Vehicle trajectory planning method, storage medium, electronic device and vehicle

Abstract

This disclosure relates to a vehicle trajectory planning method, storage medium, electronic device, and vehicle, to solve the problems of complex algorithms and high computational load in local trajectory planning methods in related technologies. The method includes: determining the positions of the two side edges of the lane where the vehicle is located; determining a first pair of driving boundary reference lines based on the positions of the two side edges of the lane; adjusting the position of at least one of the first pair of driving boundary reference lines N times to obtain N pairs of driving boundary reference lines, where N is a positive integer; determining N+1 trajectory points to be driven based on the N+1 pairs of driving boundary reference lines, wherein the nth trajectory point to be driven is located on the center line of the nth pair of driving boundary reference lines, where n is a positive integer less than or equal to N+1; and obtaining the vehicle's trajectory based on the N+1 trajectory points to be driven.

Description

Technical Field

[0001] This disclosure relates to the field of autonomous driving technology, specifically to a vehicle trajectory planning method, a storage medium, an electronic device, and a vehicle. Background Technology

[0002] Autonomous vehicles require local trajectory planning during operation. Currently, local trajectory planning methods typically rely on intelligent algorithms such as graph search, sampling, and curve fitting to generate the trajectory within the drivable area. However, these methods are computationally complex and computationally intensive. Summary of the Invention

[0003] The purpose of this disclosure is to provide a vehicle trajectory planning method, storage medium, electronic device, and vehicle to solve the problems of complex algorithms and large computational load in local trajectory planning methods in related technologies.

[0004] To achieve the above objectives, a first aspect of this disclosure provides a vehicle trajectory planning method, the method comprising:

[0005] Determine the positions of the two edges of the lane where the vehicle is located;

[0006] Based on the positions of the two sides of the lane, a first pair of driving boundary reference lines are determined;

[0007] The position of at least one of the first pair of driving boundary reference lines is adjusted N times to obtain N pairs of driving boundary reference lines, where N is a positive integer;

[0008] Based on N+1 pairs of driving boundary reference lines, determine N+1 trajectory points to be driven, where the nth trajectory point to be driven is located on the center line of the nth pair of driving boundary reference lines, and n is a positive integer less than or equal to N+1;

[0009] The vehicle's trajectory is obtained based on the N+1 trajectory points to be traveled.

[0010] Optionally, adjusting the position of at least one of the first pair of driving boundary reference lines N times to obtain N pairs of driving boundary reference lines includes:

[0011] For the two driving boundary reference lines in the first pair of driving boundary reference lines, the Kth adjustment is performed to obtain the (K+1)th pair of driving boundary reference lines, wherein the boundary line width of the (K+1)th pair of driving boundary reference lines is equal to the boundary line width of the first pair of driving boundary reference lines, and K is a positive integer less than or equal to N.

[0012] Alternatively, for one of the first pair of driving boundary reference lines, the Kth adjustment is made to obtain the (K+1)th pair of driving boundary reference lines, wherein the width of the boundary line of the (K+1)th pair of driving boundary reference lines is greater than the width of the boundary line of the Kth pair of driving boundary reference lines.

[0013] Optionally, each of the N adjustments is in the same direction, and the lateral distance between two adjacent trajectory points to be driven is equal. The longitudinal distance between the Kth trajectory point to be driven and the (K+1)th trajectory point to be driven is determined based on the vehicle's speed and a preset relationship between speed and longitudinal distance.

[0014] Optionally, a first pair of driving boundary reference lines are determined based on the positions of the two side edges of the lane, including:

[0015] Determine the length of the first pair of driving boundary reference lines;

[0016] Starting from the current position of the vehicle, line segments of the specified length are intercepted at the two sides of the lane as the first pair of driving boundary reference lines;

[0017] The longitudinal distance between the Kth trajectory point to be driven and the (K+1)th trajectory point to be driven is determined based on the vehicle's speed, the length of the first pair of driving boundary reference lines, and the preset relationship between speed, length, and longitudinal distance.

[0018] Optionally, determining the positions of the two sides of the lane where the vehicle is located includes:

[0019] When a preset command is detected, the positions of the two sides of the lane where the vehicle is located are determined, wherein the preset command is generated under any of the following conditions:

[0020] Received lane change instruction;

[0021] An obstacle avoidance command was received to avoid obstacles within the lane.

[0022] Optionally, the step of making the Kth adjustment for one of the first pair of driving boundary reference lines to obtain the (K+1)th pair of driving boundary reference lines includes:

[0023] If the preset instruction is generated upon receiving the obstacle avoidance instruction, then a target boundary reference line to be adjusted is determined from the first pair of driving boundary reference lines. The target boundary reference line is the driving boundary reference line that is farther away from the obstacle from the first pair of driving boundary reference lines.

[0024] The position of the target boundary reference line in the first pair of driving boundary reference lines is adjusted for the Kth time in a lateral direction away from the obstacle to obtain the (K+1)th pair of driving boundary reference lines.

[0025] Optionally, the width of the boundary line corresponding to the (N+1)th pair of driving boundary reference lines is less than twice the width of the boundary line corresponding to the first pair of driving boundary reference lines plus the width of the vehicle.

