WO2021159901A1 - 一种路径规划方法及相关设备 - Google Patents

一种路径规划方法及相关设备 Download PDF

Info

Publication number
WO2021159901A1
WO2021159901A1 PCT/CN2021/071212 CN2021071212W WO2021159901A1 WO 2021159901 A1 WO2021159901 A1 WO 2021159901A1 CN 2021071212 W CN2021071212 W CN 2021071212W WO 2021159901 A1 WO2021159901 A1 WO 2021159901A1
Authority
WO
WIPO (PCT)
Prior art keywords
map
index
feature point
target
terminal
Prior art date
Application number
PCT/CN2021/071212
Other languages
English (en)
French (fr)
Inventor
高凯
龚胜波
李俊超
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
Publication of WO2021159901A1 publication Critical patent/WO2021159901A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/20—Instruments for performing navigational calculations
    • 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
    • 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
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles

Definitions

  • the embodiments of the present application relate to the field of communications, and in particular, to a path planning method and related equipment.
  • autonomous driving or smart driving cars use perception modules such as video cameras, radar sensors, and ultrasonic sensors to obtain the surrounding traffic conditions.
  • perception modules such as video cameras, radar sensors, and ultrasonic sensors to obtain the surrounding traffic conditions.
  • auto parking assist APA
  • the scene information is in the form of a raster map to provide the initial judgment basis for path planning .
  • the perception module sends a grid map containing the obstacle envelope to the planning module.
  • the sensing module divides the data in the grid map into N pieces of data according to the grid index, and periodically writes each piece of data into the M frame message, and the total N cycles are sent.
  • the planning module plans the path according to the grid map, where N or M is an integer greater than or equal to 2.
  • the embodiment of the present application provides a path planning method and related equipment.
  • the transmission time using the index of the feature point is less than the transmission time of the map, so as to avoid the problem of large terminal position error caused by the high time delay of the map transmission.
  • the first aspect of the embodiments of the present application provides a path planning method.
  • the method includes: a first device sends a first index of at least one feature point to a second device, where the at least one feature point is a first obstacle on a first map.
  • the first index is used to indicate the location of at least one feature point in the first map.
  • the first device receives a second index of at least one feature point from the second device, the second index is used to indicate the position of the at least one feature point in the second map, and the generation time of the second map is later than the generation time of the first map .
  • the first device generates first path information according to the second index, and the first path information is used to indicate a first path for the terminal.
  • the first device sends the first index of the feature point in the first map to the second device, receives the second index of the feature point in the second map from the second device, and generates the first index according to the second index.
  • Path information The first device and the second device transmit the index of the characteristic point, so that the first device generates the first path information according to the index of the characteristic point.
  • the transmission time using the index of the characteristic point is less than the transmission time of the map. Due to the high time delay of the transmission of the map, the terminal position error is large.
  • the above steps further include: the first device sends a control signal or control information to the third device, and the control signal or control information is used to control the terminal according to the first path Information to exercise.
  • the interaction between the first device and the third device enables the terminal to move according to the first path information.
  • the first device sends the first index of the feature point in the first map to the second device, including: determining that the speed of the terminal is greater than the first threshold At this time, the first device sends the first index of the feature point in the first map to the second device.
  • the first device when the passing speed is greater than the threshold, the first device sends the index to the second device, so as to avoid the problem of large terminal position errors caused by the high delay of map transmission.
  • the first device sends a map update request to the second device, including, when it is determined that the speed of the terminal is less than the first threshold, the first device sends the The second device sends a map update request.
  • the first device when the passing speed is less than the threshold, the first device sends an index update map request to the second device, which avoids the problem of large terminal position errors caused by the high delay of map transmission when the speed is too fast .
  • the above steps after the first device receives the first map from the second device, the method further includes: the first device generates the outline of obstacles in the first map. Second path information, where the second path information is used to indicate a second path for the terminal.
  • the first device generates the second route information according to the map, which can first provide the feasibility of a scheme for the terminal to plan the driving route.
  • the above step after the first device generates the first path information for the terminal according to the second index, the method further includes: the first device determines at least one target feature point , The at least one target feature point belongs to at least one feature point, and the distance between the at least one target feature point and the first path is less than the second threshold.
  • the first device can determine the feature points that need to be tracked, which reduces the transmission delay.
  • the above steps further include: the first device sends a first target index of at least one target feature point to the second device, where the first target index is the at least one target feature The location information of the point in the first map.
  • the first device receives a second target index of at least one target feature point from the second device, the second target index is used to indicate the position of the at least one target feature point in the third map, and the generation time of the third map is later than the second The time when the map was generated.
  • the first device generates third path information according to the second target index, and the third path information is used to indicate a third path for the terminal.
  • the first device obtains the index of the feature point to be tracked in the new map, and generates a further optimized path.
  • the above steps further include: the first device receives alarm information from the second device, the alarm information is used to indicate that the speed value of the terminal is less than the first threshold.
  • the first device receives the alarm information from the second device, and uses the alarm information to slow down the terminal to the speed of the transmission map, so as to prevent the terminal from crashing due to untracked feature points.
  • the above steps: the first map and the second map are grid maps, or the first map and the second map are point cloud maps.
  • the terminal is an intelligent vehicle, an intelligent airplane or an intelligent robot.
  • a second aspect of the embodiments of the present application provides a path planning method.
  • the method includes: a second device receives a first index of at least one feature point from a first device, and the at least one feature point is a first obstacle in a first map.
  • the first index is used to indicate the location of at least one feature point in the first map.
  • the second device acquires a second map, and the generation time of the second map is later than the generation time of the first map.
  • the second device sends a second index to the first device, the second index is used to indicate the position of the at least one feature point in the second map, and the second index is used to indicate the first path information for the terminal.
  • the second device receives the first index of at least one feature point from the first device, obtains the second map, and sends the second index to the first device.
  • the second index is used to indicate the The first path information.
  • the transmission time using the index of the feature point is less than the time of the map transmission, so as to avoid the problem of large terminal position error caused by the high time delay of the map transmission.
