Parking path planning method and device, electronic device, and storage medium
Through the combination of mixed A* algorithm and RS curve, combined with preset algorithms and sign position planning, the problem of slow parking path planning in airports and other scenarios is solved, fast and accurate parking space is achieved, and autonomous vehicles are improved autonomous parking capability.
Patent Information
- Application Number
- CN202210778898.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-06-30
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2042-06-30
AI Technical Summary
In airports and other scenarios, the parking path planning response time is slow, the user experience is poor, and autonomous vehicles lack the ability to park autonomously.
The first path is planned using a hybrid A* algorithm, matches the connected RS curve to generate a second path, and smoothes it through the preset algorithm to generate a third path, and combines the flag position to plan the vehicle speed to ensure the safety, accuracy and speed of the parking path.
It significantly accelerates the response time of parking path planning, achieves safe, accurate and fast parking, and is suitable for autonomous vehicles in special scenarios such as airports.
Smart Images

Figure CN115014380B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of autonomous driving technology, and in particular to a parking path planning method and device, electronic equipment, and storage medium. Background Art
[0002] Path planning is one of the basic links of intelligent vehicle navigation. For parking path planning, it means that when the vehicle detects the target parking space, it needs to plan the path according to the vehicle's starting point and parking end point. If the vehicle's starting point is not within the feasible starting area, the path between the two points cannot be planned directly, and the path needs to be segmented. Overall, the path is mainly composed of two parts: the first segment of the path is the path of the vehicle from the starting point to the feasible starting area; the second segment of the path is the path of the vehicle from the feasible starting area to the parking end point.
[0003] In scenarios such as airports, airport tractors still lack the ability to park autonomously. At the same time, the overall response time of parking path planning is slow, resulting in poor user experience. Summary of the invention
[0004] The embodiments of the present application provide a parking path planning method and device, an electronic device, and a storage medium to generate a parking path while accelerating the response time of the program, so that the vehicle can be parked in a parking space safely, accurately, and quickly.
[0005] The present application embodiment adopts the following technical solutions:
[0006] In a first aspect, an embodiment of the present application provides a parking path planning method, wherein the method includes: using a hybrid A* algorithm to plan a first path; matching a first RS curve that can be connected to the first path to generate a second path; using a preset algorithm to smooth the second path to generate a third path; according to the third path, obtaining a flag position near a preset splicing point position, the preset splicing point includes the connection point position of the hybrid A* algorithm and the RS curve, and the flag position is used to plan the current speed of the vehicle; parking according to the third path as the parking path.
[0007] In a second aspect, an embodiment of the present application further provides a parking path planning device, wherein the device includes: a first planning module, used to plan a first path using a hybrid A* algorithm; a determination module, used to match a first RS curve that can be connected to the first path to generate a second path; a second planning module, used to generate a third path after smoothing the second path using a preset algorithm; a speed planning module, used to obtain a flag position near a preset splicing point position according to the third path, the preset splicing point includes the connection point position of the hybrid A* algorithm and the RS curve, and the flag position is used to plan the current speed of the vehicle; a parking module, used to park according to the third path as the parking path.
[0008] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor; and a memory arranged to store computer executable instructions, wherein the executable instructions, when executed, cause the processor to perform the above method.
[0009] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes the above method.
[0010] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:
[0011] A hybrid A* algorithm is used to plan a first path, and then a second path that meets the connection conditions of the first RS curve is determined based on the first path. Finally, a preset algorithm is used to smooth the second path to generate a third path. After the third path is obtained, the speed limit will be set near the splicing point, and finally the third path will be used as the parking path according to the current speed. BRIEF DESCRIPTION OF THE DRAWINGS
[0012] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:
[0013] Figure 1 A schematic diagram of a parking path planning method according to an embodiment of the present application;
[0014] Figure 2 This is a schematic diagram of the structure of a parking path planning device in an embodiment of the present application;
[0015] Figure 3 A schematic diagram of the implementation principle of the parking path planning method in the embodiment of the present application;
[0016] Figure 4This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION
[0017] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.
