WO2022267004A1 - 路径规划方法和装置 - Google Patents

路径规划方法和装置 Download PDF

Info

Publication number
WO2022267004A1
WO2022267004A1 PCT/CN2021/102372 CN2021102372W WO2022267004A1 WO 2022267004 A1 WO2022267004 A1 WO 2022267004A1 CN 2021102372 W CN2021102372 W CN 2021102372W WO 2022267004 A1 WO2022267004 A1 WO 2022267004A1
Authority
WO
WIPO (PCT)
Prior art keywords
vehicle
area
path
passes
end point
Prior art date
Application number
PCT/CN2021/102372
Other languages
English (en)
French (fr)
Inventor
周伟
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to PCT/CN2021/102372 priority Critical patent/WO2022267004A1/zh
Priority to CN202180099625.6A priority patent/CN117546115A/zh
Publication of WO2022267004A1 publication Critical patent/WO2022267004A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions

Definitions

  • the present application relates to the technical field of automatic driving, in particular to a path planning method and device.
  • a self-driving car is a vehicle that can perceive its surrounding environment and navigate without human intervention. It uses radar, laser, ultrasonic, global positioning system (global positioning system, GPS), odometer, computer vision and other technologies to perceive its surrounding environment, and through advanced computing and control systems to identify obstacles and various A signboard, planning a suitable path to control the driving of the vehicle.
  • radar laser, ultrasonic, global positioning system (global positioning system, GPS), odometer, computer vision and other technologies to perceive its surrounding environment, and through advanced computing and control systems to identify obstacles and various A signboard, planning a suitable path to control the driving of the vehicle.
  • the self-driving car as a transport vehicle will repeatedly roll over the road, causing deep ruts to appear on the road.
  • This kind of deep rut will cause the self-driving car to slip when driving, and in severe cases, the self-driving car will lose control and endanger driving safety.
  • the present application provides a path planning method and device, which can reduce the repeated rolling of the road by the self-driving car, reduce the generation of road ruts, and improve the safety of driving.
  • the present application provides a route planning method, the method includes: first obtaining a starting position of a vehicle and an end position of the vehicle. Then the number of times of passing through each first area in the plurality of first areas is acquired. Afterwards, path planning is performed according to the number of passes in each of the first areas in the plurality of first areas, and a passing path from the starting point to the end point is determined, and the passing path includes a path from the starting point to the end point. The second region the location passes through. Wherein, the less the number of passes in the first area is, the greater the probability that the first area is planned as the second area during the path planning.
  • the first area is a passable area in a target scene, and the target scene is a scene where the vehicle is located.
  • the optimal passing path (generally the shortest passing path) from the starting point of the vehicle to the ending point of the vehicle is determined as the planning path.
  • the route planning method provided by the present application, during route planning, areas with too few times of passing or areas that have not been traveled have a higher probability of being selected as driving areas, and areas with too many times of passing have a lower probability of being selected as driving areas.
  • the number of passes in each area is similar, reducing the probability of a certain path being repeatedly selected, and also reducing the probability of a certain area being repeatedly crushed by an autonomous vehicle, alleviating the generation of road ruts, and improving driving safety.
  • the acquiring the number of passes in each of the multiple first areas includes: acquiring first information, where the first information includes a plurality of driving trajectories, and the plurality of driving trajectories Each driving trajectory in the trajectory includes at least one first area; according to the plurality of driving trajectories, the number of times of passing through each first area in the plurality of first areas is determined.
  • the first information further includes a plurality of vehicle status information
  • the vehicle status information is used to indicate at least one of whether the vehicle is loaded with goods and whether the vehicle is a cargo vehicle, the plurality of vehicle status information One-to-one correspondence with the plurality of driving trajectories.
  • the determining the number of passes in each of the multiple first areas according to the multiple driving trajectories includes: determining the target driving time according to the multiple driving trajectories Trajectory, the target driving trajectory is the driving trajectory of the vehicle when the vehicle is loaded with goods in the multiple driving trajectories or the driving trajectory of the cargo-carrying vehicle; according to the target driving trajectory, each of the plurality of first areas is determined The number of passes in an area.
  • Cargo vehicles such as ore transport vehicles, oil tank trucks, dump trucks, dirt trucks, slag trucks, cement tank trucks, mixer trucks, etc. It will generate a large load on the road surface. Therefore, when counting the number of passages in each first area, only the number of passages of cargo vehicles in each area may be considered, thereby reducing the amount of statistics and improving the efficiency of counting the number of passages.
  • the performing path planning according to the number of times of passing, and determining the passing route from the starting point to the ending point includes: obtaining vehicle status information; if the vehicle is loaded with goods, Then, path planning is performed according to the number of passes to determine a pass route from the starting point to the end point.
  • the performing path planning according to the number of passes to determine the pass path from the starting point to the end point includes: obtaining vehicle status information; if the vehicle is carrying For vehicles, path planning is performed according to the number of passes to determine a pass path from the starting point to the end point.
  • the performing path planning according to the number of passes to determine the pass path from the starting point to the end point includes: acquiring weight information of the vehicle; if the vehicle If the weight is greater than the first threshold, path planning is performed according to the number of passes to determine a pass path from the starting point to the end point.
  • the weight of the vehicle is greater than the first threshold, it means that the weight of the vehicle is relatively large, and it will generate a large load on the road during driving. Therefore, it is necessary to consider The number of passes in each first area, so that the road loads in each first area are balanced.
  • the performing path planning according to the number of passes, and determining the pass path from the starting point to the end point includes: acquiring environmental information, the environmental information is used to indicate the The environment type of the target scene, the height of the starting point and the end point; if the target scene is a depressed mine and the height of the starting point is lower than the end point, then path planning is performed according to the number of passes to determine from A passing path from the start position to the end position.
  • the vehicle travels from a high place to a low place without a load, and then after loading minerals at the low place, the minerals are transported from the low place to the high place, so the vehicle is traveling from the high place to the low place (hereinafter referred to as When going down), it is unloaded, and from low to high (hereinafter referred to as up), that is, when the height of the starting position of the vehicle is lower than the terminal position of the vehicle, it is heavy load. Since the uplink heavy-duty vehicles will generate a large load on the road surface during driving, when planning the path of the uplink heavy-duty vehicles, it is necessary to consider the number of passes in each first area, so that the road loads in each first area are balanced.
  • the performing path planning according to the number of passes to determine the pass path from the starting point to the end point includes: obtaining environmental information; if the target scene is a hillside mine and the height of the start point is higher than the end point, then path planning is performed according to the number of passes to determine a passing path from the start point to the end point.
  • the vehicle goes from a low place to a high place without a load, and then after loading the minerals at the high place, the minerals are transported from the high place to the low place, so the vehicle is empty when it goes up, and the starting point of the vehicle when it goes down
  • the height of the position is higher than the end position of the vehicle for heavy load. Since the downlink heavy-duty vehicles will generate a large load on the road during driving, when planning the path of the downlink heavy-duty vehicles, it is necessary to consider the number of passes in each first area, so that the road load in each first area is balanced.
  • the method further includes: generating a second passing path according to the passing path, and there is a lateral deviation between the second passing path and the passing path.
  • the present application provides a path planning device, which includes: a processor and a memory coupled to the processor; the processor is used to obtain the starting position of the vehicle and the end position of the vehicle; The number of passes of each first area in a first area, the first area is a passable area in the target scene, and the target scene is the scene where the vehicle is located; path planning is carried out according to the number of passes, and it is determined A passing path from the starting point to the ending point, the passing path includes a second area passing through from the starting point to the ending point, wherein the less the number of passes in the first area is, the When the path is planned, the probability that the first area is planned as the second area is higher.
  • the processor is specifically configured to: acquire first information, where the first information includes a plurality of driving trajectories, and each driving trajectory in the plurality of driving trajectories includes at least one first an area; according to the plurality of driving trajectories, determining the number of times of passing each first area in the plurality of first areas.
  • the first information further includes a plurality of vehicle status information
  • the vehicle status information is used to indicate at least one of whether the vehicle is loaded with goods and whether the vehicle is a cargo vehicle, the plurality of vehicle status information One-to-one correspondence with the plurality of driving trajectories.
  • the processor is further specifically configured to: according to the multiple driving trajectories, determine the number of times of passing each of the multiple first areas, including: According to the multiple driving trajectories, the target driving trajectory is determined, and the target driving trajectory is the driving trajectory when the vehicle is loaded with goods in the multiple driving trajectories or the driving trajectory of the cargo-carrying vehicle; according to the target driving trajectory, determine the The number of passes in each first area among the plurality of first areas.
  • the processor is further specifically configured to: acquire vehicle status information; if the vehicle is loaded with cargo, perform route planning according to the number of passes to determine from the starting point to the destination The path of travel for the location.
  • the processor is further specifically configured to: obtain vehicle status information; if the vehicle is a cargo vehicle, perform route planning according to the number of passes to determine the destination from the starting point to the The path of travel to the destination location.
  • the processor is further specifically configured to: obtain weight information of the vehicle; if the weight of the vehicle is greater than a first threshold, perform path planning according to the number of passes A passing path from the starting point to the end point.
  • environment information is obtained, and the environment information is used to indicate the environment type of the target scene, the height of the starting point and the height of the end point; if the target scene is a sunken mine and If the height of the start point is lower than the end point, path planning is performed according to the number of passes to determine a passing path from the start point to the end point.
  • environmental information is obtained; if the target scene is a hillside mine and the height of the starting point is higher than the end point, path planning is performed according to the number of passes to determine from the starting point to the The path of travel at the end location.
  • the processor is further configured to: generate a second passing path according to the passing path, where there is a lateral deviation between the second passing path and the passing path.
  • the embodiment of the present application also provides a path planning device, which includes: at least one processor, and when the at least one processor executes program codes or instructions, the above first aspect or any possible implementation thereof can be realized method described in the method.
  • the path planning device may further include at least one memory, and the at least one memory is used to store the program code or instruction.
  • the embodiment of the present application further provides a chip, including: an input interface, an output interface, and at least one processor.
  • the chip also includes a memory.
  • the at least one processor is used to execute the code in the memory, and when the at least one processor executes the code, the chip implements the method described in the above first aspect or any possible implementation thereof.
  • the aforementioned chip may also be an integrated circuit.
  • the embodiment of the present application further provides a terminal, where the terminal includes the above-mentioned path planning device or the above-mentioned chip.
  • the terminal is a vehicle.
  • the present application further provides a computer-readable storage medium for storing a computer program, and the computer program includes a method for realizing the above-mentioned first aspect or any possible implementation thereof.
  • the embodiments of the present application further provide a computer program product including instructions, which, when run on a computer, enable the computer to implement the method described in the above-mentioned first aspect or any possible implementation thereof.
  • the path planning method, path planning device, computer storage medium, computer program product, chip, and terminal provided in this embodiment are all used to execute the path planning method provided above. Therefore, the beneficial effects that it can achieve can refer to the above The beneficial effects of the provided path planning method will not be repeated here.
  • FIG. 1 is a schematic diagram of a target scene provided by an embodiment of the present application.
  • FIG. 2 is another schematic diagram of the target scene provided by the embodiment of the present application.
  • FIG. 3 is a schematic diagram of a path provided by an embodiment of the present application.
  • FIG. 4 is a schematic structural diagram of a vehicle provided in an embodiment of the present application.
  • FIG. 5 is a schematic flowchart of a path planning method provided in an embodiment of the present application.
  • FIG. 6 is another schematic diagram of the target scene provided by the embodiment of the present application.
  • FIG. 7 is a schematic diagram of a second passage path provided by an embodiment of the present application.
  • FIG. 8 is a schematic diagram of another path provided by the embodiment of the present application.
  • FIG. 9 is a schematic structural diagram of a path planning device provided in an embodiment of the present application.
  • FIG. 10 is a schematic structural diagram of another path planning device provided by the embodiment of the present application.
  • FIG. 11 is a schematic structural diagram of a chip provided by an embodiment of the present application.
  • first and second in the specification and drawings of the present application are used to distinguish different objects, or to distinguish different processes for the same object, rather than to describe a specific sequence of objects.
  • transport vehicles such as ore transport vehicles, oil tank trucks, dump trucks, earth-pulling trucks, slag trucks, cement tank trucks, mixer trucks, etc.
  • transport vehicles are relatively fixed Cargo transportation on the route.
  • Using self-driving cars as transportation vehicles in these scenarios can reduce overall operating costs and improve transportation efficiency on the one hand, and ensure the safety of transportation personnel on the other.
  • FIG. 1 shows a map of a certain scene
  • blank grids are passable areas in the scene, which may also be referred to as first areas
  • black grids are impassable areas in the scene.
  • the self-driving car when the self-driving car needs to drive from area A (fifth row, first column) to B area (fifth row, ninth column) in Figure 1, the self-driving car will plan to drive from area A to area B.
  • the shortest path that is, the path shown in FIG. 2
  • Subsequent vehicles will repeatedly roll over the path every time they travel from area A to area B, causing deep ruts to appear on the road.
  • lateral random variables can be introduced in the process of vehicle driving, so that the path of the vehicle passing through a certain area is random each time.
  • the vehicle passes through a certain area for the first time ( Figure 2 The area in the fifth row and the third column in ) is the route 1 in FIG. 3 .
  • a lateral random variable can be introduced into path 1 to generate path 2 in Fig. 3 .
  • a lateral random variable can be introduced into path 1 to generate path 3 in Fig.
  • the planned path is always the path in Figure 2), so that the vehicle will always pass through the area in the best path (as shown in Figure 2, the area of the fifth row, the first column to the fifth row, the ninth column), Even if the traffic path of the vehicle is shifted laterally when the vehicle passes through these areas, it is still difficult to prevent the vehicle from repeatedly rolling over these areas, causing deep ruts to appear on the roads in these areas.
  • the embodiment of the present application provides a path planning method, which can reduce the repeated rolling of the road by the automatic driving vehicle, alleviate the generation of road ruts, and improve the safety of driving.
  • the path planning method can be applied to the path planning device provided in this application.
  • the path planning device may be a vehicle 100 or a network device.
  • the aforementioned network devices include but are not limited to mobile data centers (Mobile Data Center, MDC), base stations, servers, and server clusters.
  • MDC Mobile Data Center
  • base stations Base stations
  • servers servers
  • server clusters server clusters
  • Fig. 4 is a functional block diagram of the vehicle 100 provided by the embodiment of the present application.
  • the vehicle 100 is configured in a fully or partially autonomous driving mode.
  • the vehicle 100 can control itself while in the automatic driving mode, and can determine the current state of the vehicle and its surrounding environment through human operation, determine the likely behavior of at least one other vehicle in the surrounding environment, and determine the behavior of the other vehicle.
  • a confidence level corresponding to the likelihood of performing the possible action is used to control the vehicle 100 based on the determined information.
  • the vehicle 100 While the vehicle 100 is in the autonomous driving mode, the vehicle 100 may be set to operate without human interaction.
  • Vehicle 100 may include various subsystems such as travel system 102 , sensor system 104 , planning control system 106 , one or more peripheral devices 108 as well as power supply 110 , computer system 101 and user interface 116 .
  • vehicle 100 may include more or fewer subsystems, and each subsystem may include multiple elements.
  • each subsystem and element of the vehicle 100 may be interconnected by wire or wirelessly.
  • the propulsion system 102 may include components that power the vehicle 100 .
