Path planning method and device, vehicle and program product

Abstract

The invention relates to the technical field of vehicles, in particular to a path planning method and device, a vehicle and a program product, and the method comprises the steps: carrying out the grid processing of a target region map, obtaining a grid map, judging whether there is an obstacle in a current planning path, and if there is an obstacle in the current planning path, executing the step 1; if yes, the type of the obstacle, the area coverage of the obstacle in the gridding map and the height of the obstacle are determined, the roughness coefficient of the obstacle is calculated, a new path planning function is determined according to the type, the height and the roughness coefficient, and the current planning path is updated according to the new path planning function and the area coverage. And controlling the vehicle according to the updated planned path. Therefore, the problems that a dynamic obstacle avoidance algorithm is based on a machine learning algorithm, the requirement for computing power is large, the running speed is low, and the success rate of automatic driving function implementation is affected in the related technology are solved, the accuracy and efficiency of dynamic avoidance of the intelligent automobile are improved, and the driving experience of a user is improved.

Description

Technical Field

[0001] The present application relates to the field of vehicle technology, and in particular to a path planning method, device, vehicle and program product. Background Art

[0002] With the development of the automobile industry, smart driving cars have attracted much attention as key technologies. They can travel on unmanned roads, providing humans with a safer and more efficient way of travel. Automatic obstacle avoidance technology refers to the use of various sensors and algorithms by unmanned vehicles to perceive and analyze obstacles in the road environment in real time, and dynamically avoid them based on the predicted results.

[0003] Among the related technologies, the dynamic obstacle avoidance algorithm is based on the machine learning algorithm, which requires a lot of computing power and runs slowly, affecting the success rate of the smart car's autonomous driving function. Summary of the invention

[0004] The present application provides a path planning method, device, vehicle and program product to solve the problems in related technologies, such as the dynamic obstacle avoidance algorithm based on machine learning algorithm, which has high computing power requirements and slow running speed, affecting the success rate of automatic driving function, so as to improve the accuracy and efficiency of dynamic avoidance of smart cars and enhance the driving experience of users.

[0005] The first embodiment of the present application provides a path planning method, comprising the following steps:

[0006] Obtaining a target area map and a current planned path, gridding the target area map to obtain a gridded map, and determining whether there are obstacles in the current planned path;

[0007] If the obstacle exists in the current planned path, determining the type of the obstacle, the area coverage of the obstacle in the grid map and the height of the obstacle, and calculating the roughness coefficient of the obstacle;

[0008] A new path planning function is determined according to the type, the height and the roughness coefficient, and the current planned path is updated according to the new path planning function and the area coverage, and the vehicle is controlled according to the updated planned path.

[0009] Optionally, in some embodiments, calculating the roughness coefficient of the obstacle includes:

[0010] Determine a plurality of positioning points, and determine the highest height and the lowest height of the obstacle in the horizontal plane at each positioning point;

[0011] The difference between the highest height and the lowest height of the horizontal plane of each positioning point is calculated, and the average value of the differences of the multiple positioning points is used as the roughness coefficient.

[0012] Optionally, in some embodiments, determining a new path planning function according to the type, the height and the roughness coefficient includes:

[0013] When the type of the obstacle is an inanimate object, obtaining a first path planning function according to the height of the obstacle and the roughness coefficient, and using the first path planning function as the new path planning function;

[0014] When the type of the obstacle is a living object, a second path planning function is obtained according to the height of the obstacle, the roughness coefficient and a preset infinite cost, and the second path planning function is used as the new path planning function.

[0015] Optionally, in some embodiments, the first path planning function is:

[0016] f(n)=(|k|+1)*m*g(n)+h(n);

[0017] The second path planning function is:

[0018] f(n)=(|k|+1)*m*g(n)+h(n);

[0019] |k+1|*m=+∞;

[0020] Among them, f(n) is the first path planning function, k is the height of inanimate obstacles, m is the roughness coefficient of inanimate objects, g(n) is the actual cost function, and h(n) is the estimated cost function.

[0021] Optionally, in some embodiments, before controlling the vehicle according to the updated planned path, the method further includes:

[0022] The updated planned path is smoothed using a preset Bezier curve.