  • the above steps before the second device receives the first index of at least one feature point from the first device, further comprising: the second device receives the first index from the first device The update map request; and send the first map to the first device according to the update map request.
  • the second device sends the first map according to the request of the first device, which can first provide the feasibility of a solution for the path planning of the first device.
  • the first target index is the location information of at least one target feature point in the first map.
  • the second device acquires a third map, and the generation time of the third map is later than the generation time of the second map.
  • the second device sends a second target index to the first device, the second target index is used to indicate the position of the at least one target feature point in the third map, and the second target index is used to indicate third path information for the terminal.
  • the second device sends to the first device the index of the feature point in the new map that the first device needs to track, so as to generate a further optimized path.
  • the target value is used to indicate how close the second obstacle is to the terminal, and the warning information is used to indicate that the speed value of the terminal is less than the first device.
  • a threshold is used to indicate how close the second obstacle is to the terminal.
  • the second device sends alarm information to the first device, and the alarm information is used to slow down the terminal to the speed of transmitting the map, preventing the terminal from being untracked. There is a risk of collision at the characteristic point.
  • the terminal is a smart vehicle, a smart airplane or a smart robot.
  • the third aspect of the present application provides a first device, configured to execute the foregoing first aspect or the method in any possible implementation manner of the first aspect.
  • the device includes a module or unit for executing the above-mentioned first aspect or any possible implementation of the first aspect.
  • the fourth aspect of the present application provides a second device, which is configured to execute the foregoing second aspect or the method in any possible implementation manner of the second aspect.
  • the device includes a module or unit for executing the foregoing second aspect or any possible implementation of the second aspect.
  • a fifth aspect of the present application provides a first device.
  • the first device includes at least one processor and at least one communication interface. At least one communication interface is used to provide input/output of data and/or information for at least one processor; at least one processor is used to process data and/or information to enable the first device to implement the first aspect or any possible aspect of the first aspect The method in the implementation mode.
  • a sixth aspect of the present application provides a second device.
  • the second device includes at least one processor and at least one communication interface. At least one communication interface is used to provide input/output of data and/or information for at least one processor; at least one processor is used to process data and/or information to enable the first device to implement the second aspect or any possible aspect of the second aspect The method in the implementation mode.
  • the seventh aspect of the present application provides a computer storage medium that stores instructions in the computer storage medium.
  • the computer executes the foregoing first aspect or any possible implementation manner of the first aspect, and the second Aspect or any possible implementation of the second aspect.
  • the eighth aspect of the present application provides a computer program product.
  • the computer program product When the computer program product is executed on a computer, the computer executes any possible implementation of the first aspect or the first aspect, and any of the second aspect or the second aspect. Methods in possible implementations.
  • a ninth aspect of the present application provides a vehicle.
  • the vehicle includes a first device and a second device.
  • a first device for implementing the foregoing second aspect or any possible implementation of the second aspect.
  • the technical effects brought by the third, fifth, seventh, eighth aspects or any one of the possible implementation manners can be referred to the technical effects brought by the first aspect or the different possible implementation manners of the first aspect, here No longer.
  • FIG. 1 is a schematic diagram of an intelligent vehicle system architecture in an embodiment of the application
  • FIG. 2 is a schematic flowchart of a path planning method in an embodiment of this application
  • Figure 3 is a schematic diagram of the first map in an embodiment of the application.
  • FIG. 4 is a schematic diagram of feature points in the first map in an embodiment of the application.
  • FIG. 5 is a schematic diagram of the second map in an embodiment of the application.
  • Fig. 6 is a schematic structural diagram of the first device in an embodiment of the application.
  • FIG. 7 is a schematic diagram of another structure of the first device in an embodiment of the application.
  • Figure 8 is a schematic structural diagram of a second device in an embodiment of the application.
  • FIG. 9 is a schematic diagram of another structure of the second device in an embodiment of the application.
  • FIG. 10 is a schematic diagram of another structure of the first device in an embodiment of the application.
  • FIG. 11 is a schematic diagram of another structure of the second device in an embodiment of the application.
  • the embodiment of the present application provides a path planning method and related equipment. Based on this method, the index of the characteristic point is transmitted between the first device and the second device, which effectively solves the problem of large vehicle position errors caused by the high time delay of map transmission.
  • the path planning method in the embodiment of the present application may be applied to a terminal, where the terminal may be a smart vehicle, a smart airplane, or a smart robot, etc., and the details are not limited here.
  • the intelligent vehicle system architecture in the embodiment of the present application includes:
  • FIG. 1 is a schematic diagram of a system architecture of an example smart vehicle 100 (or may also be referred to as a vehicle 100) provided by an embodiment of the present application.
  • the components in the smart vehicle 100 may include at least one of a propulsion system 101, a sensing system 103, a planning system 105, a control system 107, a peripheral device 109, a power supply 110, a computing device 111, and a user interface 112.
  • the main function of the propulsion system 101 is to provide power to the smart vehicle 100.
  • the propulsion system 101 includes an engine/motor 118, an energy source 120, a rotating device 122 and tires/tires 124.
  • the engine/engine 118 may be or include any combination of an internal combustion engine, an electric motor, a steam engine, a Stirling engine, and the like. Other engines and engines are also possible.
  • the propulsion system 101 may include multiple types of engines and/or engines.
  • an electric hybrid car may include a gasoline engine and an electric motor. Other examples are possible.
  • the main function of the energy source 120 is a source of energy for supplying power to the engine/motor 118 in whole or in part. That is, the engine/motor 118 can be used to convert the energy source 120 into mechanical energy.
  • energy sources 120 include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other sources of electricity.
  • the energy source(s) 120 may additionally or alternatively include any combination of fuel tanks, batteries, capacitors, and/or flywheels. In some examples, the energy source 120 may also provide energy for other systems of the smart vehicle 100.
  • the main function of the transmission 122 is to transmit mechanical power from the engine/motor 118 to the wheels/tires 124.
