Local path planning method, device, storage medium, electronic device and vehicle

Abstract

The present invention discloses a local path planning method, device, storage medium and electronic device. The local path planning method includes: obtaining the initial constraint information of the target device, generating an unconstrained optimization equation based on the initial constraint information of the target device; obtaining the current operating state of the target device and the current operating state of the obstacle; based on a pre-set G2O solver, determining the target local path of the target device within a preset driving range according to the current operating state of the target device, the current operating state of the obstacle and the unconstrained optimization equation. The technical solution of this embodiment performs unconstrained solution of the local path based on the G2O solver, with small calculation amount, fast speed and high efficiency, and realizes real-time local path planning for unmanned vehicles.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of path planning technology, and in particular, to a local path planning method, device, storage medium, electronic device and vehicle. Background Art

[0002] With the continuous development of vehicle research and development technology, unmanned autonomous driving has become an important direction of vehicle research and development.

[0003] Local path planning is an indispensable part of unmanned vehicle path planning. Local path planning is used to achieve real-time obstacle avoidance for unmanned vehicles. Currently, there is a lack of feasible local path planning methods, which results in the inability of unmanned equipment to accurately and reliably implement path planning during driving, and whether safety can be 100% reliable. Summary of the invention

[0004] The present invention provides a local path planning method, device, storage medium, electronic equipment and vehicle to achieve the efficiency of local path planning for unmanned vehicles.

[0005] In a first aspect, an embodiment of the present invention provides a local path planning method, including:

[0006] Acquire initial constraint information of the target device, and generate an unconstrained optimization equation based on the initial constraint information of the target device;

[0007] Obtaining the current operating status of the target device and the current operating status of the obstacle;

[0008] Based on a preset G2O solver, a target local path of the target device within a preset driving range is determined according to the current operating state of the target device, the current operating state of the obstacle and the unconstrained optimization equation.

[0009] In a second aspect, an embodiment of the present invention further provides a local path planning device, including:

[0010] An optimization equation determination method is used to obtain initial constraint information of a target device and generate an unconstrained optimization equation based on the initial constraint information of the target device;

[0011] An operating status acquisition module, used to acquire the current operating status of the target device and the current operating status of the obstacle;

[0012] The local path determination module is used to determine the target local path of the target device within a preset driving range based on a preset G2O solver, according to the current operating state of the target device, the current operating state of the obstacle and the unconstrained optimization equation.

[0013] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a local path planning method as provided in any embodiment of the present invention is implemented.

[0014] In a fourth aspect, an embodiment of the present invention further provides a vehicle, which is equipped with the electronic device provided by any embodiment.

[0015] In a fifth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a local path planning method as provided in any embodiment of the present invention.

[0016] The embodiment of the present invention determines the unconstrained optimization equation of the target device and the current operating state of the target device and the current operating state of the obstacle, and plans the local path of the target device based on the G2O optimization concept through the G2O solver, thereby improving the control accuracy of the unmanned vehicle and preventing the unmanned vehicle from being surrounded by obstacles during driving. Among them, the unconstrained solution of the local path based on the G2O solver has a small amount of calculation, fast speed, and high efficiency, and realizes real-time local path planning for the unmanned vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flowchart of a local path planning method provided in Embodiment 1 of the present invention;

[0018] Figure 2 is a top view of a target device provided by Embodiment 1 of the present invention;

[0019] Figure 3 It is a flowchart of a local path planning method provided by Embodiment 2 of the present invention;

[0020] Figure 4 is a structural schematic diagram of a local path planning device provided in Embodiment 3 of the present invention;

[0021] Figure 5 A schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention;

[0022] Figure 6 It is a structural schematic diagram of a vehicle provided in Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0023] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0024] Embodiment 1

[0025] Figure 1 This is a flow chart of a local path planning method provided in Embodiment 1 of the present invention. This embodiment can be applied to quickly determine the local path planning status of a target device. The method can be executed by a local path planning device provided in an embodiment of the present invention. The device can be implemented in software or hardware and can be integrated in a target device. Specifically, the method includes the following steps:

[0026] S110 , obtaining initial constraint information of the target device, and generating an unconstrained optimization equation based on the initial constraint information of the target device.

