Path planning method, device and equipment and automatic driving vehicle

Abstract

The present disclosure provides a path planning method and device, equipment and an autonomous vehicle, relates to the technical field of artificial intelligence, in particular to the technical field of autonomous driving. The specific implementation scheme is: performing secondary planning processing on a first path segment to obtain a first planned path, performing curve fitting processing on a second path segment to obtain a second planned path; based on the first planned path and the second planned path, generating a plurality of candidate paths; in the plurality of candidate paths, a target planned path is selected to control the vehicle to travel from a starting point to an ending point along the target planned path. The technical scheme provided by the present disclosure ensures the efficiency of path planning while improving the accuracy of path planning.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and more particularly to the field of autonomous driving technology, specifically to a path planning method, apparatus, device, and autonomous vehicle. Background Technology

[0002] With the rapid development of artificial intelligence technology, using AI for autonomous driving has become a hot research area. Currently, path planning is one of the core technologies of autonomous driving, aiming to create a collision-free and safe path for the vehicle from its origin to its destination, thereby ensuring the safety and reliability of autonomous driving. Summary of the Invention

[0003] This disclosure provides a path planning method, apparatus, device, and autonomous vehicle.

[0004] According to one aspect of this disclosure, a path planning method is provided, applied to the process of controlling a vehicle to travel from a starting position to an ending position, wherein the path from the starting position to the ending position includes a first path segment and at least one second path segment;

[0005] The method includes:

[0006] The first path segment is subjected to quadratic planning to obtain the first planned path, and the second path segment is subjected to curve fitting to obtain the second planned path.

[0007] Based on the first planning path and the second planning path, multiple candidate paths are generated;

[0008] Among the multiple candidate paths, a target planned path is selected to control the vehicle to travel along the target planned path from the starting position to the ending position.

[0009] According to another aspect of this disclosure, a path planning device is provided for controlling a vehicle to travel from a starting position to an ending position, wherein the path from the starting position to the ending position includes a first path segment and at least one second path segment.

[0010] The device includes:

[0011] The processing module is used to perform secondary planning on the first path segment to obtain the first planned path, and to perform curve fitting on the second path segment to obtain the second planned path.

[0012] The generation module is used to generate multiple candidate paths based on the first planned path and the second planned path;

[0013] The selection module is used to select a target planned path from the multiple candidate paths, so as to control the vehicle to travel along the target planned path from the starting position to the ending position.

[0014] According to another aspect of this disclosure, an electronic device is provided, comprising:

[0015] At least one processor; and

[0016] The memory is communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the path planning method provided in this disclosure.

[0018] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform the path planning method provided in this disclosure.

[0019] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the path planning method provided in this disclosure.

[0020] According to another aspect of this disclosure, an autonomous vehicle is provided, including the electronic equipment provided in this disclosure.

[0021] The technical solution provided in this disclosure adopts a more flexible and accurate secondary planning method for the first segment of the path that needs to be focused on in path planning. This method can plan a more flexible path and better adapt to the scenario requirements of the vehicle's lateral, longitudinal, and height coordination. For the second segment of the path planning, a curve fitting method is used to improve the planning efficiency of the second segment, thereby improving the overall efficiency of path planning.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0023] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0024] Figure 1 This is a scene diagram illustrating a path planning method according to an embodiment of the present disclosure;

[0025] Figure 2This is a flowchart illustrating a path planning method according to an embodiment of the present disclosure;

[0026] Figure 3 This is a flowchart illustrating a path planning method according to an embodiment of the present disclosure;

[0027] Figure 4 This is a schematic diagram illustrating a path division according to an embodiment of the present disclosure;

[0028] Figure 5 This is a schematic diagram illustrating the spatial extent of an obstacle according to an embodiment of the present disclosure;

[0029] Figure 6 This is a schematic flowchart illustrating a path planning process according to an embodiment of the present disclosure;

[0030] Figure 7 This is a schematic diagram comparing a quadratic programming method with a template curve according to an embodiment of the present disclosure;

[0031] Figure 8 This is a structural block diagram of a path planning device according to an embodiment of the present disclosure;

[0032] Figure 9 This is a block diagram of an electronic device used to implement the path planning method of the embodiments of this disclosure. Detailed Implementation

[0033] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0034] The collection, storage, use, processing, transmission, provision, and disclosure of user personal information involved in the technical solution disclosed herein comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0035] First, the application scenarios involved in the embodiments of this disclosure will be described:

[0036] The path planning method provided in this disclosure can be applied to scenarios where autonomous vehicles require high coordination between lateral and longitudinal directions. Examples include interactions with other vehicles while traveling straight at an intersection, and interactions with other vehicles during lane changes. Here, lateral refers to the direction perpendicular to the lane line, and longitudinal refers to the direction of the lane. It should be understood that, for such unexpected lateral situations on the road, high accuracy in lateral path planning is typically required.

[0037] In one possible implementation, the path planning method provided in this disclosure is applied to the lateral path planning portion of three-dimensional joint planning to ensure the accuracy of lateral path planning in three-dimensional joint planning. Here, three-dimensional joint planning refers to the simultaneous consideration of spatial dimension information (such as position) and temporal dimension information (such as speed) during path planning. Lateral path planning (or lateral planning) is the process of planning the vehicle's driving path based on spatial dimension information. It should be understood that lateral path planning is a directional planning process that determines the shape of the vehicle's driving path.

[0038] In related technologies, path planning for autonomous vehicles typically involves curve fitting based on a pre-constructed template curve (such as a polynomial curve) and the vehicle's state information under specific conditions (such as speed or acceleration at the destination). However, since the template curve has a fixed shape, on the one hand, its expressive power is limited, and it may suffer from overshoot (i.e., deviation). On the other hand, the connection between the beginning and end of the template curve makes it difficult to control the shape in the middle, which may lead to problems such as vehicle collisions due to deviations.