[0026] Optionally, the step of making the Kth adjustment for one of the first pair of driving boundary reference lines to obtain the (K+1)th pair of driving boundary reference lines includes:

[0027] If the preset instruction is generated upon receiving the lane change instruction, then a target boundary reference line to be adjusted is determined from the first pair of driving boundary reference lines. The target boundary reference line is the driving boundary reference line located on the lane change direction side of the first pair of driving boundary reference lines.

[0028] According to the lane-changing direction, the position of the target boundary reference line in the first pair of driving boundary reference lines is adjusted for the Kth time to obtain the (K+1)th pair of driving boundary reference lines.

[0029] Optionally, the width of the boundary line corresponding to the (N+1)th pair of driving boundary reference lines is greater than twice the width of the boundary line corresponding to the first pair of driving boundary reference lines plus the width of the vehicle, and the width of the boundary line corresponding to the (N+1)th pair of driving boundary reference lines is less than four times the width of the boundary line corresponding to the first pair of driving boundary reference lines plus the width of the vehicle.

[0030] Optionally, determining the positions of the two sides of the lane where the vehicle is located includes:

[0031] Acquire sensor data collected by sensors on the vehicle;

[0032] When the actual lane lines of the lane are identified based on the sensor data, the position of the actual lane lines represents the positions of the two side edges of the lane;

[0033] Alternatively, based on the vehicle's location information, determine the map lane in the navigation map where the vehicle is located;

[0034] The map virtual lane lines of the map lane are determined, and the positions of the map virtual lane lines represent the positions of the two sides of the lane.

[0035] Optionally, the method further includes:

[0036] If the actual lane lines of the lane are not identified based on the sensor data, determine the drivable area in the direction of vehicle travel;

[0037] Based on the width and position of the vehicle, virtual lane lines are determined in the drivable area, wherein the width of the lane line corresponding to the virtual lane line is greater than the width of the vehicle, and the vehicle is located between the virtual lane lines;

[0038] If the obstacle is located within the range of the virtual lane line, the position of the virtual lane line is adjusted N times until the obstacle is located outside the range of the virtual lane line.

[0039] Optionally, the method further includes:

[0040] The sensor data and the vehicle's location information are uploaded to the navigation system backend so that the navigation system backend can determine whether to update the navigation map.

[0041] Optionally, determining the length of the first pair of driving boundary reference lines includes:

[0042] The length of the first pair of driving boundary reference lines is determined based on the type of preset instruction, the size of the obstacle, and the vehicle speed, wherein the type of preset instruction includes lane changing and obstacle avoidance.

[0043] A second aspect of this disclosure also provides a non-transitory computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the steps of the method described in any of the first aspects above.

[0044] A third aspect of this disclosure also provides an electronic device, comprising:

[0045] A memory on which computer programs are stored;

[0046] A processor for executing the computer program in the memory to implement the steps of the method described in any of the first aspects above.

[0047] A fourth aspect of this disclosure also provides a vehicle including the electronic equipment described in the third aspect above.

[0048] The above technical solution can achieve at least the following technical effects:

[0049] First, the positions of the two edges of the lane where the vehicle is located are determined. Based on these positions, a first pair of driving boundary reference lines are established. Then, at least one of the first pair of driving boundary reference lines is adjusted N times to obtain N pairs of driving boundary reference lines. Next, based on the N+1 pairs of driving boundary reference lines, N+1 trajectory points are determined. Finally, the vehicle's trajectory is obtained based on these N+1 trajectory points. This method determines the vehicle's trajectory through simple calculations by adjusting the driving boundary reference lines. Compared to methods relying on intelligent algorithms for local trajectory planning, this method is simpler and requires less computation.

[0050] Other features and advantages of this disclosure will be described in detail in the following detailed description section. Attached Figure Description

[0051] The accompanying drawings are provided to further illustrate the present disclosure and form part of the specification. They are used together with the following detailed description to explain the present disclosure, but do not constitute a limitation thereof. In the drawings:

[0052] Figure 1 This is a flowchart illustrating a vehicle trajectory planning method provided in an embodiment of this disclosure;

[0053] Figure 2 This is a schematic diagram of a vehicle adjusting its driving boundary reference line according to an embodiment of the present disclosure;

[0054] Figure 3 This is a schematic diagram of another vehicle adjustment driving boundary reference line provided in this embodiment of the disclosure;

[0055] Figure 4 This is a schematic diagram of an electronic device shown in an embodiment of this disclosure. Detailed Implementation

[0056] The specific embodiments of this disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit this disclosure.

[0057] It should be understood that the various steps described in the method embodiments of this disclosure may be performed in different orders and / or in parallel. Furthermore, method embodiments may include additional steps and / or omit the steps shown. The scope of this disclosure is not limited in this respect. The term "comprising" and its variations as used herein are open-ended, meaning "including but not limited to". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". Relevant definitions for other terms will be given in the description below.

[0058] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules, or units, and are not used to limit the order of functions performed by these devices, modules, or units or their interdependencies. It should also be noted that the modifications of "a" and "a plurality of" mentioned in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0059] Autonomous vehicles require local trajectory planning during operation. Currently, local trajectory planning methods typically rely on intelligent algorithms such as graph search, sampling, and curve fitting to generate the trajectory within the drivable area. However, these methods are computationally complex and computationally intensive.