[0018] The technical terms used in this application are as follows:
[0019] RS curve, the full name of RS curve is Reeds-Shepp curve, it is an optimal route that can meet the kinematic constraints of the vehicle. Its base line is composed of a straight line, several forward and backward arcs, and the spliced curve can be used by autonomous driving vehicles.
[0020] Gradient Descent, gradient descent algorithm.
[0021] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.
[0022] The present application embodiment provides a parking path planning method, such as Figure 1 As shown, a flow chart of a parking path planning method in an embodiment of the present application is provided, and the method at least includes the following steps S110 to S150:
[0023] Step S110: Plan a first path using a hybrid A* algorithm.
[0024] First, the hybrid A* algorithm is used to plan the first path. This application takes into account that it is usually impossible to plan a path in just one pass and the path can be tracked by the autonomous driving vehicle. Therefore, if the vehicle uses the RS curve from the starting point, if a path to the target point can be directly generated, and it does not collide with surrounding obstacles and meets the path and garage boundary condition constraints, it can be tracked by the autonomous driving vehicle. Otherwise, it cannot. This application is based on the situation where a path to the target point cannot be directly generated.
[0025] It can be understood that the hybrid A* algorithm is mainly based on the principle of minimizing the total cost, and its formula is expressed as follows:
[0026] f(n)=g(n)+h(n)
[0027] Where f(n) represents the evaluation function from the starting point of the path to the target point, g(n) represents the actual cost of the unmanned vehicle from the starting point of the path to node n, and h(n) represents the estimated cost of the optimal path from node n to the target point.
[0028] In the embodiment of the present application, h(n) is the Euclidean distance.
[0029] Right now x end Indicates the x-coordinate and y-coordinate of the target point end Indicates the y coordinate of the target point.
[0030] In some embodiments, when the hybrid A* algorithm is used to expand nodes, the vehicle kinematic model is mainly considered, so that the vehicle orientation and position problems in the continuous space can be guaranteed. Preferably, by combining the minimum turning radius of the vehicle and the extreme turning angle of the vehicle, the dimension of the algorithm expansion node is defined as 3, that is, expanding from the midpoint of the rear axle of the vehicle at a certain step length, such as 0.5 meters, and the expansion direction is 3, namely forward, left and right, and the search distance in each direction is 3 meters.
[0031] In some embodiments, the first frame of the hybrid A* algorithm will search based on the starting point. When the first frame search is completed, three extended paths will be generated; the second frame search will continue to expand with the end point of the previous frame search path as the starting point; and so on, the hybrid A* algorithm will generate a series of extended lines until a path from the starting point to the target point is searched. During the operation of the hybrid A* algorithm, the algorithm will consider the path cost brought by the evaluation function, discard the path with high estimated cost, and reduce the algorithm's search space.
[0032] Step S120: matching a first RS curve that can be connected to the first path to generate a second path.
[0033] According to the first path, a second path that meets the first RS curve connection condition can be determined. That is, the hybrid A* algorithm is used to search at the current point, and each search step is repeated to determine whether the first RS curve connection condition is met. If no suitable RS connection curve is found, the process continues, and if a suitable first RS connection curve is found, the loop is exited.
[0034] As you can understand, the full name of RS curve is Reeds-Shepp curve, which is an optimal route that can meet the kinematic constraints of the vehicle. Its base line is composed of a straight line, several forward and backward arcs, and there are 48 combinations (or 9 base characters) in total. The radius of the arc here cannot be less than the minimum turning radius of the vehicle, otherwise the vehicle will not be able to drive along the path planned by the curve.
[0035] The following S represents the straight line, C represents the curve turning left or right, u Indicates that there are two curves with the same length, Cπ / 2 indicates that the angle of the curve is 90°, and | indicates gear switching (from forward driving to reverse driving or from reverse driving to forward driving). The specific 9 base characters are as follows: C|C|C, CC|C, CSC, CC u |C u C, C|C u C u |C, C|Cπ / 2SC, C|Cπ / 2SCπ / 2|C, C|CC, CSCπ / 2|S. It does not specifically involve the invention of this application and will not be described in detail.