  • propulsion system 102 may include engine 118 , energy source 119 , transmission 120 , and wheels 121 .
  • the engine 118 may be an internal combustion engine, an electric motor, an air compression engine or other types of an engine or a combination of multiple engines, where the combination of various engines may include, for example: a hybrid engine composed of a gasoline engine and an electric motor , a hybrid engine consisting of an internal combustion engine and an air compression engine.
  • Engine 118 converts energy source 119 into mechanical energy.
  • Examples of energy source 119 include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other sources of electrical power. Energy source 119 may also provide energy to other systems of vehicle 100 .
  • Transmission 120 may transmit mechanical power from engine 118 to wheels 121 .
  • Transmission 120 may include a gearbox, a differential, and drive shafts.
  • the transmission 120 may also include other devices, such as clutches.
  • drive shafts may include one or more axles that may be coupled to one or more wheels 121 .
  • the sensor system 104 may include several sensors that sense information about the vehicle 100 itself and the environment surrounding the vehicle 100 .
  • the sensor system 104 may include a positioning system 122 (the positioning system may be a global positioning system (global positioning system, GPS), or a Beidou system or other positioning systems), an inertial measurement unit (inertial measurement unit, IMU) 124, a radar 126 , laser range finder 128 , camera 130 , computer vision system 138 and sensor fusion algorithm 140 .
  • the sensor system 104 may also include sensors of interior systems of the vehicle 100 (eg, interior air quality monitor, fuel gauge, oil temperature gauge, etc.). Sensor data from one or more of these sensors can be used to detect the object to be detected and its corresponding properties (position, shape, orientation, velocity, etc.). Such detection and identification is a critical function for safe operation of the vehicle 100 .
  • the global positioning system 122 may be used to estimate the geographic location of the vehicle 100 .
  • the IMU 124 is used to sense changes in position and orientation of the vehicle 100 based on inertial acceleration.
  • IMU 124 may be a combination accelerometer and gyroscope.
  • the radar 126 may utilize radio signals to sense objects in the environment surrounding the vehicle 100 .
  • radar 126 may be used to sense the velocity and/or direction of travel of objects.
  • the laser range finder 128 may utilize laser light to sense objects in the environment of the vehicle 100 .
  • laser rangefinder 128 may include one or more laser sources, a laser scanner, and one or more detectors, among other system components.
  • Camera 130 may be used to capture multiple images of the surrounding environment of vehicle 100 .
  • Camera 130 may be a still camera or a video camera.
  • Computer vision system 138 is operable to process and analyze images captured by camera 130 in order to identify objects and/or features in the environment surrounding vehicle 100 . Such objects and/or features may include traffic signals, road boundaries, and obstacles.
  • the computer vision system 138 may use object recognition algorithms, Structure from Motion (SFM) algorithms, video tracking, and other computer vision techniques. In some embodiments, computer vision system 138 may be used to map the environment, track objects, estimate the velocity of objects, and the like.
  • SFM Structure from Motion
  • the planning control system 106 is designed to control the operation of the vehicle 100 and its components. Planning control system 106 may include various elements including steering system 132 , accelerator 134 , braking unit 136 , route control system 142 , and obstacle avoidance system 144 .
  • the forward direction of the vehicle 100 can be adjusted by operating the steering system 132 .
  • the steering system 132 For example in one embodiment it could be a steering wheel system.
  • the throttle 134 is used to control the operating speed of the engine 118 and thus the speed of the vehicle 100 .
  • the braking unit 136 is used to control the deceleration of the vehicle 100 .
  • the braking unit 136 may use friction to slow the wheels 121 .
  • the brake unit 136 can convert the kinetic energy of the wheel 121 into electric current.
  • the braking unit 136 may also take other forms to slow down the wheels 121 to control the speed of the vehicle 100 .
  • the route planning system 142 is used to determine the driving route of the vehicle 100 .
  • route planning system 142 may combine data from sensors 138 , GPS 122 and one or more predetermined maps to plan a driving route for vehicle 100 that avoids potential obstacles in the environment.
  • the control system 144 is used to generate control quantities of accelerator, brake and steering angle according to the driving route/trajectory output by the route planning system, so as to control the steering system 132 , the accelerator 134 and the braking unit 136 .
  • planning control system 106 may additionally or alternatively include components other than those shown and described. Alternatively, some of the components shown above may be reduced.
  • Vehicle 100 interacts with external sensors, other vehicles, other computer systems, or users via peripherals 108 .
  • Peripherals 108 may include wireless communication system 146 , on-board computer 148 , microphone 150 and/or speaker 152 .
  • peripheral device 108 provides a means for a user of vehicle 100 to interact with user interface 116 .
  • on-board computer 148 may provide information to a user of vehicle 100 .
  • the user interface 116 may also operate the on-board computer 148 to receive user input.
  • the on-board computer 148 can be operated via a touch screen.
  • peripheral devices 108 may provide a means for vehicle 100 to communicate with other devices located within the vehicle.
  • microphone 150 may receive audio (eg, voice commands or other audio input) from a user of vehicle 100 .
  • speaker 152 may output audio to a user of vehicle 100 .
  • Wireless communication system 146 may communicate wirelessly with one or more devices, either directly or via a communication network.
  • the wireless communication system 146 can use third generation mobile communication technology (3th generation mobile communication technology, 3G) communication, such as code division multiple access (code division multiple access, CDMA), global system for mobile communications (global system for mobile communications, GSM), or the fourth generation mobile communication technology (4th generation mobile communication technology, 4G) communication, such as LTE (long term evolution, long-term evolution).
  • the fifth generation mobile communication technology (5th generation mobile communication technology, 5G) communication.
  • the wireless communication system 146 can utilize wireless fidelity (wireless fidelity, WiFi) to communicate with a wireless local area network (wireless local area network, WLAN).
  • the wireless communication system 146 may communicate directly with the device using an infrared link, Bluetooth, or Zigbee.
  • Other wireless protocols such as various vehicle communication systems, for example, wireless communication system 146 may include one or more dedicated short range communications (DSRC) devices, which may include public and/or private data communications.
  • DSRC dedicated short range communications
  • the power supply 110 may provide power to various components of the vehicle 100 .
  • the power source 110 may be a rechargeable lithium-ion or lead-acid battery.
  • One or more packs of such batteries may be configured as a power source and provide power to various components of the vehicle 100 .
  • power source 110 and energy source 119 may be implemented together, such as in an all-electric vehicle.
  • Computer system 101 may include at least one processor 113 executing instructions 115 stored in a non-transitory computer-readable medium such as memory 114 .
  • the computer system 101 may also be a plurality of computing devices that control individual components or subsystems of the vehicle 100 in a distributed manner.
  • Processor 113 may be any conventional processor, such as a commercially available central processing unit (CPU). Alternatively, the processor may be a dedicated device such as an application specific integrated circuit (ASIC) or other hardware-based processor.
  • FIG. 4 functionally illustrates the processor, memory, and other elements of the computer system 101, those of ordinary skill in the art will appreciate that the processor, memory may actually include other multiple components that are not located within the same physical enclosure. processor, or memory.
  • the memory may be a hard drive or other storage medium located in a different housing than the computer system 101 . Accordingly, a reference to a processor will be understood to include references to a collection of processors or memories that may or may not operate in parallel.
  • some components may each have their own processor that only performs calculations related to component-specific functions;
  • subsystems such as the travel system, the sensor system, and the planning control system may also have their own processors, which are used to perform calculations of related tasks of the corresponding subsystems to achieve corresponding functions.
  • the processor can be located remotely from the vehicle and be in wireless communication with the vehicle. In other aspects, some of the processes described herein are executed on a processor disposed within the vehicle, while others are executed by a remote processor, including taking the necessary steps to perform a single maneuver.
  • memory 114 may contain instructions 115 (eg, program logic) executable by processor 113 to perform various functions of vehicle 100 , including those described above.
  • Memory 114 may also contain additional instructions, including sending data to, receiving data from, interacting with, and/or controlling one or more of travel system 102, sensor system 104, planning control system 106, and peripherals 108 instructions.
  • memory 114 may also store other relevant data, such as road maps, route information, the vehicle's position, direction, speed, and other relevant information. Such information may be used by the vehicle 100 or specifically by the computer system 101 during operation of the vehicle 100 in autonomous, semi-autonomous, and/or manual modes.
  • a user interface 116 for providing information to or receiving information from a user of the vehicle 100 .
  • user interface 116 may include one or more input/output devices within set of peripheral devices 108 , such as wireless communication system 146 , onboard computer 148 , microphone 150 , and speaker 152 .
  • Computer system 101 may control functions of vehicle 100 based on input received from various subsystems (eg, travel system 102 , sensor system 104 , and planning control system 106 ) and from user interface 116 .
  • the computer system 101 is operable to provide control over many aspects of the vehicle 100 and its subsystems.
  • one or more of these components described above may be installed separately from or associated with the vehicle 100 .
  • memory 114 may exist partially or completely separate from vehicle 100 .
  • the components described above may be communicatively coupled together in a wired and/or wireless manner.
  • FIG. 4 should not be construed as a limitation to the embodiment of the present application.
  • An autonomous vehicle traveling on a road can identify objects in its surroundings to determine adjustments to the vehicle's trajectory, including adjustments to the vehicle's speed.
  • the aforementioned objects may be other vehicles, traffic control devices, or other types of objects.
  • each identified object may be considered independently, and based on the object's respective characteristics, such as its current velocity, acceleration, distance to the vehicle, etc., used to determine the trajectory plan for the autonomous vehicle, including adjustments to be made speed.
  • a computing device associated with vehicle 100 (such as computer system 101, computer vision system 138 of FIG. , etc.) to predict the behavior of the objects identified above.
  • each identified object is dependent on the behavior of the other, so all identified objects can also be considered together to predict the behavior of a single identified object.
  • the vehicle 100 is able to plan its driving trajectory (including speed) based on the predicted behavior of the above identified objects. And based on this planning result, it is determined for the self-driving car what state the vehicle will need to adjust to (in terms of speed adjustment, such as acceleration, deceleration or stop). During this process, other factors may also be considered to determine the driving trajectory of the vehicle 100 , such as the lateral position of the vehicle 100 on the driving road, the curvature of the road, the proximity of static and dynamic objects, and so on.
  • the computing device may also provide instructions to modify the steering angle of the vehicle 100 such that the autonomous vehicle follows a given trajectory and/or maintains contact with objects in the vicinity of the autonomous vehicle (e.g., , the safe lateral and longitudinal distances of cars in adjacent lanes on the road.
  • objects in the vicinity of the autonomous vehicle e.g., , the safe lateral and longitudinal distances of cars in adjacent lanes on the road.
  • the above-mentioned vehicle 100 can be a car, truck, motorcycle, bus, excavator, sprinkler, lawn mower, recreational vehicle, playground vehicle, construction equipment, tram, golf cart, etc., and the embodiment of the present application does not make a special limited
  • FIG. 5 shows a schematic flowchart of a path planning method provided by an embodiment of the present application, and the method may be applied to the vehicle 100 shown in FIG. 4 .
  • the method includes:
  • the vehicle 100 acquires the starting position of the vehicle 100 and the ending position of the vehicle 100.
  • the vehicle 100 determines the aforementioned start position and the aforementioned end position through a driving instruction.
  • the driving instruction is used to instruct the vehicle 100 to travel from the starting position to the ending position.
  • the vehicle 100 may receive a driving instruction sent by other devices (such as a network device) for instructing the vehicle 100 to travel from area A in FIG. In the area A in FIG. 1 , the end position of the vehicle 100 is in the area B in FIG. 1 .
  • other devices such as a network device
  • the vehicle 100 may upload the starting location and the ending location to the network device after acquiring the starting location and the ending location.
  • the vehicle 100 may upload the starting location and the ending location to the network device through the wireless communication system 146 after obtaining the starting location and the ending location.
  • the vehicle 100 acquires the number of passes in each first area in the plurality of first areas.
  • the first area is a passable area in the target scene.
  • the target scene is the scene where the vehicle 100 is located.
  • the target scene can be a closed park, construction site, mining area, etc.
  • the width of the first region is greater than the tire width of the vehicle.
  • the target scene is the scene shown in FIG. 1, and the first area is the passable area in FIG. 1, that is, the blank grid in FIG. Grid) the number of passes.
  • the vehicle 100 may obtain the first information through the above network device, and then determine the number of times of passing each of the above multiple first areas according to the multiple driving trajectories in the above first information. .
  • the vehicle 100 may directly determine the number of passes in each of the above-mentioned multiple first areas according to the multiple driving trajectories.
  • the first information includes driving track 1, driving track 2 and driving track 3, the vehicle in driving track 1 passes through the first area 1, the first area 2 and the first area 3, and the vehicle in driving track 2 passes through The first area 1, the first area 4, and the first area 5, and the vehicle passing through the first area 2, the first area 5, and the first area 6 in the driving trajectory 3 are taken as an example.
  • the vehicle 100 can determine that the number of times of passing in the first area 1 is 2 times, the number of times of passing in the first area 2 is 2 times, the number of times of passing in the first area 3 is 1 time, and the number of times of passing in the first area 4 can be determined according to the above-mentioned multiple driving trajectories. is 1 time, the number of times of passing in the first area 5 is 2 times, and the number of times of passing in the first area 6 is 1 time.
  • the above-mentioned first information may further include a plurality of pieces of vehicle state information, and the above-mentioned vehicle state information is used to indicate at least one of whether the vehicle carries goods and whether the vehicle is a goods-carrying vehicle.
  • the above-mentioned pieces of vehicle status information are in one-to-one correspondence with the above-mentioned pieces of driving trajectories.
  • the first information includes driving track 1 and vehicle state information 1 corresponding to driving track 1, driving track 2 and vehicle state information 2 corresponding to driving track 2, driving track 3 and vehicle state information 3 corresponding to driving track 3 .
  • the above-mentioned vehicle status information may be the weight information of the vehicle.
  • the weight of the vehicle is greater than the first threshold, it can be determined that the vehicle is loaded with goods; otherwise, when the weight of the vehicle is less than or equal to the first threshold, it can be determined that the vehicle is No cargo loaded.
  • the above vehicle status information may also be tag information of the vehicle, where the tag information may be used to indicate whether the vehicle is a cargo vehicle.
  • tag information can be 0 and 1. When the tag information of the vehicle is 0, it can be determined that the vehicle is a cargo vehicle; on the contrary, when the tag information of the vehicle is 1, it can be determined that the vehicle is a non-cargo vehicle.
  • the vehicle 100 may determine the number of passes in each first area according to the vehicle's driving trajectory when the vehicle is loaded with goods among the multiple driving trajectories included in the first information. For example, the vehicle 100 may determine the number of passes of the vehicle in each first area when the vehicle is loaded with goods as the number of passes of each first area.
  • the vehicle 100 may also determine the number of passes in each first area according to the vehicle's driving trajectory when the vehicle is loaded with cargo and the vehicle's driving trajectory when the vehicle is not loaded with cargo among the multiple driving trajectories included in the first information. For example, the vehicle 100 may determine the weighted average of the number of times the vehicle passes through each first area when it is loaded with goods and the number of times when the vehicle does not carry goods in each first area as the number of times it passes through each first area. Wherein, the weight of the number of passes when the vehicle is loaded with cargo is higher than the weight of the number of passes when the vehicle is not loaded with cargo.
  • the vehicle 100 may determine the number of passes in each first area according to the driving track of the cargo vehicle in each first area among the multiple driving trajectories included in the first information. For example, the vehicle 100 may determine the number of passing times of the cargo vehicle in each first area as the number of passing times of each first area.
  • the vehicle 100 may also determine the number of passes in each first area according to the driving trajectories of cargo vehicles and the driving trajectories of non-cargo vehicles among the multiple driving trajectories included in the first information. For example, the vehicle 100 may determine the weighted average of the passing times of cargo vehicles and the passing times of non-cargo vehicles in each first area as the passing times of each first area.
  • the load on the road surface will be greater when the truck is running. load. Therefore, when counting the number of times of passage in each first area, it is necessary to count the number of times of passage of cargo vehicles and the number of passages of non-cargo vehicles in each first area, and calculate the number of times of passage of cargo-carrying vehicles and the number of passages of non-cargo vehicles. When weighting the number of passing times to calculate the number of passing times, the passing times of the trucks are given a higher weight to ensure the accuracy of the counting of the passing times.