[0060] In view of this, the present disclosure provides a vehicle trajectory planning method, a storage medium, an electronic device, and a vehicle to solve the above problems.

[0061] The following provides a detailed description of the embodiments of the technical solution disclosed herein.

[0062] This disclosure provides a vehicle trajectory planning method, referring to... Figure 1 The method includes:

[0063] S101. Determine the positions of the two edges of the lane where the vehicle is located.

[0064] S102. Based on the positions of the two sides of the lane, determine the first pair of driving boundary reference lines.

[0065] S103. Adjust the position of at least one of the first pair of driving boundary reference lines N times to obtain N pairs of driving boundary reference lines.

[0066] Where N is a positive integer.

[0067] S104. Based on N+1 pairs of driving boundary reference lines, determine N+1 driving trajectory points.

[0068] The nth trajectory point to be driven is located on the center line of the nth pair of driving boundary reference lines, where n is a positive integer less than or equal to N+1.

[0069] S105. Obtain the vehicle's trajectory based on N+1 trajectory points to be driven.

[0070] The above method first determines the positions of the two edges of the lane where the vehicle is located. Based on these positions, a first pair of driving boundary reference lines is determined. Then, at least one of the first pair of driving boundary reference lines is adjusted N times to obtain N pairs of driving boundary reference lines. Next, based on the N+1 pairs of driving boundary reference lines, N+1 trajectory points to be determined are identified. Finally, the vehicle's trajectory is obtained based on these N+1 trajectory points. This method determines the vehicle's trajectory through simple calculations by adjusting the driving boundary reference lines. Compared to methods relying on intelligent algorithms for local trajectory planning, this method is simpler and requires less computation.

[0071] To enable those skilled in the art to better understand the vehicle trajectory planning method provided in this disclosure, the above steps are illustrated in detail below.

[0072] In one possible approach, adjusting the position of at least one of the first pair of driving boundary reference lines N times to obtain N pairs of driving boundary reference lines can be as follows: For two driving boundary reference lines in the first pair, perform the Kth adjustment to obtain the (K+1)th pair of driving boundary reference lines, where the width of the (K+1)th pair of driving boundary reference lines is equal to the width of the first pair of driving boundary reference lines. Alternatively, for one driving boundary reference line in the first pair, perform the Kth adjustment to obtain the (K+1)th pair of driving boundary reference lines, where the width of the (K+1)th pair of driving boundary reference lines is greater than the width of the Kth pair of driving boundary reference lines.

[0073] For example, the two driving boundary reference lines in the first pair can be adjusted for the Kth time. That is, the two driving boundary reference lines are moved parallel to each other without changing their width, resulting in the (K+1)th pair of driving boundary reference lines. This yields K+1 points for the vehicle's trajectory, which are then used to determine the vehicle's driving trajectory and control the vehicle to follow that trajectory. Alternatively, one driving boundary reference line in the first pair can be adjusted for the Kth time. That is, one driving boundary reference line is fixed, and the other driving boundary reference line is moved with each adjustment, resulting in K+1 pairs of driving boundary reference lines with different widths. This yields K+1 points for the vehicle's trajectory, which are then used to determine the vehicle's driving trajectory and control the vehicle to follow that trajectory.

[0074] In the possible ways, each of the N adjustments is in the same direction, and the lateral distance between two adjacent trajectory points to be driven is equal. The longitudinal distance between the Kth trajectory point to be driven and the (K+1)th trajectory point to be driven is determined based on the vehicle's speed and the preset relationship between speed and longitudinal distance.

[0075] For example, in each of the N adjustments, the direction of each adjustment is the same, so that the vehicle moves in the same direction, and in order to ensure that the vehicle can move smoothly in the adjusted direction, the lateral distance between two adjacent points on the trajectory to be traveled is equal. This lateral distance can be a preset fixed lateral distance, or it can be a lateral distance determined based on the width of the travel boundary reference line; this disclosure does not limit this. Furthermore, the preset relationship between speed and longitudinal distance is directly proportional; that is, the faster the vehicle's speed, the longer the longitudinal distance.

[0076] In one possible approach, determining the first pair of driving boundary reference lines based on the positions of the two sides of the lane can be achieved by: determining the length of the first pair of driving boundary reference lines, starting from the vehicle's current position, and extracting line segments of that length at the two sides of the lane as the first pair of driving boundary reference lines. The longitudinal distance between the Kth and (K+1)th points of the trajectory to be driven is determined based on the vehicle's speed, the length of the first pair of driving boundary reference lines, and a preset relationship between speed, length, and longitudinal distance.

[0077] For example, to avoid adjusting the positions of both sides of the entire lane, the vehicle's current position can be used as the starting point, and line segments of a certain length can be extracted from the two sides of the lane as the first pair of driving boundary reference lines. This reduces the computational cost when planning the path. The specific length can be adjusted as needed. Furthermore, the preset relationship between speed, length, and longitudinal distance is directly proportional; that is, the faster the vehicle's speed, the longer the longitudinal distance, and the longer the determined first pair of driving boundary reference lines. Since the lateral distance adjusted each time is equal, the longitudinal distance will also be longer. It should be noted that the longitudinal distance between two adjacent points on the driving trajectory can be equal or unequal. For example, when the vehicle is traveling at a constant speed, the longitudinal distance between two adjacent points on the driving trajectory is equal; however, when the vehicle is traveling at varying speeds, the longitudinal distance between two adjacent points on the driving trajectory is unequal.

