Vehicle obstacle avoidance trajectory planning method and device, computer equipment and storage medium

Abstract

The invention relates to a vehicle obstacle avoidance trajectory planning method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of obtaining information of obstacles around a current vehicle; predicting driving tracks of all obstacles in a future preset time period according to the information of the obstacles around the current vehicle; under the condition that the condition that no fast approaching obstacle exists behind the current vehicle is obtained based on the driving track analysis, target obstacles needing to be subjected to in-lane obstacle avoidance are screened and recognized; calculating a lane occupation space of the target obstacle based on the driving data of the target obstacle; calculating the lane driving space of the current vehicle according to the lane occupation space of the target obstacle; and performing path planning and speed planning solution based on the lane driving space of the current vehicle, and generating an obstacle avoidance track of the current vehicle. By adopting the method, vehicles in the same direction of the adjacent lanes can be effectively avoided during driving on the expressway, and the driving safety is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a vehicle obstacle avoidance trajectory planning method, device, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] The development of autonomous driving technology has made vehicle obstacle avoidance trajectory planning the key to safe and efficient driving. In a changing traffic environment, autonomous vehicles must accurately perceive the surrounding environment and make correct decisions. The core of obstacle avoidance trajectory planning is to generate a safe and comfortable driving path that avoids obstacles.

[0003] For high-speed scenarios, autonomous vehicles need to plan safe trajectories to avoid collisions, especially large vehicles such as tractors and vans, which need to provide enough space for adjacent vehicles on highways to improve safety. This relies on the environmental perception module to accurately identify and track obstacles, as well as predict their trajectories, so as to plan avoidance paths.

[0004] At present, autonomous driving solutions adopt different strategies for static and dynamic obstacles, but most of them have defects, especially when driving on highways, they cannot effectively avoid vehicles in the same direction in adjacent lanes, which poses a safety risk. Therefore, there is an urgent need for a vehicle obstacle avoidance trajectory planning method, device, computer equipment, computer-readable storage medium and computer program product, which can effectively avoid vehicles in the same direction in adjacent lanes when driving on highways and improve driving safety. Summary of the invention

[0005] Based on this, it is necessary to provide a vehicle obstacle avoidance trajectory planning method, device, computer equipment, computer-readable storage medium and computer program product that can effectively avoid vehicles going in the same direction in adjacent lanes and improve driving safety when driving on highways to address the above technical problems.

[0006] In a first aspect, the present application provides a vehicle obstacle avoidance trajectory planning method, comprising:

[0007] Get the obstacle information around the current vehicle;

[0008] Based on the obstacle information around the current vehicle, predict the driving trajectory of all obstacles in the future preset period of time;

[0009] When it is determined based on the driving trajectory analysis that there is no fast-approaching obstacle behind the current vehicle, screening and identifying a target obstacle that needs to be avoided in the lane;

[0010] Based on the driving data of the target obstacle, the lane occupation space of the target obstacle is calculated;

[0011] Calculate the lane travel space of the current vehicle based on the lane occupied space of the target obstacle;

[0012] Based on the current vehicle's lane driving space, path planning and speed planning are solved to generate the current vehicle obstacle avoidance trajectory and output it to the vehicle control module.

[0013] In one embodiment, the screening and identifying of target obstacles requiring lane avoidance includes:

[0014] The obstacle that is in front of the current vehicle, is not in the lane changing state, has a speed not greater than the current vehicle speed, and is in a different lane from the current vehicle is regarded as the target obstacle.

[0015] In one embodiment, the driving data includes position information and speed information; and the step of calculating the lane occupied space of the target obstacle based on the driving data of the target obstacle includes:

[0016] Based on the driving data of the target obstacle, the distance difference and speed difference between the obstacle and the current vehicle are obtained;

[0017] Calculate the remaining time of the encounter between the obstacle and the current vehicle based on the distance difference and speed difference between the obstacle and the current vehicle;

[0018] According to the remaining time of the encounter between the two vehicles, the length of the reserved space corresponding to the obstacle is calculated to obtain the longitudinal occupied size of the lane of the target obstacle;

[0019] Based on the obstacle width information and lane line information, the lateral lane occupancy size of the target obstacle is calculated.

[0020] In one embodiment, the path planning and speed planning are performed based on the lane driving space of the current vehicle to generate the obstacle avoidance trajectory of the current vehicle, including:

[0021] Based on the lane driving space of the current vehicle, analyzing whether the current vehicle meets the vehicle passing space requirements;

[0022] When the lane driving space of the current vehicle does not meet the vehicle passing space requirements, adjusting the driving area and driving speed of the current vehicle;

[0023] When the lane driving space of the current vehicle meets the vehicle passage space requirements, path planning and speed planning are solved to generate the obstacle avoidance trajectory of the current vehicle.

[0024] In one embodiment, the method further comprises:

[0025] When it is determined based on the driving trajectory analysis that there is a fast-approaching obstacle behind the current vehicle, the current vehicle is kept driving in the center of the current lane to avoid performing an avoidance action.

[0026] In one embodiment, the method further comprises:

[0027] Obstacles that meet any of the preset conditions are considered obstacles that do not need to be avoided;

[0028] The preset conditions include not being in front of the current vehicle, being in a lane changing state, the obstacle speed being greater than the current vehicle speed, and being in the same lane as the current vehicle.

[0029] In a second aspect, the present application also provides a vehicle obstacle avoidance trajectory planning device, comprising:

[0030] The perception module is used to obtain obstacle information around the current vehicle;

[0031] The prediction module is used to predict the driving trajectory of all obstacles in a future preset period of time based on the obstacle information around the current vehicle;

[0032] A screening module, for screening and identifying target obstacles that require in-lane obstacle avoidance when there is no fast-approaching obstacle behind the current vehicle based on the driving trajectory analysis;

[0033] A calculation module, used for calculating a lane occupation space of a target obstacle based on the driving data of the target obstacle;

[0034] The calculation module is also used to calculate the lane travel space of the current vehicle according to the lane occupation space of the target obstacle;

[0035] The trajectory planning module is used to perform path planning and speed planning based on the current vehicle's lane driving space, generate the current vehicle obstacle avoidance trajectory, and output it to the vehicle control module.