  • the network device may determine, according to the multiple driving trajectories in the first information, the number of passes in each of the multiple first areas.
  • the vehicle 100 performs route planning according to the number of times of passing, and determines a passing route from the starting point to the ending point.
  • the passage path includes a second area passing from the starting point to the ending point.
  • the second area includes the area in the fifth row and the second column in FIG.
  • the probability of the first area being planned as the second area during the path planning is greater. Conversely, if the number of times of passing through the first area is greater, the probability that the first area is planned as the second area during the path planning is smaller.
  • the probability of the first area being selected as the second area is lower than that of other first areas during subsequent route planning.
  • the increase rate of the number of passes in this first area will be lower than that of other first areas, so after a period of time, the number of passes in other first areas will be close to the number of passes in this first area, so there will not be a certain first area.
  • the number of passes in the area is much higher than the number of passes in the other first areas.
  • the probability of this first area being selected as the second area is higher than that of other first areas during subsequent path planning, and accordingly the The number of passes in the first area will also increase faster than other first areas, so after a period of time the number of passes in this first area will be close to the number of passes in other first areas, so there will be no traffic in a certain first area The number of times is much lower than that of the other first zone.
  • the path planning method provided by the embodiment of the present application can balance the number of passages in each first area, make each first area evenly bear the vehicle traffic load, and reduce the situation that a certain area bears too much vehicle traffic load. It also reduces the probability of a certain area being repeatedly rolled over by self-driving cars, alleviates the generation of road ruts, and improves driving safety.
  • the above-mentioned vehicle 100 performs route planning according to the above-mentioned number of passages, and determines the passage route from the above-mentioned starting point to the above-mentioned end point, which may include: if the above-mentioned vehicle 100 is loaded with goods, The system 142 performs path planning according to the above-mentioned number of passes, and determines the pass-through path from the above-mentioned start point to the above-mentioned end point. Conversely, if the vehicle 100 is not loaded with cargo, the route planning system 142 of the vehicle 100 determines the path from the starting point to the ending point as the shortest path between the starting point and the ending point.
  • the vehicle 100 may determine whether the vehicle 100 is loaded with cargo according to the starting position and the ending position. For example, if the starting point is an excavation area and the end point is an unloading area, the vehicle 100 may determine that the vehicle 100 is loaded with goods. For another example, if the start point is an unloading area and the end point is an excavation area, the vehicle 100 may determine that the vehicle 100 is not loaded with cargo.
  • the vehicle 100 may determine whether the vehicle 100 carries cargo according to the environment information, the starting location and the ending location. For example, if the environmental information indicates that the environment where the vehicle is located is a hillside mine and the height of the starting point is higher than the end point, it can be determined that the vehicle 100 is loaded with cargo; loaded with cargo. For another example, if the environment information indicates that the environment where the vehicle is located is a sunken mine and the height of the starting point is lower than the end point, it can be determined that the vehicle 100 is loaded with cargo; No cargo loaded.
  • the above-mentioned vehicle 100 performs path planning according to the above-mentioned number of passes, and determines the passage path from the above-mentioned starting point to the above-mentioned end point, which may include: if the above-mentioned vehicle 100 is a cargo vehicle, the above-mentioned vehicle 100 The route planning system 142 performs route planning according to the above-mentioned number of times of passing, and determines a passing route from the above-mentioned start point to the above-mentioned end point. Conversely, if the vehicle 100 is a non-cargo vehicle, the route planning system 142 of the vehicle 100 determines that the path from the starting point to the ending point is the shortest path between the starting point and the ending point.
  • the trucks will generate a large load on the road during driving, so when planning the route of the trucks, it is necessary to consider the number of passes in each first area, so that the road load of each first area balanced.
  • Non-cargo vehicles will not generate a large load on the road surface during driving, so when planning routes for non-cargo vehicles, only the travel distance of each path can be considered.
  • the vehicle 100 performs route planning according to the number of times of passing, and determines the passing route from the starting position to the ending position, including: the route planning system 142 of the vehicle 100 first calculates the route according to the starting position and the ending position Determine a plurality of passages and determine the number of passes of each passage in the plurality of passages, and then determine that the passage from the above-mentioned starting position to the above-mentioned end point is the passage with the least number of passes among the above-mentioned multiple passages.
  • the vehicle 100 needs to go from area A to area B in FIG. 6 .
  • the route planning system 142 of the vehicle 100 first determines the multiple passing paths from the A region to the B region (for the sake of brevity, FIG. 6 only schematically shows three paths, and the actual number of paths may be more than three), and then determines the The number of passages of each passage in the passages, and finally determine the passage from area A to area B as the passage with the least number of passages among the above multiple passages.
  • the route planning system 142 of the vehicle 100 can use various methods (such as Dijkstra algorithm, heuristic search (A*) algorithm, or rapidly exploring random trees (rapidly exploring random trees, RRT) Algorithm) Determine a plurality of passing paths according to the above-mentioned start position and the above-mentioned end position.
  • various methods such as Dijkstra algorithm, heuristic search (A*) algorithm, or rapidly exploring random trees (rapidly exploring random trees, RRT) Algorithm
  • the passing times of each passing path may be an average value of the passing times of multiple first areas that each path passes through.
  • the travel path 1 passes through the first area 1 , the first area 2 , the first area 3 and the first area 4 .
  • the number of times of travel in the first area 1 is 20
  • the number of times of travel in the first area 2 is 16
  • the number of times of travel in the first area 3 is 12
  • other devices can be grouped for each vehicle (for example, one excavator and six ore transport vehicles can be grouped), and the vehicles in the same group The start position and end position of the drive are the same.
  • the vehicle 100 may send the above-mentioned passing paths to other vehicles in the formation after obtaining the above-mentioned passing paths. In this way, it is possible for multiple vehicles in the same formation to determine the passing paths of all the vehicles in the formation only by performing path planning on one of them before each driving, which improves the efficiency of formation path planning.
  • vehicle formation A1 includes vehicle 1 , vehicle 2 , vehicle 3 , vehicle 4 , vehicle 5 and vehicle 6 .
  • Vehicle 1 sends the travel route to Vehicle 2, Vehicle 3, Vehicle 4, Vehicle 5, and Vehicle 6 after determining the travel route from the start location to the destination location.
  • vehicle 2 , vehicle 3 , vehicle 4 , vehicle 5 and vehicle 6 can directly use the passing route sent by vehicle 1 .
  • the path planning method provided in the embodiment of the present application may also be executed by a network device.
  • the network device may receive the starting position and the ending position sent by the vehicle 100, and then obtain the number of times of passing through each first area in the plurality of first areas, and then perform path planning according to the number of passing times, and determine the distance from the starting point to the above-mentioned The path of travel at the end location.
  • the network device may also receive formation information sent by the vehicle 100 through the wireless communication system 146 .
  • the network device can plan a route for any vehicle in the same group to determine the passing path from the starting point to the ending point, and then send the above passing path to all the vehicles in the grouping.
  • the vehicle 100 may generate a second passing route according to the above passing route. Wherein, there is a lateral deviation between the second passing path and the aforementioned passing path.
  • the vehicle 100 may generate the second passing path shown on the right side of FIG. 7 according to the above passing path shown on the left side of FIG. 7 .
  • the vehicle 100 may laterally offset the paths in each second area of the above-mentioned passing paths to obtain the second passing paths.
  • the above passing route is the route shown in FIG. 2 as an example.
  • the second area passed by the path includes the area in the fifth row and the second column, the area in the fifth row and the third column, the area in the fifth row and the fourth column, the area in the fifth row and the fifth column in FIG. The area of the six columns, the area of the fifth row and the seventh column, and the area of the fifth row and the eighth column. Then the vehicle can laterally shift the paths in each of the above-mentioned second areas, and then obtain multiple paths.
  • the passage path in a certain second area in the above passage path is path 1 in Figure 7, and multiple paths can be obtained by laterally offsetting path 1 (such as path 2, path 3, path 4, and path 8 in Fig. 8). 5. Path 6 and path 7), and then one path may be selected as the passage path in the second area in the second passage path.
  • the path with the least number of passes among the multiple paths in each second area may be selected as the pass path of each second area in the second pass path.
  • the number of times of passage of route 1 is 5 times
  • the number of times of passage of route 2 is 4 times
  • the number of times of passage of route 3 is 3 times
  • the number of times of passage of route 4 is 1 time.
  • the number of passing times of route 5 is 3 times
  • the number of passing times of route 6 is 3 times
  • the number of passing times of route 7 is 4 times. It can be seen that route 4 has the least number of times of passing, then route 4 in the second area can be used as the second passing route in the second area.
  • the vehicle 100 may perform smoothing processing on the above passing path.
  • the specific implementation process of smoothing the passing path may refer to the specific implementation process of the existing smoothing process, which will not be repeated here.
  • the above-mentioned passing path can be smoothed by a B-spline curve method.
  • the planning control system 106 of the vehicle 100 can control the travel system 102 to make the vehicle 100 travel from the above-mentioned starting point to the above-mentioned end point according to the above-mentioned passing route.
  • the vehicle 100 can also record its own driving trajectory during driving and send the driving trajectory to the network device through the wireless communication system 146 .
  • the path planning method provided by the embodiment of the present application is introduced in conjunction with Fig. 5, and the path planning device for executing the above path planning method will be described below in conjunction with Fig. 9 and Fig. 10 .
  • the route planning device may be the vehicle 100 in the above method embodiment capable of executing the method performed by the vehicle 100 in the above method.
  • the path planning apparatus may also be the network device in the above method embodiment capable of executing the method performed by the network device in the above method.
  • the path planning device includes hardware and/or software modules corresponding to each function.
  • the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed by hardware or computer software drives hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions in combination with the embodiments for each specific application, but such implementation should not be regarded as exceeding the scope of the present application.
  • the path planning device may be divided into functional modules according to the above method examples.
  • each functional module may be divided corresponding to each function, or two or more functions may be integrated into one processing module.
  • the above integrated modules may be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is schematic, and is only a logical function division, and there may be other division methods in actual implementation.
  • FIG. 9 shows a possible composition diagram of the path planning device involved in the above embodiment.
  • the device 900 may include: a transceiver unit 901 and a processing unit 902, the transceiving unit 901 is used to obtain the start position, the end position and the number of times of each first area in the plurality of first areas in the above-mentioned method embodiment, and the processing unit 902 can implement the method in the above-mentioned embodiment Methods performed by a path planning device, and/or other processes for the techniques described herein.
  • the apparatus 900 may include a processing unit, a storage unit and a communication unit.
  • the processing unit may be used to control and manage the actions of the apparatus 900, for example, may be used to support the apparatus 900 to execute the steps performed by the above-mentioned units.
  • the storage unit may be used to support the device 900 to execute stored program codes, and/or data, and the like.
  • the communication unit may be used to support communication of the apparatus 900 with other devices.
  • the processing unit may be a processor or a controller. It can implement or execute the various illustrative logical blocks, modules and circuits described in connection with the present disclosure.
  • the processor can also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of digital signal processing (digital signal processing, DSP) and a microprocessor, and the like.
  • the storage unit may be a memory.
  • the communication unit may be a device that interacts with other electronic devices, such as a radio frequency circuit, a Bluetooth chip, and a Wi-Fi chip.
  • the path planning apparatus involved in this embodiment of the present application may be an apparatus 1000 having the structure shown in FIG. 10 , where the apparatus 1000 includes a processor 1001 and a transceiver 1002 .
  • the transceiver unit 901 and the processing unit 902 in FIG. 9 may be implemented by the processor 1001 .
  • the apparatus 1000 may further include a memory 1003, and the processor 1001 and the memory 1003 communicate with each other through an internal connection path.
  • the relevant functions implemented by the storage unit in FIG. 9 may be implemented by the memory 1003 .
  • the embodiment of the present application also provides a computer storage medium, the computer storage medium stores computer instructions, and when the computer instructions are run on the electronic device, the electronic device executes the above-mentioned related method steps to realize the path planning method in the above-mentioned embodiment .
  • the embodiment of the present application also provides a computer program product.
  • the computer program product When the computer program product is run on a computer, the computer is made to perform the above-mentioned related steps, so as to realize the path planning method in the above-mentioned embodiment.
  • the embodiment of the present application also provides a path planning device, and the device may specifically be a chip, an integrated circuit, a component, or a module.
  • the device may include a connected processor and a memory for storing instructions, or the device may include at least one processor for fetching instructions from an external memory.
  • the processor can execute instructions, so that the chip executes the path planning methods in the above method embodiments.
  • FIG. 11 shows a schematic structural diagram of a chip 1100 .
  • the chip 1100 includes one or more processors 1101 and an interface circuit 1102 .
  • the above-mentioned chip 1100 may further include a bus 1103 .
  • the processor 1101 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the path planning method above may be completed by an integrated logic circuit of hardware in the processor 1101 or instructions in the form of software.
  • the above-mentioned processor 1101 may be a general-purpose processor, a digital signal processing (digital signal processing, DSP) device, an integrated circuit (application specific integrated circuit, ASIC), a field-programmable gate array (field-programmable gate array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
  • DSP digital signal processing
  • ASIC application specific integrated circuit
  • FPGA field-programmable gate array
  • a general-purpose processor may be a microprocessor, or the processor may be any conventional processor, or the like.
  • the interface circuit 1102 can be used for sending or receiving data, instructions or information.
  • the processor 1101 can use the data, instructions or other information received by the interface circuit 1102 to process, and can send the processing completion information through the interface circuit 1102 .
  • the chip further includes a memory, which may include a read-only memory and a random access memory, and provides operation instructions and data to the processor.
  • a portion of the memory may also include non-volatile random access memory (NVRAM).
  • NVRAM non-volatile random access memory
  • the memory stores executable software modules or data structures
  • the processor can execute corresponding operations by calling operation instructions stored in the memory (the operation instructions can be stored in the operating system).
  • the chip may be used in the path planning device, the vehicle 100 or the network device involved in the embodiment of the present application.
  • the interface circuit 1102 may be used to output an execution result of the processor 1101 .
  • processor 1101 and the interface circuit 1102 can be realized by hardware design, software design, or a combination of software and hardware, which is not limited here.
  • the path planning device, computer storage medium, computer program product or chip provided in this embodiment are all used to execute the corresponding method provided above, therefore, the beneficial effects it can achieve can refer to the corresponding method provided above The beneficial effects of the method will not be repeated here.
  • sequence numbers of the above-mentioned processes do not mean the order of execution, and the execution order of the processes should be determined by their functions and internal logic, and should not be used in the embodiments of the present application.
  • the implementation process constitutes any limitation.
  • the disclosed systems, devices and methods may be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the above units is only a logical function division. In actual implementation, there may be other division methods.
  • multiple units or components can be combined or can be Integrate into another system, or some features may be ignored, or not implemented.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.
  • the units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, each unit may exist separately physically, or two or more units may be integrated into one unit.
  • the technical solution of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the above-mentioned methods in various embodiments of the present application.
  • the aforementioned storage medium includes: U disk, mobile hard disk, read only memory (Read Only Memory, ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other various media that can store program codes.