  • the transmission 122 may include a gearbox, a clutch, a differential, a drive shaft, and/or other elements.
  • the drive shaft includes one or more shafts for coupling to wheels/tires 124.
  • the wheels/tires 124 of the smart vehicle 100 may be configured in various forms, including a unicycle, a bicycle/motorcycle, a tricycle, or a car/truck four-wheel form. Other wheel/tyre forms are also possible, such as those that include six or more wheels.
  • the wheels/tires 124 of the smart vehicle 100 may be configured to rotate differentially with respect to other wheels/tires 124.
  • the wheel/tire 124 may include at least one wheel fixedly attached to the transmission 122 and at least one tire coupled to the edge of the wheel in contact with the driving surface.
  • the wheel/tire 124 may include any combination of metal and rubber, or a combination of other materials.
  • the propulsion system 101 may additionally or alternatively include components other than those shown.
  • the main function of the perception system 103 is to perceive and recognize the external environment and/or the situation of the vehicle itself through devices such as sensors and cameras.
  • the sensor may include at least one of a global positioning system (GPS), an inertial measurement unit (IMU), a radio, a radar (radar), and a camera.
  • GPS global positioning system
  • IMU inertial measurement unit
  • radio radio
  • radar radar
  • camera camera
  • the GPS may be any sensor used to estimate the geographic location of the smart vehicle 100.
  • GPS may include a transceiver to estimate the position of the smart vehicle 100 relative to the earth based on satellite positioning data.
  • the computing device 111 may be used in conjunction with the map data 116 to use GPS to estimate the position of the lane boundary on the road on which the smart vehicle 100 can travel. GPS can also take other forms.
  • the IMU may be used to sense changes in the position and orientation of the smart vehicle 100 based on inertial acceleration and any combination thereof.
  • the combination of sensors may include, for example, an accelerometer and a gyroscope. Other combinations of sensors are also possible.
  • LIDAR laser radar
  • LIDAR is an optical remote sensing technology that can measure the distance to the target or other properties of the target by illuminating the target with light.
  • LIDAR may include a laser source and/or laser scanner configured to emit laser pulses, and a detector for receiving reflections of laser pulses.
  • LIDAR may include a laser rangefinder reflected by a rotating mirror, and scan laser light around the digitized scene in one or two dimensions, so as to collect distance measurement values at specified angular intervals.
  • LIDAR may include components such as light (e.g., laser) sources, scanners and optical systems, light detectors and receiver electronics, and location and navigation systems.
  • LIDAR can be configured to use ultraviolet light (UV), visible light, or infrared light to image objects, and can be used for a wide range of targets, including non-metallic objects.
  • UV ultraviolet light
  • narrow laser beams can be used to map physical features of objects with high resolution.
  • Three-dimensional (3D) imaging can be achieved using both scanning LIDAR systems and non-scanning LIDAR systems.
  • 3D gated viewing laser radar (3D gated viewing laser radar)
  • Imaging LIDAR can also use high-speed detector arrays that are usually constructed on a single chip using complementary metal oxide semiconductor (CMOS) and hybrid complementary metal oxide semiconductor/charge coupled device (CCD) manufacturing technologies And modulation sensitive detector array to perform.
  • CMOS complementary metal oxide semiconductor
  • CCD charge coupled device
  • modulation sensitive detector array to perform.
  • each pixel can be processed locally by demodulating or gating at high speed so that the array can be processed to represent the image from the camera.
  • thousands of pixels can be acquired at the same time to create a 3D point cloud representing objects or scenes detected by LIDAR.
  • the point cloud may include a set of vertices in a 3D coordinate system. These vertices can be defined by X, Y, and Z coordinates, for example, and can represent the outer surface of the object.
  • LIDAR can be configured to create a point cloud by measuring a large number of points on the surface of an object, and can output the point cloud as a data file. As a result of the 3D scanning process of the object through LIDAR, the point cloud can be used to identify and visualize the object.
  • the point cloud can be directly rendered to visualize the object.
  • the point cloud can be converted into a polygonal or triangular mesh model through a process that can be referred to as surface reconstruction.
  • Example techniques for converting a point cloud into a 3D surface may include Delaunay triangulation, alpha shape, and rotating sphere. These techniques include constructing a network of triangles on the existing vertices of the point cloud.
  • Other example techniques may include converting a point cloud into a volumetric distance field, and reconstructing such a defined implicit surface through a moving cube algorithm.
  • the camera can be used for any camera (for example, a still camera, a video camera, etc.) that acquires an image of the environment in which the smart vehicle 100 is located.
  • the camera may be configured to detect visible light, or may be configured to detect light from other parts of the spectrum, such as infrared light or ultraviolet light. Other types of cameras are also possible.
  • the camera may be a two-dimensional detector, or may have a three-dimensional spatial range.
  • the camera may be, for example, a distance detector configured to generate a two-dimensional image indicating the distance from the camera to several points in the environment. To this end, the camera can use one or more distance detection techniques.
  • the camera may be configured to use structured light technology, where the smart vehicle 100 illuminates objects in the environment with a predetermined light pattern, such as a grid or checkerboard pattern, and uses the camera to detect the reflection of the predetermined light pattern from the object. Based on the distortion in the reflected light pattern, the smart vehicle 100 may be configured to detect the distance of the point on the object.
  • the predetermined light pattern may include infrared light or light of other wavelengths.
  • the main function of the planning system 105 is to plan the formal path of the smart vehicle 100 and send control instructions to the control system 107 on the basis of receiving the information sensed by the perception module.
  • the planning system 105 may include an obstacle avoidance system, and the main function of the obstacle avoidance system is to identify, evaluate and avoid or otherwise cross obstacles in the environment where the smart vehicle 100 is located.
  • the main function of the control system 107 is to control the operation of the intelligent vehicle 100 and its components and to receive control instructions from the planning system 105.
  • the control system 107 may include a steering 126, a throttle 128, and a brake 130.
  • the main function of the steering 126 is to adjust the forward direction or direction of the smart vehicle 100.