[0027] S120: Acquire the current operating status of the target device and the current operating status of the obstacle.

[0028] S130. Based on a preset G2O solver, according to the current operating state of the target device, the current operating state of the obstacle and the unconstrained optimization equation, determine a target local path of the target device within a preset driving range.

[0029] The initial constraint information of the target device is used to basically limit the movement of the target device, so that the movement of the target device conforms to the basic movement rules, and avoids the planned route obtained by local path planning not conforming to the basic movement rules and being unable to be realized. Exemplarily, the target device can be a device with automatic movement function, such as but not limited to a vehicle (such as an unmanned vehicle), a motion model, etc. Correspondingly, the initial constraint information is determined according to the type of the target device, and different target devices can correspond to different initial constraint information.

[0030] Optionally, the initial constraint information includes kinematic constraint information, speed and acceleration constraint information, distance constraint information from obstacles, and runtime constraint information of the target device, wherein the kinematic constraint information is used to constrain the speed, turning angle, and distance from obstacles of the target device, so that the movement of the target device conforms to the kinematic law, the speed and acceleration constraint information is used to constrain the speed and acceleration of the target device, the distance constraint information from obstacles is used to constrain the distance between the target device and obstacles in the surrounding environment to be greater than 0, and the runtime constraint information is used to constrain the travel time of the target device in the local planning path to be minimum. Among them, the kinematic constraint information, speed and acceleration constraint information, distance constraint information from obstacles, and runtime constraint information of the target device can all be presented in the form of constraint equations.

[0031] See also Figure 2 , Figure 2 is a top view of a target device provided in the first embodiment of the present invention. Among them, the kinematic equation for:

[0032]

[0033] in, is the motion constraint formula of the target device along the motion direction, is the motion constraint formula of the target device in the direction perpendicular to the motion direction, is the angular motion constraint formula of the target device, v(t) is the motion speed of the target device at time t, β(t) is the motion angle of the target device at time t, φ(t) is the maximum rotation angle of the target device, and L is the length of the target device.

[0034] The velocity and acceleration equations are:

[0035]

[0036] in, The acceleration of the target device in the X direction, The acceleration of the target device in the Y direction.

[0037] The distance formula to the obstacle is:

[0038]

[0039] Among them, x(t) and y(t) are the coordinates of the target device at time t, respectively. o and o are the coordinates of the obstacles respectively.

[0040] The running time equation is: Where, ΔT k is the running time of each interval, k is the number of intervals of the local path, and n-1 is the total number of intervals of the local path. It should be noted that the local path is composed of multiple position points, and the path between any adjacent position points is an interval.

[0041] Based on the above constraint information, the unconstrained optimization equation is a minimization equation that performs weighted summation of the kinematic constraint information of the target device, the speed and acceleration constraint information, the distance constraint information from the obstacle, and the running time constraint information.

[0042] Exemplarily, the unconstrained optimization equation is:

[0043] Among them, ω0, ω1, ω2 and ω3 are the weights of the constraint information of running time, kinematic constraint information, speed and acceleration constraint information and distance constraint information from obstacles. It should be noted that the initial constraint information of the target device does not include the constraint information of the local path. Accordingly, the path cost is not considered in the process of local path planning based on the unconstrained optimization equation to improve the speed of path planning.

[0044] It should be noted that the initial constraint information of the target device may be pre-set in the target device. When the target device is started, or when the target device starts automatic driving, the initial constraint information of the target device is called, and the unconstrained optimization equation in the current driving process is generated according to the weight information input externally, wherein the weight of each constraint information can be set according to the emphasis on each constraint information. Optionally, the weight information can be determined according to the type of the target device. In some embodiments, the unconstrained optimization equation of the target device may also be pre-set, and accordingly, the weight of each constraint information is a fixed weight. When the target device is started, or when the target device starts automatic driving, the unconstrained optimization equation of the target device is called.