[0039] In this embodiment of the disclosure, a path planning scheme combining quadratic programming and curve fitting is provided. For the first segment of the path that needs to be focused on in the path planning, the more flexible and accurate quadratic programming method is used to plan the path, which can plan a more flexible path and better adapt to the scenario requirements of the vehicle's lateral, longitudinal and vertical alignment. For the second segment of the path planning, the curve fitting method is used to improve the planning efficiency of the second segment, thereby improving the overall path planning efficiency.

[0040] Figure 1 This is a scene diagram illustrating a path planning method according to an embodiment of this disclosure. It should be noted that the path planning method provided in this embodiment is executed by an autonomous driving device in an autonomous vehicle. See also... Figure 1 This autonomous driving device can provide Figure 1 The terminal device 101 or server 102 shown.

[0041] The terminal device 101 can be at least one of the following: a smartphone, a smartwatch, a desktop computer, a laptop, a virtual reality terminal, an augmented reality terminal, a wireless terminal, and a laptop computer. In one possible implementation, the terminal device 101 has communication capabilities and can access a wired or wireless network. The term "terminal device 101" can refer to one of multiple terminal devices; this embodiment uses only terminal device 101 as an example. Those skilled in the art will understand that the number of terminal devices can be greater or less.

[0042] Server 102 may be an independent physical server, a server cluster consisting of multiple physical servers, a distributed file system, or at least one of the following cloud servers providing basic cloud computing services: cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms. This disclosure does not limit the specific type of server 102. In some embodiments, server 102 and terminal device 101 are directly or indirectly connected via wired or wireless communication. This disclosure does not limit the specific type of server 102. In one possible implementation, the number of servers 102 may be more or fewer. This disclosure does not limit the specific type of server 102. Of course, server 102 may also include other functional servers to provide more comprehensive and diversified services.

[0043] In one possible implementation of the aforementioned autonomous driving device, the autonomous driving device includes a control module, a positioning module, a perception module, a decision-making module, and a planning module.

[0044] The control module is used to control the vehicle's motion state. In one possible implementation, the vehicle can change the power output by the power generating device such as the engine or electric motor, or change the braking force output by the braking device, based on the control signals output by the control module, thus achieving control of the vehicle's speed by the control module; or, in another possible implementation, the vehicle can change the vehicle's steering angle based on the control signals output by the control module, thus achieving control of the vehicle's direction of motion by the control module.

[0045] The positioning module is used for vehicle location and tracking; for example, it can be a Global Positioning System (GPS) device. In one possible implementation, the positioning module can acquire the vehicle's real-time location and reflect its real-time location and trajectory on an electronic map, thereby visualizing the vehicle's trajectory.

[0046] The perception module is used to detect information about objects around the vehicle, such as their position, speed, and orientation. In one possible implementation, the perception module provides functions such as road boundary detection, lane line detection, pedestrian detection, vehicle detection, and traffic sign detection.

[0047] The decision-making module is used to make decisions based on the information output by the positioning module and the perception module in order to determine the vehicle's driving decision.

[0048] The planning module is used to plan the path for vehicles, that is, to predict the future trajectory of vehicles.

[0049] In this embodiment of the disclosure, the vehicle can be provided with autonomous driving functionality through the cooperation between the control module, the positioning module, the perception module, the decision-making module, and the planning module.

[0050] Figure 2 This is a flowchart illustrating a path planning method according to an embodiment of the present disclosure. The path planning method is applied to control a vehicle moving from a starting point to a destination. The path from the starting point to the destination includes a first path segment and at least one second path segment. The path planning method provided in this embodiment is executed by an electronic device. In one possible implementation, the electronic device can be provided as described above. Figure 1 The image shows an autonomous driving device. (As shown) Figure 2 As shown, the method includes the following steps.

[0051] In step S201, the electronic device performs secondary planning processing on the first path segment to obtain the first planned path, and performs curve fitting processing on the second path segment to obtain the second planned path.

[0052] In step S202, the electronic device generates multiple candidate paths based on the first planned path and the second planned path.

[0053] In step S203, the electronic device selects the target planned path from the multiple candidate paths to control the vehicle to travel along the target planned path from the starting position to the ending position.

[0054] The technical solution provided in this disclosure adopts a more flexible and accurate secondary planning method for the first segment of the path that needs to be focused on in path planning. This method can plan a more flexible path that can better adapt to the scenario requirements of vehicle lateral, longitudinal, and height coordination. For the second segment of the path planning, a curve fitting method is used to improve the planning efficiency of the second segment, thereby improving the overall path planning efficiency.

[0055] Figure 3 This is a flowchart illustrating a path planning method according to an embodiment of the present disclosure. This path planning method is applied to controlling a vehicle's movement from a starting point to a destination. The path planning method provided in this embodiment is executed by an electronic device. In one possible implementation, the electronic device can be provided as described above. Figure 1 The image shows an autonomous driving device. (As shown) Figure 3 As shown, the method includes the following steps.

[0056] In step S301, the electronic device divides the path from the starting position to the ending position to obtain a first path segment and at least one second path segment.

[0057] The starting position refers to the location where the vehicle begins its journey. In one possible implementation, the electronic device determines the vehicle's current location as the starting position. The destination position refers to the location the vehicle intends to reach. In one possible implementation, the destination position is a pre-set location. For example, before activating the autonomous driving function, the user can upload the destination position to the electronic device, which will then be able to obtain that destination position.