[0036] Step S130: After smoothing the second path using a preset algorithm, a third path is generated.
[0037] As an optimization step of the above steps, a preset algorithm may be used to smooth the second path and generate a third path. The smoothed third path is the target path.
[0038] Preferably, after smoothing the second path by a preset algorithm, generating the third path includes: using a preset algorithm to add parking space boundary constraints and / or constructing an obstacle model around the parking space to generate the third path. In order to obtain the target path, the second path may be smoothed by a preset algorithm, including a smoothing method of adding parking space boundary constraints to obtain the third path. The second path may also be smoothed by a preset algorithm, including constructing an obstacle model around the parking space to obtain the third path.
[0039] It should be noted that those skilled in the art may choose to add constraint conditions or surrounding obstacle models according to actual conditions. In addition, parking space boundary constraint conditions and / or building a parking space surrounding obstacle model are well known to those skilled in the art and can be obtained according to methods in related technologies.
[0040] Step S140, according to the third path, obtaining a flag position near a preset splicing point position, wherein the preset splicing point includes a connection point position of the hybrid A* algorithm and the RS curve, and the flag position is used to plan the current speed of the vehicle.
[0041] By setting a flag at the junction of the hybrid A* algorithm and the RS curve, the speed planning module of the tractor can make corresponding speed planning when reading the flag. That is to say, when the hybrid A* algorithm and the RS curve are near the junction, the relevant flag (speed limit sign) is set, and when the vehicle drives near this point, it stops (the chassis speed is 0) for a period of time to ensure that the vehicle can smoothly drive along the planned route without jumping.
[0042] Setting a flag at the junction of the hybrid A* algorithm and the RS curve can ensure that the vehicle transitions between the two points safely and effectively.
[0043] Step S150: Parking the vehicle using the third path as the parking path.
[0044] The control module performs parking according to the third path as the parking path.
[0045] Taking into account special scenarios such as airports, the above method can be applied to airport tractors to enable them to park automatically.
[0046] In one embodiment of the present application, the preset algorithm is Gradient Descent, which is used to smoothly blend the path generated by A*.
[0047] Gradient Descent refers to the gradient descent algorithm. In this application, the Gradient Descent algorithm is used to smooth the path generated by the hybrid A* algorithm. Because the principle of the hybrid A* algorithm to generate a path is to search forward from different nodes, there will be uneven trajectory points at the joint points of the path, and the trajectory followed by the autonomous driving vehicle needs to be absolutely smooth, so it is particularly important to find a suitable path smoothing algorithm.
[0048] Gradient Descent mainly includes four items, namely obstacleTerm (obstacle term, used to constrain the path to stay away from obstacles), curvatureTerm (curvature term, used to ensure turnability and passability), smoothnessTerm (smoothness term, used to distribute nodes equidistantly and try to keep the same direction), voronoiTerm (Voronoi term, used to constrain the autonomous driving vehicle to drive along the map boundary and the center of obstacles), and endpointTerm (end point term, used to constrain the heading of the path end point to maintain the original direction).
[0049] In one embodiment of the present application, after smoothing the second path using a preset algorithm, generating a third path includes: smoothing the second path using any one or more of an obstacle term, a curvature term, a smoothness term, a Venoi term, and an end point term in the preset algorithm to generate the smoothed third path. The principle of the hybrid A* algorithm to generate a path is that different nodes search forward, so there will be uneven trajectory points at the joint points of the path, and the trajectory followed by the autonomous driving vehicle needs to be absolutely smooth, so a suitable path smoothing optimization algorithm is found.
[0050] In one embodiment of the present application, according to the third path, a flag bit near a preset splicing point position is obtained, the preset splicing point includes a connection point position of the hybrid A* algorithm and the RS curve, and the flag bit is used to plan the current speed of the vehicle, including: when passing near the flag bit of the connection point position of the hybrid A* algorithm and the RS curve, the current speed planned by the speed planning module of the vehicle is zero.
[0051] In a specific implementation, when the mark position of the connection point calculated by the hybrid A* algorithm and the RS curve is near, the current speed planned by the vehicle's speed planning module is zero, ensuring that the vehicle safely and effectively transitions between the two points.