[0045] In this embodiment, the status information of the target device includes the speed and turning angle of the target device, wherein the speed and turning angle can be obtained by monitoring the target device. For example, the target device is a vehicle, and a tachometer is provided in the vehicle. The speed of the target device can be obtained by reading the speed data in the tachometer. The turning angle of the vehicle can be determined by monitoring the angle between the wheels and the direction of the vehicle body. Furthermore, it can be determined by monitoring the angle between the driving wheels of the vehicle and the direction of the vehicle body.

[0046] Optionally, the obstacles include static obstacles and dynamic obstacles, wherein the static obstacles may be, but are not limited to, objects or buildings on the road, etc., and the dynamic obstacles may be, but are not limited to, moving vehicles, bicycles, electric vehicles, pedestrians, animals, etc. The current running state of the obstacle includes the speed, turning angle, and distance of the obstacle from the target device, wherein detection sensors are arranged around the target device. Exemplarily, since obstacles may exist on the left, right, front, and back of the target device, detection sensors are arranged at the front, rear, and left and right sides of the target device, respectively, to fully detect obstacles.

[0047] Optionally, the detection sensor includes a laser radar sensor, for example, the laser radar sensor may be a laser speed sensor, which is used to measure the distance between the target device and the obstacle, and further, the speed of the obstacle is detected by the distance between the target device and the obstacle. Specifically, by continuously monitoring the distance between the target device and the obstacle within a preset time period (for example, 200ms, 500ms or 1s), the speed of the obstacle is determined according to the change in the distance between the target device and the obstacle and the speed of the target device within the preset time period. The obstacle speed may be V2=V1+ΔS / t, wherein V2 is the speed of the obstacle, V1 is the speed of the target device, and ΔS is the change in the distance between the target device and the obstacle within the preset time period t. Optionally, the detection sensor also includes a visual sensor, which is used to detect the turning angle of the obstacle. For example, if the obstacle is a moving vehicle, the wheel of the obstacle is detected by the visual sensor, and the turning angle of the wheel is determined as the turning angle of the obstacle.

[0048] In this embodiment, the speed and turning angle of the obstacle can be used to predict the movement state of the obstacle at the next time, which is used to assist local path planning and avoid the situation where the movement state of the obstacle in the next time period changes and causes the target device to be surrounded by obstacles.

[0049] It should be noted that the execution order of step S110 and step S120 is not limited in this embodiment, and they may be executed sequentially, or step S120 may be executed first and then step S110, or step S110 and step S120 may be executed simultaneously.

[0050] In this embodiment, the G2O solver is pre-set and has a path optimization function. The obtained unconstrained optimization equation, the current operating state of the target device, and the current operating state of the obstacle are input into the G2O solver, and the target local path of the target device can be quickly output. Among them, the G2O solver analyzes and calculates the unconstrained optimization equation, the current operating state of the target device, and the current operating state of the obstacle based on the G2O optimization idea, and outputs a smooth target local path. It should be noted that since the unconstrained optimization equation does not include cost constraints on the local path, when performing local path planning, only the G2O solver is used for calculation, so the calculation speed is fast and the path planning cost is low. Correspondingly, since there is no cost constraint on the local path during the local path planning process, further, the obtained target local path is subjected to feasibility detection to determine the feasibility of the target local path.

[0051] In this embodiment, the target device is a low-speed unmanned vehicle, wherein the speed of the target device may be less than a preset speed, for example, the preset speed may be 10 km / h. Optionally, the target device is a low-speed unmanned delivery vehicle for delivery services such as take-out and express delivery. Specifically, the low-speed unmanned vehicle generates an unconstrained optimization equation applicable to the low-speed unmanned vehicle based on the initial constraint information of the low-speed unmanned vehicle, obtains the current operating state of the low-speed unmanned vehicle and the current operating state of the obstacle, and determines the target local path of the low-speed unmanned vehicle in the preset driving range based on the preset g2o solver according to the current operating state of the low-speed unmanned vehicle, the current operating state of the obstacle and the unconstrained optimization equation.