[0058] In this embodiment of the disclosure, the path from the starting point to the ending point includes a first path segment and at least one second path segment. The first path segment is the earlier path segment in the path from the starting point to the ending point. The second path segment is the later path segment in the path from the starting point to the ending point. It should be understood that the first path segment is the path segment originating from the vehicle's starting point.

[0059] In one possible implementation, the first path segment satisfies at least one of the following conditions: the endpoint is a location point at a preset distance from the starting point; the endpoint is a location point that satisfies an orientation condition with the vehicle's endpoint, the orientation condition including at least one of the following: the orientation is the same or the orientation angle difference is less than a preset threshold.

[0060] The preset distance is a pre-defined distance value, such as 5 meters, 10 meters, or other distance values. The preset threshold is a pre-defined angle difference value, such as 15 degrees, 30 degrees, or other angle difference values. This embodiment does not limit the values ​​of the preset distance and the preset threshold. In this embodiment, by setting the positional conditions that the first path segment needs to meet, the first path segment and the at least one second path segment can be quickly divided, improving the efficiency of path division and thus ensuring the efficiency of path planning. It should be noted that in another possible implementation, the electronic device can also set other types of positional conditions, and then use the set positional conditions for path division. This embodiment does not limit this.

[0061] Based on the aforementioned positional conditions required for the first path segment, the process by which the electronic device divides the path into a first path segment and at least one second path segment includes: In one possible implementation, the electronic device determines a position point at a preset distance from the starting point in the path from the starting point to the ending point, uses this position point as a dividing point, divides the path, and designates the preceding path segment as the first path segment and the following path segment as the second path segment. Alternatively, in another possible implementation, the electronic device determines a position point in the path from the starting point to the ending point that satisfies the orientation condition relative to the vehicle's ending point, uses this position point as a dividing point, divides the path, and designates the preceding path segment as the first path segment and the following path segment as the second path segment.

[0062] The above process uses the division into one second path segment as an example. In another possible implementation, for the second path segment, the electronic device further divides it into multiple second path segments. For example, the electronic device divides the second path segment evenly to obtain multiple second path segments. Of course, the electronic device can also use other methods to divide the second path segment, and this disclosure does not limit this approach.

[0063] In one possible implementation, the electronic device performs spatial sampling along the path from the starting point to the ending point, obtaining multiple sampling points included in the path. Then, among these multiple sampling points, it determines either a location point at a preset distance from the starting point or a location point that satisfies an orientation condition with respect to the vehicle's ending point. Thus, by selecting a location point that meets the positional conditions from multiple sampling points obtained through spatial sampling, path division can be achieved more quickly, improving the efficiency of path division.

[0064] Regarding the above spatial sampling process, in one possible implementation, the electronic device samples along the lane direction to obtain multiple sampling points along the lane direction. Then, it samples along the vertical lines of the lane where these multiple sampling points are located to obtain multiple sampling points included in the path.

[0065] Based on the location conditions required for the first path segment, the electronic device selects a sampling point at a preset distance from the starting point from among the multiple sampling points included in the path, and determines the path segment between the starting point and the sampling point as the first path segment, and the path segment between the sampling point and the ending point as the second path segment. Alternatively, in another possible implementation, the electronic device determines a sampling point from among the multiple sampling points included in the path that satisfies the orientation condition with respect to the vehicle's ending point, determines the path segment between the starting point and the sampling point as the first path segment, and the path segment between the sampling point and the ending point as the second path segment.

[0066] For example, Figure 4 This is a schematic diagram illustrating a path division according to an embodiment of this disclosure. See also... Figure 4 ,exist Figure 4 The illustrated path includes multiple sampling points along the lane direction and the perpendicular direction of the lane. The sampling points shown within the solid box 401 are those included in the first path segment, and the sampling points shown within the dashed box 402 are those included in the second path segment. In this embodiment, quadratic programming is used for path planning in the first path segment, and curve fitting is used for path planning in the second path segment. The following description of the path planning process will use the example of the first and second path segments each including multiple sampling points to illustrate the process.

[0067] In step S302, the electronic device performs secondary planning processing on the first path segment to obtain the first planned path.

[0068] Quadratic Programming (QP) is used to solve a mathematical optimization problem, specifically a quadratic optimization problem based on linear constraints. This means optimizing (minimizing or maximizing) a quadratic function of multiple variables while adhering to the linear constraints of those variables. The first planning path refers to the path obtained by planning the first path segment. In one possible implementation, there is at least one first planning path.

[0069] In one possible implementation, the electronic device obtains the feasible domain range of the vehicle, and performs secondary planning processing on the first path segment based on the feasible domain range to obtain the first planned path.

[0070] The feasible region is used to indicate the road area within which the vehicle is permitted to travel. In one possible implementation, the feasible region is represented by a lane reference line corresponding to the feasible region and the lateral distances between multiple points within the feasible region and the lane reference line. The lateral distance is also the normal distance of the sampling points on the lane reference line. For example, the lane reference line can be a lane centerline or a lane boundary line.

[0071] In the above embodiments, when performing secondary planning processing for the first path segment, the feasible domain range of the vehicle is taken into account. In this way, a path that conforms to the vehicle's own state can be planned, thus improving the accuracy of path planning.

[0072] In one possible implementation, the process by which the electronic device obtains the feasible domain of the vehicle includes: determining the feasible domain of the vehicle based on at least one of the boundary range of the road where the vehicle is located, the spatial range of dynamic obstacles around the vehicle, the spatial range of static obstacles around the vehicle, and the circular arc constraint boundary value.

[0073] Dynamic obstacles can be moving vehicles, bicycles, or pedestrians. Static obstacles can be parked vehicles, bicycles, or roadside equipment. In one possible implementation, dynamic or static obstacles around the vehicle are determined based on its current location and an electronic map. The electronic map can be map data of the area where the vehicle is currently located, such as map data of the lane the vehicle is in. It should be understood that querying the electronic map based on the vehicle's location information can obtain obstacle information within a certain range of the vehicle's location.