[0078] One possible approach to determining the positions of the vehicle's lane edges is to: acquire sensor data collected by sensors on the vehicle; and, if the actual lane lines are identified based on the sensor data, the positions of the actual lane lines represent the positions of the lane edges. Alternatively, based on the vehicle's location information, determine the map lane the vehicle is in on the navigation map, and then determine the map virtual lane lines for that map lane; the positions of the map virtual lane lines represent the positions of the lane edges.

[0079] For example, based on the lane marking information (lane lines) identified by the vehicle's vision sensors, the actual position of the lane line where the vehicle is currently located is used as the position of the two sides of the lane. It should be noted that the vehicle's forward-looking vision sensor can identify real-time road surface information ahead of the vehicle and can simultaneously identify lane lines of multiple lanes. Furthermore, based on the road surface information identified by the forward-looking vision sensor, after data processing, the boundary information of multiple lanes, as well as the length and line type of each lane boundary, can be obtained. Based on this information, the boundary length and the lateral distance information between the vehicle and the multiple lane boundaries at different forward-looking distances can be determined.

[0080] For example, since the high-precision map contains lane information such as lane width and virtual lane lines, the vehicle's lane position in the high-precision map is determined based on the vehicle's positioning information. Then, the corresponding lane information is determined based on the lane position, and the position of the virtual lane line in the lane information provided by the high-precision map is used as the position of the two sides of the lane.

[0081] It should be noted that during vehicle operation, sensors continuously monitor the road environment ahead. This information includes road obstacles, road changes, ongoing construction or repairs, worn or repainted road markings, and altered traffic signs. Road obstacles include dynamic obstacles such as vehicles and pedestrians, as well as static obstacles like roadblocks and rocks that obstruct traffic. The system also detects the length, width, height, type, speed, acceleration, and distance of these obstacles. The vehicle's decision-making and planning module generates control commands based on path planning and sensor-perceived road environment information. For example, in multi-lane situations requiring a left or right turn, the module generates a lane-change command to plan the vehicle's path to the left or right turn lane. Similarly, if sensors detect an obstacle ahead in the vehicle's current lane, and if it is a static obstacle, the module generates control commands such as a stop command, obstacle avoidance command, or lane-change command based on the presence of multiple lanes and the obstacle's dimensions. If it is a dynamic obstacle, the vehicle's decision planning module will generate control commands such as stop command, follow command, obstacle avoidance command, or lane change command based on factors such as whether there are multiple lanes, the length, width, height, and speed of the obstacle.

[0082] Furthermore, if the generated control command is a stop command, a travel distance is determined based on the centerline of the driving boundary reference lines (the first pair of driving boundary reference lines) of the lane in which the vehicle is located, and a deceleration and stopping path is planned based on the vehicle's current speed. This controls the vehicle to decelerate from the starting point of the travel distance to the ending point and stop, where the travel distance must be less than the distance between the vehicle and the obstacle. If the generated control command is a follow command, lane keeping control and adaptive following function are implemented based on the centerline of the driving boundary reference lines (the first pair of driving boundary reference lines) of the lane in which the vehicle is located, while maintaining a safe distance from the obstacle. If the generated control command is a lane change command or an obstacle avoidance command, the position of the driving boundary reference lines of the lane in which the vehicle is located needs to be adjusted to determine the trajectory point for lane change to control the vehicle to change lanes, or the trajectory point for obstacle avoidance to control the vehicle to avoid obstacles.

[0083] In one possible manner, determining the positions of the two sides of the lane in which the vehicle is located can be done by: determining the positions of the two sides of the lane in which the vehicle is located when a preset instruction is detected, wherein the preset instruction is generated in any of the following situations: receiving a lane-changing instruction; receiving an obstacle avoidance instruction to avoid obstacles in the lane.

[0084] For example, when the vehicle's decision planning module generates a lane-changing or obstacle-avoidance command, it further generates a preset command based on the lane-changing or obstacle-avoidance command, and then adjusts the position of the first pair of driving boundary reference lines N times according to the preset command to obtain N+1 pairs of driving boundary reference lines.

[0085] In one possible way, the length of the first pair of driving boundary reference lines can be determined by: determining the length of the first pair of driving boundary reference lines based on the type of preset instruction, the size of the obstacle, and the vehicle speed, wherein the type of preset instruction includes lane changing and obstacle avoidance.

[0086] For example, since lane-changing instructions require a greater offset distance than obstacle avoidance instructions, under the same conditions, the length of the driving boundary reference line corresponding to a lane-changing instruction is usually greater than that corresponding to an obstacle avoidance instruction. Furthermore, the size of the obstacle and the vehicle's speed are directly proportional to the length of the driving boundary reference line; that is, the larger the obstacle, the greater the offset distance the vehicle needs to make, and therefore the longer the determined driving boundary reference line. Correspondingly, the faster the vehicle's speed, the longer the determined driving boundary reference line will be. This prevents the determined driving boundary reference line from being too short, which could cause the vehicle to deviate rapidly within a short distance and lead to a safety accident.