[0023] A second aspect of the present application provides a path planning device, including:

[0024] An acquisition module is used to acquire a target area map and a current planned path, grid the target area map to obtain a grid map, and determine whether there are obstacles in the current planned path;

[0025] a calculation module, for determining the type of the obstacle, the area coverage of the obstacle in the grid map and the height of the obstacle, and calculating the roughness coefficient of the obstacle when the obstacle exists in the current planned path;

[0026] A control module is used to determine a new path planning function according to the type, the height and the roughness coefficient, update the current planned path according to the new path planning function and the area coverage, and control the vehicle according to the updated planned path.

[0027] Optionally, in some embodiments, the computing module is specifically used to:

[0028] Determine a plurality of positioning points, and determine the highest height and the lowest height of the obstacle in the horizontal plane at each positioning point;

[0029] The difference between the highest height and the lowest height of the horizontal plane of each positioning point is calculated, and the average value of the differences of the multiple positioning points is used as the roughness coefficient.

[0030] Optionally, in some embodiments, the control module is specifically used to:

[0031] When the type of the obstacle is an inanimate object, obtaining a first path planning function according to the height of the obstacle and the roughness coefficient, and using the first path planning function as the new path planning function;

[0032] When the type of the obstacle is a living object, a second path planning function is obtained according to the height of the obstacle, the roughness coefficient and a preset infinite cost, and the second path planning function is used as the new path planning function.

[0033] Optionally, in some embodiments, the first path planning function is:

[0034] f(n)=(|k|+1)*m*g(n)+h(n);

[0035] The second path planning function is:

[0036] f(n)=(|k|+1)*m*g(n)+h(n);

[0037] |k+1|*m=+∞;

[0038] Among them, f(n) is the first path planning function, k is the height of inanimate obstacles, m is the roughness coefficient of inanimate objects, g(n) is the actual cost function, and h(n) is the estimated cost function.

[0039] Optionally, in some embodiments, before controlling the vehicle according to the updated planned path, the control module is further configured to:

[0040] The updated planned path is smoothed using a preset Bezier curve.

[0041] A third aspect of the present application provides a vehicle, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the path planning method as described in the above embodiment.

[0042] The fourth aspect of the present application provides a computer program product on which a computer program is stored, and the program is executed to implement the path planning method as described in the above embodiment.

[0043] Therefore, this application obtains the target area map and the current planned path, grids the target area map, obtains the grid map, and determines whether there are obstacles in the current planned path. If there are obstacles in the current planned path, the type of obstacle, the area coverage of the obstacle in the grid map and the height of the obstacle are determined, and the roughness coefficient of the obstacle is calculated. According to the type, height and roughness coefficient, a new path planning function is determined, and the current planned path is updated according to the new path planning function and area coverage, and the vehicle is controlled according to the updated planned path. Therefore, the problem that the dynamic obstacle avoidance algorithm is based on the machine learning algorithm in the related technology, has a large demand for computing power, and has a slow running speed, which affects the success rate of the automatic driving function is solved, and the accuracy and efficiency of the dynamic avoidance of smart cars are improved, and the driving experience of users is improved.

[0044] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0046] Figure 1 A flow chart of a path planning method provided according to an embodiment of the present application;

[0047] Figure 2 is a flow chart of a path planning method according to a specific embodiment of the present application;

[0048] Figure 3 A block diagram of a path planning device provided according to an embodiment of the present application;

[0049] Figure 4 It is a block diagram of a vehicle provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0050] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0051] The path planning method, device, vehicle and program product of the embodiment of the present application are described below with reference to the accompanying drawings. In view of the problem that the dynamic obstacle avoidance algorithm mentioned in the above background technology is based on a machine learning algorithm, has a large demand for computing power, and has a slow running speed, which affects the success rate of the automatic driving function, the present application provides a path planning method, in which a target area map and a current planned path are obtained, the target area map is gridded to obtain a grid map, and it is determined whether there is an obstacle in the current planned path; if there is an obstacle in the current planned path, the type of obstacle, the area coverage of the obstacle in the grid map and the height of the obstacle are determined, and the roughness coefficient of the obstacle is calculated; a new path planning function is determined according to the type, height and roughness coefficient, and the current planned path is updated according to the new path planning function and area coverage, and the vehicle is controlled according to the updated planned path. Thus, the problem that the dynamic obstacle avoidance algorithm is based on a machine learning algorithm, has a large demand for computing power, and has a slow running speed, which affects the success rate of the automatic driving function is solved, the accuracy and efficiency of the dynamic avoidance of the intelligent vehicle are improved, and the driving experience of the user is improved.