[0036] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0037] Get the obstacle information around the current vehicle;

[0038] Based on the obstacle information around the current vehicle, predict the driving trajectory of all obstacles in the future preset period of time;

[0039] When it is determined based on the driving trajectory analysis that there is no fast-approaching obstacle behind the current vehicle, screening and identifying a target obstacle that needs to be avoided in the lane;

[0040] Based on the driving data of the target obstacle, the lane occupation space of the target obstacle is calculated;

[0041] Calculate the lane travel space of the current vehicle based on the lane occupied space of the target obstacle;

[0042] Based on the current vehicle's lane driving space, path planning and speed planning are solved to generate the current vehicle obstacle avoidance trajectory and output it to the vehicle control module.

[0043] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0044] Get the obstacle information around the current vehicle;

[0045] Based on the obstacle information around the current vehicle, predict the driving trajectory of all obstacles in the future preset period of time;

[0046] When it is determined based on the driving trajectory analysis that there is no fast-approaching obstacle behind the current vehicle, screening and identifying a target obstacle that needs to be avoided in the lane;

[0047] Based on the driving data of the target obstacle, the lane occupation space of the target obstacle is calculated;

[0048] Calculate the lane travel space of the current vehicle based on the lane occupied space of the target obstacle;

[0049] Based on the current vehicle's lane driving space, path planning and speed planning are solved to generate the current vehicle obstacle avoidance trajectory and output it to the vehicle control module.

[0050] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0051] Get the obstacle information around the current vehicle;

[0052] Based on the obstacle information around the current vehicle, predict the driving trajectory of all obstacles in the future preset period of time;

[0053] When it is determined based on the driving trajectory analysis that there is no fast-approaching obstacle behind the current vehicle, screening and identifying a target obstacle that needs to be avoided in the lane;

[0054] Based on the driving data of the target obstacle, the lane occupation space of the target obstacle is calculated;

[0055] Calculate the lane travel space of the current vehicle based on the lane occupied space of the target obstacle;

[0056] Based on the current vehicle's lane driving space, path planning and speed planning are solved to generate the current vehicle obstacle avoidance trajectory and output it to the vehicle control module.

[0057] The above-mentioned vehicle obstacle avoidance trajectory planning method, device, computer equipment, computer-readable storage medium and computer program product can effectively identify obstacles that need to be avoided and plan a safe obstacle avoidance trajectory by accurately sensing the surrounding environment and predicting the obstacle trajectory, thereby reducing the risk of collision with obstacles, especially under high-speed driving conditions, and improving the safety of autonomous driving vehicles. Under the premise of ensuring safety, the method enables the vehicle to effectively avoid in a limited space through obstacle avoidance trajectory planning in the lane, avoiding traffic congestion or unnecessary parking and waiting caused by improper avoidance, thereby improving the traffic efficiency of the road. The method is particularly suitable for large vehicles such as tractors and vans driving in high-speed scenarios, and can effectively handle the intersection problem with vehicles in the same direction of adjacent lanes, and adapt to complex and changeable traffic environments. By introducing the calculation of lane occupied space and the dynamic planning of lane driving space, the method enhances the reliability of the autonomous driving system when dealing with complex traffic conditions, so that the autonomous driving vehicle can operate stably in various situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0059] FIG1 is a diagram showing an application environment of a vehicle obstacle avoidance trajectory planning method according to an embodiment;

[0060] FIG2 is a schematic diagram of a process flow of a vehicle obstacle avoidance trajectory planning method in one embodiment;

[0061] FIG3 is a schematic diagram of a flow chart of a vehicle obstacle avoidance trajectory planning method in another embodiment;

[0062] FIG4 is a flow chart of vehicle obstacle avoidance trajectory planning in the most detailed embodiment;

[0063] FIG5 is a flowchart of the target obstacle screening of the vehicle obstacle avoidance driving in the most detailed embodiment;

[0064] FIG6 is a schematic diagram of a drivable area corresponding to a vehicle avoiding obstacles in the most detailed embodiment;

[0065] FIG7 is a structural block diagram of a vehicle obstacle avoidance trajectory planning device in one embodiment;

[0066] FIG8 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0068] The vehicle obstacle avoidance trajectory planning method provided in the embodiment of the present application can be applied to the application environment shown in Figure 1. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers.

[0069] The server 104 obtains obstacle information around the current vehicle; predicts the driving trajectories of all obstacles within a preset time period in the future based on the obstacle information around the current vehicle; screens and identifies target obstacles that require in-lane obstacle avoidance when it is determined based on the driving trajectory analysis that there are no fast-approaching obstacles behind the current vehicle; calculates the lane occupation space of the target obstacle based on the driving data of the target obstacle; calculates the lane driving space of the current vehicle based on the lane occupation space of the target obstacle; performs path planning and speed planning solutions based on the lane driving space of the current vehicle, generates the obstacle avoidance trajectory of the current vehicle, and outputs it to the vehicle control module of the terminal 102.

[0070] The terminal 102 may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The IoT devices may be smart speakers, smart TVs, smart air conditioners, smart car devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. Head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. The server 104 may be an independent physical server, a server cluster or distributed system consisting of multiple physical servers, or a cloud server that provides cloud computing services.

[0071] In an exemplary embodiment, as shown in FIG2 , a vehicle obstacle avoidance trajectory planning method is provided, which is described by taking the method applied to the server in FIG1 as an example, and includes the following steps S202 to S212. Among them:

[0072] Step S202, obtaining obstacle information around the current vehicle.

[0073] Specifically, the perception module is responsible for collecting obstacle information around the vehicle, which is the basis for obstacle avoidance trajectory planning. The perception module usually includes a variety of sensors, such as cameras, LiDAR, millimeter-wave radar, etc., which can provide detailed data about the vehicle's surroundings. For autonomous driving vehicles for highway scenarios, the forward perception distance needs to be no less than 200 meters to ensure that the vehicle has enough space for obstacle avoidance. The obstacle information obtained by the perception module needs to include the size of the obstacle, the position of the center point, the speed and the heading angle. The obstacle information obtained mainly includes the size (length x width x height), the center point information, the speed information and the heading angle information.