[0087] In one possible approach, adjusting one of the first pair of driving boundary reference lines for the Kth time to obtain the K+1th pair of driving boundary reference lines can be done as follows: If the preset command is generated upon receiving an obstacle avoidance command, then a target boundary reference line to be adjusted is determined from the first pair of driving boundary reference lines. The target boundary reference line is the driving boundary reference line in the first pair of driving boundary reference lines that is farther away from the obstacle. The position of the target boundary reference line in the first pair of driving boundary reference lines is adjusted for the Kth time in the lateral direction away from the obstacle to obtain the K+1th pair of driving boundary reference lines.

[0088] Among them, the width of the boundary line corresponding to the N+1th pair of driving boundary reference lines is less than twice the width of the boundary line corresponding to the first pair of driving boundary reference lines plus the width of the vehicle.

[0089] For example, refer to Figure 2 The vehicle travels along the centerline of the current lane's driving boundary reference line (reference centerline 1). The vehicle's decision-making and planning module generates obstacle avoidance instructions based on obstacle information perceived by the perception module. It then captures a segment of driving boundary reference line of length 1 within the current driving boundary reference line and determines a target boundary reference line (lane boundary 2) that is far from the obstacle. Lane boundary 2 is adjusted, either by determining the number of adjustments based on obstacle information (e.g., length, width, speed) to maintain a safe distance from the obstacle after adjustment. Alternatively, the number of adjustments can be determined based on a preset width requirement; for example, adjusting the target boundary reference line to twice the lane width (the position of lane boundary 3) would place the centerline of the adjusted driving boundary reference line at the position of lane boundary line 2. Based on N+1 pairs of driving boundary reference lines during the adjustment process, N+1 points are determined to obtain the vehicle's obstacle avoidance trajectory (local trajectory 2). This disclosure does not limit this specific approach. As long as the width of the boundary line corresponding to the N+1th pair of driving boundary reference lines is less than twice the width of the boundary line corresponding to the first pair of driving boundary reference lines plus the width of the vehicle, the planned driving path of the vehicle can avoid obstacles and the distance is within the driving safety requirements.

[0090] It should be noted that the length of the captured segment is 1 to avoid capturing the entire driving boundary reference line for adjustment, thereby reducing the calculation cost when the vehicle plans the path. The specific length can be adjusted according to the needs, as long as the planned driving path of the vehicle can avoid obstacles and the distance is within the driving safety requirements.

[0091] In one possible approach, adjusting one of the first pair of driving boundary reference lines for the Kth time to obtain the (K+1)th pair of driving boundary reference lines can be done as follows: If the preset command is generated upon receiving a lane-changing driving command, then a target boundary reference line to be adjusted is determined from the first pair of driving boundary reference lines. The target boundary reference line is the driving boundary reference line located on the lane-changing direction side of the first pair of driving boundary reference lines. The position of the target boundary reference line in the first pair of driving boundary reference lines is adjusted for the Kth time according to the lane-changing direction to obtain the (K+1)th pair of driving boundary reference lines.

[0092] Among them, the width of the boundary line corresponding to the N+1th pair of driving boundary reference lines is greater than twice the width of the boundary line corresponding to the first pair of driving boundary reference lines plus the width of the vehicle, and the width of the boundary line corresponding to the N+1th pair of driving boundary reference lines is less than four times the width of the boundary line corresponding to the first pair of driving boundary reference lines plus the width of the vehicle.

[0093] For example, refer to Figure 2 The vehicle travels along the centerline (reference centerline 1) of the current lane's driving boundary reference line. The vehicle's decision-making and planning module generates a lane-change command based on obstacle information detected by the perception module or the need to change lanes. It then captures a segment of driving boundary reference line of length 2 within the current driving boundary reference line and determines a target boundary reference line (lane boundary 2) located on the side of the lane-change direction. The lane-change direction includes changing lanes to the left or to the right. Figure 2 Taking a left lane change as an example, the lane boundary 2 is adjusted. The number of adjustments can be determined based on a preset width requirement. For example, adjusting the target boundary reference line to three times the lane width (the position of lane boundary 4) will place the center line of the adjusted driving boundary reference line at the position of reference center line 2. Based on the N+1 pairs of driving boundary reference lines during the adjustment process, N+1 trajectory points are determined to obtain the vehicle's lane-changing trajectory (local trajectory 3). Since the lane has a certain width, the vehicle can deviate within a certain width when changing lanes. Therefore, the width of the boundary line corresponding to the N+1th pair of driving boundary reference lines can meet the vehicle's lane-changing requirements if it is greater than twice the width of the boundary line corresponding to the first pair of driving boundary reference lines plus the vehicle's width, but less than four times the width of the boundary line corresponding to the first pair of driving boundary reference lines plus the vehicle's width. In other words, the number of times the target boundary reference line can be adjusted within this range is not limited in this disclosure.