[0074] The spatial extent of dynamic / static obstacles is used to indicate the activity space of the dynamic / static obstacles. In this embodiment of the disclosure, the spatial extent of the dynamic / static obstacles is determined based on the vehicle's decision information and distance information relative to the dynamic / static obstacles. The decision information refers to the type of decision the vehicle makes relative to the dynamic / static obstacles, such as detouring to the left, detouring to the right, or not detouring. The distance information refers to the distance between the vehicle and the dynamic / static obstacles. Accordingly, in one possible implementation, the electronic device determines the spatial extent of the dynamic obstacle based on the vehicle's decision information and distance information relative to the dynamic obstacle. In another possible implementation, the electronic device determines the spatial extent of the static obstacle based on the vehicle's decision information and distance information relative to the static obstacle.

[0075] For example, Figure 5 This is a schematic diagram illustrating the spatial extent of an obstacle according to an embodiment of this disclosure. See also... Figure 5 , Figure 5 Taking an obstacle vehicle as an example, solid lines are used to represent lane lines, and trapezoidal dashed lines are used to represent the spatial range of the obstacle. Taking obstacle vehicle 501 as an example, the spatial range of the obstacle vehicle is the area above the trapezoidal dashed line 502. Accordingly, if obstacle vehicle 501 is an obstacle around the vehicle (current vehicle), and the vehicle's decision relative to obstacle vehicle 501 is to detour to the right, and the distance between the vehicle and obstacle vehicle 501 reaches the allowable detour distance, then the feasible domain of the vehicle is the area between the trapezoidal dashed line 502 and the lower boundary line of the lane.

[0076] The circular arc constraint boundary value is used to constrain the curvature of the vehicle's travel path. In one possible implementation, the circular arc constraint boundary value is determined based on the path curvature.

[0077] It should be noted that the electronic device can determine the feasible domain of the vehicle based on one, two, or more of the following: the boundary range of the road where the vehicle is located, the spatial range of dynamic obstacles surrounding the vehicle, the spatial range of static obstacles surrounding the vehicle, and the circular arc constraint boundary value. For example, in one possible implementation, the electronic device determines the feasible domain of the vehicle based on the boundary range of the road where the vehicle is located, the spatial range of dynamic obstacles surrounding the vehicle, and the spatial range of static obstacles surrounding the vehicle; or, in another possible implementation, the electronic device can determine the feasible domain of the vehicle based on the boundary range of the road where the vehicle is located and the circular arc constraint boundary value; or, in yet another possible implementation, the electronic device determines the feasible domain of the vehicle based on the boundary range of the road where the vehicle is located, the spatial range of dynamic obstacles surrounding the vehicle, the spatial range of static obstacles surrounding the vehicle, and the circular arc constraint boundary value. These three implementations are presented as examples of combinations to illustrate the process of determining the feasible domain of the vehicle. Of course, electronic devices can also employ other combinations to determine the feasible domain of the vehicle, and this disclosure does not limit this.

[0078] In the above embodiments, when determining the feasible domain of the vehicle, rich reference information such as the boundary range of the road, the spatial range of obstacles, or the circular arc constraint boundary value is set, which increases the amount of information referenced in the feasible domain range, improves the accuracy of determining the feasible domain range, and by setting the circular arc constraint boundary value, the driver's driving experience can be ensured and the reliability of path planning can be improved.

[0079] In one possible implementation, the process of the electronic device performing secondary planning based on the feasible region includes: constructing an objective function for secondary planning using the path curve formed by multiple sampling points included in the first path segment, the first derivative of the path curve, the second derivative of the path curve, and the smoothness of the third derivative of the path curve as the desired objective; solving the objective function based on the feasible region to obtain the lateral position, lateral velocity, and lateral acceleration of the multiple sampling points; and generating the first planned path based on the lateral position, lateral velocity, and lateral acceleration of the multiple sampling points. The lateral position is represented by the lateral distance between the sampling points.

[0080] In one possible implementation, the electronic device constructs an SL coordinate system and projects the position coordinates of multiple sampling points included in the first path segment from the XY coordinate system to the SL coordinate system, that is, using variables s and l to describe the position of the sampling points. For example, the SL coordinate system uses the direction of the road centerline as the S-axis and the direction perpendicular to the road centerline as the L-axis. Then, based on the SL coordinate system, a quadratic programming objective function is constructed to solve for the lateral position, lateral velocity, and lateral acceleration of the multiple sampling points. Based on the lateral position, lateral velocity, and lateral acceleration of the multiple sampling points, one or more first-planned paths can be determined.

[0081] In one possible implementation, the objective function of the quadratic programming is shown in the following function (1):

[0082]

[0083]

[0084]

[0085] l i+1 "=l i "+l"′ i→i+1 ×Δs (1)

[0086] Where f represents the objective function, the objective of which is to smooth the path curve formed by multiple sampling points, its first derivative, its second derivative, and its third derivative; i represents the sampling points, the number of which is n-1, where i is a positive integer greater than or equal to 0, and n is a positive integer greater than 1; w i Represents the state variable l i Weighting coefficients; state variable l i w represents the lateral position of sampling point i (which can be understood as the lateral distance); i ′ represents the state variable l i The weighting coefficients of ′; state variable l i ′ represents the derivative of the lateral position of sampling point i, which also represents the lateral velocity; w i "" represents the state variable l i The weighting coefficient of ""; state variable l i "" represents the second derivative of the lateral position of sampling point i, which also represents the lateral acceleration; w i "′ represents the state variable l i The weighting coefficients of "″′; state variable l i "″′ represents the third derivative of the horizontal position of sampling point i, which is a constant; l i+1 Indicates the horizontal position of sampling point i+1; li+1 ′ represents the derivative of the lateral position of sampling point i+1, which also represents the lateral velocity; l i+1 "" represents the second derivative of the lateral position of sampling point i+1, which also represents the lateral acceleration; Δs represents the longitudinal distance between sampling point i and sampling point i+1.