[0074] Step S204, predicting the driving trajectories of all obstacles within a future preset time period based on the obstacle information around the current vehicle.

[0075] Specifically, the prediction module uses the data provided by the perception module, combined with machine learning algorithms and artificial intelligence algorithms, to predict the possible driving trajectory and behavior of obstacles in the future (for example, 5-8 seconds). The selection of the preset time period is crucial to the accuracy and practicality of the prediction. A suitable preset time period can ensure that the vehicle has enough time to respond to the prediction results and plan a safe obstacle avoidance trajectory. The prediction content includes but is not limited to the speed change of the obstacle, possible turning actions, lane change behavior, acceleration and deceleration, etc. Due to the complexity of the traffic environment, the prediction module needs to be able to handle a variety of traffic situations, including multiple lanes, multiple vehicles, and obstacles of different speeds and directions.

[0076] The prediction results will directly affect the decision of obstacle avoidance trajectory planning. If the prediction shows that an obstacle will enter the vehicle's driving path, then the obstacle avoidance trajectory planning needs to take this into account and plan a new safe path. The prediction module needs to be updated in real time to reflect the latest behavior of obstacles and environmental changes to ensure the real-time and accuracy of obstacle avoidance trajectory planning.

[0077] Step S206 , when it is determined based on the driving trajectory analysis that there is no fast approaching obstacle behind the current vehicle, a target obstacle that needs to be avoided in the lane is screened and identified.

[0078] Specifically, before performing in-lane obstacle avoidance, it is necessary to first analyze the obstacle situation behind the current vehicle. This is to ensure that there will be no collision with the vehicle approaching quickly from behind when performing in-lane obstacle avoidance operations. Confirming that there are no obstacles approaching quickly from behind is a prerequisite for performing in-lane obstacle avoidance actions. If there is a vehicle approaching quickly from behind, then performing in-lane obstacle avoidance may increase the risk of collision, so it is necessary to stay in the current lane or take other obstacle avoidance measures.

[0079] After confirming that the rear is safe, the system will screen the obstacles in front and identify those target obstacles that need to be avoided in the lane. This usually involves analyzing the position, speed, predicted trajectory and other information of the obstacle. The screening conditions may include whether the obstacle is in front of the vehicle, whether it is in a lane change state, whether the speed is greater than the speed of the vehicle, whether it is in the same lane as the vehicle, etc. These conditions help determine which obstacles pose a direct obstacle avoidance requirement for the current vehicle.

[0080] Step S208: Calculate the lane occupation space of the target obstacle based on the driving data of the target obstacle.

[0081] Specifically, first, the perception module collects relevant information about the target obstacle, including its position, speed, size (length, width, height), heading angle, etc. Lane occupancy refers to the area occupied by the obstacle on the lane, which includes the physical size of the obstacle and the additional space reserved for safety considerations. Calculating lane occupancy usually involves analyzing the size and driving state of the obstacle. For example, the width and length of the obstacle can be combined with its position on the lane to determine its occupied area on the lane. When calculating lane occupancy, safety redundancy is usually added, which means that a certain amount of additional space will be added around the actual occupied space of the obstacle to ensure safety during obstacle avoidance. The driving state of the obstacle changes dynamically, so the calculation of lane occupancy also needs to be updated in real time to reflect the latest position and speed of the obstacle.

[0082] Step S210, calculating the lane travel space of the current vehicle according to the lane occupation space of the target obstacle.

[0083] Specifically, first, the space occupied by the target obstacles on the lane is calculated based on their size, location and driving trajectory. Then the total width of the lane is understood, which is usually a fixed value but varies depending on the region and road design.

[0084] The lane space occupied by the target obstacle is subtracted from the total width of the lane to obtain the lane travel space of the current vehicle. During the calculation process, safety redundancy is usually added around the space occupied by the obstacle to ensure that there is enough space to avoid collision. Therefore, the actual drivable space will be smaller than the difference between the total lane width and the space occupied by the obstacle. Since the traffic environment is dynamically changing, the calculation of the drivable space needs to be updated in real time to adapt to changes in the position and speed of the obstacle. When calculating the drivable space, the size of the current vehicle also needs to be considered to ensure that the vehicle has enough space to pass when avoiding obstacles and does not come into contact with obstacles or lane boundaries.

[0085] Step S212, path planning and speed planning are solved based on the lane driving space of the current vehicle, an obstacle avoidance trajectory of the current vehicle is generated, and output to the vehicle control module.

[0086] Specifically, path planning refers to determining the specific trajectory of the vehicle within the lane to avoid obstacles and ensure safety. This usually involves calculating the optimal path for the vehicle, which not only meets the limitations of the lane driving space, but also takes into account the location and movement of obstacles. Speed ​​planning refers to determining the optimal speed of the vehicle during the obstacle avoidance process to ensure that the vehicle can smoothly and safely pass through potential danger areas. Speed ​​planning needs to take into account the dynamic performance of the vehicle, road conditions, traffic regulations, and the relative speed to obstacles.

[0087] Based on the results of path planning and speed planning, the system solves an obstacle avoidance trajectory that enables the vehicle to avoid obstacles and continue to drive to the destination while maintaining a safe distance. Since the traffic environment is dynamically changing, path planning and speed planning need to be performed in real time to adapt to the movement of obstacles and changes in road conditions.

[0088] The planned obstacle avoidance trajectory needs to be output to the vehicle control module for execution. The vehicle control module adjusts the vehicle's steering wheel, accelerator, and brakes based on the received trajectory information to achieve accurate tracking of the obstacle avoidance trajectory. During the execution of the obstacle avoidance trajectory, the vehicle's perception module continuously monitors the surrounding environment and feeds real-time data back to the path planning and speed planning system. If the environment changes, the system will re-plan the trajectory and update the instructions of the vehicle control module.