  • the main function of the throttle 128 is to control the operating speed and acceleration of the engine/engine 118 and thereby control the speed and acceleration of the smart vehicle 100.
  • the main function of the brake 130 is to control the intelligent vehicle 100 to decelerate.
  • braking 130 may use friction to slow the wheels/tires 124.
  • the control system 107 may additionally or alternatively include components other than those shown.
  • the main function of the peripheral device 109 is to interact with external sensors, other vehicles and/or users.
  • the peripheral device 109 may include, for example, a wireless communication system 132, a touch screen 134, a microphone 136, and a speaker 138.
  • the wireless communication system 132 may be any system that is configured to be directly or wirelessly coupled to one or more other vehicles, sensors, or other entities via the same wireless communication system.
  • the wireless communication system 132 may include an antenna and chipset for communicating with other vehicles, sensors, or other entities directly or through an air interface.
  • the chipset or the entire wireless communication system 132 may be configured to communicate according to one or more other types of wireless communication, such as Bluetooth, communication protocol, cellular technology, and radio frequency identification (RFID) communication.
  • RFID radio frequency identification
  • the main function of the touch screen 134 is for the user to input commands to the smart vehicle 100.
  • the touch screen 134 may be configured to sense at least one of the position of the user's finger and the movement of China via capacitance sensing, resistance sensing, or surface acoustic wave process, or the like.
  • the touch screen 134 may be capable of sensing finger movement in a direction parallel to the surface of the touch screen or in the same plane as the surface of the touch screen, in a direction perpendicular to the surface of the touch screen, or in both directions, and may also sense finger movement applied to the touch screen.
  • the level of pressure on the surface may be formed of one or more translucent or transparent insulating layers and one or more translucent or transparent conductive layers.
  • the touch screen 134 may also take other forms.
  • the main function of the microphone 136 is to receive user audio of the smart vehicle 100 (for example, voice commands or other audio input).
  • the speaker 138 may be configured to output audio to the user of the smart vehicle 100.
  • the computing device 111 may include a processor 113 and a memory 114.
  • the computing device 111 may be a controller or a part of the controller of the smart vehicle 100.
  • the memory 114 may include instructions 115 executable by the processor 113, and may also store map data 116.
  • the map data 116 may be a grid map, a point cloud map, etc., and the map data 116 may also take other forms.
  • the components of the smart vehicle 100 may be configured to work in an interconnected manner with each other and/or with other components coupled to various systems.
  • the power supply 110 may provide power to all components of the smart vehicle 100.
  • the computing device 111 may be configured to receive data from the propulsion system 101, the sensing system 103, the planning system 105, the control system 107, and the peripheral devices 109 and control them.
  • the computing device 111 may be configured to generate a display of images on the user interface 112 and receive input from the user interface 112.
  • the smart vehicle 100 may include more, fewer, or different systems or modules, and each system/module may include more, fewer, or different components.
  • the systems/modules and components shown in FIG. 1 can be combined or divided in any manner.
  • the sensing system 103 and the planning system 105 can be independent or integrated into one device.
  • the planning system 105 and the control system 107 may be independent or integrated into one device.
  • the driving speed of the smart vehicle is less than the first threshold in the low-speed mode, and the driving speed is greater than the first threshold in the high-speed mode as an example for schematic illustration.
  • the low-speed mode may be that the traveling speed of the smart vehicle is less than or equal to the first threshold
  • the high-speed mode may be that the traveling speed of the smart vehicle is greater than the first threshold.
  • the low-speed mode may be that the traveling speed of the smart vehicle is less than the first threshold
  • the high-speed mode may be that the traveling speed of the smart vehicle is greater than or equal to the first threshold.
  • the above-mentioned first threshold may be pre-configured, or set in advance according to actual needs, or prescribed or restricted by laws, regulations or road driving rules, which is not specifically limited in this application.
  • the “less than” appearing in the embodiments of the present application may be “less than” or “less than or equal to”.
  • the “greater than” appearing in the embodiments of the present application can be “greater than” or “greater than or equal to”. That is: when “less than” is “less than”, “greater than” is “greater than or equal to”. When “less than” is “less than or equal to”, “greater than” is “greater than”. The details are not limited here.
  • the first device in the embodiment of the present application may be a planning system, or an internal element in the planning system, such as a chip or integrated circuit
  • the second device may be a sensing system or an internal element in the sensing system, such as a chip or integrated circuit
  • the third device may be a control system or an internal component in the control system, such as a chip or an integrated circuit.
  • an embodiment of the path planning method in the embodiment of the present application includes:
  • the first device sends a map update request to the second device. This step is optional. It can also be understood that the first device may not send a map update request to the second device.
  • the triggering condition of this step can be in multiple ways. For example, optionally, when the speed of the smart vehicle is less than the first threshold, the first device sends a map update request to the second device, or it can trigger the first device every other cycle. Send a map update request to the second device. It can be understood that in actual applications, it can also be triggered by other conditions. Among them, the period can be set as needed, which can be 30 minutes or 1 hour, etc. The trigger conditions and period of this step The specific setting method is not limited here.
  • the first device may obtain the speed of the smart vehicle, and determine the magnitude of the speed of the smart vehicle and the first threshold. When the speed of the smart vehicle is less than the first threshold, execute this step. When the speed of the smart vehicle is greater than the first threshold, step 205 is executed.
  • this step may be executed when the speed of the smart vehicle is less than or equal to the first threshold, and step 205 may be executed when the speed of the smart vehicle is greater than the first threshold. It is also possible to execute this step when the speed of the smart vehicle is less than the first threshold value, and execute step 205 when the speed of the smart vehicle is greater than or equal to the first threshold value. The details are not limited here.
  • the speed information of the smart vehicle acquired by the first device may come from the speed information measured by the speed measuring device other than the first device, for example, from the speed information sensed by the speed sensor in the second device.
  • a speed sensor for detecting speed information may also be installed in the first device, and the specific speed determination method is not limited here.