[0052] Specifically, Figure 1 A flowchart of a path planning method provided in an embodiment of the present application.

[0053] like Figure 1 As shown, the path planning method includes the following steps:

[0054] In step S101, a target area map and a current planned path are obtained, the target area map is gridded to obtain a gridded map, and it is determined whether there are obstacles in the current planned path.

[0055] Among them, the currently planned path in the embodiment of the present application refers to the path from the starting point to the end point calculated on the target area map according to the A-star algorithm f(n)=g(n)+h(n).

[0056] It is understandable that in order to improve the processing speed of dynamic avoidance and make path planning more efficient, the embodiment of the present application grids the map of the target area, that is, divides the map into many small cells (grids), each grid containing specific geographical location information. Specifically, the embodiment of the present application can obtain a map of the target area from a GPS (Global Positioning System), a map service, or a pre-stored map, and grid it to obtain a grid map.

[0057] It should be noted that the grid map of the embodiment of the present application contains coordinate information. After the target area map is gridded, the embodiment of the present application can also obtain the coordinate information of the starting point and the end point of the current planned path.

[0058] Furthermore, in order to implement the dynamic obstacle avoidance algorithm, the embodiment of the present application needs to detect whether there are obstacles in the current planned path. Optionally, the embodiment of the present application uses the vehicle's laser radar, camera and other sensors to detect the surrounding environment in real time, combined with the A-star algorithm to determine whether the current planned path crosses the boundary of the obstacle.

[0059] Therefore, the embodiment of the present application grids the target area map and simplifies the complex map information into grid units that are easy to manage and analyze, thereby improving the efficiency of path planning and dynamic obstacle avoidance. Path planning on the grid map can make it easier to find and avoid obstacles, thereby improving the robustness and safety of the path. The grid map allows a more detailed analysis of the resources and features in the area, which helps to optimize resource allocation and utilization and improve data processing capabilities.

[0060] In step S102, if there is an obstacle in the current planned path, the type of the obstacle, the area coverage of the obstacle in the grid map and the height of the obstacle are determined, and the roughness coefficient of the obstacle is calculated.

[0061] Among them, the types of obstacles in the embodiments of the present application include inanimate objects and living objects. Inanimate objects can be buildings, trees, rocks, etc., and living objects can be pedestrians, small animals, etc.

[0062] It is understandable that the vehicle starts to travel along the currently planned path. If an obstacle is detected in the currently planned path at a certain moment, it is necessary to analyze the obstacle to determine the type of obstacle, its area coverage and height in the grid map for path planning and dynamic obstacle avoidance.

[0063] Specifically, the embodiment of the present application can calculate the projection area of ​​the obstacle on the ground, estimate the coverage of the obstacle, and calculate the coordinates of each point in the grid map of the obstacle area coverage area through the data collected by the laser radar. The embodiment of the present application can measure the height of the obstacle through the laser radar for determination of the subsequent path planning algorithm.

[0064] Optionally, the embodiment of the present application combines lidar data with other sensor data (such as cameras, radars, etc.) and uses a machine learning algorithm to classify obstacles and determine the type of obstacles.

[0065] Optionally, in some embodiments, calculating the roughness coefficient of the obstacle includes: determining multiple positioning points, and determining the highest height and the lowest height of the obstacle in the horizontal plane at each positioning point; calculating the difference between the highest height and the lowest height of the horizontal plane of each positioning point, and taking the average value of the differences between the multiple positioning points as the roughness coefficient.

[0066] Among them, the positioning points in the embodiment of the present application are multiple representative points selected on the surface of the obstacle.

[0067] Those skilled in the art will appreciate that calculating the roughness coefficient of an obstacle is a method for evaluating the surface roughness of the obstacle, which is particularly important for the navigation and obstacle avoidance systems of autonomous vehicles. Therefore, the path planning method of the embodiment of the present application also has a state analysis function for potholes and uneven roads.