[0089] In the above-mentioned vehicle obstacle avoidance trajectory planning method, by accurately sensing the surrounding environment and predicting the obstacle trajectory, the method can effectively identify the obstacles that need to be avoided and plan a safe obstacle avoidance trajectory, thereby reducing the risk of collision with obstacles, especially under high-speed driving conditions, and improving the safety of autonomous driving vehicles. Under the premise of ensuring safety, the method enables the vehicle to effectively avoid in a limited space through obstacle avoidance trajectory planning in the lane, avoiding traffic congestion or unnecessary parking and waiting caused by improper avoidance, thereby improving the traffic efficiency of the road. This method is particularly suitable for large vehicles such as tractors and vans driving in high-speed scenarios, and can effectively handle the intersection problem with vehicles in the same direction of adjacent lanes, adapting to complex and changing traffic environments. By introducing the calculation of lane occupied space and the dynamic planning of lane driving space, this method enhances the reliability of the autonomous driving system when dealing with complex traffic conditions, so that the autonomous driving vehicle can operate stably in various situations.

[0090] In an exemplary embodiment, screening and identifying target obstacles that require lane avoidance includes:

[0091] The obstacle that is in front of the current vehicle, is not in the lane changing state, has a speed not greater than the current vehicle speed, and is in a different lane from the current vehicle is regarded as the target obstacle.

[0092] Specifically, the condition of being in front of the current vehicle ensures that only obstacles that are in front of the autonomous vehicle are considered for in-lane obstacle avoidance. This is because the vehicle usually only needs to pay attention to obstacles in front of it to avoid collisions.

[0093] Not in lane-changing state: If an obstacle is changing lanes, especially into the lane where the autonomous vehicle is located, then this obstacle may soon become an obstacle in the same lane and requires special attention.

[0094] The obstacle speed is no greater than the current vehicle speed condition is used to exclude obstacles that are moving faster than the autonomous vehicle. If the obstacles are faster, they are less likely to require lane avoidance by the autonomous vehicle because they may pass in front of the vehicle.

[0095] The condition of being in a different lane from the current vehicle ensures that only obstacles in adjacent lanes are considered. If the obstacle is in the same lane as the autonomous vehicle, then the vehicle may need to consider other obstacle avoidance strategies such as slowing down or changing lanes.

[0096] In this embodiment, through these conditions, target obstacles that require special attention can be accurately identified, and obstacle avoidance paths within the lane can be planned for these obstacles. This screening method helps to improve the efficiency and safety of obstacle avoidance strategies and ensure that autonomous vehicles can make correct obstacle avoidance decisions in complex traffic environments. In this way, autonomous vehicles can reduce unnecessary obstacle avoidance actions while responding quickly to obstacles that really need to be avoided.

[0097] In an exemplary embodiment, as shown in FIG3 , the driving data includes position information and speed information; based on the driving data of the target obstacle, calculating the lane occupation space of the target obstacle includes:

[0098] Step S302, based on the driving data of the target obstacle, obtaining the distance difference and speed difference between the obstacle and the current vehicle;

[0099] Step S304, calculating the remaining time for the obstacle and the current vehicle to meet each other based on the distance difference and speed difference between the obstacle and the current vehicle;

[0100] Step S306, calculating the length of the reserved space corresponding to the obstacle according to the remaining time of the encounter between the two, and obtaining the longitudinal occupied size of the lane of the target obstacle;

[0101] Step S308: Based on the obstacle width information and the lane line information, the lateral occupied size of the lane of the target obstacle is calculated.

[0102] Specifically, first, the system needs to determine the distance difference (i.e., the distance between the obstacle and the vehicle) and the speed difference (i.e., the difference between the obstacle speed and the vehicle speed) between the obstacle and the current vehicle. These data provide the basis for subsequent calculations. Using the distance difference and speed difference, the remaining time before the obstacle meets the current vehicle is calculated. This time reflects how much time the vehicle has to react and plan obstacle avoidance before the obstacle reaches the vehicle's current position.

[0103] According to the remaining time of the encounter, the length of the reserved space corresponding to the obstacle is calculated, that is, the length of the space that the obstacle will occupy when encountering. This length is the length of the obstacle plus the additional length reserved for safety considerations. The longitudinal occupation size of the lane refers to the space occupied by the obstacle along the direction of vehicle travel. By calculating the length of the reserved space of the obstacle, the longitudinal occupation size of the obstacle on the lane can be obtained. The lateral occupation size of the lane refers to the space occupied by the obstacle along the width direction of the vehicle travel. This is usually calculated based on the actual width of the obstacle and the lane line information. At the same time, considering safety redundancy, a certain amount of space may be added on the basis of the obstacle width.

[0104] By combining the longitudinal and lateral occupancy dimensions, we can get the complete spatial area occupied by the obstacle on the lane, that is, the lane occupancy space. This spatial area is the area that needs to be avoided when planning the obstacle avoidance path. After obtaining the lane occupancy space of the obstacle, the system can plan an obstacle avoidance path to ensure that the vehicle does not enter this area during driving, thereby avoiding collisions with obstacles. Since the state of obstacles and vehicles changes dynamically, these calculations need to be updated in real time to ensure the accuracy and safety of the obstacle avoidance path.

[0105] In this embodiment, through this process, the autonomous driving system can accurately predict the future position of obstacles and plan a safe obstacle avoidance path accordingly, thereby improving the safety and reliability of autonomous driving.

[0106] In an exemplary embodiment, path planning and speed planning are performed based on the lane driving space of the current vehicle to generate the obstacle avoidance trajectory of the current vehicle, including:

[0107] Based on the lane driving space of the current vehicle, analyzing whether the current vehicle meets the vehicle passing space requirements;

[0108] When the lane driving space of the current vehicle does not meet the vehicle passing space requirements, adjusting the driving area and driving speed of the current vehicle;

[0109] When the lane driving space of the current vehicle meets the vehicle passage space requirements, path planning and speed planning are solved to generate the obstacle avoidance trajectory of the current vehicle.

[0110] Specifically, first, the system needs to evaluate whether the current lane space of the vehicle is sufficient for the vehicle to pass safely. This includes considering the size of the vehicle itself, the space occupied by obstacles, and the additional space required for safe driving (such as safety redundancy).

[0111] If the current lane space of the vehicle is not enough for safe passage, the system needs to adjust the vehicle's driving area and speed. This may include: Widening the driving area: Try to widen the available driving space by changing the position of the vehicle in the lane. Slowing down: Reduce the speed of the vehicle to increase reaction time and reduce the risk of collision in a narrow space. Temporary parking: In extreme cases, if it is impossible to pass safely, the vehicle may need to stop temporarily and wait for sufficient driving space.