  • the first device can directly determine the speed of the smart vehicle through the speed sensor, or indirectly determine the speed of the smart vehicle, for example, by collecting the number of pulses per unit time.
  • the wheel speed or engine speed can also be used, which is not specifically limited here.
  • the first threshold value is only 10 kilometers per hour (km/h) as an example for schematic illustration. It is understandable that in practical applications, the first threshold value is set according to actual needs, and may be 20 km/h. h or 40km/h, etc., which are not specifically limited here.
  • the thresholds (the first threshold, the second threshold, and the preset conditions) in the embodiments of the present application can be set in many ways.
  • the message can be transmitted through the controller area network (CAN) bus or solidified in the program, which is not specifically limited here.
  • CAN controller area network
  • the second device acquires the first map.
  • the timing for the second device to acquire the first map may be after the second device receives the map update request sent by the first device, or it may be acquired in advance.
  • the second device acquires the first map, because the first map at this time is new, which is beneficial to subsequent generation of better second path information.
  • the first map is a raster map as an example for schematic description. It can be understood that, in actual applications, the first map may also be a point cloud map or other types of maps. Make a limit.
  • the second device may obtain the first map through other devices such as ultrasonic sensors on the smart vehicle, GPS, etc.
  • the specifics are not limited here.
  • the map is acquired by ultrasonic sensors or other devices on the smart vehicle, so the smart vehicle is always located at the center of the map.
  • the second device sends the first map to the first device; this step is optional. It can also be understood that the first device may obtain the first map in other possible ways.
  • the second device after acquiring the first map, the second device sends the first map to the first device.
  • the first device generates second path information according to the outline of the obstacle in the first map; this step is optional. It can also be understood that the first device may generate the second path information in other ways.
  • the first device determines the second route information according to the outline of the obstacle in the first map, and the smart vehicle can drive according to the second route in the second route information.
  • the first map 300 is a grid map, and the first map 300 contains an obstacle outline 301.
  • the first device generates a second path 302 through the obstacle contour 301 in the first map 300.
  • the vehicle travels according to the second path 302 and does not contact the obstacle contour 301.
  • the obstacle outline in the embodiment of the present application can be represented by an unclosed broken line composed of points (as shown in the upper part 301 in FIG. 3), or it may be a closed pattern formed by multiple line segments (in the lower part 301 in FIG. 3). Shown), etc.
  • the specific form of the obstacle profile is not limited here.
  • FIG. 3 only illustrates that the first map 300 contains an obstacle outline 301, and the specific obstacle outline 301 and the number of grids in the first map 300 are not limited here.
  • the first device sends the first index of at least one characteristic point to the second device.
  • the trigger condition of this step can be in various ways. For example, when the speed of the smart vehicle is greater than the first threshold, the first device is triggered to send the first index of at least one characteristic point to the second device, or the first index can be triggered every other cycle. One device sends the first index of at least one feature point to the second device. It is understandable that in practical applications, it can also be triggered by other conditions. Among them, the period can be set as needed, which can be 30 minutes or 1 hour, etc.
  • the trigger condition and period setting method of this step are not specifically limited here.
  • the first device first determines the vertices of the convex hull according to the contour of the first obstacle in the first map, and uses the representative convex hull vertices as feature points (402 as shown in FIG. 4).
  • the convex hull vertex involved in this application can be an inflection point on the contour of the obstacle (as shown by 403 in Figure 4), or any point on the contour of the obstacle.
  • the inflection point is a convex point on the contour of the obstacle, It is conducive to subsequent path planning, and the specific form of the convex hull vertex is not limited here.
  • the first device determines a plurality of convex hull vertices according to the obstacle contour line 401 in the first map, and uses the convex hull vertices 402 that are closer to the second path 403 among the convex hull vertices as the feature points. , Or the convex hull vertex 402 close to the side of the smart vehicle as a feature point.
  • the first map is a 20 by 20 grid map (as shown in FIG. 4), and the two feature points 402 in FIG. 4 are taken as an example for description.
  • the coordinates of the two feature points 402 are (5, -1) and (-4, -5), respectively.
  • (5, -1) means that the point is in positive five rows and negative one column
  • (-4, -5) means that the point is in negative four rows and negative five columns.
  • the first indexes corresponding to the two coordinates are 005101 and 104105 respectively.
  • 005 in 005101 indicates that the point is in the positive five rows
  • 101 indicates that the point is in the negative column.
  • 104 in 104105 indicates that the point is in the minus four row, and 105 indicates that the point is in the minus five column.
  • the method for determining the first index corresponding to the remaining feature points is similar, and will not be repeated here.
  • the number of feature points in the embodiments of the present application may be different according to actual conditions, and the specific points are not limited here.
  • the first device After the first device determines the first index corresponding to the at least one characteristic point, the first device sends the first index to the second device.
  • the second device acquires the second map.
  • the timing for the second device to acquire the second map may be after receiving the first index sent by the second device, or before receiving the first index sent by the second device, after sending the first map, which is not specifically limited here. .
  • acquiring the second map can make the acquired second map a new map, and the solution is optimal.
  • the second device After receiving the first index sent by the first device, the second device acquires the second map at the current moment, that is, the second map is a new map, that is, the second map is generated later than the first map.
  • the second device sends a second index of at least one characteristic point to the first device.
  • the second device After acquiring the second map, the second device determines the second index of the feature point corresponding to the first index in the second map by comparing the first map with the second map, that is, to update the index of the feature point in the new map, The first index is the index of the feature point in the old map, and the second index is the index of the feature point in the new map. After determining the second index, the second device sends the second index to the first device.
  • the first indexes of the two feature points 503 in the first map 500 are 005101 and 104105, respectively.
  • the second device determines that the second indexes of the two feature points 503 in the second map 502 are 007006 and 102002, respectively.
  • the second device may mark the second map as a historical map to facilitate subsequent continuous updating of the index of the feature point in the new map.
  • the first device generates first path information according to the second index.
  • the first device After the first device receives the second index sent by the second device, it is mapped into plane coordinates according to the second index.