[0087] In one possible implementation, the first constraint condition of the objective function is determined based on the feasible region of the vehicle, and then the objective function is solved based on the first constraint condition. The first constraint condition is used to constrain the feasible region of the vehicle. In one possible implementation, the first constraint condition of the objective function is described in constraint condition (2) below, where the state variable l i The constraint (2) indicates the lateral position and shows the range of the lateral position, which represents the feasible region of the vehicle. Accordingly, the constraint (2) also shows the range of the first derivative, second derivative, and third derivative of the lateral position based on the range of the lateral position, so that a secondary planning process can be performed subsequently based on the range of the lateral position, the first derivative, the second derivative, and the third derivative of the lateral position.

[0088]

[0089]

[0090]

[0091]

[0092] In one possible implementation, the electronic device further determines a second constraint condition for the objective function based on the vehicle's endpoint position and at least one of the vehicle's lateral velocity and lateral acceleration at that endpoint position, and then solves the objective function based on the constraint condition. The second constraint condition is used to constrain the vehicle's endpoint alignment. In one possible implementation, the second constraint condition for the objective function is described in constraint condition (3) below, where (l t ,l t ′,l t ") indicates the endpoint sampling point, l t l represents the lateral position of the vehicle at time t. t ′ represents the lateral velocity of the vehicle at time t, l t "" represents the lateral acceleration of the vehicle at time t, l n Indicates the lateral position (lateral distance) corresponding to the endpoint position, l n′ represents the lateral velocity corresponding to the endpoint position. Thus, by setting constraints to ensure that the lateral position corresponding to the endpoint position is the same as the lateral position of the endpoint sampling point, and consequently ensures that the lateral velocity corresponding to the endpoint position is the same as the lateral velocity of the endpoint sampling point, thereby ensuring that the vehicle's path planning meets the expectation of the vehicle reaching the endpoint position.

[0093] (l t ,l′ t ,l″ t ),l n =l t ,l′ n =l′ t (3)

[0094] In the above embodiments, the path curve formed by multiple sampling points, the smoothness of the first derivative, the second derivative, and the third derivative of the path curve are taken as the desired objective. A quadratic programming objective function is constructed. By solving the objective function, the relevant information of multiple sampling points that satisfy the above desired objective can be output. That is, one or more planned paths that satisfy the above desired objective can be determined, thus improving the accuracy of path planning.

[0095] In step S303, the electronic device performs curve fitting on the second path segment to obtain the second planned path.

[0096] Curve fitting refers to curve fitting of a path based on a pre-defined template curve. In one possible implementation, the template curve is a polynomial spiral. The second planned path refers to the path obtained by planning the second path segment. In one possible implementation, there is at least one second planned path.

[0097] In one possible implementation, the electronic device performs curve fitting on the second path segment based on a pre-set template curve, the starting position of the second path segment, and the ending position of the second path segment to obtain the second planned path. The corresponding process is as follows: based on the pre-set template curve, the starting position of the second path segment, the ending position of the second path segment, and the vehicle's speed and acceleration at the ending position are substituted to obtain the correlation coefficient of the template curve, and then the second planned path is determined based on the correlation coefficient of the template curve.

[0098] In steps S302 to S303, for the initial segment of the path that requires focus in path planning, a more flexible and accurate secondary planning method is used for path planning. This results in a more flexible path that better adapts to the scenario requirements of vehicle lateral, longitudinal, and height coordination. For the subsequent segment of the path planning, since it is only used as reference information for subsequent path evaluation, a more efficient curve fitting method is used to improve the planning efficiency of the subsequent segment, thereby improving the overall path planning efficiency. It should be noted that the above embodiment uses the example of executing step S302 first and then step S303 to illustrate the solution. In another possible implementation, the electronic device executes step S303 first and then step S302, or the electronic device executes steps S302 and S303 simultaneously. This disclosure embodiment does not limit the execution order of steps S302 and S303.

[0099] In step S304, the electronic device acquires at least one speed sample of the vehicle.

[0100] In this system, each speed sample corresponds to a speed value. In one possible implementation, the electronic device obtains the at least one speed sample through time sampling. Alternatively, in another possible implementation, the electronic device obtains the at least one speed sample from a database associated with a server, wherein the server maintains at least one pre-defined speed sample.

[0101] Furthermore, in one possible implementation, after obtaining the at least one speed sample, the electronic device removes speed samples that do not meet the speed requirements, and performs subsequent steps based on the removed speed samples. The path requirements are pre-defined and used to filter path samples that meet the vehicle planning needs. For example, speed samples with speed values ​​exceeding a speed threshold are removed. This embodiment of the disclosure does not limit the setting of the speed requirements. Thus, by removing speed samples that do not meet the speed requirements, the number of speed samples is reduced, the computational load on those speed samples is decreased, and the efficiency of path planning is improved.

[0102] In step S305, the electronic device combines the first planned path and the second planned path to obtain at least one path sample for the vehicle.

[0103] In one possible implementation, the electronic device combines the first planned path and the second planned path, where the endpoint sampling point and the starting sampling point are in the same or similar positions, based on the endpoint sampling point in the first planned path and the starting sampling point in the second planned path, to obtain at least one path sample for the vehicle.