[0112] If the current vehicle's lane driving space meets the traffic requirements, the system will perform specific path planning and speed planning solutions to generate an obstacle avoidance trajectory. This includes: Path planning: Determine the specific driving path of the vehicle in the lane, avoid obstacles while considering the vehicle's dynamic performance and road conditions. Speed ​​planning: Determine the optimal speed of the vehicle during obstacle avoidance to ensure that the vehicle can pass through potential dangerous areas smoothly and safely. Generate obstacle avoidance trajectory: Based on the results of path planning and speed planning, the system generates an obstacle avoidance trajectory. This trajectory describes in detail how the vehicle should drive within a specific time period to safely avoid obstacles. The planned obstacle avoidance trajectory needs to be output to the vehicle control module for execution. The vehicle control module adjusts the vehicle's steering wheel, accelerator, brake, etc. based on the received trajectory information to achieve accurate tracking of the obstacle avoidance trajectory.

[0113] It should be noted that during the execution of the obstacle avoidance trajectory, the system's perception module continuously monitors the surrounding environment and feeds real-time data back to the path planning and speed planning systems. If the environment changes, the system will re-plan the trajectory and update the instructions of the vehicle control module.

[0114] In this embodiment, through this process, the autonomous driving vehicle can effectively avoid obstacles and continue driving towards the destination while ensuring safety.

[0115] In an exemplary embodiment, the method further comprises:

[0116] When it is determined based on the driving trajectory analysis that there is a fast-approaching obstacle behind the current vehicle, the current vehicle is kept centered in the current lane to avoid performing evasive actions.

[0117] Specifically, the rules first require that the autonomous driving system be able to detect the situation behind the vehicle, especially whether there is an obstacle approaching quickly. This is usually achieved through the vehicle's rear perception module, such as radar, camera or other sensors. When the system detects a fast-approaching obstacle from behind, it needs to evaluate whether the current avoidance action will increase the risk of collision with the obstacle behind. This evaluation is based on the speed, distance and driving trajectory of the obstacle.

[0118] If the evaluation results indicate that performing an evasive maneuver will increase the risk of a collision, the rule requires the autonomous vehicle to remain centered in the current lane and not perform any lane changes or in-lane evasive maneuvers. In this case, keeping the vehicle centered in the current lane can reduce interference with the rear obstacle while providing both the autonomous vehicle and the rear obstacle with enough time and space to respond and adjust. This rule emphasizes that safety is the most important consideration in obstacle avoidance strategies. Even if this means giving up some avoidance opportunities, the safety of the vehicle and passengers must be prioritized.

[0119] The system needs to continuously monitor the dynamics of the rear obstacle and dynamically adjust the strategy based on real-time data. If the threat of the rear obstacle is eliminated, the system can re-evaluate whether to perform an avoidance action.

[0120] While keeping the lane center, the system may also need to consider other driving strategies, such as slowing down, warning the driver, etc., to cope with complex traffic environments.

[0121] In this embodiment, the obstacle avoidance strategy of the autonomous driving vehicle is more comprehensive and detailed, and can effectively deal with various complex traffic situations while ensuring safety. Through accurate risk assessment and timely strategy adjustment, the autonomous driving vehicle can protect the safety of passengers while minimizing the interference with traffic flow.

[0122] In an exemplary embodiment, the method further comprises:

[0123] Obstacles that meet any of the preset conditions are considered obstacles that do not need to be avoided;

[0124] The preset conditions include not being in front of the current vehicle, being in a lane-changing state, the obstacle speed being greater than the current vehicle speed, and being in the same lane as the current vehicle.

[0125] Specifically, preset conditions are the criteria that the autonomous driving system uses to determine which obstacles do not need to be avoided. These conditions help the system screen out obstacles that do not pose a direct threat to the current vehicle or do not require avoidance action. If an obstacle meets any of the preset conditions, the system marks it as an obstacle that does not need to be avoided. This means that the vehicle can ignore these obstacles when planning the obstacle avoidance path.

[0126] Not in front of the current vehicle: If obstacles are not directly in front of the vehicle, it may mean that they do not directly affect the vehicle's path and therefore do not need to be avoided.

[0127] Changing lanes: If an obstacle is changing lanes, especially into the vehicle's lane, the vehicle may need to maintain its current position to avoid interfering with the obstacle's lane change, or may need to take other actions (such as slowing down) rather than simply avoiding it.

[0128] Obstacle speed is greater than current vehicle speed: If the obstacle's speed is greater than the vehicle's speed, this means the obstacle may quickly overtake the vehicle, or is behind the vehicle, so no avoidance is required.

[0129] In the same lane as the current vehicle: If the obstacle is in the same lane as the vehicle, the vehicle may need to take other measures (such as slowing down or changing lanes) to deal with it instead of simply avoiding it.

[0130] In this embodiment, by setting these preset conditions, the autonomous driving system can simplify the obstacle avoidance decision-making process, reduce unnecessary avoidance actions, improve driving efficiency, and help improve the safety and efficiency of autonomous driving vehicles because it allows the system to focus resources and attention on obstacles that really need to be avoided.

[0131] The most detailed embodiment of this application is:

[0132] The present invention provides a vehicle obstacle avoidance trajectory planning method, and the specific process is shown in FIG4 .

[0133] First of all, the autonomous driving system consists of a perception module, a prediction module, a trajectory planning module, a vehicle control module and other parts. The obstacle information within a certain range around the vehicle is mainly obtained by the perception module, and the acquisition methods include camera perception, lidar point cloud perception, millimeter wave radar perception and other methods. The perception range requirements of the perception module are mainly determined by the operating scenario of the autonomous driving vehicle. The forward perception distance for the highway scenario needs to be no less than 200m to ensure that the vehicle has enough space for obstacle avoidance. The obstacle information obtained by the perception module mainly includes size (length x width x height), center point information, speed information and heading angle information. Based on the above information, the prediction module solves the driving trajectory of the obstacle in the future (5~8 seconds). The prediction module usually uses machine learning algorithms and artificial intelligence algorithms to predict the driving behavior of other obstacles on the road, such as possible turning actions, lane change actions, and walking directions of pedestrians of other vehicles. This information can guide the trajectory planning module to make driving strategy decisions to ensure vehicle safety and traffic efficiency. Based on obstacle information and the corresponding obstacle prediction trajectory, it can support the autonomous driving vehicle to safely perform obstacle avoidance trajectory planning tasks.