  • step 205 and step 207 the plane coordinates are mapped according to the second index. That is, 007 in 007006 indicates that the point is in positive seven rows, and 006 indicates that the point is in positive six columns, that is, the coordinate value corresponding to the point is (7, 6). 102 in 102002 indicates that the point is in the negative two rows, and 002 indicates that the point is in the positive two columns, that is, the coordinate value corresponding to the point is (-2, 2).
  • the first device generates first route information according to the mapped coordinate values, and the smart vehicle can travel according to the first route in the first route information.
  • the first device sends a control signal or control information to the third device.
  • the first device After the first device generates the first route information, it may send a control signal or control information to the third device, where the control signal or control information is used to control the smart vehicle to travel according to the first route.
  • the first device determines at least one target feature point.
  • the first device After the first device generates the first path, it determines the target feature points whose distance from the first path 505 is less than the second threshold. That is, determining the feature points that need to be tracked continuously can reduce the data transmission of unimportant feature points.
  • the second threshold in the embodiment of the present application is set according to actual needs, for example, set to 1 meter or 0.5 meter. The details are not limited here.
  • the second threshold is 1 meter
  • the feature point 503 on the right side of the smart vehicle in Figure 5 is less than 1 meter away from the first path 505
  • the first device determines that the feature point 503 on the right side of the smart vehicle is The target feature point, and the target index corresponding to the target feature point is determined. Since step 208 has been analyzed above, it will not be repeated here, that is, the target index is 102002.
  • judging the distance between the first path and the target feature point can be the vertical distance from the target feature point to the first path, or the distance between the target feature point and the point where the intelligent vehicle is located at the current moment, which is not specifically limited here. , Subject to the distance relationship between the characteristic point and the path.
  • the first device sends the first target index of at least one target feature point to the second device.
  • the first device After determining the target feature point, the first device sends the first target index of the target feature point to the second device.
  • the second device acquires the third map
  • the timing for the second device to obtain the third map may be after receiving the first target index sent by the second device, or before receiving the first target index sent by the second device, which is not specifically limited here.
  • acquiring the third map can make the acquired third map the latest map, and the solution is optimal.
  • the second device After receiving the first index sent by the first device, the second device acquires the third map at the current moment, that is, the third map is a new map, that is, the generation time of the third map is later than the second map.
  • the second device sends a second target index of at least one target feature point to the first device.
  • the second device determines the second target index of the target feature point corresponding to the first target index in the third map by comparing the latest map (the third map) with the historical map (the first map), that is, It is the index of the updated feature point.
  • the first index is the index of the feature point in the old map
  • the second index is the index of the feature point in the new map.
  • the first indexes of the two feature points 503 in the first map 500 are 005101 and 104105, respectively.
  • the second device determines that the second indexes of the two feature points 503 in the second map 502 are 007006 and 102002, respectively.
  • the second device may mark the second map as a historical map to facilitate subsequent continuous updating of the index of the feature in the new map.
  • the first device generates third path information according to the second target index.
  • the first device After the first device receives the second target index sent by the second device, it is mapped into plane coordinates according to the second target index. For details, reference may be made to the first device in step 208 to generate the first path information according to the second index, which will not be repeated here.
  • the third path information generated in this step is optimized compared to the second path information in step 208.
  • Steps 211 to 214 are to repeatedly refresh the index of the feature point to be tracked in the latest map, and generate path information.
  • repeating steps 211 to 214 to continuously update the new index of the target feature point to be tracked in the latest map can reduce the data transmission of unimportant feature points and reduce the time delay.
  • the second device determines that there is a second obstacle
  • This step may be before step 214 or after step 212, as long as it is after step 206.
  • the second device compares the third map with the second map, and can determine the newly added second obstacle in the third map.
  • the second device compares the second map with the first map, and can determine the second obstacle added in the second map.
  • the second device judges the target value of the second obstacle approaching the path based on the posture of the vehicle.
  • the target value is used as a probability or distance for a schematic description. It is understandable that the target value may also be other parameters, which are not specifically limited here.
  • the target value is 90%. That is, the second device determines that if the smart vehicle continues to drive along the planned path, there will be a 90% probability of hitting the second obstacle.
  • the target value is 0.1 meters. That is, if the distance of the second obstacle close to the path is 0.1 meters based on the historical driving situation, the smart vehicle will continue to drive and hit the second obstacle.
  • step 208 the planned path is the first path. If this step is before step 208, the planned path is the second path.
  • the second device sends an alarm message to the first device
  • the preset conditions in the embodiments of the present application can be pre-configured or set according to actual needs. For example, combined with historical paths, it is concluded that 30% is dangerous to a smart vehicle, and the preset condition is that if the smart vehicle follows If the planned route continues to travel, there will be a 30% probability of hitting the new obstacle.
  • the specific value is not limited here.
  • the target value is used to indicate how close the second obstacle is to the smart vehicle.
  • the target value and the preset condition can be a probability, or can be a parameter such as a distance or a difference, which is not specifically limited here.
  • the preset condition is greater than the third threshold, assuming that the target value is 90%. If the target value is greater than the third threshold (that is, the target value is 90% greater than 30%, the smart vehicle in Figure 5 continues to drive along the planned path, There is a 90% probability of hitting the second obstacle), and the second device sends an alarm message to the first device.
  • the second device can determine the distance D1 between the second obstacle and the smart vehicle at the current moment, and at the time before the determination, the distance D2 between the second obstacle and the smart vehicle, if The difference between D1-D2 is less than or equal to 0 (equivalent to that the distance between the smart vehicle and the second obstacle at the current moment is less than the distance between the smart vehicle and the second obstacle at the previous moment, that is, the second obstacle and the smart vehicle are getting closer ), and D1 is less than the distance of the fourth threshold, the second device sends alarm information to the first device.
  • the second device may also first define a reference point based on information such as the historical trajectory of the smart vehicle, that is, the second device infers the location information of the next smart vehicle based on the historical trajectory and vehicle attitude, and then determines the position information of the next smart vehicle.