[0052] It should be noted that the target local path for the target device can be the path of the target device within a preset driving range, wherein the preset range can be a driving range within 100 meters or 50 meters from the current position. In this embodiment, by planning the local path of the vehicle in real time during the driving process of the target device from the starting point to the end point, the control accuracy of the driving details of the unmanned vehicle is improved, the traffic status of the unmanned vehicle is ensured, and the automatic driving quality of the unmanned vehicle is improved. When the unmanned vehicle is a delivery vehicle, the delivery efficiency is improved.

[0053] The technical solution of this embodiment plans the local path of the target device based on the G2O optimization concept by determining the unconstrained optimization equation of the target device and the current operating state of the target device and the current operating state of the obstacle, thereby improving the control accuracy of the target device and preventing the target device from being surrounded by obstacles during driving. The unconstrained solution of the local path based on the G2O solver has a small amount of calculation, high speed and high efficiency, and realizes real-time local path planning for the target device.

[0054] Based on the above embodiment, the G2O solver is used to generate at least one local path based on the current operating state of the target device, the current operating state of the obstacle and the unconstrained optimization equation, calculate the evaluation value of each local path, and determine the target local path according to the evaluation value.

[0055] Among them, the G2O solver can obtain at least one local path based on the current operating state of the target device, the current operating state of the obstacle and the unconstrained optimization equation. When the number of local paths is greater than 1, the optimal target local path is screened from the above local paths. Among them, the evaluation value of each local path can be determined according to preset rules, and the local path with the highest evaluation value is determined as the target local path.

[0056] Optionally, the calculation of the evaluation value of each local path includes: calculating the evaluation value of each local path based on the parameter information of the local path and the weight of each parameter information, wherein the parameter information of the local path includes at least one of the length of the local path, the road width, the number of turns, and the road surface smoothness. The weight of each parameter information may be determined by user demand. For example, if the user demand is to improve the driving smoothness of the target device, the weight may be increased for increasing the road width and the road surface smoothness, and if the demand is to improve the driving efficiency of the target device, the weight may be increased for increasing the length of the local path.

[0057] In one embodiment, the evaluation value of the local path is determined by the length of the local path, wherein the evaluation value of the local path is negatively correlated with the length of the local path, that is, the smaller the length of the local path, the higher the evaluation value of the local path. The local path with the smallest length is determined as the target local path to reduce the travel time of the target device. Optionally, the length constraint of the path can also be used as a constraint information to generate a new unconstrained optimization equation, and the target local path is output based on the new unconstrained optimization equation.

[0058] Embodiment 2

[0059] Figure 3 : is a flow chart of a local path planning method provided in Embodiment 2 of the present invention, which is optimized on the basis of the above embodiment. The method specifically includes:

[0060] S210 , obtaining initial constraint information of the target device, and generating an unconstrained optimization equation based on the initial constraint information of the target device.

[0061] S220: Acquire the current operating status of the target device and the current operating status of the obstacle.

[0062] S230: Based on a preset G2O solver, according to the current operating state of the target device, the current operating state of the obstacle and the unconstrained optimization equation, determine a target local path of the target device within a preset driving range.

[0063] S240: Obtain a current cost map of the target device, and verify the feasibility of the target local path based on the current cost map.

[0064] In this embodiment, the feasibility of the target local path is verified through a cost map, wherein the cost map includes the target local path and obstacles of the target device, and the target local path and obstacles can be displayed on the map in equal proportions based on different colors. When there are no obstacles on the target local path, the target local path is determined to be feasible, and the driving of the target device is controlled based on the target local path; when there are obstacles on the target local path, the target local path is determined to be infeasible, the target local path is abandoned, and the local path planning is performed again.