[0068] Specifically, the embodiment of the present application selects a plurality of representative positioning points on the obstacle surface, and these points should be evenly distributed on the obstacle surface to ensure the comprehensiveness of the evaluation. Then, a laser radar or other height measurement sensor is used to determine the highest and lowest heights of each positioning point on the horizontal plane. In order to obtain the degree of unevenness of the obstacle surface at each positioning point, the embodiment of the present application calculates the difference between the highest and lowest heights of each positioning point, adds the height differences of all positioning points, and then takes the average value, which is the roughness coefficient of the obstacle.

[0069] It should be noted that the roughness coefficient of the embodiment of the present application is greater than 0.

[0070] Furthermore, the embodiment of the present application adjusts the path planning and dynamic obstacle avoidance strategy of the autonomous driving vehicle according to the roughness coefficient of the obstacle. For example, a larger safety distance may be required for obstacles with more uneven surfaces. In addition, the roughness coefficient can help the vehicle choose a smoother path to avoid vehicle bumps or damage caused by the uneven surface of the obstacle, thereby improving the user's driving experience.

[0071] Therefore, the embodiment of the present application calculates the roughness coefficient of obstacles, allowing the autonomous driving vehicle to understand and evaluate the surrounding environment more carefully, thereby making more accurate and safe navigation decisions, thereby improving the reliability of autonomous driving technology and passenger comfort.

[0072] In step S103, a new path planning function is determined according to the type, height and roughness coefficient, and the current planned path is updated according to the new path planning function and area coverage, and the vehicle is controlled according to the updated planned path.

[0073] It can be understood that after the vehicle is started, it travels according to the current planned path calculated by the A-star algorithm f(n)=g(n)+h(n). At a certain moment, the automatic driving system detects the presence of an obstacle in the current planned path. At this time, the embodiment of the present application needs to determine a new path planning function based on the type of obstacle, the height of the obstacle and the roughness coefficient of the obstacle, and then update the current planned path based on the new path planning function and the area coverage of the obstacle.

[0074] Specifically, the embodiment of the present application improves the above-mentioned A-star algorithm according to the obstacle type, obstacle height and obstacle roughness coefficient to obtain a new path planning function.

[0075] Optionally, in some embodiments, a new path planning function is determined based on the type, height and roughness coefficient, including: when the type of obstacle is an inanimate object, a first path planning function is obtained based on the height and roughness coefficient of the obstacle, and the first path planning function is used as a new path planning function; when the type of obstacle is a living object, a second path planning function is obtained based on the height, roughness coefficient and a preset infinite cost of the obstacle, and the second path planning function is used as a new path planning function.

[0076] Optionally, in some embodiments, the first path planning function is:

[0077] f(n)=(|k|+1)*m*g(n)+h(n); (1)

[0078] The second path planning function is:

[0079] f(n)=(|k|+1)*m*g(n)+h(n); |k+1|*m=+∞; (2)

[0080] Among them, f(n) is the first path planning function, k is the height of inanimate obstacles, m is the roughness coefficient of inanimate objects, g(n) is the actual cost function, and h(n) is the estimated cost function.

[0081] It can be understood that the embodiment of the present application adjusts the A-star algorithm according to the type, height and roughness coefficient of the obstacle, so that the autonomous driving system can better adapt to different obstacle environments.

[0082] In some cases, for obstacles such as inanimate objects, the embodiment of the present application only needs to consider the height and roughness coefficient of the obstacle to obtain the above formula (1), which is the first path planning function of the embodiment of the present application.

[0083] In some cases, for obstacles of living things, in addition to considering the height and roughness coefficient of the obstacles, the embodiments of the present application also need to add a preset infinite cost, that is, the value of |k+1|*m tends to infinity, to ensure that the vehicle avoids conflicts with living things as much as possible.

[0084] It should be noted that, in the case where the obstacle is a living object, the embodiment of the present application also needs to set an emergency stop function to further ensure that there is no conflict with the living object. In addition, optionally, when |k+1|*m tends to infinity, an upper limit or a special case processing strategy can be defined to avoid computational problems or unreasonable path planning results.