  • the distance between the second obstacle and the location information if the distance is less than a certain value, it can be determined that the second obstacle is potentially dangerous.
  • the first device sends a deceleration signal to the third device.
  • the first device After the first device receives the warning information from the second device, it can send a deceleration signal to the third device.
  • the third device controls the smart vehicle to decelerate to less than 10km/h, which prevents the smart vehicle from driving out of the first map without target feature points Feedback, at this time, decelerate to less than 10km/h, and then realize the second device and the first device to transmit the map.
  • steps 201 to 204 may be referred to as a low-speed mode
  • steps 205 to 208 or steps 205 to 209 may be referred to as a high-speed mode
  • steps 215 and 216 or steps 215 to 217 may be referred to as an early warning mode.
  • the embodiments of this application can be applied to "high speed” mode, "high speed-early warning” mode, "low speed-high speed” mode, “low speed-high speed-early warning” mode, “low speed-high speed-early warning-low speed” mode or "low speed-high speed” -Early warning-low speed-high speed "mode, etc.
  • Step 209 in the embodiment of the present application may be after step 210 or after step 214.
  • the low-speed mode from step 201 to step 204 can also be after steps 205 to 208 (that is, the low-speed mode can be after the high-speed mode or before the high-speed mode), and the details are not limited here.
  • the first device and the second device in the embodiment of the present application are two separate devices (the two devices can perform data transmission through a CAN bus or a wireless connection).
  • the first device and the third device may be two separate devices, or an integrated device (planning control device).
  • the first device is a multi-domain controller (MDC) or a smart driving domain controller, or both the first device and the third device may belong to a part of the MDC.
  • MDC multi-domain controller
  • smart driving domain controller or both the first device and the third device may belong to a part of the MDC.
  • the second device and the first device when the driving speed of the terminal is less than the first threshold, the second device and the first device are used to transmit the map, so that the first device generates the second route according to the map.
  • the traveling speed of the terminal is greater than the first threshold, the second device and the first device transmit the characteristic points, so that the first device generates the first route according to the characteristic points, and the transmission time using the characteristic points is less than the transmission time of the first map ,
  • the terminal is slowed down to the speed of the transmission map to prevent the terminal from crashing due to the feature points that are not tracked.
  • an embodiment of the first device in the embodiment of the present application includes:
  • the sending unit 601 is configured to send a first index of at least one feature point to the second device, the at least one feature point is a feature point of the first obstacle in the first map, and the first index is used to indicate that the at least one feature point is in the first map. A location on the map.
  • the receiving unit 602 is configured to receive a second index of at least one feature point from the second device, the second index is used to indicate the position of the at least one feature point in the second map, and the second map is generated later than the first map The moment of generation.
  • the generating unit 603 is configured to generate first path information according to the second index, where the first path information is used to indicate a first path for the terminal.
  • the sending unit 601 sends the first index of the feature point in the first map to the second device
  • the receiving unit 602 receives the second index of the feature point in the second map from the second device
  • the generating unit 603 is based on
  • the second index generates the first path information
  • the sending unit 601, the receiving unit 602, and the second device transmit the index of the characteristic point, so that the generating unit 603 generates the first path information according to the index of the characteristic point, and transmits it using the index of the characteristic point.
  • the duration of is less than the duration of map transmission, which avoids the problem of large terminal position errors caused by the high delay of map transmission.
  • another embodiment of the first device in the embodiment of the present application includes:
  • the sending unit 701 is configured to send a first index of at least one feature point to the second device, the at least one feature point is a feature point of the first obstacle in the first map, and the first index is used to indicate that the at least one feature point is in the first map. A location on the map.
  • the receiving unit 702 is configured to receive a second index of at least one feature point from the second device, the second index is used to indicate the position of the at least one feature point in the second map, and the second map is generated later than the first map The moment of generation.
  • the generating unit 703 is configured to generate first path information according to the second index, where the first path information is used to indicate a first path for the terminal.
  • the first determining unit 704 is configured to determine that the speed of the terminal is greater than the first threshold.
  • the second determining unit 705 is configured to determine that the speed of the terminal is less than the first threshold.
  • the third determining unit 706 is configured to determine at least one target feature point, the at least one target feature point belongs to at least one feature point, and the distance between the at least one target feature point and the first path is less than the second threshold.
  • the sending unit 701 is further configured to send a control signal to the third device, where the control signal is used to control the terminal to move according to the first path information; send a map update request to the second device; and send the first device of at least one target feature point to the second device A target index, where the first target index is position information of at least one target feature point in the first map.
  • the receiving unit 702 is further configured to receive a first map from the second device; to receive a second target index of at least one target feature point from the second device, and the second target index is used to indicate that at least one target feature point is on the third map.
  • the position in, the generation time of the third map is later than the generation time of the second map; it is also used to receive alarm information from the second device, and the alarm information is used to indicate that the speed value of the terminal is less than the first threshold.
  • the generating unit 703 is further configured to generate second path information according to the outline of the obstacle in the first map, the second path information is used to indicate the second path for the terminal; the third path information is generated according to the second target index, and the third path information is The path information is used to indicate the third path for the terminal.
  • the first determining unit 704, the second determining unit 705, and the third determining unit 706 in this embodiment may be the same determining unit or different determining units, which are not specifically limited here.
  • the sending unit 701, the receiving unit 702, and the second device transmit the map so that the generating unit 703 generates the second route according to the map.
  • the sending unit 701, the receiving unit 702, and the second device transmit the characteristic points, so that the generating unit 703 generates the first path according to the characteristic points, and the transmission time using the characteristic points is less than the first path.
  • the time length of map transmission avoids the problem of large terminal position error caused by the high delay of transmitting the first map.
  • the receiving unit 702 receives the alarm information of the second device to slow down, thereby ensuring the safety of the terminal.
  • An embodiment of the second device in the embodiment of the present application includes:
  • the receiving unit 801 is configured to receive a first index of at least one feature point from a first device, the at least one feature point is a feature point of the first obstacle in the first map, and the first index is used to indicate that the at least one feature point is The location in the first map.
