected lane-changing time; determine the degree of impact of each candidate trajectory based on the lane area occupied by the target lane during the lane-changing process; determine the risk level of each candidate trajectory based on the probability of collision with the vehicle in front during the lane-changing process; and determine the trajectory evaluation result of each candidate trajectory based on trajectory stability, lane-changing efficiency, degree of impact, and degree of risk.

[0175] The evaluation module 620 is also used to perform a weighted summation of the trajectory stability, lane-changing efficiency, impact degree, and risk degree to obtain an evaluation value for each candidate trajectory; and to determine the optimal trajectory based on the evaluation value as the trajectory evaluation result.

[0176] The decision module 630 is used to determine the lane change decision based on the trajectory evaluation results, user instructions, and preset navigation information.

[0177] The decision module 630 is further configured to determine the lane change decision as no lane change if any of the trajectory evaluation result, user instructions, or preset navigation information does not meet the preset conditions.

[0178] The vehicle lane-changing decision-making device also includes: a determination module.

[0179] The determination module is used to determine the lane change requirement and the target lane based on at least one of the user's lane change command, preset navigation information, and vehicle driving status.

[0180] The determination module is also used for:

[0181] Get the vehicle's speed;

[0182] If the vehicle's speed is less than a preset threshold, the expected lane-changing behavior in the adjacent lanes is evaluated.

[0183] The target lane is determined based on the assessment results.

[0184] Each module in the aforementioned vehicle lane-changing decision-making device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0185] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 7 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a vehicle lane-changing decision-making method. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0186] Those skilled in the art will understand that Figure 7 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0187] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0188] Obtain information about the vehicle's surrounding environment;

[0189] Based on the surrounding environment information, the trajectory evaluation result for switching to the target lane is determined;

[0190] The lane-changing decision is determined based on the trajectory evaluation results, user instructions, and preset navigation information.

[0191] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0192] Obtain information about the vehicle's surrounding environment;

[0193] Based on the surrounding environment information, the trajectory evaluation result for switching to the target lane is determined;

[0194] The lane-changing decision is determined based on the trajectory evaluation results, user instructions, and preset navigation information.

[0195] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0196] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0197] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0198] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A vehicle lane-changing decision-making method, characterized in that, The method includes: Obtain information about the vehicle's surrounding environment; Based on the surrounding environment information, the trajectory evaluation result for switching to the target lane is determined; The lane-changing decision is determined based on the trajectory evaluation results, user instructions, and preset navigation information. The trajectory evaluation result for switching to the target lane based on the surrounding environment information includes: Multiple candidate trajectories are determined based on the target lane; Trajectory stability is determined based on the number of times each candidate trajectory is identified as the optimal trajectory within a preset time period; The lane-changing efficiency of each candidate trajectory is determined based on the estimated lane-changing time. The impact of each candidate trajectory is determined based on the area occupied by the target lane during the lane change process; The risk level of each candidate trajectory is determined based on the probability of collision with the vehicle in front during lane changing. The trajectory evaluation result for each candidate trajectory is determined based on trajectory stability, lane-changing efficiency, impact level, and risk level.

2. The method according to claim 1, characterized in that, The acquisition of the vehicle's surrounding environment information includes: Obtain at least one of the following: road information, vehicle driving information, and surrounding obstacle information.

3. The method according to claim 1, characterized in that, Before determining the trajectory evaluation result for switching to the target lane based on the surrounding environment information, the following steps are included: The lane change request and target lane are determined based on at least one of the user's lane change command, preset navigation information, and vehicle driving status.

4. The method according to claim 3, characterized in that, The process of determining lane-changing needs and target lanes based on vehicle driving status includes: Get the vehicle's speed; If the vehicle's speed is less than a preset threshold, the expected lane-changing behavior in the adjacent lanes is evaluated. The target lane is determined based on the assessment results.

5. The method according to claim 1, characterized in that, The trajectory evaluation results for each candidate trajectory, determined based on trajectory stability, lane-changing efficiency, impact level, and risk level, also include: The trajectory stability, lane-changing efficiency, impact degree, and risk degree are weighted and summed to obtain the evaluation value of each candidate trajectory; The optimal trajectory is determined based on the evaluation value and is used as the trajectory evaluation result.

6. The method according to claim 1, characterized in that, The process of determining the lane-changing decision based on the trajectory evaluation result, user instructions, and preset navigation information includes: If any of the trajectory evaluation results, user instructions, and preset navigation information does not meet the preset conditions, the lane change decision result is no lane change.

7. A vehicle lane-changing decision-making device, characterized in that, The device includes: The acquisition module is used to acquire information about the vehicle's surrounding environment. The evaluation module is used to determine the trajectory evaluation result for switching to the target lane based on the surrounding environmental information; The decision module is used to determine the lane-changing decision result based on the trajectory evaluation result, user instructions, and preset navigation information; The evaluation module is further configured to: determine multiple candidate trajectories based on the target lane; determine trajectory stability based on the number of times each candidate trajectory is determined as the optimal trajectory within a preset time period; determine the lane-changing efficiency of each candidate trajectory based on the estimated lane-changing time; determine the degree of impact of each candidate trajectory based on the lane area occupied by the target lane during the lane-changing process; determine the risk level of each candidate trajectory based on the probability of collision with the vehicle in front during the lane-changing process; and determine the trajectory evaluation result of each candidate trajectory based on trajectory stability, lane-changing efficiency, degree of impact, and degree of risk.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images