[0085] Therefore, by improving the A-star algorithm and obtaining a new path planning function, autonomous driving vehicles can more accurately evaluate the impact of obstacles on the driving route and develop a more reasonable and safe navigation path.

[0086] Furthermore, if the area covered by the obstacle is large, the system can start adjusting the driving route earlier to avoid the need to make a sharp turn or turn when approaching the obstacle, which helps reduce the number of emergency braking and sharp turns and improve driving stability and safety. In addition, based on the area coverage of the obstacle, the system can more accurately judge the type and size of the obstacle, thereby adopting a more appropriate obstacle avoidance strategy.

[0087] Therefore, when the embodiment of the present application updates the current planned path according to the new path planning function, it is also necessary to consider the area coverage of the obstacles, so as to make more accurate path planning and obstacle avoidance decisions.

[0088] Optionally, in some embodiments, before controlling the vehicle according to the updated planned path, the method further includes: smoothing the updated planned path using a preset Bezier curve.

[0089] Specifically, the embodiment of the present application uses Bezier curves or other smoothing algorithms to smooth the updated planned path to improve the smoothness of vehicle driving and user comfort, thereby enhancing the user's driving experience.

[0090] Therefore, the embodiment of the present application is based on the A-star algorithm, combined with the type, height and roughness coefficient of the obstacle, to dynamically adjust the obstacle avoidance strategy to ensure that the vehicle always travels along the optimal path, to ensure that the vehicle can follow the planned path, avoid all obstacles, and finally reach the destination safely.

[0091] In order to enable those skilled in the art to further understand the path planning method of the embodiment of the present application, the following examples are listed to schematically illustrate the implementation steps of the method.

[0092] Specifically, Figure 2 This is a flow chart of a path planning method according to a specific embodiment of the present application. Figure 2 As shown, the path planning method includes the following steps:

[0093] Step S1, obtaining a map of the target area and performing grid processing on the map;

[0094] Step S2, determining the coordinate information of the starting point and the end point of the vehicle based on the grid map;

[0095] Step S3, using f(n)=g(n)+h(n) to plan the route from the starting point to the end point;

[0096] Step S4, the vehicle travels along the planned route;

[0097] Step S5, judging whether there is an unknown obstacle through the sensor status of the vehicle's laser radar, etc.;

[0098] Step S6: if there is an unknown obstacle in front of the vehicle at time t0, then area coverage and height measurement are performed, and the type of obstacle is determined;

[0099] Step S7, calculating the coordinates of each point in the grid map of the obstacle area coverage area;

[0100] Step S8, if the type of obstacle is an inanimate object, the obstacle height k is calculated using the laser radar 3D (Three-Dimensional) data;

[0101] Step S9, using the laser radar 3D data to calculate the average value m of the difference between the highest and lowest horizontal planes of the obstacle, and taking it as the roughness coefficient, and the roughness coefficient m>0;

[0102] Step S10, using f(n)=(|k|+1)*m*g(n)+h(n), where k is the height of the inanimate object and m is the regional roughness coefficient;

[0103] Step S11, if the type of obstacle is a living object, f(n) is calculated according to f(n)=(|k|+1)*m*g(n)+h(n), |k+1|*m=+∞;

[0104] Step S12, determining the size of f(n) at the next moment, and performing path planning and avoidance at the next moment;

[0105] Step S13, smoothing the available point path using a Bezier curve;

[0106] Step S14, complete the overall path planning according to the above logic until the vehicle reaches the destination.

[0107] Therefore, this application promotes the development and application of autonomous driving technology by combining advanced perception technology, dynamic path planning algorithms and real-time obstacle avoidance strategies.

[0108] According to the path planning method proposed in the embodiment of the present application, by obtaining the target area map and the current planned path, the target area map is gridded to obtain a grid map, and it is determined whether there are obstacles in the current planned path. If there are obstacles in the current planned path, the type of obstacle, the area coverage of the obstacle in the grid map and the height of the obstacle are determined, and the roughness coefficient of the obstacle is calculated. A new path planning function is determined according to the type, height and roughness coefficient, and the current planned path is updated according to the new path planning function and area coverage, and the vehicle is controlled according to the updated planned path. In this way, the problems in the related technology that the dynamic obstacle avoidance algorithm is based on the machine learning algorithm, has a large demand for computing power, and has a slow running speed, which affects the success rate of the automatic driving function, are solved, and the accuracy and efficiency of the dynamic avoidance of smart cars are improved, and the driving experience of users is enhanced.