[0134] In order to improve the safety of autonomous vehicles during obstacle avoidance, it is first necessary to detect the vehicle's driving status towards obstacles. If there is a fast-moving obstacle behind the vehicle, obstacle avoidance driving within the vehicle's lane should be avoided. At this time, if there is an obstacle in front, the autonomous vehicle will use deceleration as the main response strategy. If, after inspection, there is no fast-moving and approaching obstacle behind the vehicle, when there is an obstacle in the adjacent lane in front of the vehicle that meets the conditions, the in-lane obstacle avoidance driving strategy can be executed to improve the vehicle's driving efficiency while meeting the requirements for safe driving.

[0135] Obstacle avoidance driving in the lane is mainly aimed at obstacles in adjacent lanes. When obstacles in adjacent lanes are running on the line, it is necessary to avoid them to prevent collisions. At the same time, for vehicles with a wider vehicle width, such as tractors and vans, when they intersect with obstacles in adjacent lanes, it is necessary to perform obstacle avoidance driving in the lane to prevent the risk of collision and endanger driving safety. Therefore, before planning the obstacle avoidance trajectory, it is necessary to screen and process the obstacles in the perception module, screen out the obstacles that meet the obstacle avoidance conditions in the lane, and perform targeted obstacle avoidance trajectory planning. The specific screening conditions are shown in Figure 5: ① Whether the obstacle is within the forward range of the ego vehicle. If it is, it is necessary to consider whether to execute the in-lane obstacle avoidance strategy. Otherwise, no processing is required; ② Whether the obstacle is changing lanes. If it changes from the adjacent lane to the ego vehicle lane, in-lane avoidance cannot be performed. If it changes from the ego vehicle lane to the adjacent lane, in-lane obstacle avoidance can be performed; ③ Whether the obstacle speed is greater than the ego vehicle speed. If it is greater than the ego vehicle speed, in-lane obstacle avoidance is not required; ④ Whether the obstacle is in the same lane as the ego vehicle. If it is in the same lane, there is no space for in-lane obstacle avoidance. If the obstacle meets the above screening conditions, the obstacle information is recorded, and the trajectory planning module performs targeted in-lane obstacle avoidance trajectory planning.

[0136] Before performing trajectory planning, the trajectory planning module needs to cut the drivable area according to the obstacle information. The specific principle is shown in Figure 6. First, there are obstacles A and B that meet the screening conditions in front of the autonomous driving vehicle. The information that can be obtained includes obstacle length, width, driving speed, etc. The drivable area cutting is mainly divided into two parts, namely the longitudinal length calculation and the lateral size calculation. The longitudinal length is mainly obtained by adding the vehicle length and the reserved space length. The vehicle length is a fixed value, and the reserved space length is obtained by the encounter time between the autonomous driving vehicle and the obstacle x the obstacle speed. The encounter time setting range is less than or equal to 3 seconds, which can be adjusted according to the scene. The lateral size is mainly obtained by subtracting the lane width from the obstacle width. At the same time, in order to increase safety, the redundancy can be increased, for example, the redundancy is set to 0.4m, which can be adjusted according to the scene.

[0137] After completing the drivable area clipping, it is necessary to determine whether the drivable area can meet the vehicle passage space requirements. If the lateral space of the drivable area is insufficient and cannot support the passage of the autonomous driving vehicle, the drivable area needs to be appropriately widened to support the autonomous driving vehicle to complete trajectory planning to ensure that the vehicle can drive stably and continuously. At this time, the autonomous driving vehicle needs to consider slowing down to avoid collision with obstacles in front. If the drivable area space meets the driving requirements of the autonomous driving vehicle, the obstacle avoidance driving trajectory planning can be carried out in the vehicle lane to achieve safe and efficient obstacle avoidance driving of the autonomous driving vehicle.

[0138] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0139] Based on the same inventive concept, the embodiment of the present application also provides a vehicle obstacle avoidance trajectory planning device for implementing the vehicle obstacle avoidance trajectory planning method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more vehicle obstacle avoidance trajectory planning device embodiments provided below can refer to the limitations of the vehicle obstacle avoidance trajectory planning method above, and will not be repeated here.

[0140] In an exemplary embodiment, as shown in FIG7 , a vehicle obstacle avoidance trajectory planning device is provided, comprising:

[0141] The perception module 702 is used to obtain obstacle information around the current vehicle;

[0142] The prediction module 704 is used to predict the driving trajectory of all obstacles in a future preset period of time based on the obstacle information around the current vehicle;

[0143] A screening module 706 is used to screen and identify target obstacles that need to be avoided in the lane when there is no fast-approaching obstacle behind the current vehicle based on the driving trajectory analysis;

[0144] A calculation module 708, configured to calculate a lane occupation space of a target obstacle based on the driving data of the target obstacle;

[0145] The calculation module 708 is further used to calculate the lane travel space of the current vehicle according to the lane occupation space of the target obstacle;

[0146] The trajectory planning module 710 is used to perform path planning and speed planning based on the lane driving space of the current vehicle, generate the obstacle avoidance trajectory of the current vehicle, and output it to the vehicle control module 712.

[0147] In an exemplary embodiment, the screening module 706 is specifically configured to: select an obstacle that is in front of the current vehicle, is not in a lane changing state, has a speed not greater than the current vehicle speed, and is in a different lane from the current vehicle as a target obstacle.

[0148] In an exemplary embodiment, the driving data includes position information and speed information; the calculation module 708 is specifically used to obtain the distance difference and speed difference between the obstacle and the current vehicle based on the driving data of the target obstacle; calculate the remaining encounter time between the obstacle and the current vehicle according to the distance difference and speed difference between the obstacle and the current vehicle; calculate the length of the reserved space corresponding to the obstacle according to the remaining encounter time between the two, and obtain the longitudinal occupancy size of the lane of the target obstacle; calculate the lateral occupancy size of the lane of the target obstacle based on the obstacle width information and lane line information.