[0052] In one embodiment of the present application, before the hybrid A* algorithm is used to plan the first path, it also includes: if the second RS curve of the vehicle from the starting point to the target point meets the connection condition, using the second RS curve as the parking path for parking.
[0053] In specific implementation, before calculating the hybrid A* algorithm to plan the first path, if the second RS curve of the vehicle from the starting point to the target point meets the connection condition, the second RS curve is used as the parking path for parking, that is, the vehicle uses the RS curve from the starting point. If a path to the target point can be directly generated, and it does not collide with surrounding obstacles and meets the path and garage boundary condition constraints, then the path is used for tracking by the autonomous driving vehicle.
[0054] Furthermore, if the second RS curve based on the starting point to the target point of the vehicle does not meet the connection conditions, the hybrid A* algorithm is used to search at the current point according to the preset step size, that is, the hybrid A* algorithm is used to search at the current point, and each search step is used to determine whether the RS curve meets the path requirements from the starting point to the target point. If no suitable RS connection curve is found, the calculation is repeated; if a suitable RS connection curve is found, the calculation is no longer performed.
[0055] In one embodiment of the present application, using the third path as a parking path for parking includes: sending the third path to a control module of the vehicle as a parking path for a vertical parking space, a side parking space, or an inclined parking space for parking.
[0056] In specific implementation, according to the parking path planning results, the parking path can be used as a vertical parking space, a side parking space, or an inclined parking space for parking. In this application, the selection can be made according to the actual situation.
[0057] like Figure 3 As shown, the implementation principle of the parking path planning method in the embodiment of the present application is as follows:
[0058] (1) Perform RS curve search at the starting point. If the vehicle can directly generate a path to the target point using the RS curve from the starting point without colliding with surrounding obstacles and satisfying the path and garage boundary constraints, the path is directly used for tracking by the autonomous vehicle.
[0059] (2) If it fails, use the hybrid A* algorithm to search at the current point. Repeat step (1) for each search step. If no suitable RS connection curve is found, continue to repeat step (1). If a suitable RS connection curve is found, exit the loop.
[0060] (3) Use Gradient Descent to smooth the path generated in step (2).
[0061] (4) A flag is set at the splicing point of the hybrid A* algorithm and the RS curve (i.e., the splicing point flag). When the speed planning module reads the flag, it can make corresponding speed planning.
[0062] (5) The processed path is sent to the control module and the vehicle is parked.
[0063] The present application also provides a device 200 for identifying a tractor and a trailer. Figure 2 As shown, a schematic diagram of the structure of the identification device of the tractor and the trailer in the embodiment of the present application is provided, and the device 200 at least includes: a first planning module 210, a determination module 220, a second planning module 230, a speed planning module 240 and a parking module 250, wherein:
[0064] In one embodiment of the present application, the first planning module 210 is specifically used to plan a first path using a hybrid A* algorithm.
[0065] First, the hybrid A* algorithm is used to plan the first path. The present application takes into account that it is usually impossible to plan a path in just one pass and the path can be tracked by the autonomous driving vehicle. Therefore, if the vehicle uses the RS curve from the starting point, if a path to the target point can be directly generated, and it does not collide with surrounding obstacles and meets the path and garage boundary condition constraints, it can be tracked by the autonomous driving vehicle. Otherwise, it cannot. The present application is based on the situation that a path to the target point cannot be directly generated.
[0066] It can be understood that the hybrid A* algorithm is mainly based on the principle of minimizing the total cost, and its formula is expressed as follows:
[0067] f(n)=g(n)+h(n)
[0068] Where f(n) represents the evaluation function from the starting point of the path to the target point, g(n) represents the actual cost of the unmanned vehicle from the starting point of the path to node n, and h(n) represents the estimated cost of the optimal path from node n to the target point.
[0069] In the embodiment of the present application, h(n) is the Euclidean distance.
[0070] Right now x end Indicates the x-coordinate and y-coordinate of the target point end Indicates the y coordinate of the target point.