[0065] Optionally, obtaining the current cost map of the target device includes: obtaining the size information and distance information of the obstacle of the target device; rendering the obstacle on the grid map according to the size information and distance information of each obstacle to generate the current cost map. Infrared sensors are arranged around the target device to detect the size information and distance information of the obstacle. According to the size information and distance information of the obstacle, the obstacle, the target device, and the target local path of the target device are proportionally rendered on the grid map. The grid map divides the environment into a series of grids, each of which corresponds to a position information. By rendering the obstacle, the target device, and the target local path of the target device on the grid map, the accuracy of the cost map is improved. In the grid map, the obstacle and the target device can be represented by a rectangle, wherein the size of the rectangle is proportional to the size information of the obstacle and the target device; the target local path of the target device can be represented by multiple position points.

[0066] Optionally, the feasibility verification of the target local path based on the current cost map includes: adding the position points in the target local path to the current cost map; when any position point in the target local path overlaps with the obstacle, the target local path is determined to be infeasible. When any position point in the target local path overlaps with an obstacle, it indicates that the target device will collide with the obstacle during the actual driving process, so the target local path is determined to be infeasible. When all position points in the target local path do not overlap with any obstacle, the target local path is determined to be feasible. Optionally, in the cost map, an expansion area is set around each position point in the target local path. Since the target device has a certain bandwidth and length, the area occupied by the target device at the position point is characterized by the expansion area. Accordingly, the area of ​​the expansion area is determined according to the size of the target device. Accordingly, when any position point in the target local path or the expansion area of ​​any position point overlaps with an obstacle, the target local path is determined to be infeasible. When all position points in the target local path and the expansion areas of all position points do not overlap with any obstacle, the target local path is determined to be feasible.

[0067] On the basis of the above embodiment, before the feasibility verification of the target partial path is performed based on the current cost map, it also includes: performing linear interpolation on the target partial path. By linear interpolation, the number of position points in the target partial path is increased, and accordingly, the feasibility verification of the target partial path after linear interpolation is performed, which can improve the accuracy of the feasibility verification.

[0068] The technical solution of this embodiment, after outputting the target local path based on the g2o solver, verifies the feasibility of the target local path through the cost map, avoids safety problems caused by the infeasibility of the target local path, improves the quality of local path planning, and ensures safe driving in the target device.

[0069] Embodiment 3

[0070] Figure 4 3 is a schematic diagram of the structure of a local path planning device provided in Embodiment 3 of the present invention, the device includes an optimization equation determination method 310, an optimization equation determination method 310 and a local path determination module 330, wherein:

[0071] The optimization equation determination method 310 is used to obtain initial constraint information of a target device and generate an unconstrained optimization equation based on the initial constraint information of the target device;

[0072] An operating status acquisition module 320 is used to acquire the current operating status of the target device and the current operating status of the obstacle;

[0073] The local path determination module 330 is used to determine the target local path of the target device within a preset driving range based on a preset G2O solver, according to the current operating state of the target device, the current operating state of the obstacle and the unconstrained optimization equation.

[0074] Based on the above embodiment, the initial constraint information includes kinematic constraint information of the target device, speed and acceleration constraint information, distance constraint information from obstacles, and running time constraint information.

[0075] Based on the above embodiment, the unconstrained optimization equation is a minimization equation that performs weighted summation of the kinematic constraint information of the target device, the speed and acceleration constraint information, the distance constraint information from the obstacle, and the running time constraint information.

[0076] Based on the above embodiment, detection sensors are arranged around the target device, wherein the detection sensors are used to collect the current operating status of obstacles in various directions of the target device, wherein the current operating status of the obstacle includes the speed, turning angle and distance of the obstacle from the target device.