[0109] Next, the path planning device proposed according to the embodiment of the present application is described with reference to the accompanying drawings.

[0110] Figure 3 It is a block diagram of a path planning device according to an embodiment of the present application.

[0111] like Figure 3 As shown, the path planning device 10 includes: an acquisition module 100 , a calculation module 200 and a control module 300 .

[0112] Specifically, the acquisition module 100 is used to obtain the target area map and the current planned path, grid the target area map to obtain a grid map, and determine whether there are obstacles in the current planned path; the calculation module 200 is used to determine the type of obstacle, the area coverage of the obstacle in the grid map and the height of the obstacle when there are obstacles in the current planned path, and calculate the roughness coefficient of the obstacle; the control module 300 is used to determine a new path planning function according to the type, height and roughness coefficient, and update the current planned path according to the new path planning function and area coverage, and control the vehicle according to the updated planned path.

[0113] Optionally, in some embodiments, the calculation module 200 is specifically used to: determine multiple positioning points, and determine the highest and lowest horizontal plane heights of the obstacle at each positioning point; calculate the difference between the highest and lowest horizontal plane heights of each positioning point, and use the average value of the differences between the multiple positioning points as the roughness coefficient.

[0114] Optionally, in some embodiments, the control module 300 is specifically used to: when the type of obstacle is an inanimate object, obtain a first path planning function based on the height and roughness coefficient of the obstacle, and use the first path planning function as a new path planning function; when the type of obstacle is a living object, obtain a second path planning function based on the height, roughness coefficient and a preset infinite cost of the obstacle, and use the second path planning function as a new path planning function.

[0115] Optionally, in some embodiments, the first path planning function is:

[0116] f(n)=(|k|+1)*m*g(n)+h(n);

[0117] The second path planning function is:

[0118] f(n)=(|k|+1)*m*g(n)+h(n);

[0119] |k+1|*m=+∞;

[0120] Among them, f(n) is the first path planning function, k is the height of inanimate obstacles, m is the roughness coefficient of inanimate objects, g(n) is the actual cost function, and h(n) is the estimated cost function.

[0121] Optionally, in some embodiments, before controlling the vehicle according to the updated planned path, the control module 300 is further configured to: smooth the updated planned path using a preset Bezier curve.

[0122] It should be noted that the above explanation of the path planning method embodiment is also applicable to the path planning device of this embodiment, and will not be repeated here.

[0123] According to the path planning device proposed in the embodiment of the present application, by obtaining the target area map and the current planned path, the target area map is gridded to obtain a grid map, and it is determined whether there are obstacles in the current planned path. If there are obstacles in the current planned path, the type of obstacle, the area coverage of the obstacle in the grid map and the height of the obstacle are determined, and the roughness coefficient of the obstacle is calculated. A new path planning function is determined according to the type, height and roughness coefficient, and the current planned path is updated according to the new path planning function and area coverage, and the vehicle is controlled according to the updated planned path. In this way, the problems in the related technology that the dynamic obstacle avoidance algorithm is based on the machine learning algorithm, has a large demand for computing power, and has a slow running speed, which affects the success rate of the automatic driving function, are solved, and the accuracy and efficiency of the dynamic avoidance of smart cars are improved, and the driving experience of users is enhanced.

[0124] Figure 4 A schematic diagram of the structure of a vehicle provided in an embodiment of the present application. The vehicle may include:

[0125] Memory 401 , processor 402 , and a computer program stored in the memory 401 and executable on the processor 402 .

[0126] When the processor 402 executes the program, the path planning method provided in the above embodiment is implemented.

[0127] Furthermore, the vehicle also includes:

[0128] The communication interface 403 is used for communication between the memory 401 and the processor 402 .

[0129] The memory 401 is used to store computer programs that can be executed on the processor 402 .