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种路径规划方法和装置，涉及自动驾驶技术领域，能够减少自动驾驶汽车对道路的反复碾压，减少道路车辙的生成，提高行车的安全性。该方法包括：先获取车辆的起点位置和该车辆的终点位置（S501）。然后获取多个第一区域中每个第一区域的通行次数（S502）。之后根据这多个第一区域中每个第一区域的通行次数进行路径规划，确定从起点位置到达终点位置的通行路径（S503），通行路径包括从起点位置到达终点位置经过的第二区域。其中，第一区域的通行次数越少，在路径规划时第一区域被规划为第二区域的概率越大。第一区域为目标场景内的可通行区域，目标场景为车辆所在的场景。

Description

路径规划方法和装置 技术领域
本申请涉及自动驾驶技术领域，尤其涉及路径规划方法和装置。
背景技术
自动驾驶汽车，是一种无须人工干预而能够感知其周边环境和导航的车辆。它利用了包括雷达、激光、超声波、全球定位系统(global positioning system，GPS)、里程计、计算机视觉等多种技术来感知其周边环境，通过先进的计算和控制系统，来识别障碍物和各种标识牌，规划合适的路径来控制车辆行驶。
在一些道路相对封闭的场景(如矿山、封闭园区、工地等)中，运输车辆在相对固定的路线上进行货物运输。在这些场景中采用自动驾驶汽车作为运输车辆，可以降低整体作业成本，提高运输效率。
然而，在上述场景中自动驾驶汽车作为运输车辆会对道路反复碾压，使道路上出现较深的车辙。这种较深的车辙会导致自动驾驶汽车在行驶时产生侧滑，严重时会使自动驾驶汽车失去控制，危及行车安全。
发明内容
本申请提供路径规划方法和装置，能够减少自动驾驶汽车对道路的反复碾压，减少道路车辙的生成，提高行车的安全性。
第一方面，本申请提供了路径规划方法，该方法包括：先获取车辆的起点位置和该车辆的终点位置。然后获取多个第一区域中每个第一区域的通行次数。之后根据这多个第一区域中每个第一区域的通行次数进行路径规划，确定从所述起点位置到达所述终点位置的通行路径，所述通行路径包括从所述起点位置到达所述终点位置经过的第二区域。其中，所述第一区域的通行次数越少，在所述路径规划时所述第一区域被规划为所述第二区域的概率越大。所述第一区域为目标场景内的可通行区域，所述目标场景为所述车辆所在的场景。
相较于现有路径规划方法在路径规划时，将从车辆的起点位置到车辆的终点位置的最优通行路径(一般为最短通行路径)确定为规划路径。本申请提供的路径规划方法在路径规划时，通行次数过少的或未行驶过的区域被选为行驶区域的概率较高，通行次数过多的区域被选为行驶区域的概率较低。从而使得各区域的通行次数相近，降低了某一通行路径被重复选取的概率，也减少了某一区域被自动驾驶汽车反复碾压的概率，缓解了道路车辙的生成，提高行车的安全性。
在一种可能的实现方式中，所述获取多个第一区域中每个第一区域的通行次数，包括：获取第一信息，所述第一信息包括多条行车轨迹，所述多条行车轨迹中的每条行车轨迹包含至少一个第一区域；根据所述多条行车轨迹，确定所述多个第一区域中每个第一区域的 通行次数。
可选地，所述第一信息还包括多个车辆状态信息，所述车辆状态信息用于指示车辆是否载有货物和车辆是否为载货车辆中的至少一项，所述多个车辆状态信息与所述多条行车轨迹一一对应。
在一种可能的实现方式中，所述根据所述多条行车轨迹，确定所述多个第一区域中每个第一区域的通行次数，包括：根据所述多条行车轨迹，确定目标行车轨迹，所述目标行车轨迹为所述多条行车轨迹中车辆载有货物时的行车轨迹或载货车辆的行驶轨迹；根据所述目标行车轨迹，确定所述多个第一区域中每个第一区域的通行次数。
可以理解的是，载有货物的车辆相较于未载有货物的车辆在行驶过程中会对路面产生较大负荷。因此，在统计每个第一区域的通行次数可以仅考虑每个第一区域中车辆载有货物时的行车轨迹，以减少统计第一区域的通行次数时的统计量，从而提高统计第一区域的通行次数时的统计效率。
载货车辆(如矿石运输车、油罐车、泥头车、拉土车、运渣车、水泥罐车、搅拌车等)相较于非载货车辆(如轿车、摩托车等)在行驶过程中会对路面产生较大负荷。因此，在统计各第一区域的通行次数可以仅考虑各区域中载货车辆的通行次数，从而减少统计量，提高统计通行次数的效率。
在一种可能的实现方式中，所述根据所述通行次数进行路径规划，确定从所述起点位置到达所述终点位置的通行路径，包括：获取车辆状态信息；若所述车辆载有货物，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径。
可以理解的是，载有货物的车辆在行驶过程中会对路面产生较大负荷，因此在对载有货物的车辆进行路径规划时，需要考虑各第一区域的通行次数，以使得各第一区域的路面负荷均衡。
在另一种可能的实现方式中，所述根据所述通行次数进行路径规划，确定从所述起点位置到达所述终点位置的通行路径，包括：获取车辆状态信息；若所述车辆为载货车辆，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径。
可以理解的是，载货车辆在行驶过程中会对路面产生较大负荷，因此在对载货车辆进行路径规划时，需要考虑各第一区域的通行次数，以使得各第一区域的路面负荷均衡。
在又一种可能的实现方式中，所述根据所述通行次数进行路径规划，确定从所述起点位置到达所述终点位置的通行路径，包括：获取所述车辆的重量信息；若所述车辆的重量大于第一阈值，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径。
需要说明的是，若车辆的重量大于第一阈值说明该车辆的重量较大，在行驶过程中会对路面产生较大负荷，因此在对重量大于第一阈值的车辆进行路径规划时，需要考虑各第一区域的通行次数，以使得各第一区域的路面负荷均衡。
在又一种可能的实现方式中，所述根据所述通行次数进行路径规划，确定从所述起点位置到达所述终点位置的通行路径，包括：获取环境信息，所述环境信息用于指示所述目标场景的环境类型、所述起点位置和所述终点位置的高度；若所述目标场景为凹陷矿且所述起点位置的高度低于终点位置，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径。
可以理解是，凹陷矿环境中，车辆空载由高处前往低处，然后在低处装载矿物后，将矿物由低处运往高处，因此车辆在由高处向低处行驶(以下简称为下行)时为空载，而由低处向高处(以下简称为上行)即车辆的起点位置的高度低于车辆的终点位置时为重载。由于上行重载车辆在行驶过程中会对路面产生较大负荷，因此在对上行重载车辆进行路径规划时，需要考虑各第一区域的通行次数，以使得各第一区域的路面负荷均衡。
在又一种可能的实现方式中，所述根据所述通行次数进行路径规划，确定从所述起点位置到达所述终点位置的通行路径，包括：获取环境信息；若所述目标场景为山坡矿且起点位置的高度高于终点位置，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径。
可以理解是，山坡矿环境中，车辆空载由低处前往高处，然后在高处装载矿物后，将矿物由高处运往低处，因此车辆上行时为空载，而下行即车辆的起点位置的高度高于车辆的终点位置时为重载。由于下行重载车辆在行驶过程中会对路面产生较大负荷，因此在对下行重载车辆进行路径规划时，需要考虑各第一区域的通行次数，以使得各第一区域的路面负荷均衡。
在一种可能的实现方式中，所述方法还包括：根据所述通行路径生成第二通行路径，所述第二通行路径与所述通行路径之间存在横向偏差。
可以理解的，车辆在通过某个区域时会碾压上述区域产生车辙，若该车辆或其他车辆采用相同行驶路径通过上述区域时，会使上述产生相同的车辙，即会使之前产生的车辙加深。而本申请实施例中通过对通行路径进行横向偏移可以使不同车辆或同一车辆在通过同一区域时采用的路径存在横向偏差，即可以使不同车辆或同一车辆在通过同一区域时采用的不同的行驶路径，这样可以避免第一区域内产生较深车辙。
第二方面，本申请提供了一种路径规划装置，该装置包括：处理器和与所述处理器耦合的存储器；所述处理器用于获取车辆的起点位置和所述车辆的终点位置；获取多个第一区域中每个第一区域的通行次数，所述第一区域为目标场景内的可通行区域，所述目标场景为所述车辆所在的场景；根据所述通行次数进行路径规划，确定从所述起点位置到达所述终点位置的通行路径，所述通行路径包括从所述起点位置到达所述终点位置经过的第二区域，其中，所述第一区域的通行次数越少，在所述路径规划时所述第一区域被规划为所述第二区域的概率越大。
在一种可能的实现方式中，所述处理器具体用于：获取第一信息，所述第一信息包括多条行车轨迹，所述多条行车轨迹中的每条行车轨迹包含至少一个第一区域；根据所述多条行车轨迹，确定所述多个第一区域中每个第一区域的通行次数。
可选地，所述第一信息还包括多个车辆状态信息，所述车辆状态信息用于指示车辆是否载有货物和车辆是否为载货车辆中的至少一项，所述多个车辆状态信息与所述多条行车轨迹一一对应。
在一种可能的实现方式中，所述处理器还具体用于：所述根据所述多条行车轨迹，确定所述多个第一区域中每个第一区域的通行次数，包括：根据所述多条行车轨迹，确定目标行车轨迹，所述目标行车轨迹为所述多条行车轨迹中车辆载有货物时的行车轨迹或载货车辆的行驶轨迹；根据所述目标行车轨迹，确定所述多个第一区域中每个第一区域的通行次数。
在一种可能的实现方式中，所述处理器还具体用于：获取车辆状态信息；若所述车辆载有货物，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径。
在另一种可能的实现方式中，所述处理器还具体用于：获取车辆状态信息；若所述车辆为载货车辆，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径。
在又一种可能的实现方式中，所述处理器还具体用于：获取所述车辆的重量信息；若所述车辆的重量大于第一阈值，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径。
在又一种可能的实现方式中，获取环境信息，所述环境信息用于指示所述目标场景的环境类型、所述起点位置和所述终点位置的高度；若所述目标场景为凹陷矿且所述起点位置的高度低于终点位置，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径。
在又一种可能的实现方式中，获取环境信息；若所述目标场景为山坡矿且起点位置的高度高于终点位置，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径。
在一种可能的实现方式中，所述处理器还用于：根据所述通行路径生成第二通行路径，所述第二通行路径与所述通行路径之间存在横向偏差。
第三方面，本申请实施例还提供一种路径规划装置，该装置包括：至少一个处理器，当所述至少一个处理器执行程序代码或指令时，实现上述第一方面或其任意可能的实现方式中所述的方法。
可选地，该路径规划装置还可以包括至少一个存储器，该至少一个存储器用于存储该程序代码或指令。
第四方面，本申请实施例还提供一种芯片，包括：输入接口、输出接口、至少一个处理器。可选地，该芯片还包括存储器。该至少一个处理器用于执行该存储器中的代码，当该至少一个处理器执行该代码时，该芯片实现上述第一方面或其任意可能的实现方式中所述的方法。
可选地，上述芯片还可以为集成电路。
第五方面，本申请实施例还提供一种终端，该终端包括上述路径规划装置或上述芯片。示例地，该终端为车辆。
第六方面，本申请还提供一种计算机可读存储介质，用于存储计算机程序，该计算机程序包括用于实现上述第一方面或其任意可能的实现方式中所述的方法。
第七方面，本申请实施例还提供一种包含指令的计算机程序产品，当其在计算机上运行时，使得计算机实现上述第一方面或其任意可能的实现方式中所述的方法。
本实施例提供的路径规划方法、路径规划装置、计算机存储介质、计算机程序产品、芯片和终端均用于执行上文所提供的路径规划方法，因此，其所能达到的有益效果可参考上文所提供的路径规划方法中的有益效果，此处不再赘述。
附图说明
图1为本申请实施例提供的目标场景的一种示意图；
图2为本申请实施例提供的目标场景的另一种示意图；
图3为本申请实施例提供的一种路径的示意图；
图4为本申请实施例提供的车辆的结构示意图；
图5为本申请实施例提供的路径规划方法的流程示意图；
图6为本申请实施例提供的目标场景的又一种示意图；
图7为本申请实施例提供的第二通行路径的示意图；
图8为本申请实施例提供的另一种路径的示意图；
图9为本申请实施例提供的一种路径规划装置的结构示意图；
图10为本申请实施例提供的另一种路径规划装置的结构示意图；
图11为本申请实施例提供的芯片的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。基于本申请中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本申请保护的范围。