[0104] Furthermore, in one possible implementation, after obtaining the at least one path sample, the electronic device removes path samples that do not meet the path requirements, and performs subsequent steps based on the removed path samples. The path requirements are pre-defined and used to filter path samples that meet the vehicle's planning needs. For example, path samples irrelevant to the vehicle's future path or path samples containing obstacles are removed. This disclosure does not limit the setting of the path requirements. Thus, by removing path samples that do not meet the path requirements, the number of path samples is reduced, the computational load on those path samples is decreased, and the efficiency of path planning is improved.

[0105] In step S306, the electronic device generates multiple candidate paths based on the at least one path sample and the at least one speed sample, wherein different candidate paths correspond to different speed samples.

[0106] In one possible implementation, the electronic device combines the at least one path sample with the at least one speed sample to obtain the plurality of candidate paths. For example, taking the number of the at least one path sample as m and the number of the at least one speed sample as n, where m and n are positive integers greater than 0, by combining the m path samples with the n speed samples, m*n candidate paths can be obtained.

[0107] In this embodiment, after obtaining at least one path sample, by setting different speeds at the sampling points included in the path sample, speed trajectories with different speeds can be generated, that is, multiple candidate paths can be generated. In this way, the effect of combining time sampling and spatial sampling can be achieved, thereby improving the accuracy of path planning.

[0108] Furthermore, in one possible implementation, the electronic device eliminates candidate paths from the multiple candidate paths that do not meet the path planning requirements, and then executes the subsequent step S307 based on the eliminated candidate paths. The path planning requirements are pre-set requirements used to filter path samples that meet the vehicle's planning needs. For example, eliminating candidate paths irrelevant to the vehicle's future path or candidate paths containing obstacles, etc. This embodiment of the disclosure does not limit the setting of the path planning requirements. Thus, by eliminating candidate paths that do not meet the path planning requirements, the number of candidate paths is reduced, the subsequent computational load on these candidate paths is reduced, and the efficiency of path planning is improved.

[0109] In steps S304 to S306 above, the electronic device generates multiple candidate paths based on at least one path sample composed of the first planned path and the second planned path, as well as at least one speed sample. In this way, not only spatial dimension information is considered, but also temporal dimension information is considered, realizing the combination of temporal sampling and spatial sampling, that is, realizing the horizontal and vertical coupling of path planning, improving the accuracy of path planning and improving the effect of path planning.

[0110] In step S307, the electronic device selects the target planned path from the multiple candidate paths to control the vehicle to travel along the target planned path from the starting position to the ending position.

[0111] The target planned path refers to the path planned for the vehicle.

[0112] In one possible implementation, the electronic device determines the path cost information of each of the multiple candidate paths, and selects the candidate path with the minimum path cost information as the target planning path. Thus, by utilizing the path cost information of the multiple candidate paths, the path costs corresponding to each candidate path can be evaluated, and the candidate path with the minimum path cost can be selected, thereby obtaining the optimal candidate path and improving the accuracy of path planning.

[0113] In one specific embodiment, Figure 6 This is a schematic flowchart illustrating a path planning method according to an embodiment of this disclosure. See also... Figure 6 The path planning process includes: First, acquiring at least one path sample for the vehicle through spatial sampling, and performing path pre-pruning on the acquired path sample to remove path samples that do not meet the path requirements. Simultaneously, acquiring at least one speed sample for the vehicle through temporal sampling, and performing speed pre-pruning on the acquired speed sample to remove speed samples that do not meet the speed requirements. Next, performing spatiotemporal sampling based on the at least one path sample and the at least one speed sample, that is, combining the at least one path sample and the at least one speed sample, to obtain multiple candidate paths for the vehicle, and pruning these multiple candidate paths to remove candidate paths that do not meet the path planning requirements. Then, by calculating the path cost information of these multiple candidate paths, selecting the candidate path with the minimum path cost information, and using the selected candidate path as the optimal smooth trajectory, that is, obtaining the target planned path for the vehicle.

[0114] This disclosure provides a path planning scheme that couples time and spatial sampling. It considers both spatial and temporal dimensions, combining them to achieve horizontal and vertical coupling, thus improving accuracy and effectiveness. In contrast, path planning technologies typically employ separate horizontal and vertical planning, such as first planning the vehicle's path without considering time, and then performing vertical planning based on this path to obtain a series of trajectory points containing speed and time, forming a complete trajectory. However, this separate planning mechanism leads to poor coordination between the two dimensions, making it unsuitable for scenarios requiring high coordination.

[0115] This disclosure provides a path planning scheme that combines quadratic programming and curve fitting. Compared to related technologies that directly sample curves based on template curves, the technical solution provided in this disclosure improves the accuracy of path planning while ensuring its efficiency. For example, Figure 7 This is a schematic diagram comparing quadratic programming and template curves according to an embodiment of this disclosure. See also... Figure 7 ,exist Figure 7 In the road diagram shown, solid line 701 represents the planned path determined by a scatter-smoothing method based on quadratic programming, while dashed line 702 represents the planned path determined by a curve fitting method based on template curves. It can be observed that the dashed line 702 is not smooth enough, which may lead to vehicle collisions due to deviations. In contrast, solid line 701 is smoother and avoids deviations caused by the limited expressive power of template curves. The planned path determined by the scatter-smoothing method based on quadratic programming is more in line with the vehicle's expectations, ensuring the safety and reliability of vehicle operation.

[0116] The technical solution provided in this disclosure adopts a more flexible and accurate secondary planning method for the first segment of the path that needs to be focused on in path planning. This method can plan a more flexible path that can better adapt to the scenario requirements of vehicle lateral, longitudinal, and height coordination. For the second segment of the path planning, a curve fitting method is used to improve the planning efficiency of the second segment, thereby improving the overall path planning efficiency.