[0071] In some embodiments, when the hybrid A* algorithm is used to expand nodes, the vehicle kinematic model is mainly considered, so that the vehicle orientation and position problems in the continuous space can be guaranteed. Preferably, by combining the minimum turning radius of the vehicle and the extreme turning angle of the vehicle, the dimension of the algorithm expansion node is defined as 3, that is, expanding from the midpoint of the rear axle of the vehicle at a certain step length, such as 0.5 meters, and the expansion direction is 3, namely forward, left and right, and the search distance in each direction is 3 meters.
[0072] In some embodiments, the first frame of the hybrid A* algorithm will search based on the starting point. When the first frame search is completed, three extended paths will be generated; the second frame search will continue to expand with the end point of the previous frame search path as the starting point; and so on, the hybrid A* algorithm will generate a series of extended lines until a path from the starting point to the target point is searched. During the operation of the hybrid A* algorithm, the algorithm will consider the path cost brought by the evaluation function, discard the path with high estimated cost, and reduce the algorithm's search space.
[0073] In one embodiment of the present application, the determination module 220 is specifically configured to: match a first RS curve that can be connected to the first path to generate a second path.
[0074] According to the first path, a second path that meets the first RS curve connection condition can be determined. That is, the hybrid A* algorithm is used to search at the current point, and each search step is repeated to determine whether the first RS curve connection condition is met. If no suitable RS connection curve is found, the process continues, and if a suitable first RS connection curve is found, the loop is exited.
[0075] As you can understand, the full name of RS curve is Reeds-Shepp curve, which is an optimal route that can meet the kinematic constraints of the vehicle. Its base line is composed of a straight line, several forward and backward arcs, and there are 48 combinations (or 9 base characters) in total. The radius of the arc here cannot be less than the minimum turning radius of the vehicle, otherwise the vehicle will not be able to drive along the path planned by the curve.
[0076] The following S represents the straight line, C represents the curve turning left or right, u Indicates that there are two curves with the same length, Cπ / 2 indicates that the angle of the curve is 90°, and | indicates gear switching (from forward driving to reverse driving or from reverse driving to forward driving). The specific 9 base characters are as follows: C|C|C, CC|C, CSC, CC u |C u C, C|C u C u |C, C|Cπ / 2SC, C|Cπ / 2SCπ / 2|C, C|CC, CSCπ / 2|S. It does not specifically involve the inventive point of this application and will not be described in detail.
[0077] In one embodiment of the present application, the second planning module 230 is specifically configured to: generate a third path after smoothing the second path using a preset algorithm.
[0078] As an optimization step of the above steps, a preset algorithm may be used to smooth the second path and generate a third path. The smoothed third path is the target path.
[0079] Preferably, after smoothing the second path by a preset algorithm, generating the third path includes: using a preset algorithm to add parking space boundary constraints and / or constructing an obstacle model around the parking space to generate the third path. In order to obtain the target path, the second path may be smoothed by a preset algorithm, including a smoothing method of adding parking space boundary constraints to obtain the third path. The second path may also be smoothed by a preset algorithm, including constructing an obstacle model around the parking space to obtain the third path.
[0080] It should be noted that those skilled in the art may choose to add constraint conditions or surrounding obstacle models according to actual conditions. In addition, parking space boundary constraint conditions and / or building a parking space surrounding obstacle model are well known to those skilled in the art and can be obtained according to methods in related technologies.
[0081] In one embodiment of the present application, the speed planning module 240 is specifically used to: obtain a flag position near a preset splicing point position according to the third path, the preset splicing point includes the connection point position of the hybrid A* algorithm and the RS curve, and the flag position is used to plan the current speed of the vehicle.
[0082] By setting a flag at the junction of the hybrid A* algorithm and the RS curve, the speed planning module of the tractor can make corresponding speed planning when reading the flag. That is to say, when the hybrid A* algorithm and the RS curve are near the junction, the relevant flag (speed limit sign) is set. When the vehicle drives near this point, it stops (the chassis speed is 0) for a short period of time to ensure that the vehicle can smoothly drive along the planned route without jumping.