本申请中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。
本申请的说明书以及附图中的术语“第一”和“第二”等是用于区别不同的对象，或者用于区别对同一对象的不同处理，而不是用于描述对象的特定顺序。
此外，本申请的描述中所提到的术语“包括”和“具有”以及它们的任何变形，意图在于覆盖不排他的包含。例如包含了一系列步骤或单元的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可选地还包括其他没有列出的步骤或单元，或可选地还包括对于这些过程、方法、产品或设备固有的其他步骤或单元。
需要说明的是，本申请实施例的描述中，“示例性地”或者“例如”等词用于表示作例子、例证或说明。本申请实施例中被描述为“示例性地”或者“例如”的任何实施例或设计方案不应被解释为比其他实施例或设计方案更优选或更具优势。确切而言，使用“示例性地”或者“例如”等词旨在以具体方式呈现相关概念。
在本申请的描述中，除非另有说明，“多个”的含义是指两个或两个以上。
在矿山、封闭园区、建筑工地等道路相对封闭的场景中，运输车辆(如矿石运输车、油罐车、泥头车、拉土车、运渣车、水泥罐车、搅拌车等)在相对固定的路线上进行货物运输。在这些场景中采用自动驾驶汽车作为运输车辆，一方面可以降低整体作业成本，提高运输效率，另一方面可以保障运输人员的安全。
但是目前，自动驾驶汽车大多会选择最优通行路径(一般为最短通行路径)作为行驶路径，在上述场景中自动驾驶汽车作为运输车辆会对道路(如最优路径的道路)反复碾压，使道路上出现较深的车辙。这种较深的车辙会导致自动驾驶汽车在行驶时产生侧滑，严重时会使自动驾驶汽车失去控制，甚至翻车，危及行车安全。
示例性地，如图1所示，图1示出了某个场景的地图，空白格子为该场景中的可通行区域也可称为第一区域，黑色格子为该场景中的不可通行区域。在该场景中，当自动驾驶汽车需要从图1中的A区域(第五行第一列)行驶至B区域(第五行第九列)时，自动驾驶汽车会规划出A区域行驶至B区域的最短路径(即图2所示的路径)，然后通过该路径由A区域行驶至B区域。后续车辆每次从A区域行驶至B区域就会反复碾压该路径，使道路上出现较深的车辙。
一些技术中，可以在车辆行驶过程中引入横向的随机变量，使车辆在每次通过某区域的通行路径是随机的，如图3所示，车辆在第一次通过某个区域(如图2中的第五行第三列的区域)时的行驶路径为图3中的路径1。车辆在第二次行驶通过该区域时，可以对路径1引入横向的随机变量生成图3中的路径2。车辆在第三次行驶通过该区域时，可以对路径1引入横向的随机变量生成图3中的路径3，但由于车辆在行驶规划时还是采用最优路径(如车辆每次从A区域到B区域时，规划的路径始终为图2中的路径)，这样车辆始终还是要经过最佳路径中的区域(如图2中的第五行第一列的区域至第五行第九列的区域)，即使在车辆通过这些区域时对车辆的通行路径进行横向偏移，还是难以避免车辆反复碾压这些区域，使这些区域道路上出现较深的车辙。
为此，本申请实施例提供了一种路径规划方法，能够减少自动驾驶汽车对道路的反复碾压，缓解了道路车辙的生成，提高行车的安全性。该路径规划方法可适用于本申请提供的路径规划装置。该路径规划装置可以为车辆100或者网络设备。
上述网络设备包括但不限于移动数据中心(Mobile Data Center，MDC)、基站、服务器和服务器集群。
图4是本申请实施例提供的车辆100的功能框图。在一个实施例中，将车辆100配置为完全或部分地自动驾驶模式。例如，车辆100可以在处于自动驾驶模式中的同时控制自身，并且可通过人为操作来确定车辆及其周边环境的当前状态，确定周边环境中的至少一个其他车辆的可能行为，并确定该其他车辆执行可能行为的可能性相对应的置信水平，基于所确定的信息来控制车辆100。在车辆100处于自动驾驶模式中时，可以将车辆100置为在没有和人交互的情况下操作。
车辆100可包括各种子系统，例如行进系统102、传感器系统104、规划控制系统106、一个或多个外围设备108以及电源110、计算机系统101和用户接口116。可选地，车辆100可包括更多或更少的子系统，并且每个子系统可包括多个元件。另外，车辆100的每个子系统和元件可以通过有线或者无线互连。
行进系统102可包括为车辆100提供动力的组件。在一个实施例中，推进系统102可包括引擎118、能量源119、传动装置120和车轮121。其中，引擎118可以是内燃引擎、电动机、空气压缩引擎或其他类型的一种引擎或多种引擎的组合，这里多种引擎的组合，举例来说可以包括：汽油发动机和电动机组成的混动引擎，内燃引擎和空气压缩引擎组成的混动引擎。引擎118将能量源119转换成机械能量。
能量源119的示例包括汽油、柴油、其他基于石油的燃料、丙烷、其他基于压缩气体的燃料、乙醇、太阳能电池板、电池和其他电力来源。能量源119也可以为车辆100的其他系统提供能量。
传动装置120可以将来自引擎118的机械动力传送到车轮121。传动装置120可包括 变速箱、差速器和驱动轴。在一个实施例中，传动装置120还可以包括其他器件，比如离合器。其中，驱动轴可包括可耦合到一个或多个车轮121的一个或多个轴。
传感器系统104可包括感测关于车辆100自身以及车辆100周边的环境的信息的若干个传感器。例如，传感器系统104可包括定位系统122(定位系统可以是全球定位系统(global positioning system，GPS)，也可以是北斗系统或者其他定位系统)、惯性测量单元(inertial measurement unit，IMU)124、雷达126、激光测距仪128、相机130、计算机视觉系统138以及传感器融合算法140。传感器系统104还可包括车辆100的内部系统的传感器(例如，车内空气质量监测器、燃油量表、机油温度表等)。来自这些传感器中的一个或多个传感器数据可用于检测待检测的对象及其相应特性(位置、形状、方向、速度等)。这种检测和识别是车辆100实现安全操作的关键功能。
全球定位系统122可用于估计车辆100的地理位置。IMU124用于基于惯性加速度来感测车辆100的位置和朝向变化。在一个实施例中，IMU124可以是加速度计和陀螺仪的组合。
雷达126可利用无线电信号来感测车辆100的周边环境中的物体。在一些实施例中，除了感测物体以外，雷达126还可用于感测物体的速度和/或行进方向。
激光测距仪128可利用激光来感测车辆100所处环境中的物体。在一些实施例中，激光测距仪128可包括一个或多个激光源、激光扫描器以及一个或多个检测器，以及其他系统组件。
相机130可用于捕捉车辆100的周边环境的多个图像。相机130可以是静态相机或视频相机。
计算机视觉系统138可以操作来处理和分析由相机130捕捉的图像以便识别车辆100周边环境中的物体和/或特征。上述物体和/或特征可包括交通信号、道路边界和障碍物。计算机视觉系统138可使用物体识别算法、运动中恢复结构(Structure from Motion，SFM)算法、视频跟踪和其他计算机视觉技术。在一些实施例中，计算机视觉系统138可以用于为环境绘制地图、跟踪物体、估计物体的速度等等。
规划控制系统106为控制车辆100及其组件的操作。规划控制系统106可包括各种元件，其中包括转向系统132、油门134、制动单元136、路线控制系统142以及障碍物避免系统144。
通过对转向系统132的操作可以调整车辆100的前进方向。例如在一个实施例中可以为方向盘系统。
油门134用于控制引擎118的操作速度并进而控制车辆100的速度。
制动单元136用于控制车辆100减速。制动单元136可使用摩擦力来减慢车轮121。在其他实施例中，制动单元136可将车轮121的动能转换为电流。制动单元136也可采取其他形式来减慢车轮121转速从而控制车辆100的速度。
路线规划系统142用于确定车辆100的行驶路线。在一些实施例中，路线规划系统142可结合来自传感器138、GPS122和一个或多个预定地图的数据为车辆100规划出能避开环境中潜在障碍物的行驶路线。
控制系统144用于根据路线规划系统输出的行驶路线/行驶轨迹生成油门刹车以及转向角的控制量，从而对转向系统132、油门134以及制动单元136进行控制。
当然，在一个实例中，规划控制系统106可以增加或替换地包括除了所示出和描述的那些以外的组件。或者也可以减少一部分上述示出的组件。
车辆100通过外围设备108与外部传感器、其他车辆、其他计算机系统或用户之间进行交互。外围设备108可包括无线通信系统146、车载电脑148、麦克风150和/或扬声器152。
在一些实施例中，外围设备108提供车辆100的用户与用户接口116交互的手段。例如，车载电脑148可向车辆100的用户提供信息。用户接口116还可操作车载电脑148来接收用户的输入。在一种实现方式中，车载电脑148可以通过触摸屏进行操作。在其他情况中，外围设备108可提供用于车辆100与位于车内的其他设备通信的手段。例如，麦克风150可从车辆100的用户接收音频(例如，语音命令或其他音频输入)。类似地，扬声器152可向车辆100的用户输出音频。
无线通信系统146可以直接地或者经由通信网络来与一个或多个设备无线通信。例如，无线通信系统146可使用第三代移动通信技术(3th generation mobile communication technology，3G)通信，例如码分多址(code division multiple access，CDMA)、全球移动通信系统(global system for mobile communications，GSM)，或者第四代移动通信技术(4th generation mobile communication technology，4G)通信，例如LTE(long term evolution，长期演进)。或者第五代移动通信技术(5th generation mobile communication technology，5G)通信。无线通信系统146可利用无线保真(wireless fidelity，WiFi)与无线局域网(wireless localarea network，WLAN)通信。在一些实施例中，无线通信系统146可利用红外链路、蓝牙或紫蜂(Zigbee)与设备直接通信。其他无线协议，例如各种车辆通信系统，例如，无线通信系统146可包括一个或多个专用短程通信(dedicated short range communications，DSRC)设备，这些设备可包括车辆和/或路边台站之间的公共和/或私有数据通信。
电源110可向车辆100的各种组件提供电力。在一个实施例中，电源110可以为可再充电锂离子或铅酸电池。这种电池的一个或多个电池组可被配置为电源并为车辆100的各种组件提供电力。在一些实施例中，电源110和能量源119可一起实现，如全电动车中。
车辆100的部分或所有功能受计算机系统101控制。计算机系统101可包括至少一个处理器113，处理器113执行存储在例如存储器114这样的非暂态计算机可读介质中的指令115。计算机系统101还可以是采用分布式方式控制车辆100的个体组件或子系统的多个计算设备。
处理器113可以是任何常规的处理器，诸如商业可获得的中央处理器(central processing unit，CPU)。替选地，该处理器可以是诸如集成电路(application specific integrated circuit，ASIC)或其他基于硬件的处理器的专用设备。尽管图4功能性的图示了处理器、存储器、以及计算机系统101的其他元件，但是本领域的普通技术人员应该理解该处理器、存储器实际上可以包括不位于相同物理外壳内的其他多个处理器、或存储器。例如，存储器可以是硬盘驱动器或位于不同于计算机系统101的外壳内的其他存储介质。因此，对处理器的引用将被理解为包括对可以并行或不并行操作的处理器或存储器的集合的引用。不同于使用单一的处理器来执行此处所描述的步骤，诸如转向组件和减速组件的一些组件每个都可以具有其自己的处理器，上述处理器只执行与特定于组件的功能相关的计算；或者行进系统、传感器系统、规划控制系统等子系统也可以有自己的处理器，用于实现对应子 系统的相关任务的计算从而实现相应功能。
在此处所描述的各个方面中，处理器可以位于远离该车辆的地方并且与该车辆进行无线通信。在其他方面中，此处所描述的过程中的一些在布置于车辆内的处理器上执行，而其他则由远程处理器执行，包括采取执行单一操纵的必要步骤。
在一些实施例中，存储器114可包含指令115(例如，程序逻辑)，指令115可被处理器113执行来执行车辆100的各种功能，包括以上描述的那些功能。存储器114也可包含额外的指令，包括向行进系统102、传感器系统104、规划控制系统106和外围设备108中的一个或多个发送数据、从其接收数据、与其交互和/或对其进行控制的指令。
除了指令115以外，存储器114还可存储其他相关数据，例如道路地图、路线信息，车辆的位置、方向、速度以及其他相关信息。这种信息可在车辆100处于自主、半自主和/或手动模式的操作期间被车辆100或具体被计算机系统101使用。