[0094] It should be understood that if a vehicle needs to change lanes to overtake, it will follow the driving path of local trajectory 3. If a vehicle needs to change lanes, after reaching the position of reference centerline 2, it can plan its driving path based on the driving boundary reference line of the current lane, that is, it will drive along the centerline of the driving boundary reference line of the current lane (reference centerline 2). In addition, the captured length 2 is to avoid capturing the entire driving boundary reference line for adjustment, reducing the calculation cost of the vehicle when planning the path. The specific length can be adjusted according to needs, as long as the planned driving path of the vehicle allows the vehicle to change lanes.

[0095] Furthermore, the vehicle controls its lateral and longitudinal speeds based on the lateral distance, longitudinal distance, and angle information between each two adjacent trajectory points in the adjusted driving path, so that the vehicle travels along the adjusted driving path.

[0096] In one possible approach, the method further includes: determining a drivable area in the vehicle's direction of travel when no actual lane lines are identified based on sensor data; determining virtual lane lines within the drivable area based on the vehicle's width and position; wherein the width of the virtual lane lines is greater than the width of the vehicle, and the vehicle is positioned between the virtual lane lines. If an obstacle is located within the virtual lane lines, the position of the virtual lane lines is adjusted N times until the obstacle is located outside the virtual lane lines.

[0097] For example, when a vehicle is on a road section without a high-precision map and without road markings, the area can be segmented based on obstacle information identified by the vehicle's sensors to determine the drivable area in the vehicle's direction of travel. Obstacles can be vehicles, trees, pedestrians, buildings, or other obstacles that impede vehicle movement. Then, based on the vehicle's width, virtual lane lines that do not coincide with obstacles within a certain distance are determined within the drivable area, and the positions of these virtual lane lines are used as the two side edges of the lanes. Here, "certain distance" refers to the distance within which the vehicle might collide with the obstacle. The vehicle is positioned between the virtual lane lines, and the width of the corresponding lane line is greater than the width of the vehicle to ensure a safe driving distance between the vehicle and obstacles during travel. The specific width can be determined based on the distance requirements for safe driving; this disclosure does not limit this.

[0098] For example, if the obstacle is within the range of the virtual lane lines, the position of the virtual lane lines is adjusted N times until the obstacle is outside the range of the virtual lane lines. Furthermore, the driving path is determined based on the N+1 pairs of driving boundary reference lines that form the trajectory points to be driven. The vehicle controls its lateral and longitudinal speeds according to the lateral distance, longitudinal distance, and angle information between each pair of adjacent trajectory points in the adjusted driving path, so that the vehicle travels along the adjusted driving path.

[0099] For example, refer to Figure 3 The vehicle travels along the centerline of the currently determined virtual lane line 1 (virtual lane centerline 1). The vehicle's decision-making and planning module determines whether there are other drivable areas based on obstacle information perceived by the perception module, and performs obstacle avoidance maneuvers accordingly. If such areas exist, an obstacle avoidance command is generated; otherwise, a stop command or follow command is generated depending on whether the obstacle is dynamic. If the vehicle's decision-making and planning module generates an obstacle avoidance command, it determines the target boundary reference line (virtual left boundary 1) furthest from the obstacle from the first pair of driving boundary reference lines, and then determines the lateral direction (left side) that moves the target boundary reference line away from the obstacle. Finally, according to the lateral direction, the position of the first pair of driving boundary reference lines is adjusted N times within a preset lateral movement range until the obstacle is located outside the N+1th pair of driving boundary reference lines. Figure 3 The virtual left boundary 1 and virtual right boundary 1 are moved to the left by a distance d1 to obtain the adjusted virtual left boundary 2 and virtual right boundary 2.

[0100] For example, refer to Figure 3 The distance between virtual left boundary 2 and the left obstacle area is L1, the distance between virtual right boundary 2 and the right obstacle area is R1, and the lane width between virtual left and right boundaries 2 is W2. The distance between virtual left boundary 1 and the left obstacle area is L2, the distance between virtual right boundary 1 and the right obstacle area is R2, the lane width between virtual left and right boundaries 1 is W1, the distance between virtual lane centerline 1 and virtual lane centerline 2 is d1, and the preset lateral movement interval is one-quarter of the lane width. Taking the above parameters as an example, the constraint equations for the left and right virtual lane boundary lines and lane widths are as follows:

[0101]

[0102] Among them, L i R represents the distance between the virtual left boundary and the obstacle region on the left. i W represents the distance between the virtual right boundary and the obstacle area on the right. i Indicates lane width, d j This indicates the width of the preset horizontal movement range.

[0103] It should be noted that the above constraint equations are only illustrative and can be adjusted according to requirements in practical applications, for example, L i With R i It can be set to the distance required for safe vehicle operation, d j It can be set to a lane width to enable vehicles to overtake, etc., but this disclosure does not impose specific restrictions on it.

[0104] It's worth noting that when the vehicle's decision-making and planning module determines whether there are other drivable areas based on obstacle information perceived by the perception module, it can move the current virtual lane line left or right to search for other drivable areas. This allows it to determine the lateral direction with minimal vehicle deviation and generate corresponding control commands. For example, it might move a quarter of the lane line width each time. If the moved driving boundary reference line does not overlap with the obstacle, this quarter of the lane line width is used as a preset lateral movement interval. The vehicle can then adjust the driving boundary reference line multiple times within this interval to obtain a driving path. If the moved driving boundary reference line overlaps with the obstacle, the adjustment continues until they no longer overlap. The system then determines whether the vehicle can drive normally based on the distance between the adjusted driving boundary reference line and the obstacle. For example, excessive deviation within a short distance might prevent the vehicle from driving normally. If the vehicle can drive normally, the adjusted lateral distance is used as a preset lateral movement interval, allowing the vehicle to adjust the driving boundary reference line multiple times within this interval to obtain a driving path. Otherwise, a stop command or follow command can be generated to make the vehicle drive along the centerline of the current driving boundary reference line.