[0117] Figure 8 This is a structural block diagram of a path planning device according to an embodiment of the present disclosure. The path planning device is used to control a vehicle moving from a starting point to a destination. The path from the starting point to the destination includes a first path segment and at least one second path segment. See also... Figure 8The device includes a processing module 801, a generation module 802, and a selection module 803. Wherein:

[0118] The processing module 801 is used to perform secondary planning processing on the first path segment to obtain the first planned path, and to perform curve fitting processing on the second path segment to obtain the second planned path.

[0119] The generation module 802 is used to generate multiple candidate paths based on the first planned path and the second planned path;

[0120] The selection module 803 is used to select a target planned path from the multiple candidate paths, so as to control the vehicle to travel along the target planned path from the starting position to the ending position.

[0121] The technical solution provided in this disclosure adopts a more flexible and accurate secondary planning method for the first segment of the path that needs to be focused on in path planning. This method can plan a more flexible path that can better adapt to the scenario requirements of vehicle lateral, longitudinal, and height coordination. For the second segment of the path planning, a curve fitting method is used to improve the planning efficiency of the second segment, thereby improving the overall path planning efficiency.

[0122] In one possible implementation, the first path segment satisfies at least one of the following conditions:

[0123] The endpoint is a point at a preset distance from the starting point.

[0124] The endpoint is a point that satisfies the orientation condition with respect to the vehicle's endpoint position. The orientation condition includes at least one of the following: the orientation is the same or the orientation angle difference is less than a preset threshold.

[0125] In one possible implementation, the processing module 801 includes:

[0126] The acquisition submodule is used to acquire the feasible domain range of the vehicle, which indicates the road range in which the vehicle is allowed to travel;

[0127] The processing submodule is used to perform secondary planning processing on the first path segment based on the feasible domain range to obtain the first planned path.

[0128] In one possible implementation, the acquisition submodule is used for:

[0129] The feasible domain of the vehicle is determined based on at least one of the following: the boundary range of the road where the vehicle is located, the spatial range of dynamic obstacles around the vehicle, the spatial range of static obstacles around the vehicle, and the circular arc constraint boundary value.

[0130] The spatial extent of the dynamic / static obstacle is determined based on the vehicle's decision information and distance information relative to the dynamic / static obstacle; the circular arc constraint boundary value is determined based on the path curvature.

[0131] In one possible implementation, the first path segment includes multiple sampling points;

[0132] This processing submodule is used for:

[0133] The objective function of quadratic programming is constructed with the smoothness of the path curve formed by the multiple sampling points, the first derivative of the path curve, the second derivative of the path curve, and the third derivative of the path curve as the desired objective.

[0134] Based on the feasible region, the objective function is solved to obtain the lateral position, lateral velocity, and lateral acceleration of the multiple sampling points;

[0135] Based on the lateral position, lateral velocity, and lateral acceleration of these multiple sampling points, the first planned path is generated.

[0136] In one possible implementation, an acquisition module is also included for acquiring at least one speed sample of the vehicle;

[0137] This generation module 802 is used for:

[0138] The first planned path and the second planned path are combined to obtain at least one path sample for the vehicle;

[0139] Based on the at least one path sample and the at least one speed sample, multiple candidate paths are generated, wherein different candidate paths correspond to different speed samples.

[0140] In one possible implementation, a deletion module is also included, which is used to delete candidate paths that do not meet the path planning requirements from the multiple candidate paths;

[0141] The selection module 803 is also used to perform the step of selecting a target planned path from the multiple candidate paths based on the reduced multiple candidate paths, so as to control the vehicle to travel along the target planned path from the starting position to the ending position.

[0142] According to embodiments of the present disclosure, the present disclosure also provides an electronic device, including at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the path planning method provided by the present disclosure.

[0143] According to embodiments of the present disclosure, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to cause the computer to execute the path planning method provided in the present disclosure.

[0144] According to embodiments of this disclosure, this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the path planning method provided in this disclosure.

[0145] According to embodiments of this disclosure, this disclosure also provides an autonomous driving vehicle, including the electronic equipment provided in this disclosure.

[0146] Figure 9 A schematic block diagram of an example electronic device 900 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0147] like Figure 9 As shown, the electronic device 900 includes a computing unit 901, which can perform various appropriate actions and processes based on a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. The RAM 903 may also store various programs and data required for the operation of the electronic device 900. The computing unit 901, ROM 902, and RAM 903 are interconnected via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0148] Multiple components in electronic device 900 are connected to I / O interface 905, including: input unit 906, such as keyboard, mouse, etc.; output unit 907, such as various types of displays, speakers, etc.; storage unit 908, such as disk, optical disk, etc.; and communication unit 909, such as network card, modem, wireless transceiver, etc. Communication unit 909 allows electronic device 900 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0149] The computing unit 901 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 901 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. The computing unit 901 performs the various methods and processes described above, such as the process of obtaining a planned path in the path planning method provided in the embodiments of this disclosure. For example, in some embodiments, the path planning method can be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as storage unit 908. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 900 via ROM 902 and / or communication unit 909. When the computer program is loaded into RAM 903 and executed by the computing unit 901, one or more steps in the path planning method described above can be performed. Alternatively, in other embodiments, the computing unit 901 may be configured to perform a path planning method by any other suitable means (e.g., by means of firmware).

[0150] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard parts (ASSPs), systems-on-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0151] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0152] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory (EPROM or flash memory), optical fibers, compact disc read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0153] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a cathode ray tube (CRT) or liquid crystal display (LCD) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0154] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0155] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, servers in distributed systems, or servers incorporating blockchain technology.