用户接口116，用于向车辆100的用户提供信息或从其接收信息。可选地，用户接口116可包括在外围设备108的集合内的一个或多个输入/输出设备，例如无线通信系统146、车载电脑148、麦克风150和扬声器152。
计算机系统101可基于从各种子系统(例如，行进系统102、传感器系统104和规划控制系统106)以及从用户接口116接收的输入来控制车辆100的功能。在一些实施例中，计算机系统101可操作以对车辆100及其子系统的许多方面提供控制。
可选地，上述这些组件中的一个或多个可与车辆100分开安装或关联。例如，存储器114可以部分或完全地与车辆100分开存在。上述组件可以按有线和/或无线方式来通信地耦合在一起。
可选地，上述组件只是一个示例，实际应用中，上述各个模块中的组件有可能根据实际需要增添或者删除，图4不应理解为对本申请实施例的限制。
在道路行进的自动驾驶汽车，如上面的车辆100，可以识别其周围环境内的物体以确定对车辆行驶轨迹的调整，其中包括对车辆速度的调整。上述物体可以是其他车辆、交通控制设备、或者其他类型的物体。在一些示例中，可以独立地考虑每个识别的物体，并且基于物体的各自的特性，诸如它的当前速度、加速度、与车辆的间距等，用来确定自动驾驶汽车的轨迹规划，包含所要调整的速度。
可选地，与车辆100相关联的计算设备(如图4的计算机系统101、计算机视觉系统138)可以基于所识别的物体的特性和周围环境的状态(例如，交通、雨、道路上的冰、等等)来预测上述识别的物体的行为。可选地，每一个所识别的物体都依赖于彼此的行为，因此还可以将所识别的所有物体全部一起考虑来预测单个识别的物体的行为。车辆100能够基于预测的上述识别的物体的行为来规划它的行驶轨迹(其中包括速度)。并基于该规划结果为自动驾驶汽车确定车辆将需要调整到什么状态(就速度调整而言，例如加速、减速或停止)。在这个过程中，也可以考虑其他因素来确定车辆100的行驶轨迹，诸如，车辆100在行驶的道路中的横向位置、道路的曲率、静态和动态物体的接近度等等。
基于规划结果，除了为自动驾驶汽车调整速度以外，计算设备还可以提供修改车辆100的转向角的指令，以使得自动驾驶汽车遵循给定的轨迹和/或维持与自动驾驶汽车附近的物体(例如，道路上的相邻车道中的轿车)的安全横向和纵向距离。
上述车辆100可以为轿车、卡车、摩托车、公共汽车、挖掘机、洒水车、割草机、娱 乐车、游乐场车辆、施工设备、电车、高尔夫球车等，本申请实施例不做特别的限定
图5示出了本申请实施例提供的路径规划方法的示意性流程图，该方法可以应用于如图4所示车辆100。该方法包括：
S501、车辆100获取车辆100的起点位置和车辆100终点位置。
在一种可能的实现方式中，车辆100通过行驶指令确定上述起点位置和上述终点位置。上述行驶指令用于指示车辆100从上述起点位置行驶至上述终点位置。
示例性地，车辆100可以接收其他设备(如网络设备)发送的用于指示车辆100图1中的A区域行驶至B区域的行驶指令，然后车辆100根据该行驶指令确定车辆100的起点位置为图1中的A区域，车辆100的终点位置为图1中的B区域。
在本申请实施例中，车辆100可以在获取起点位置和终点位置后，向网络设备上传上述起点位置和上述终点位置。例如，车辆100可以在获取起点位置和终点位置后，通过无线通信系统146向网络设备上传上述起点位置和上述终点位置。
S502、车辆100获取多个第一区域中每个第一区域的通行次数。
其中，第一区域是目标场景内的可通行区域。目标场景为车辆100所在的场景。例如目标场景可以为封闭园区、工地、矿区等。第一区域的宽度大于车辆的轮胎宽度。
示例性地，以目标景为图1所示的场景，第一区域为图1中的可通行区域即图1中的空白格子为例，则车辆100获取图1中每个第一区域(空白格子)的通行次数。
在一种可能实现方式中，车辆100可以通过上述网络设备获取包括第一信息，然后根据上述第一信息中的多条行车轨迹，确定上述多个第一区域中每个第一区域的通行次数。
在本申请实施例中，车辆100可以直接根据这多条行车轨迹，确定上述多个第一区域中每个第一区域的通行次数。
示例性地，以第一信息包括行车轨迹1、行车轨迹2和行车轨迹3，行车轨迹1中车辆经过了第一区域1、第一区域2和第一区域3，行车轨迹2中车辆经过了第一区域1、第一区域4和第一区域5，行车轨迹3中车辆经过了第一区域2、第一区域5和第一区域6为例。车辆100可以根据上述多条行车轨迹确定第一区域1的通行次数为2次，第一区域2的通行次数为2次，第一区域3的通行次数为1次，第一区域4的通行次数为1次，第一区域5的通行次数为2次，第一区域6的通行次数为1次。
可选地，上述第一信息还可以包括多个车辆状态信息，上述车辆状态信息用于指示车辆是否载有货物和车辆是否为载货车辆中的至少一项。其中，上述多个车辆状态信息与上述多条行车轨迹一一对应。例如，第一信息包括行车轨迹1和与行车轨迹1对应的车辆状态信息1、行车轨迹2和与行车轨迹2对应的车辆状态信息2、行车轨迹3和与行车轨迹3对应的车辆状态信息3。
可选地，上述车辆状态信息可以是车辆的重量信息，当车辆的重量大于第一阈值，则可以确定该车辆载有货物；反之当车辆的重量小于或等于第一阈值，则可以确定该车辆未载有货物。
可选地，上述车辆状态信息也可以为车辆的标签信息，其中，标签信息可以用于指示车辆是否为载货车辆。例如，标签信息可以为0和1。当车辆的标签信息为0时，可以确定该车辆为载货车辆；反之，当车辆的标签信息为1时，可以确定该车辆为非载货车辆。
在本申请实施例中，存在第一信息包括多个车辆状态信息且上述车辆状态信息用于指 示车辆是否载有货物的情况的场景(以下简称第一场景)。在第一场景中，车辆100可以根据第一信息里包括的多条行车轨迹中车辆载有货物时的行车轨迹确定每个第一区域的通行次数。例如，车辆100可以将每个第一区域中车辆载有货物时的通行次数确定为每个第一区域的通行次数。
可以理解的是，载有货物的车辆相较于未载有货物的车辆在行驶过程中会对路面产生较大负荷。因此，在统计每个第一区域的通行次数可以仅考虑每个第一区域中车辆载有货物时的行车轨迹，以减少统计第一区域的通行次数时的统计量，从而提高统计第一区域的通行次数时的统计效率。
在第一场景中，车辆100也可以根据第一信息包括的多条行车轨迹中车辆载有货物时的行车轨迹和车辆未载有货物时的行车轨迹确定每个第一区域的通行次数。例如，车辆100可以将每个第一区域车辆载有货物时的通行次数和每个第一区域车辆未载有货物时的通行次数的加权平均值确定为每个第一区域的通行次数。其中，车辆载有货物时的通行次数的权重高于车辆未载有货物时的通行次数的权重。
可以理解的是，载有货物的车辆相较于未载有货物的车辆在行驶过程中会对路面产生较大负荷，载有货物的车辆通行一次对路面产生的负荷相当于未载有货物的车辆通行多次对路面产生的负荷。因此，在统计各第一区域的通行次数需要分别统计每个第一区域中车辆载有货物时的通行次数和车辆未载有货物时的通行次数，并在通过车辆载有货物时的通行次数和车辆未载有货物时的通行次数加权计算通行次数时，赋予车辆载有货物时的通行次数较高的权重，以保证通行次数统计的准确性。
在本申请实施例中，存在第一信息包括多个车辆状态信息且上述车辆状态信息用于指示车辆是否为载货车辆的场景(以下简称第二场景)。在第二场景中，车辆100可以根据第一信息包括的多条行车轨迹中每个第一区域中载货车辆的行车轨迹确定每个第一区域的通行次数。例如，车辆100可以将每个第一区域中载货车辆的通行次数确定为每个第一区域的通行次数。
可以理解的是，载货车辆(如矿石运输车、油罐车、泥头车、拉土车、运渣车、水泥罐车、搅拌车等)相较于非载货车辆(如轿车、摩托车等)在行驶过程中会对路面产生较大负荷。因此，在统计各第一区域的通行次数可以仅考虑各区域中载货车辆的通行次数，从而减少统计量，提高统计通行次数的效率。
在第二场景中，车辆100也可以根据第一信息包括的多条行车轨迹中载货车辆的行车轨迹和非载货车辆的行车轨迹确定每个第一区域的通行次数。例如，车辆100可以将每个第一区域中载货车辆的通行次数和非载货车辆的通行次数的加权平均值确定为每个第一区域的通行次数。
可以理解的是，载货车辆相较于非载货车辆在行驶过程中会对路面产生较大负荷，载货车辆通行一次对路面产生的负荷相当于非载货车辆通行多次对路面产生的负荷。因此，在统计各第一区域的通行次数需要分别统计每个第一区域中载货车辆的通行次数和非载货车辆的通行次数，并在通过载货车辆的通行次数和非载货车辆的通行次数加权计算通行次数时，赋予载货车辆的通行次数较高的权重，以保证通行次数统计的准确性。
在一种可能的实现方式中，网络设备可以根据上述第一信息中的多条行车轨迹，确定上述多个第一区域中每个第一区域的通行次数。
S503、车辆100根据上述通行次数进行路径规划，确定从上述起点位置到达上述终点位置的通行路径。
其中，上述通行路径包括从上述起点位置到达上述终点位置经过的第二区域。
示例性地，以上述通行路径为图2中示出的A到B的路径为例，则第二区域包括图2中的第五行第二列的区域、第五行第三列的区域、第五行第四列的区域、第五行第五列的区域、第五行第六列的区域、第五行第七列的区域和第五行第八列的区域。
在本申请实施例中，对于每个第一区域，若该第一区域的通行次数越少，则在上述路径规划时该第一区域被规划为上述第二区域的概率越大。反之，若该第一区域的通行次数越大，则在上述路径规划时该第一区域被规划为上述第二区域的概率越小。
可以理解的是，若当前某个第一区域的通行次数比其他区域的通行次数高，则在后续路径规划时，该第一区域的被选为第二区域的概率低于其他第一区域，相应地该第一区域的通行次数的增加速度也会低于其他第一区域，那么一段时间后其他第一区域的通行次数会接近该第一区域的通行次数，因此不会出现某个第一区域的通行次数远远高于其他第一区域的通行次数的情况。
反之，若当前某个第一区域的通行次数比其他区域的通行次数低，则在后续路径规划时，该第一区域的被选为第二区域的概率高于其他第一区域，相应地该第一区域的通行次数的增加速度也会高于其他第一区域，那么一段时间后该第一区域的通行次数会接近其他第一区域的通行次数，因此不会出现某个第一区域的通行次数远远低于其他第一区域的通行次数的情况。
可以看出，本申请实施例提供的路径规划方法，可以使各第一区域的通行次数的均衡，使各第一区域均匀承担车辆通行负载，减少某一区域由于承担过多车辆通行负载的情况发生，也减少了某一区域被自动驾驶汽车反复碾压的概率，缓解了道路车辙的生成，提高行车的安全性。
在一种可能的实现方式中，上述车辆100根据上述通行次数进行路径规划，确定从上述起点位置到达上述终点位置的通行路径，可以包括：若上述车辆100载有货物，上述车辆100的路线规划系统142则根据上述通行次数进行路径规划，确定从上述起点位置到达上述终点位置的通行路径。反之，若上述车辆100未载有货物，上述车辆100的路线规划系统142则确定从上述起点位置到达上述终点位置的通行路径为上述起点位置与上述终点位置之间的最短通行路径。
可选地，上述车辆100可以根据上述起点位置和上述终点位置，确定上述车辆100是否载有货物。例如，若起点位置为采掘区，终点位置为卸载区，则上述车辆100可以确定上述车辆100载有货物。又例如，若起点位置为卸载区，终点位置为采掘区，则上述车辆100可以确定上述车辆100未载有货物。
可选地，上述车辆100可以根据环境信息、上述起点位置和上述终点位置，确定上述车辆100是否载有货物。例如，若环境信息指示车辆所在环境为山坡矿且起点位置的高度高于终点位置，则可以确定上述车辆100载有货物；反之若起点位置的高度低于终点位置，则可以确定上述车辆100未载有货物。又例如，若环境信息指示车辆所在环境为凹陷矿且起点位置的高度低于终点位置，则可以确定上述车辆100载有货物；反之若起点位置的高度高于终点位置，则可以确定上述车辆100未载有货物。
需要说明的是，载有货物的车辆在行驶过程中会对路面产生较大负荷，因此在对载有货物的车辆进行路径规划时，需要考虑各第一区域的通行次数，以使得各第一区域的路面负荷均衡。而未载有货物的车辆在行驶过程中不会对路面产生较大负荷，因此在对未载有货物的车辆进行路径规划时，可以仅考虑各路径的通行距离。
在另一种可能的实现方式中，上述车辆100根据上述通行次数进行路径规划，确定从上述起点位置到达上述终点位置的通行路径，可以包括：若上述车辆100为载货车辆，上述车辆100的路线规划系统142则根据上述通行次数进行路径规划，确定从上述起点位置到达上述终点位置的通行路径。反之，若上述车辆100为非载货车辆，上述车辆100的路线规划系统142则确定从上述起点位置到达上述终点位置的通行路径为上述起点位置与上述终点位置之间的最短通行路径。
需要说明的是，载货车辆在行驶过程中会对路面产生较大负荷，因此在对载货车辆进行路径规划时，需要考虑各第一区域的通行次数，以使得各第一区域的路面负荷均衡。而非载货车辆在行驶过程中不会对路面产生较大负荷，因此在对非载货车辆进行路径规划时，可以仅考虑各路径的通行距离。
在一种可能的实现方式中，车辆100根据上述通行次数进行路径规划，确定从上述起点位置到达上述终点位置的通行路径，包括：车辆100的路线规划系统142先根据上述起点位置和上述终点位置确定多条通行路径并确定这多条通行路径中每条通行路径的通行次数，然后确定从上述起点位置到达上述终点位置的通行路径为上述多条通行路径中通行次数最少的通行路径。