[0105] It should be noted that since the driving boundary reference line can extend indefinitely, determining whether there is an overlap between the driving boundary reference line and the obstacle refers to determining whether there is an overlap between the driving boundary reference line and the obstacle within a certain distance. For example, if the obstacle in the current lane is a static obstacle and the distance between it and the vehicle is less than a certain distance, and the newly found driving boundary reference line does not overlap with the obstacle within a certain distance, then an obstacle avoidance command can be generated. This "certain distance" refers to the distance within which the vehicle might collide with the obstacle.

[0106] In some possible ways, the method also includes uploading sensor data and vehicle location information to the navigation system backend so that the navigation system backend can determine whether to update the navigation map.

[0107] For example, for road sections where navigation maps exist, the vehicle's perception module determines whether the actual road environment matches the information provided by the navigation map based on the perceived road environment information. If they do not match, the information is uploaded to the navigation system for updating the navigation map. The vehicle's perception module can also upload real-time perceived road environment information to the navigation system, which then determines whether to update the navigation map. For road sections where no navigation map exists, the vehicle's perception module can upload real-time perceived road environment information to the navigation system, which then determines whether to create a new navigation map. This disclosure does not limit this approach.

[0108] Based on the same inventive concept, this disclosure also provides a non-transitory computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described vehicle trajectory planning method steps.

[0109] Based on the same inventive concept, this disclosure also provides an electronic device, including:

[0110] A memory on which computer programs are stored;

[0111] A processor is used to execute the computer program in the memory to implement the steps of the vehicle trajectory planning method described above.

[0112] Based on the same inventive concept, this disclosure also provides a vehicle including the above-mentioned electronic equipment.

[0113] Figure 4 This is a block diagram illustrating an electronic device 400 according to an exemplary embodiment. (Refer to...) Figure 4 The electronic device 400 includes a processor 401, which may be one or more, and a memory 402 for storing computer programs executable by the processor 401. The computer programs stored in the memory 402 may include one or more modules, each corresponding to a set of instructions. Furthermore, the processor 401 may be configured to execute the computer program to perform the vehicle trajectory planning method described above.

[0114] Additionally, the electronic device 400 may also include a power supply component 405 and a communication component 403. The power supply component 405 can be configured to perform power management of the electronic device 400, and the communication component 403 can be configured to enable communication of the electronic device 400, such as wired or wireless communication. Furthermore, the electronic device 400 may also include an input / output (I / O) interface 404. The electronic device 400 can operate on an operating system, such as Windows Server, stored in the memory 402. TM Mac OSX TM Unix TM Linux TM etc.

[0115] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the vehicle trajectory planning method described above. For example, the non-transitory computer-readable storage medium may be the memory 402 including program instructions, which may be executed by the processor 401 of the electronic device 400 to complete the vehicle trajectory planning method described above.

[0116] In another exemplary embodiment, a computer program product is also provided, the computer program product comprising a computer program executable by a programmable device, the computer program having a code portion for performing the vehicle driving trajectory planning method described above when executed by the programmable device.

[0117] The preferred embodiments of this disclosure have been described in detail above with reference to the accompanying drawings. However, this disclosure is not limited to the specific details of the above embodiments. Within the scope of the technical concept of this disclosure, various simple modifications can be made to the technical solutions of this disclosure, and these simple modifications all fall within the protection scope of this disclosure.

[0118] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, this disclosure will not describe the various possible combinations separately.

[0119] Furthermore, various different embodiments of this disclosure can be combined in any way, as long as they do not violate the spirit of this disclosure, they should also be regarded as the content disclosed in this disclosure.

Claims

1. A method for planning vehicle driving trajectory, characterized in that, The method includes: Determine the positions of the two edges of the lane where the vehicle is located; Based on the positions of the two sides of the lane, a first pair of driving boundary reference lines are determined; The position of at least one of the first pair of driving boundary reference lines is adjusted N times to obtain N pairs of driving boundary reference lines, where N is a positive integer; Based on N+1 pairs of driving boundary reference lines, determine N+1 trajectory points to be driven, where the nth trajectory point to be driven is located on the center line of the nth pair of driving boundary reference lines, and n is a positive integer less than or equal to N+1; The vehicle's trajectory is obtained based on the N+1 trajectory points to be traveled; The step of adjusting the position of at least one of the first pair of driving boundary reference lines N times to obtain N pairs of driving boundary reference lines includes: For the two driving boundary reference lines in the first pair of driving boundary reference lines, the Kth adjustment is performed to obtain the (K+1)th pair of driving boundary reference lines, wherein the boundary line width of the (K+1)th pair of driving boundary reference lines is equal to the boundary line width of the first pair of driving boundary reference lines, and K is a positive integer less than or equal to N. Alternatively, for one of the first pair of driving boundary reference lines, the Kth adjustment is made to obtain the (K+1)th pair of driving boundary reference lines, wherein the width of the boundary line of the (K+1)th pair of driving boundary reference lines is greater than the width of the boundary line of the Kth pair of driving boundary reference lines. In the N adjustments, each adjustment is in the same direction, and the lateral distance between two adjacent trajectory points is equal. The longitudinal distance between the Kth trajectory point and the (K+1)th trajectory point is determined based on the vehicle's speed and a preset relationship between speed and longitudinal distance.