[0083] Setting a flag at the junction of the hybrid A* algorithm and the RS curve can ensure that the vehicle transitions between the two points safely and effectively.
[0084] In one embodiment of the present application, the parking module 250 is specifically configured to: park the vehicle according to the third path as the parking path.
[0085] The control module performs parking according to the third path as the parking path.
[0086] In one embodiment of the present application, the preset algorithm is Gradient Descent, which is used to smoothly blend the path generated by A*.
[0087] Gradient Descent refers to the gradient descent algorithm. In this application, the Gradient Descent algorithm is used to smooth the path generated by the hybrid A* algorithm. Because the principle of the hybrid A* algorithm to generate a path is to search forward from different nodes, there will be uneven trajectory points at the joint points of the path, and the trajectory followed by the autonomous driving vehicle needs to be absolutely smooth, so it is particularly important to find a suitable path smoothing algorithm.
[0088] Gradient Descent mainly includes four items, namely obstacleTerm (obstacle term, used to constrain the path to stay away from obstacles), curvatureTerm (curvature term, used to ensure turnability and passability), smoothnessTerm (smoothness term, used to distribute nodes equidistantly and try to keep the same direction), voronoiTerm (Voronoi term, used to constrain the autonomous driving vehicle to drive along the map boundary and the center of obstacles), and endpointTerm (end point term, used to constrain the heading of the path end point to maintain the original direction).
[0089] It can be understood that the above-mentioned parking path planning device can implement each step of the parking path planning method provided in the above-mentioned embodiment. The relevant explanations about the parking path planning method are applicable to the parking path planning device and will not be repeated here.
[0090] Figure 4This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 4 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.
[0091] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0092] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.
[0093] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a parking path planning device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:
[0094] The first path is planned using the hybrid A* algorithm;
[0095] matching a first RS curve that can be connected to the first path to generate a second path;
[0096] After smoothing the second path using a preset algorithm, a third path is generated;
[0097] According to the third path, a flag position near a preset splicing point position is obtained, wherein the preset splicing point includes a connection point position of the hybrid A* algorithm and the RS curve, and the flag position is used to plan the current speed of the vehicle;
[0098] Parking is performed along the third route as the parking route.
[0099] The above application Figure 1 The method performed by the parking path planning device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.
[0100] The electronic device may also perform Figure 1 The method for executing the parking path planning device in the Figure 1 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.
[0101] The present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to execute Figure 1 The method executed by the parking path planning device in the illustrated embodiment is specifically used to execute:
[0102] The first path is planned using the hybrid A* algorithm;
[0103] matching a first RS curve that can be connected to the first path to generate a second path;
[0104] After smoothing the second path using a preset algorithm, a third path is generated;
[0105] According to the third path, a flag position near a preset splicing point position is obtained, wherein the preset splicing point includes a connection point position of the hybrid A* algorithm and the RS curve, and the flag position is used to plan the current speed of the vehicle;
[0106] Parking is performed along the third route as the parking route.
[0107] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0108] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0109] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0111] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0112] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0113] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0114] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0115] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0116] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims
1. A parking path planning method, wherein: The method comprises: When the second RS curve from the starting point to the target point of the vehicle meets the connection condition, the second RS curve is used as the parking path for parking, and the connection condition means that the vehicle can directly generate a path to the target point using the RS curve from the starting point, and does not collide with surrounding obstacles and meets the path and garage boundary condition constraints; when the second RS curve from the starting point to the target point of the vehicle does not meet the connection condition, the hybrid A* algorithm is used to plan the first path, The hybrid A* algorithm is based on the principle of minimizing the total cost, and its formula is as follows: f(n)=g(n)+h(n) Where f(n) represents the valuation function from the starting point of the path to the target point, g(n) represents the actual cost of the unmanned vehicle from the starting point of the path to node n, and h(n) represents the estimated cost of the best path from node n to the target point. h(n) is the Euclidean distance; x end Indicates the x-coordinate and y-coordinate of the target point end Indicates the y coordinate of the target point; By combining the minimum turning radius of the vehicle and the maximum turning angle of the vehicle, the dimensions of the hybrid A* algorithm expansion node are defined as three, namely forward, left and right; Matching a first RS curve that can be connected to the first path to generate a second path includes: Use the hybrid A* algorithm to search at the current point. Every time a step is searched, it is repeatedly determined whether the first RS curve connection condition is met. If no suitable RS connection curve is found, the search is repeated. If a suitable first RS connection curve is found, the loop is exited. After smoothing the second path using a preset algorithm, generating a third path includes: Smoothing the second path using any one or more of an obstacle term, a curvature term, a smoothness term, a Venoi term, and an end point term in a preset algorithm to generate the smoothed third path; According to the third path, a flag bit near a preset splicing point position is obtained, wherein the preset splicing point includes a connection point position of the hybrid A* algorithm and the RS curve, and the flag bit is used to plan a current speed of the vehicle. When the vehicle passes near the flag bit of the connection point position of the hybrid A* algorithm and the first RS curve, the current speed planned by the speed planning module of the vehicle is zero; Parking is performed along the third route as the parking route.