[0156] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0157] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A path planning method, applied to controlling a vehicle to travel from a starting position to an ending position in a scenario with coordinated lateral and longitudinal heights, wherein the path from the starting position to the ending position includes a first path segment and at least one second path segment; wherein, The first path segment satisfies at least one of the following conditions: the endpoint is a point at a preset distance from the starting point; The endpoint is a point that satisfies the orientation condition with respect to the endpoint position of the vehicle. The orientation condition includes at least one of the following: the orientation is the same or the orientation angle difference is less than a preset threshold. The method includes: The first path segment is subjected to a second planning process to obtain a first planned path, and the second path segment is subjected to a curve fitting process to obtain a second planned path. Based on the first planned path and the second planned path, multiple candidate paths are generated; Among the multiple candidate paths, a target planned path is selected to control the vehicle to travel along the target planned path from the starting position to the ending position.

2. The method according to claim 1, wherein, The step of performing secondary planning on the first path segment to obtain the first planned path includes: Obtain the feasible domain range of the vehicle, which is used to indicate the road range in which the vehicle is allowed to travel; Based on the feasible region, a secondary planning process is performed on the first path segment to obtain the first planned path.

3. The method according to claim 2, wherein, The process of obtaining the feasible domain range of the vehicle includes: The feasible domain of the vehicle is determined based on at least one of the following: the boundary range of the road where the vehicle is located, the spatial range of dynamic obstacles around the vehicle, the spatial range of static obstacles around the vehicle, and the circular arc constraint boundary value. The spatial range of the dynamic / static obstacles is determined based on the vehicle's decision information and distance information relative to the dynamic / static obstacles; the circular arc constraint boundary value is determined based on the path curvature.

4. The method according to claim 2, wherein, The first path segment includes multiple sampling points; The step of performing secondary planning on the first path segment based on the feasible region to obtain the first planned path includes: The objective function of quadratic programming is constructed with the smoothness of the path curve formed by the multiple sampling points, the first derivative of the path curve, the second derivative of the path curve, and the third derivative of the path curve as the desired objective. Based on the feasible region, the objective function is solved to obtain the lateral position, lateral velocity, and lateral acceleration of the multiple sampling points; The first planned path is generated based on the lateral position, lateral velocity, and lateral acceleration of the multiple sampling points.

5. The method according to claim 1, further comprising: Obtain at least one speed sample of the vehicle; The process of generating multiple candidate paths based on the first planned path and the second planned path includes: The first planned path and the second planned path are combined to obtain at least one path sample for the vehicle; Based on the at least one path sample and the at least one speed sample, the plurality of candidate paths are generated, wherein different candidate paths correspond to different speed samples.

6. The method according to claim 1, further comprising: Among the multiple candidate paths, candidate paths that do not meet the path planning requirements are eliminated; Based on the reduced number of candidate paths, the step of selecting a target planned path from the candidate paths to control the vehicle to travel along the target planned path from the starting position to the ending position is executed.

7. A path planning device, used to control a vehicle to travel from a starting position to an ending position in a scenario where lateral and longitudinal heights are coordinated, wherein the path from the starting position to the ending position includes a first path segment and at least one second path segment; wherein, The first path segment satisfies at least one of the following conditions: the endpoint is a point at a preset distance from the starting point; The endpoint is a point that satisfies the orientation condition with respect to the endpoint position of the vehicle. The orientation condition includes at least one of the following: the orientation is the same or the orientation angle difference is less than a preset threshold. The device includes: The processing module is used to perform secondary planning on the first path segment to obtain a first planned path, and to perform curve fitting on the second path segment to obtain a second planned path. The generation module is used to generate multiple candidate paths based on the first planned path and the second planned path; The selection module is used to select a target planned path from the multiple candidate paths, so as to control the vehicle to travel along the target planned path from the starting position to the ending position.

8. The apparatus according to claim 7, wherein, The processing module includes: The acquisition submodule is used to acquire the feasible domain range of the vehicle, which is used to indicate the road range in which the vehicle is allowed to travel; The processing submodule is used to perform secondary planning processing on the first path segment based on the feasible domain range to obtain the first planned path.

9. The apparatus according to claim 8, wherein, The acquisition submodule is used for: The feasible domain of the vehicle is determined based on at least one of the following: the boundary range of the road where the vehicle is located, the spatial range of dynamic obstacles around the vehicle, the spatial range of static obstacles around the vehicle, and the circular arc constraint boundary value. The spatial range of the dynamic / static obstacles is determined based on the vehicle's decision information and distance information relative to the dynamic / static obstacles; the circular arc constraint boundary value is determined based on the path curvature.

10. The apparatus according to claim 8, wherein, The first path segment includes multiple sampling points; The processing submodule is used for: The objective function of quadratic programming is constructed with the smoothness of the path curve formed by the multiple sampling points, the first derivative of the path curve, the second derivative of the path curve, and the third derivative of the path curve as the desired objective. Based on the feasible region, the objective function is solved to obtain the lateral position, lateral velocity, and lateral acceleration of the multiple sampling points; The first planned path is generated based on the lateral position, lateral velocity, and lateral acceleration of the multiple sampling points.

11. The apparatus of claim 7, further comprising an acquisition module for acquiring at least one speed sample of the vehicle; The generation module is used for: The first planned path and the second planned path are combined to obtain at least one path sample for the vehicle; Based on the at least one path sample and the at least one speed sample, the plurality of candidate paths are generated, wherein, Different candidate paths correspond to different speed samples.

12. The apparatus according to claim 7 further includes a deletion module, used to delete candidate paths that do not meet the path planning requirements from the plurality of candidate paths; The selection module is further configured to perform the step of selecting a target planned path from the multiple candidate paths based on the reduced candidate paths, so as to control the vehicle to travel along the target planned path from the starting position to the ending position.

13. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-6.

15. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

16. An autonomous vehicle, including the electronic equipment as claimed in claim 13.

Images