2. The method according to claim 1, characterized in that, Based on the positions of the two side edges of the lane, a first pair of driving boundary reference lines are determined, including: Determine the length of the first pair of driving boundary reference lines; Starting from the current position of the vehicle, line segments of the specified length are intercepted at the two sides of the lane as the first pair of driving boundary reference lines; The longitudinal distance between the Kth trajectory point to be driven and the (K+1)th trajectory point to be driven is determined based on the vehicle's speed, the length of the first pair of driving boundary reference lines, and the preset relationship between speed, length, and longitudinal distance.

3. The method according to claim 2, characterized in that, Determining the positions of the two edges of the lane where the vehicle is located includes: When a preset command is detected, the positions of the two sides of the lane where the vehicle is located are determined, wherein the preset command is generated under any of the following conditions: Received lane change instruction; An obstacle avoidance command was received to avoid obstacles within the lane.

4. The method according to claim 3, characterized in that, The step of making the Kth adjustment to one of the first pair of driving boundary reference lines to obtain the (K+1)th pair of driving boundary reference lines includes: If the preset instruction is generated upon receiving the obstacle avoidance instruction, then a target boundary reference line to be adjusted is determined from the first pair of driving boundary reference lines. The target boundary reference line is the driving boundary reference line that is farther away from the obstacle from the first pair of driving boundary reference lines. The position of the target boundary reference line in the first pair of driving boundary reference lines is adjusted for the Kth time in a lateral direction away from the obstacle to obtain the (K+1)th pair of driving boundary reference lines.

5. The method according to claim 4, characterized in that, The width of the boundary line corresponding to the (N+1)th pair of driving boundary reference lines is less than twice the width of the boundary line corresponding to the first pair of driving boundary reference lines plus the width of the vehicle.

6. The method according to claim 3, characterized in that, The step of making the Kth adjustment to one of the first pair of driving boundary reference lines to obtain the (K+1)th pair of driving boundary reference lines includes: If the preset instruction is generated upon receiving the lane change instruction, then a target boundary reference line to be adjusted is determined from the first pair of driving boundary reference lines. The target boundary reference line is the driving boundary reference line located on the lane change direction side of the first pair of driving boundary reference lines. According to the lane-changing direction, the position of the target boundary reference line in the first pair of driving boundary reference lines is adjusted for the Kth time to obtain the (K+1)th pair of driving boundary reference lines.

7. The method according to claim 6, characterized in that, The width of the boundary line corresponding to the (N+1)th pair of driving boundary reference lines is greater than twice the width of the boundary line corresponding to the first pair of driving boundary reference lines plus the width of the vehicle; the width of the boundary line corresponding to the (N+1)th pair of driving boundary reference lines is less than four times the width of the boundary line corresponding to the first pair of driving boundary reference lines plus the width of the vehicle.

8. The method according to claim 3, characterized in that, Determining the positions of the two edges of the lane where the vehicle is located includes: Acquire sensor data collected by sensors on the vehicle; When the actual lane lines of the lane are identified based on the sensor data, the position of the actual lane lines represents the positions of the two side edges of the lane; Alternatively, based on the vehicle's location information, determine the map lane in the navigation map where the vehicle is located; The map virtual lane lines of the map lane are determined, and the positions of the map virtual lane lines represent the positions of the two sides of the lane.

9. The method according to claim 8, characterized in that, The method further includes: If the actual lane lines of the lane are not identified based on the sensor data, determine the drivable area in the direction of vehicle travel; Based on the width and position of the vehicle, virtual lane lines are determined in the drivable area, wherein the width of the lane line corresponding to the virtual lane line is greater than the width of the vehicle, and the vehicle is located between the virtual lane lines; If the obstacle is located within the range of the virtual lane line, the position of the virtual lane line is adjusted N times until the obstacle is located outside the range of the virtual lane line.

10. The method according to claim 8, characterized in that, The method further includes: The sensor data and the vehicle's location information are uploaded to the navigation system backend so that the navigation system backend can determine whether to update the navigation map.

11. The method according to claim 3, characterized in that, Determining the length of the first pair of driving boundary reference lines includes: The length of the first pair of driving boundary reference lines is determined based on the type of preset instruction, the size of the obstacle, and the vehicle speed, wherein the type of preset instruction includes lane changing and obstacle avoidance.

12. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by a processor, the program implements the steps of the method described in any one of claims 1-11.

13. An electronic device, characterized in that, include: A memory on which computer programs are stored; A processor for executing the computer program in the memory to implement the steps of the method according to any one of claims 1-11.

14. A vehicle, characterized in that, Includes the electronic device as described in claim 13.

Images