2. The method of claim 1, wherein: After smoothing the second path by using a preset algorithm, generating a third path includes: The third path is generated by using a preset algorithm, adding parking space boundary constraints and / or constructing an obstacle model around the parking space.
3. The method of claim 2, wherein: The preset algorithm uses Gradient Descent.
4. The method of claim 1, wherein: Using the third path as a parking path for parking includes: The third path is sent to the control module of the vehicle as a parking path for a perpendicular parking space, a side parking space or an inclined parking space for parking.
5. A parking path planning device, wherein: The device comprises: The first planning module is used for parking by using the second RS curve from the starting point to the target point of the vehicle when the second RS curve from the starting point to the target point meets the connection condition, wherein the connection condition refers to that the vehicle can directly generate a path to the target point using the RS curve from the starting point, and does not collide with surrounding obstacles and meets the path and garage boundary condition constraints; when the second RS curve from the starting point to the target point of the vehicle does not meet the connection condition, a hybrid A* algorithm is used to plan the first path, The hybrid A* algorithm is based on the principle of minimizing the total cost, and its formula is as follows: f(n)=g(n)+h(n) Where f(n) represents the valuation function from the starting point of the path to the target point, g(n) represents the actual cost of the unmanned vehicle from the starting point of the path to node n, and h(n) represents the estimated cost of the best path from node n to the target point. h(n) is the Euclidean distance; x end Indicates the x-coordinate and y-coordinate of the target point end Indicates the y coordinate of the target point; By combining the minimum turning radius of the vehicle and the maximum turning angle of the vehicle, the dimensions of the hybrid A* algorithm expansion node are defined as three, namely forward, left and right; A determination module, used to match a first RS curve that can be connected to the first path to generate a second path, comprising: Use the hybrid A* algorithm to search at the current point. Every time a step is searched, it is repeatedly determined whether the first RS curve connection condition is met. If no suitable RS connection curve is found, the search is repeated. If a suitable first RS connection curve is found, the loop is exited. The second planning module is used to generate a third path after smoothing the second path using a preset algorithm, including: Smoothing the second path using any one or more of an obstacle term, a curvature term, a smoothness term, a Venoi term, and an end point term in a preset algorithm to generate the smoothed third path; a speed planning module, configured to obtain a flag bit near a preset splicing point position according to the third path, wherein the preset splicing point includes a connection point position of the hybrid A* algorithm and the RS curve, and the flag bit is used to plan the current speed of the vehicle. When the vehicle passes near the flag bit of the connection point position of the hybrid A* algorithm and the first RS curve, the current speed planned by the speed planning module of the vehicle is zero; The parking module is used to park the vehicle according to the third path as a parking path.
6. An electronic device comprising: processor; as well as A memory arranged to store computer executable instructions, which when executed cause the processor to perform the method of any one of claims 1 to 4.
7. A computer-readable storage medium storing one or more programs, which, when executed by an electronic device including a plurality of application programs, causes the electronic device to execute any one of the methods of claims 1 to 4.