示例性地，如图6所示，车辆100需要从图6中的A区域前往B区域。车辆100的路线规划系统142先根据确定A区域至B区域的多条通行路径(为了描述简洁，图6仅示意性的示出了三条路径，实际路径数可以多于三条)，然后确定这多条通行路径中每条通行路径的通行次数，最后确定从A区域到达B区域的通行路径为上述多条通行路径中通行次数最少的通行路径。
在本申请实施例中，车辆100的路线规划系统142可以通过多种方式(如迪科斯彻(Dijkstra)算法、启发式搜索(A*)算法或快速搜索随机树(rapidly exploring random trees，RRT)算法)根据上述起点位置和上述终点位置确定多条通行路径。
可选地，上述每条通行路径的通行次数可以是每条路径所经过的多个第一区域的通行次数均值。例如，通行路径1经过了第一区域1、第一区域2、第一区域3和第一区域4。其中，第一区域1的通行次数为20、第一区域2的通行次数为16、第一区域3的通行次数为12、第一区域4的通行次数为16，则通行路径1的通行次数为(20+16+12+16)/4＝16。
在本申请实施例中，其他设备(如网络设备)可以为每辆车辆编组(例如，可以将一辆挖掘机和六辆矿石运输车辆编为一组)，其中同一个编组内的车辆每次行驶的起点位置和终点位置相同。为了避免同一个编组内的车辆重复规划路径，车辆100可以在得到上述通行路径后向编组内的其他车辆发送上述通行路径。这样可以使得同一个编组内的多辆车辆在每次行驶前只需其中的一辆进行路径规划就可以确定编组内的所有车辆的通行路径，提升了编组路径规划的效率。
示例性地，车辆编组A1包括车辆1、车辆2、车辆3、车辆4、车辆5和车辆6。车辆1在确定从起点位置到达终点位置的通行路径后向车辆2、车辆3、车辆4、车辆5和 车辆6发送该通行路径。这样车辆2、车辆3、车辆4、车辆5和车辆6就可以直接使用车辆1发送的通行路径。
需要说明的是，本申请实施例提供的路径规划方法也可以由网络设备执行。具体地，网络设备可以接收车辆100发送的起点位置和终点位置，然后获取多个第一区域中每个第一区域的通行次数，接着根据上述通行次数进行路径规划，确定从上述起点位置到达上述终点位置的通行路径。
可选地，网络设备还可以接收车辆100通过无线通信系统146发送的编组信息。网络设备可以为同一个编组内的任意一个车辆规划路线以确定从起点位置到达终点位置的通行路径，然后向该编组内的所有车辆发送上述通行路径。
可选地，车辆100可以根据上述通行路径生成第二通行路径。其中，第二通行路径与上述通行路径之间存在横向偏差。
示例性地，如图7所示，车辆100可以根据上述图7左侧所示的通行路径生成图7右侧所示的第二通行路径。
在一种可能的实现方式中，车辆100可以对上述通行路径中每个第二区域内的路径进行横向偏移得到第二通行路径。
示例性地，以上述通行路径为图2所示的路径为例。可以看出该路径经过的第二区域包括图2中的第五行第二列的区域、第五行第三列的区域、第五行第四列的区域、第五行第五列的区域、第五行第六列的区域、第五行第七列的区域和第五行第八列的区域。则车辆可以对上述每个第二区域内的路径进行横向偏移，然后得到多条路径。
例如，上述通行路径中某个第二区域内的通行路径为图7中的路径1，可以对路径1横向偏移得到多条路径(如图8中的路径2、路径3、路径4、路径5、路径6和路径7)，然后可以从中选择一条路径作为第二通行路径中该第二区域内的通行路径。
可选地，可以选择每个第二区域内的多条路径中通行次数最少的路径作为第二通行路径中每个第二区域的通行路径。
例如，图8所示的某个第二区域内的路径1的通行次数为5次，路径2的通行次数为4次，路径3的通行次数为3次，路径4的通行次数为1次，路径5的通行次数为3次，路径6的通行次数为3次，路径7的通行次数为4次。可以看出路径4的通行次数最少，则可以将该第二区域内的路径4作为第二通行路径该第二区域内的通行路径。
可以理解的，车辆在通过某个区域时会碾压上述区域产生车辙，若该车辆或其他车辆采用相同行驶路径通过上述区域时，会使上述产生相同的车辙，即会使之前产生的车辙加深。而本申请实施例中通过对通行路径进行横向偏移可以使不同车辆或同一车辆在通过同一区域时采用不同的行驶路径，这样可以避免第一区域内产生较深车辙。
可选地，车辆100可以对上述通行路径进行平滑处理。其中，对通行路径进行平滑处理的具体实现过程可以参照现有平滑处理的具体实现过程，在此就不再赘述。例如，可以通过B样条曲线方法对上述通行路径进行平滑处理。
在本申请实施例中，车辆100的规划控制系统106可以通过控制行进系统102使车辆100按照上述通行路径从上述起点位置行驶至上述终点位置。车辆100还可以在行驶过程中记录自身的行驶轨迹并通过无线通信系统146向网络设备发送该行驶轨迹。
结合图5介绍了本申请实施例提供的路径规划方法，下面将结合图9和图10介绍用 于执行上述路径规划方法的路径规划装置。
需要说明的是，该路径规划装置可以为上述方法实施例中的车辆100能够执行上述方法中由车辆100所执行的方法。该路径规划装置也可以为上述方法实施例中的网络设备能够执行上述方法中由网络设备所执行的方法。
可以理解的是，路径规划装置为了实现上述功能，其包含了执行各个功能相应的硬件和/或软件模块。结合本文中所公开的实施例描述的各示例的算法步骤，本申请能够以硬件或硬件和计算机软件的结合形式来实现。某个功能究竟以硬件还是计算机软件驱动硬件的方式来执行，取决于技术方案的特定应用和设计约束条件。本领域技术人员可以结合实施例对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
本申请实施例可以根据上述方法示例对路径规划装置进行功能模块的划分，例如，可以对应各个功能划分各个功能模块，也可以将两个或两个以上的功能集成在一个处理模块中。上述集成的模块可以采用硬件的形式实现。需要说明的是，本实施例中对模块的划分是示意性的，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式。
在采用对应各个功能划分各个功能模块的情况下，图9示出了上述实施例中涉及的路径规划装置的一种可能的组成示意图，如图9所示，该装置900可以包括：收发单元901和处理单元902，该收发单元901用于获取上述方法实施例中的起点位置、终点位置和多个第一区域中每个第一区域的通行次数，该处理单元902可以实现上述方法实施例中由路径规划装置所执行的方法，和/或用于本文所描述的技术的其他过程。
需要说明的是，上述方法实施例涉及的各步骤的所有相关内容均可以援引到对应功能模块的功能描述，在此不再赘述。
在采用集成的单元的情况下，装置900可以包括处理单元、存储单元和通信单元。其中，处理单元可以用于对装置900的动作进行控制管理，例如，可以用于支持装置900执行上述各个单元执行的步骤。存储单元可以用于支持装置900执行存储程序代码、和/或数据等。通信单元可以用于支持装置900与其他设备的通信。
其中，处理单元可以是处理器或控制器。其可以实现或执行结合本申请公开内容所描述的各种示例性地逻辑方框，模块和电路。处理器也可以是实现计算功能的组合，例如包含一个或多个微处理器组合，数字信号处理(digital signal processing，DSP)和微处理器的组合等等。存储单元可以是存储器。通信单元具体可以为射频电路、蓝牙芯片、Wi-Fi芯片等与其他电子设备交互的设备。
在一种可能的实现方式中，本申请实施例所涉及的路径规划装置可以为具有图10所示结构的装置1000，该装置1000包括处理器1001和收发器1002。图9中的收发单元901和处理单元902所实现的相关功能可以由处理器1001来实现。
可选地，该装置1000还可以包括存储器1003，该处理器1001和该存储器1003通过内部连接通路互相通信。图9中的存储单元所实现的相关功能可以由存储器1003来实现。
本申请实施例还提供一种计算机存储介质，该计算机存储介质中存储有计算机指令，当该计算机指令在电子设备上运行时，使得电子设备执行上述相关方法步骤实现上述实施例中的路径规划方法。
本申请实施例还提供了一种计算机程序产品，当该计算机程序产品在计算机上运行 时，使得计算机执行上述相关步骤，以实现上述实施例中的路径规划方法。
本申请实施例还提供一种路径规划装置，这个装置具体可以是芯片、集成电路、组件或模块。具体的，该装置可包括相连的处理器和用于存储指令的存储器，或者该装置包括至少一个处理器，用于从外部存储器获取指令。当装置运行时，处理器可执行指令，以使芯片执行上述各方法实施例中的路径规划方法。
图11示出了一种芯片1100的结构示意图。芯片1100包括一个或多个处理器1101以及接口电路1102。可选的，上述芯片1100还可以包含总线1103。
处理器1101可能是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述路径规划方法的各步骤可以通过处理器1101中的硬件的集成逻辑电路或者软件形式的指令完成。
可选地，上述的处理器1101可以是通用处理器、数字信号处理(digital signal processing，DSP)器、集成电路(application specific integrated circuit，ASIC)、现场可编程门阵列(field-programmable gate array，FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本申请实施例中的公开的各方法、步骤。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。
接口电路1102可以用于数据、指令或者信息的发送或者接收，处理器1101可以利用接口电路1102接收的数据、指令或者其他信息，进行加工，可以将加工完成信息通过接口电路1102发送出去。
可选的，芯片还包括存储器，存储器可以包括只读存储器和随机存取存储器，并向处理器提供操作指令和数据。存储器的一部分还可以包括非易失性随机存取存储器(non-volatile random access memory，NVRAM)。
可选的，存储器存储了可执行软件模块或者数据结构，处理器可以通过调用存储器存储的操作指令(该操作指令可存储在操作系统中)，执行相应的操作。
可选的，芯片可以使用在本申请实施例涉及的路径规划装置、车辆100或网络设备中。可选的，接口电路1102可用于输出处理器1101的执行结果。关于本申请的一个或多个实施例提供的路径规划方法可参考前述各个实施例，这里不再赘述。
需要说明的，处理器1101、接口电路1102各自对应的功能既可以通过硬件设计实现，也可以通过软件设计来实现，还可以通过软硬件结合的方式来实现，这里不作限制。
其中，本实施例提供的路径规划装置、计算机存储介质、计算机程序产品或芯片均用于执行上文所提供的对应的方法，因此，其所能达到的有益效果可参考上文所提供的对应的方法中的有益效果，此处不再赘述。
应理解，在本申请的各种实施例中，上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。
本领域普通技术人员可以意识到，结合本申请中所公开的实施例描述的各示例的单元及算法步骤，能够以电子硬件、或者计算机软件和电子硬件的结合来实现。这些功能究竟以硬件还是软件方式来执行，取决于技术方案的特定应用和设计约束条件。专业技术人员可以对每个特定的应用来使用不同方法来实现所描述的功能，但是这种实现不应认为超出本申请的范围。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统、装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统、装置和方法，可以通过其他的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，上述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其他的形式。
上述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。
上述功能如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例上述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read Only Memory，ROM)、随机存取存储器(Random Access Memory，RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的具体实施方式，但本申请的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请的保护范围之内。因此，本申请的保护范围应所述以权利要求的保护范围为准。