[0077] Based on the above embodiment, the G2O solver is used to generate at least one local path based on the current operating state of the target device, the current operating state of the obstacle and the unconstrained optimization equation, calculate the evaluation value of each local path, and determine the target local path according to the evaluation value.

[0078] Based on the above embodiment, the G2O solver is used to calculate the evaluation value of each local path based on the parameter information of the local path and the weight of each parameter information, wherein the parameter information of the local path includes at least one of the length of the local path, the road width, the number of turns, and the road surface flatness.

[0079] Based on the above embodiment, the device further includes:

[0080] A cost map acquisition module, used to acquire the current cost map of the target device;

[0081] A feasibility verification module is used to verify the feasibility of the target local path based on the current cost map.

[0082] Based on the above embodiment, the cost map acquisition module is used to:

[0083] Obtaining size information and distance information of obstacles of the target device;

[0084] The obstacles are rendered on a grid map according to the size information and distance information of each obstacle to generate a current cost map.

[0085] Based on the above embodiment, the target local path is composed of multiple position points;

[0086] Accordingly, the feasibility verification module is used to:

[0087] Adding the position points in the target local path to the current cost map;

[0088] When any position point in the target partial path overlaps with the obstacle, it is determined that the target partial path is not feasible.

[0089] Based on the above embodiment, it also includes:

[0090] A linear interpolation module is used to perform linear interpolation on the target local path before verifying the feasibility of the target local path based on the current cost map.

[0091] The local path planning device provided in the embodiment of the present invention can execute the local path planning method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the local path planning method.

[0092] Embodiment 4

[0093] Figure 5 A schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Figure 5 A block diagram of an electronic device 412 suitable for implementing embodiments of the present invention is shown. Figure 5 The electronic device 412 shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention. The device 412 is typically an electronic device that performs image classification functions.

[0094] like Figure 5 As shown, the electronic device 412 is in the form of a general purpose computing device. The components of the electronic device 412 may include, but are not limited to: one or more processors 416, a storage device 428, and a bus 418 connecting different system components (including the storage device 428 and the processor 416).

[0095] Bus 418 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MCA) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0096] The electronic device 412 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 412, including volatile and non-volatile media, removable and non-removable media.

[0097] The storage device 428 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 430 and / or cache memory 432. The electronic device 412 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 434 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5 not shown, usually called a "hard drive"). Although Figure 5Not shown in the figure, a disk drive for reading and writing a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing a removable non-volatile optical disk (e.g., a read-only optical disk (Compact Disc-Read Only Memory, CD-ROM), a digital video disk (Digital Video Disc-Read Only Memory, DVD-ROM) or other optical media) may be provided. In these cases, each drive may be connected to the bus 418 via one or more data medium interfaces. The storage device 428 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0098] A program 436 having a set (at least one) of program modules 426 may be stored, for example, in a storage device 428, such program modules 426 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination thereof may include an implementation of a network environment. Program modules 426 generally perform the functions and / or methods of the embodiments described herein.

[0099] The electronic device 412 may also communicate with one or more external devices 414 (e.g., keyboard, pointing device, camera, display 424, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 412, and / or communicate with any device that enables the electronic device 412 to communicate with one or more other computing devices (e.g., network card, modem, etc.). Such communication may be performed through an input / output (I / O) interface 422. In addition, the electronic device 412 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN) and / or a public network, such as the Internet) through a network adapter 420. As shown, the network adapter 420 communicates with other modules of the electronic device 412 through a bus 418. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 412, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, disk arrays (Redundant Arrays of Independent Disks, RAID) systems, tape drives, and data backup storage systems.

[0100] The processor 416 executes various functional applications and data processing by running the programs stored in the storage device 428, such as implementing the local path planning method provided in the above embodiment of the present invention.