[0130] The memory 401 may include a high-speed RAM (Random Access Memory) memory, and may also include a non-volatile memory, such as at least one disk memory.

[0131] If the memory 401, the processor 402 and the communication interface 403 are implemented independently, the communication interface 403, the memory 401 and the processor 402 can be connected to each other through a bus and communicate with each other. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0132] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can communicate with each other through an internal interface.

[0133] The processor 402 may be a CPU (Central Processing Unit), or an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement the embodiments of the present application.

[0134] An embodiment of the present application also provides a computer program product, on which a computer program is stored, and when the program is executed, the above path planning method is implemented.

[0135] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms are not necessarily directed to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0136] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0137] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0138] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one or a combination of multiple of the following technologies known in the art: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array, a field programmable gate array, etc.

[0139] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0140] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A path planning method, characterized in that: The following steps are involved: Obtaining a target area map and a current planned path, gridding the target area map to obtain a gridded map, and determining whether there are obstacles in the current planned path; If the obstacle exists in the current planned path, determining the type of the obstacle, the area coverage of the obstacle in the grid map and the height of the obstacle, and calculating the roughness coefficient of the obstacle; A new path planning function is determined according to the type, the height and the roughness coefficient, and the current planned path is updated according to the new path planning function and the area coverage, and the vehicle is controlled according to the updated planned path.

2. The method according to claim 1, characterized in that The calculating the roughness coefficient of the obstacle comprises: Determine a plurality of positioning points, and determine the highest height and the lowest height of the obstacle in the horizontal plane at each positioning point; The difference between the highest height and the lowest height of the horizontal plane of each positioning point is calculated, and the average value of the differences of the multiple positioning points is used as the roughness coefficient.

3. The method according to claim 1, characterized in that The determining of a new path planning function according to the type, the height and the roughness coefficient comprises: When the type of the obstacle is an inanimate object, obtaining a first path planning function according to the height of the obstacle and the roughness coefficient, and using the first path planning function as the new path planning function; When the type of the obstacle is a living object, a second path planning function is obtained according to the height of the obstacle, the roughness coefficient and a preset infinite cost, and the second path planning function is used as the new path planning function.

4. The method according to claim 3, characterized in that The first path planning function is: f(n)=(|k|+1)*m*g(n)+h(n); The second path planning function is: f(n)=(|k|+1)*m*g(n)+h(n); |k+1|*m=+∞; Among them, f(n) is the first path planning function, k is the height of inanimate obstacles, m is the roughness coefficient of inanimate objects, g(n) is the actual cost function, and h(n) is the estimated cost function.

5. The method according to claim 1, characterized in that Before controlling the vehicle according to the updated planned path, the method further includes: The updated planned path is smoothed using a preset Bezier curve.

6. A path planning device, characterized in that: include: An acquisition module is used to acquire a target area map and a current planned path, grid the target area map to obtain a grid map, and determine whether there are obstacles in the current planned path; a calculation module, for determining the type of the obstacle, the area coverage of the obstacle in the grid map and the height of the obstacle, and calculating the roughness coefficient of the obstacle when the obstacle exists in the current planned path; A control module is used to determine a new path planning function according to the type, the height and the roughness coefficient, update the current planned path according to the new path planning function and the area coverage, and control the vehicle according to the updated planned path.

7. The device according to claim 6, characterized in that The computing module is specifically used for: Determine a plurality of positioning points, and determine the highest height and the lowest height of the obstacle in the horizontal plane at each positioning point; The difference between the highest height and the lowest height of the horizontal plane of each positioning point is calculated, and the average value of the differences of the multiple positioning points is used as the roughness coefficient.

8. The device according to claim 6, characterized in that The control module is specifically used for: When the type of the obstacle is an inanimate object, obtaining a first path planning function according to the height of the obstacle and the roughness coefficient, and using the first path planning function as the new path planning function; When the type of the obstacle is a living object, a second path planning function is obtained according to the height of the obstacle, the roughness coefficient and a preset infinite cost, and the second path planning function is used as the new path planning function.

9. A vehicle, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the path planning method according to any one of claims 1 to 5.

10. A computer program product, comprising a computer program, characterized in that The computer program is executed to implement the path planning method according to any one of claims 1 to 5.

Images