[0149] In an exemplary embodiment, the trajectory planning module 710 is specifically used to analyze whether the current vehicle meets the vehicle passage space requirements based on the lane driving space of the current vehicle; when the lane driving space of the current vehicle does not meet the vehicle passage space requirements, adjust the driving area and driving speed of the current vehicle; when the lane driving space of the current vehicle meets the vehicle passage space requirements, perform path planning and speed planning solutions to generate the obstacle avoidance trajectory of the current vehicle.

[0150] In an exemplary embodiment, the vehicle control module 712 is used to keep the current vehicle centered in the current lane and avoid performing avoidance actions when it is determined based on the driving trajectory analysis that there is a fast-approaching obstacle behind the current vehicle.

[0151] In an exemplary embodiment, the screening module 706 is specifically used to treat obstacles that meet any one of the preset conditions as obstacles that do not need to be avoided; the preset conditions include not being in front of the current vehicle, being in a lane changing state, the obstacle speed is greater than the current vehicle speed, and being in the same lane as the current vehicle.

[0152] Each module in the above-mentioned vehicle obstacle avoidance trajectory planning device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0153] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG8. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the driving data of the target obstacle. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a vehicle obstacle avoidance trajectory planning method is implemented.

[0154] Those skilled in the art will understand that the structure shown in FIG. 8 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0155] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0156] Get the obstacle information around the current vehicle;

[0157] Based on the obstacle information around the current vehicle, predict the driving trajectory of all obstacles in the future preset period of time;

[0158] When there is no fast-approaching obstacle behind the current vehicle based on the driving trajectory analysis, the target obstacle that needs to be avoided in the lane is screened and identified;

[0159] Based on the driving data of the target obstacle, the lane occupation space of the target obstacle is calculated;

[0160] Calculate the lane travel space of the current vehicle based on the lane occupied space of the target obstacle;

[0161] Based on the current vehicle's lane driving space, path planning and speed planning are solved to generate the current vehicle obstacle avoidance trajectory and output it to the vehicle control module.

[0162] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0163] The obstacle that is in front of the current vehicle, is not in the lane changing state, has a speed not greater than the current vehicle speed, and is in a different lane from the current vehicle is regarded as the target obstacle.

[0164] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0165] Driving data includes location information and speed information;

[0166] Based on the driving data of the target obstacle, the distance difference and speed difference between the obstacle and the current vehicle are obtained;

[0167] Calculate the remaining time of the encounter between the obstacle and the current vehicle based on the distance difference and speed difference between the obstacle and the current vehicle;

[0168] According to the remaining time of the encounter between the two vehicles, the length of the reserved space corresponding to the obstacle is calculated to obtain the longitudinal occupied size of the lane of the target obstacle;

[0169] Based on the obstacle width information and lane line information, the lateral lane occupancy size of the target obstacle is calculated.

[0170] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0171] Based on the lane driving space of the current vehicle, analyzing whether the current vehicle meets the vehicle passing space requirements;

[0172] When the lane driving space of the current vehicle does not meet the vehicle passing space requirements, adjusting the driving area and driving speed of the current vehicle;

[0173] When the lane driving space of the current vehicle meets the vehicle passage space requirements, path planning and speed planning are solved to generate the obstacle avoidance trajectory of the current vehicle.

[0174] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0175] When it is determined based on the driving trajectory analysis that there is a fast-approaching obstacle behind the current vehicle, the current vehicle is kept centered in the current lane to avoid performing evasive actions.

[0176] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0177] Obstacles that meet any of the preset conditions are considered obstacles that do not need to be avoided;

[0178] The preset conditions include not being in front of the current vehicle, being in a lane-changing state, the obstacle speed being greater than the current vehicle speed, and being in the same lane as the current vehicle.

[0179] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0180] Get the obstacle information around the current vehicle;

[0181] Based on the obstacle information around the current vehicle, predict the driving trajectory of all obstacles in the future preset period of time;

[0182] When there is no fast-approaching obstacle behind the current vehicle based on the driving trajectory analysis, the target obstacle that needs to be avoided in the lane is screened and identified;

[0183] Based on the driving data of the target obstacle, the lane occupation space of the target obstacle is calculated;

[0184] Calculate the lane travel space of the current vehicle based on the lane occupied space of the target obstacle;

[0185] Based on the current vehicle's lane driving space, path planning and speed planning are solved to generate the current vehicle obstacle avoidance trajectory and output it to the vehicle control module.

[0186] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0187] The obstacle that is in front of the current vehicle, is not in the lane changing state, has a speed not greater than the current vehicle speed, and is in a different lane from the current vehicle is regarded as the target obstacle.

[0188] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0189] Driving data includes location information and speed information;

[0190] Based on the driving data of the target obstacle, the distance difference and speed difference between the obstacle and the current vehicle are obtained;

[0191] Calculate the remaining time of the encounter between the obstacle and the current vehicle based on the distance difference and speed difference between the obstacle and the current vehicle;

[0192] According to the remaining time of the encounter between the two vehicles, the length of the reserved space corresponding to the obstacle is calculated to obtain the longitudinal occupied size of the lane of the target obstacle;

[0193] Based on the obstacle width information and lane line information, the lateral lane occupancy size of the target obstacle is calculated.

[0194] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0195] Based on the lane driving space of the current vehicle, analyzing whether the current vehicle meets the vehicle passing space requirements;

[0196] When the lane driving space of the current vehicle does not meet the vehicle passing space requirements, adjusting the driving area and driving speed of the current vehicle;

[0197] When the lane driving space of the current vehicle meets the vehicle passage space requirements, path planning and speed planning are solved to generate the obstacle avoidance trajectory of the current vehicle.

[0198] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0199] When it is determined based on the driving trajectory analysis that there is a fast-approaching obstacle behind the current vehicle, the current vehicle is kept centered in the current lane to avoid performing evasive actions.

[0200] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0201] Obstacles that meet any of the preset conditions are considered obstacles that do not need to be avoided;

[0202] The preset conditions include not being in front of the current vehicle, being in a lane-changing state, the obstacle speed being greater than the current vehicle speed, and being in the same lane as the current vehicle.