[0101] Embodiment 5

[0102] Figure 6 is a structural schematic diagram of a vehicle provided in Embodiment 5 of the present invention, and the vehicle 500 includes the electronic device 400 provided in the above embodiment. By configuring an electronic device with a local path planning function in the vehicle, when the vehicle is automatically driving, the local path of the vehicle is planned in real time, the control accuracy of the driving details of the unmanned vehicle is improved, the traffic status of the unmanned vehicle is ensured, and the automatic driving quality of the unmanned vehicle is improved.

[0103] Embodiment 6

[0104] Embodiment 6 of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the local path planning method provided in the embodiment of the present invention is implemented.

[0105] Of course, the computer-readable storage medium provided by the embodiment of the present invention stores a computer program which is not limited to the method operation described above, but can also execute the local path planning method provided by any embodiment of the present invention.

[0106] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0107] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable source code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0108] Source code embodied on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0109] Computer source code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The source code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0110] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A local path planning method, characterized in that: include: Acquire initial constraint information of the target device, and generate an unconstrained optimization equation based on the initial constraint information of the target device; Obtaining the current operating status of the target device and the current operating status of the obstacle; Based on a preset G2O solver, determining a target local path of the target device within a preset driving range according to the current operating state of the target device, the current operating state of the obstacle and the unconstrained optimization equation; Among them, the G2O solver is used to generate at least one local path based on the current operating state of the target device, the current operating state of the obstacle and the unconstrained optimization equation, determine the evaluation value of each local path according to preset rules, and determine the local path with the highest evaluation value as the target local path.

2. The method according to claim 1, characterized in that The initial constraint information includes kinematic constraint information of the target device, speed and acceleration constraint information, distance constraint information from obstacles, and running time constraint information; The unconstrained optimization equation is a minimization equation that performs weighted summation of the kinematic constraint information of the target device, the speed and acceleration constraint information, the distance constraint information from the obstacle, and the running time constraint information.

3. The method according to claim 1, characterized in that Detection sensors are arranged around the target device, wherein the detection sensors are used to collect the current operating status of obstacles in various directions of the target device, wherein the current operating status of the obstacles includes the speed, turning angle and distance of the obstacles from the target device.

4. The method according to claim 1, characterized in that The step of calculating the evaluation value of each local path includes: The evaluation value of each local path is calculated based on the parameter information of the local path and the weight of each parameter information, wherein the parameter information of the local path includes at least one of the length of the local path, the road width, the number of turns, and the flatness of the road surface.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: A current cost map of the target device is obtained, and feasibility verification of the target local path is performed based on the current cost map.

6. The method according to claim 1, characterized in that Obtain the current costmap of the target device, including: Obtaining size information and distance information of obstacles of the target device; The obstacles are rendered on a grid map according to the size information and distance information of each obstacle to generate a current cost map.

7. The method according to claim 6, characterized in that The target local path consists of multiple location points wherein the feasibility verification of the target local path based on the current cost map comprises: Adding the position points in the target local path to the current cost map; When any position point in the target partial path overlaps with the obstacle, it is determined that the target partial path is not feasible.

8. The method according to claim 7, characterized in that Before performing feasibility verification on the target local path based on the current cost map, the method further includes: Linear interpolation is performed on the target local path.

9. A local path planning device, characterized in that: include: An optimization equation determination method is used to obtain initial constraint information of a target device and generate an unconstrained optimization equation based on the initial constraint information of the target device; An operating status acquisition module, used to acquire the current operating status of the target device and the current operating status of the obstacle; A local path determination module is used to determine the target local path of the target device within a preset driving range based on a preset G2O solver, according to the current operating state of the target device, the current operating state of the obstacle and the unconstrained optimization equation; wherein the G2O solver is used to generate at least one local path based on the current operating state of the target device, the current operating state of the obstacle and the unconstrained optimization equation, determine the evaluation value of each local path according to preset rules, and determine the local path with the highest evaluation value as the target local path.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the local path planning method as described in any one of claims 1-8 is implemented.

11. A vehicle, characterized in that: The electronic device according to claim 10 is provided.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the local path planning method as described in any one of claims 1 to 8 is implemented.

Images