Claims (17)

  1. 一种路径规划方法，其特征在于，包括：
    获取车辆的起点位置和所述车辆的终点位置；
    获取多个第一区域中每个第一区域的通行次数，所述第一区域为目标场景内的可通行区域；
    根据所述通行次数进行路径规划，确定从所述起点位置到达所述终点位置的通行路径，所述通行路径包括从所述起点位置到达所述终点位置经过的第二区域，其中，所述第一区域的通行次数越少，在所述路径规划时所述第一区域被规划为所述第二区域的概率越大。
  2. 根据权利要求1所述的方法，其特征在于，所述获取多个第一区域中每个第一区域的通行次数，包括：
    获取第一信息，所述第一信息包括多条行车轨迹，所述多条行车轨迹中的每条行车轨迹包含至少一个第一区域；
    根据所述多条行车轨迹，确定所述多个第一区域中每个第一区域的通行次数。
  3. 根据权利要求2所述的方法，其特征在于，所述第一信息还包括多个车辆状态信息，所述车辆状态信息用于指示车辆是否载有货物和车辆是否为载货车辆中的至少一项，所述多个车辆状态信息与所述多条行车轨迹一一对应；
    所述根据所述多条行车轨迹，确定所述多个第一区域中每个第一区域的通行次数，包括：
    根据所述多条行车轨迹，确定目标行车轨迹，所述目标行车轨迹为所述多条行车轨迹中车辆载有货物时的行车轨迹或载货车辆的行驶轨迹；
    根据所述目标行车轨迹，确定所述多个第一区域中每个第一区域的通行次数。
  4. 根据权利要求1至3中任一项所述的方法，其特征在于，所述根据所述通行次数进行路径规划，确定从所述起点位置到达所述终点位置的通行路径，包括：
    获取车辆状态信息，所述车辆状态信息用于指示所述车辆是否载有货物和/或是否为载货车辆；
    若所述车辆载有货物，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径；
    或者，
    若所述车辆为载货车辆，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径。
  5. 根据权利要求1至3中任一项所述的方法，其特征在于，所述根据所述通行次数进行路径规划，确定从所述起点位置到达所述终点位置的通行路径，包括：
    获取所述车辆的重量信息；
    若所述车辆的重量大于第一阈值，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径。
  6. 根据权利要求1至3中任一项所述的方法，其特征在于，所述根据所述通行次数进行路径规划，确定从所述起点位置到达所述终点位置的通行路径，包括：
    获取环境信息，所述环境信息用于指示所述目标场景的环境类型、所述起点位置和所述终点位置的高度；
    若所述目标场景为凹陷矿且所述起点位置的高度低于终点位置，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径；
    或者，
    若所述目标场景为山坡矿且起点位置的高度高于终点位置，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径。
  7. 根据权利要求1至6中任一项所述的方法，其特征在于，所述方法还包括：
    根据所述通行路径生成第二通行路径，所述第二通行路径与所述通行路径之间存在横向偏差。
  8. 一种路径规划装置，其特征在于，包括：处理器和与所述处理器耦合的存储器；
    所述处理器用于获取车辆的起点位置和所述车辆的终点位置；获取多个第一区域中每个第一区域的通行次数，所述第一区域为目标场景内的可通行区域；根据所述通行次数进行路径规划，确定从所述起点位置到达所述终点位置的通行路径，所述通行路径包括从所述起点位置到达所述终点位置经过的第二区域，其中，所述第一区域的通行次数越少，在所述路径规划时所述第一区域被规划为所述第二区域的概率越大。
  9. 根据权利要求8所述的装置，其特征在于，所述处理器具体用于：
    获取第一信息，所述第一信息包括多条行车轨迹，所述多条行车轨迹中的每条行车轨迹包含至少一个第一区域；
    根据所述多条行车轨迹，确定所述多个第一区域中每个第一区域的通行次数。
  10. 根据权利要求9所述的装置，其特征在于，所述第一信息还包括多个车辆状态信息，所述车辆状态信息用于指示车辆是否载有货物和车辆是否为载货车辆中的至少一项，所述多个车辆状态信息与所述多条行车轨迹一一对应，所述处理器还具体用于：
    所述根据所述多条行车轨迹，确定所述多个第一区域中每个第一区域的通行次数，包括：
    根据所述多条行车轨迹，确定目标行车轨迹，所述目标行车轨迹为所述多条行车轨迹中车辆载有货物时的行车轨迹或载货车辆的行驶轨迹；
    根据所述目标行车轨迹，确定所述多个第一区域中每个第一区域的通行次数。
  11. 根据权利要求8至10中任一项所述的装置，其特征在于，所述处理器具体用于：
    获取车辆状态信息，所述车辆状态信息用于指示所述车辆是否载有货物和/或是否为载货车辆；
    若所述车辆载有货物，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径；
    或者，
    若所述车辆为载货车辆，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径。
  12. 根据权利要求8至10中任一项所述的装置，其特征在于，所述处理器具体用于：
    获取所述车辆的重量信息；
    若所述车辆的重量大于第一阈值，则根据所述通行次数进行路径规划确定从所述起点 位置到达所述终点位置的通行路径。
  13. 根据权利要求8至10中任一项所述的装置，其特征在于，所述处理器具体用于：
    获取环境信息，所述环境信息用于指示所述目标场景的环境类型、所述起点位置和所述终点位置的高度；
    若所述目标场景为凹陷矿且所述起点位置的高度低于终点位置，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径；
    或者，
    若所述目标场景为山坡矿且起点位置的高度高于终点位置，则根据所述通行次数进行路径规划确定从所述起点位置到达所述终点位置的通行路径。
  14. 根据权利要求8至13中任一项所述的装置，其特征在于，所述处理器还用于：
    根据所述通行路径生成第二通行路径，所述第二通行路径与所述通行路径之间存在横向偏差。
  15. 一种芯片设备，包括存储器和处理器，所述存储器与所述处理器耦合，所述存储器存储有代码，所述处理器被配置为执行所述代码，当所述代码被执行时，实现上述权利要求1至7中任一项所述的方法。
  16. 一种计算机可读存储介质，用于存储计算机程序，其特征在于，所述计算机程序包括用于实现上述权利要求1至7中任一项所述的方法的指令。
  17. 一种计算机程序产品，所述计算机程序产品中包含指令，其特征在于，当所述指令在计算机或处理器上运行时，使得所述计算机或所述处理器实现上述权利要求1至7中任一项所述的方法。
PCT/CN2021/102372 2021-06-25 2021-06-25 路径规划方法和装置 WO2022267004A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2021/102372 WO2022267004A1 (zh) 2021-06-25 2021-06-25 路径规划方法和装置
CN202180099625.6A CN117546115A (zh) 2021-06-25 2021-06-25 路径规划方法和装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2021/102372 WO2022267004A1 (zh) 2021-06-25 2021-06-25 路径规划方法和装置

Publications (1)

Publication Number Publication Date
WO2022267004A1 true WO2022267004A1 (zh) 2022-12-29

Family

ID=84544017

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/102372 WO2022267004A1 (zh) 2021-06-25 2021-06-25 路径规划方法和装置

Country Status (2)

Country Link
CN (1) CN117546115A (zh)
WO (1) WO2022267004A1 (zh)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010021888A1 (en) * 2000-03-07 2001-09-13 Burns Ray L. Anti-rut system for autonomous-vehicle guidance
US20070179690A1 (en) * 2006-02-01 2007-08-02 Stewart Brian G Variable path automated guided vehicle
US20120029753A1 (en) * 2010-07-28 2012-02-02 Johnson David A Robotic mower home finding system
CN103246284A (zh) * 2012-02-10 2013-08-14 本田技研工业株式会社 无人行驶作业车的控制装置
CN106462166A (zh) * 2016-04-28 2017-02-22 株式会社小松制作所 作业机械的管理装置
CN112198875A (zh) * 2020-09-25 2021-01-08 北京慧拓无限科技有限公司 一种防止道路碾压车辙的无人驾驶矿车控制方法
CN112731935A (zh) * 2020-12-25 2021-04-30 格力博(江苏)股份有限公司 自动割草机的路径规划方法、系统、设备及自动割草机
CN113002540A (zh) * 2020-04-17 2021-06-22 青岛慧拓智能机器有限公司 矿用自卸车控制方法及装置

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20010021888A1 (en) * 2000-03-07 2001-09-13 Burns Ray L. Anti-rut system for autonomous-vehicle guidance
US20070179690A1 (en) * 2006-02-01 2007-08-02 Stewart Brian G Variable path automated guided vehicle
US20120029753A1 (en) * 2010-07-28 2012-02-02 Johnson David A Robotic mower home finding system
CN103246284A (zh) * 2012-02-10 2013-08-14 本田技研工业株式会社 无人行驶作业车的控制装置
CN106462166A (zh) * 2016-04-28 2017-02-22 株式会社小松制作所 作业机械的管理装置
CN113002540A (zh) * 2020-04-17 2021-06-22 青岛慧拓智能机器有限公司 矿用自卸车控制方法及装置
CN112198875A (zh) * 2020-09-25 2021-01-08 北京慧拓无限科技有限公司 一种防止道路碾压车辙的无人驾驶矿车控制方法
CN112731935A (zh) * 2020-12-25 2021-04-30 格力博(江苏)股份有限公司 自动割草机的路径规划方法、系统、设备及自动割草机

Also Published As

Publication number Publication date
CN117546115A (zh) 2024-02-09

Similar Documents

Publication Publication Date Title
US20220332348A1 (en) Autonomous driving method, related device, and computer-readable storage medium
CN111123952B (zh) 一种轨迹规划方法及装置
CN112146671B (zh) 路径规划方法、相关设备及计算机可读存储介质
US11203337B2 (en) Vehicle with autonomous driving capability
WO2022027304A1 (zh) 一种自动驾驶车辆的测试方法及装置
WO2021102955A1 (zh) 车辆的路径规划方法以及车辆的路径规划装置
US9451020B2 (en) Distributed communication of independent autonomous vehicles to provide redundancy and performance
KR101763261B1 (ko) 장애물 평가 기법
CN112230642B (zh) 道路可行驶区域推理方法及装置
US9928431B2 (en) Verifying a target object with reverse-parallax analysis
CN110356401B (zh) 一种自动驾驶车辆及其变道控制方法和系统
CN112672942B (zh) 一种车辆换道方法及相关设备
CN114440908B (zh) 一种规划车辆驾驶路径的方法、装置、智能车以及存储介质
WO2022016901A1 (zh) 一种规划车辆行驶路线的方法以及智能汽车
CN113835421A (zh) 训练驾驶行为决策模型的方法及装置
CN112429016A (zh) 一种自动驾驶控制方法及装置
WO2022267004A1 (zh) 路径规划方法和装置
CN112829762A (zh) 一种车辆行驶速度生成方法以及相关设备
WO2022127502A1 (zh) 控制方法和装置
WO2023010267A1 (zh) 确定泊出方向的方法和装置
WO2022061725A1 (zh) 交通元素的观测方法和装置
US20230256970A1 (en) Lane Change Track Planning Method and Apparatus
CN115407344B (zh) 栅格地图创建方法、装置、车辆及可读存储介质
US20240171633A1 (en) Mobile Offloading for Disconnected Terminal Operation
US20240166221A1 (en) Mobile offloading for disconnected terminal operation

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21946498

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 202180099625.6

Country of ref document: CN

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21946498

Country of ref document: EP

Kind code of ref document: A1