[0203] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0204] Get the obstacle information around the current vehicle;

[0205] Based on the obstacle information around the current vehicle, predict the driving trajectory of all obstacles in the future preset period of time;

[0206] When there is no fast-approaching obstacle behind the current vehicle based on the driving trajectory analysis, the target obstacle that needs to be avoided in the lane is screened and identified;

[0207] Based on the driving data of the target obstacle, the lane occupation space of the target obstacle is calculated;

[0208] Calculate the lane travel space of the current vehicle based on the lane occupied space of the target obstacle;

[0209] Based on the current vehicle's lane driving space, path planning and speed planning are solved to generate the current vehicle obstacle avoidance trajectory and output it to the vehicle control module.

[0210] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0211] The obstacle that is in front of the current vehicle, is not in the lane changing state, has a speed not greater than the current vehicle speed, and is in a different lane from the current vehicle is regarded as the target obstacle.

[0212] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0213] Driving data includes location information and speed information;

[0214] Based on the driving data of the target obstacle, the distance difference and speed difference between the obstacle and the current vehicle are obtained;

[0215] Calculate the remaining time of the encounter between the obstacle and the current vehicle based on the distance difference and speed difference between the obstacle and the current vehicle;

[0216] According to the remaining time of the encounter between the two vehicles, the length of the reserved space corresponding to the obstacle is calculated to obtain the longitudinal occupied size of the lane of the target obstacle;

[0217] Based on the obstacle width information and lane line information, the lateral lane occupancy size of the target obstacle is calculated.

[0218] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0219] Based on the lane driving space of the current vehicle, analyzing whether the current vehicle meets the vehicle passing space requirements;

[0220] When the lane driving space of the current vehicle does not meet the vehicle passing space requirements, adjusting the driving area and driving speed of the current vehicle;

[0221] When the lane driving space of the current vehicle meets the vehicle passage space requirements, path planning and speed planning are solved to generate the obstacle avoidance trajectory of the current vehicle.

[0222] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0223] When it is determined based on the driving trajectory analysis that there is a fast-approaching obstacle behind the current vehicle, the current vehicle is kept centered in the current lane to avoid performing evasive actions.

[0224] In one embodiment, when the computer program is executed by a processor, the following steps are also implemented:

[0225] Obstacles that meet any of the preset conditions are considered obstacles that do not need to be avoided;

[0226] The preset conditions include not being in front of the current vehicle, being in a lane-changing state, the obstacle speed being greater than the current vehicle speed, and being in the same lane as the current vehicle.

[0227] 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, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0228] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory 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. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0229] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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 application.

[0230] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A vehicle obstacle avoidance trajectory planning method, characterized in that: The method comprises: Get the obstacle information around the current vehicle; Based on the obstacle information around the current vehicle, predict the driving trajectory of all obstacles in the future preset period of time; When it is determined based on the driving trajectory analysis that there is no fast-approaching obstacle behind the current vehicle, screening and identifying a target obstacle that needs to be avoided in the lane; Based on the driving data of the target obstacle, the lane occupation space of the target obstacle is calculated; Calculate the lane travel space of the current vehicle based on the lane occupied space of the target obstacle; Based on the current vehicle's lane driving space, path planning and speed planning are solved to generate the current vehicle obstacle avoidance trajectory and output it to the vehicle control module.

2. The method according to claim 1, characterized in that The screening identifies target obstacles that require lane avoidance, including: The obstacle that is in front of the current vehicle, is not in the lane changing state, has a speed not greater than the current vehicle speed, and is in a different lane from the current vehicle is regarded as the target obstacle.

3. The method according to claim 1, characterized in that The driving data includes position information and speed information; The calculating the lane occupied space of the target obstacle based on the driving data of the target obstacle includes: Based on the driving data of the target obstacle, the distance difference and speed difference between the obstacle and the current vehicle are obtained; Calculate the remaining time of the encounter between the obstacle and the current vehicle based on the distance difference and speed difference between the obstacle and the current vehicle; According to the remaining time of the encounter between the two vehicles, the length of the reserved space corresponding to the obstacle is calculated to obtain the longitudinal occupied size of the lane of the target obstacle; Based on the obstacle width information and lane line information, the lateral lane occupancy size of the target obstacle is calculated.

4. The method according to claim 1, characterized in that: The path planning and speed planning are performed based on the lane driving space of the current vehicle to generate the obstacle avoidance trajectory of the current vehicle, including: Based on the lane driving space of the current vehicle, analyzing whether the current vehicle meets the vehicle passing space requirements; When the lane driving space of the current vehicle does not meet the vehicle passing space requirements, adjusting the driving area and driving speed of the current vehicle; When the lane driving space of the current vehicle meets the vehicle passage space requirements, path planning and speed planning are solved to generate the obstacle avoidance trajectory of the current vehicle.

5. The method according to claim 1, characterized in that The method further comprises: When it is determined based on the driving trajectory analysis that there is a fast-approaching obstacle behind the current vehicle, the current vehicle is kept driving in the center of the current lane to avoid performing an avoidance action.

6. The method according to claim 2, characterized in that The method further comprises: Obstacles that meet any of the preset conditions are considered obstacles that do not need to be avoided; The preset conditions include not being in front of the current vehicle, being in a lane changing state, the obstacle speed being greater than the current vehicle speed, and being in the same lane as the current vehicle.

7. A vehicle obstacle avoidance trajectory planning device, characterized in that: The device comprises: Perception module, used to obtain obstacle information around the current vehicle; The prediction module is used to predict the driving trajectory of all obstacles in a future preset period of time based on the obstacle information around the current vehicle; A screening module, for screening and identifying target obstacles that require in-lane obstacle avoidance when there is no fast-approaching obstacle behind the current vehicle based on the driving trajectory analysis; A calculation module, used for calculating a lane occupation space of a target obstacle based on the driving data of the target obstacle; The calculation module is also used to calculate the lane travel space of the current vehicle according to the lane occupation space of the target obstacle; The trajectory planning module is used to perform path planning and speed planning based on the current vehicle's lane driving space, generate the current vehicle obstacle avoidance trajectory, and output it to the vehicle control module.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

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

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images