  • the acquiring unit 802 is configured to acquire a second map, and the generation time of the second map is later than the generation time of the first map.
  • the sending unit 803 is configured to send a second index to the first device, the second index is used to indicate the position of the at least one feature point in the second map, and the second index is used to indicate the first path information for the terminal.
  • the receiving unit 801 and the acquiring unit 802 in this embodiment may be the same unit or different units, and the details are not limited here.
  • the receiving unit 801 receives the first index of at least one feature point from the first device, the acquiring unit 802 acquires the second map, and the sending unit 803 sends the second index to the first device, so that the first device according to the first index
  • the second index generates the first path information.
  • the receiving unit 801, the sending unit 803, and the first device transmit the index of the feature point, so that the first device generates the first path information according to the index of the feature point.
  • the transmission time using the index of the feature point is less than the time of map transmission. Due to the high time delay of the transmission of the map, the terminal position error is large.
  • another embodiment of the second device in the embodiment of the present application includes:
  • the receiving unit 901 is configured to receive a first index of at least one feature point from the first device, the at least one feature point is a feature point of the first obstacle in the first map, and the first index is used to indicate that the at least one feature point is The location in the first map.
  • the acquiring unit 902 is configured to acquire a second map, and the generation time of the second map is later than the generation time of the first map.
  • the sending unit 903 is configured to send a second index to the first device, the second index is used to indicate the position of the at least one feature point in the second map, and the second index is used to indicate the first path information for the terminal.
  • the determining unit 904 is configured to determine that there is a second obstacle, the second obstacle exists on the second map, and the second obstacle does not exist on the first map.
  • the receiving unit 901 is further configured to receive a map update request from the first device; receive a first target index of at least one target feature point from the first device, where the first target index is the number of at least one target feature point in the first map. location information.
  • the acquiring unit 902 is further configured to acquire a third map, and the generation time of the third map is later than the generation time of the second map;
  • the sending unit 903 is further configured to send a second target index to the first device, the second target index is used to indicate the position of the at least one target feature point in the third map, and the second target index is used to indicate the third Path information; also used to send alarm information to the first device if the target value of the second obstacle meets the preset condition, the target value is used to indicate the proximity of the second obstacle to the terminal, and the alarm information is used to indicate the speed of the terminal The value is less than the first threshold.
  • the receiving unit 901 receives the first index of at least one feature point from the first device
  • the acquiring unit 902 acquires the second map
  • the sending unit 903 sends the second index to the first device so that the first The device generates first path information according to the second index.
  • the receiving unit 901, the sending unit 903, and the first device transmit the index of the characteristic point, so that the first device generates the first path information according to the index of the characteristic point.
  • the transmission time using the index of the characteristic point is less than the transmission time of the map. Due to the high time delay of the transmission of the map, the terminal position error is large.
  • the second obstacle is determined by the determining unit 904. If the target value of the second obstacle meets the preset condition, the sending unit 903 sends alarm information to the first device to slow down the first device, thereby ensuring the safety of the terminal. .
  • FIG. 10 is a schematic structural diagram of a first device provided by an embodiment of the present application.
  • the first device 1000 includes at least one processor 1001 and at least one communication interface (ie, the input/output interface 1003 in FIG. 10).
  • the input/output interface 1003 is used to provide input/output of data and/or information for the processor 1001, and the processor 1001 is used to process the data and/or information.
  • the first device 1000 further includes a memory 1004, and the processor 1001 is coupled with the memory 1004 and the input/output interface 1003.
  • the memory 1004 may store one or more application programs, data and/or information. Among them, the memory 1004 may be volatile storage or persistent storage.
  • the program stored in the memory 1004 may include one or more modules, and each module may include a series of command operations on the server.
  • the processor 1001 may be configured to communicate with the memory 1004, and execute a series of instruction operations in the memory 1004 on the first device 1000.
  • the memory 1004 is used to store path information and configuration files
  • the processor 1001 is used to process the speed determination, target feature point determination, and path generation in the aforementioned embodiment shown in FIG. 2.
  • the input and output interface 1003 is used for sending and receiving data of the first device in the embodiment shown in FIG. 2.
  • the first device 1000 may also include one or more power supplies 1002.
  • the first device 1000 may also include at least one wired or wireless network interface, and/or, at least one or more operating systems, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
  • operating systems such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
  • the processor 1001 can perform operations performed by the first device in the embodiment shown in FIG. 2, and details are not described herein again.
  • FIG. 11 is a schematic structural diagram of a second device provided by an embodiment of the present application.
  • the second device 1100 includes at least one processor 1101 and at least one communication interface (ie, the input/output interface 1104 in FIG. 11).
  • the input/output interface 1104 is used to provide input/output of data and/or information for the processor 1101, and the processor 1101 is used to process the data and/or information.
  • the second device 1100 further includes a memory 1105, and the processor 1101 is coupled with the memory 1105 and the input/output interface 1104.
  • the memory 1105 may be volatile storage or persistent storage.
  • the program stored in the memory 1105 may include one or more modules, and each module may include a series of instruction operations on the server.
  • the processor 1101 may be configured to communicate with the memory 1105, and execute a series of instruction operations in the memory 1105 on the second device 1100.
  • the memory 1105 is used to store the first map, the second map, the third map, and the configuration file
  • the processor 1101 is used to process the determination of the second obstacle in the foregoing embodiment shown in FIG. 2.
  • the input and output interface 1104 is used for sending and receiving data of the second device in the embodiment shown in FIG. 2.
  • the second device 1100 may also include at least one power supply 1102, at least one wired or wireless network interface 1103, and/or at least one operating system, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
  • operating system such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.
  • the processor 1101 can perform operations performed by the second device in the foregoing embodiment shown in FIG. 2, and details are not described herein again.
  • the embodiment of the present application also provides a first terminal.
  • the first terminal includes a first device and a second device.
  • the first device is used to perform operations performed by the first device in the embodiment shown in FIG. 2 and the second device is used to perform the embodiment shown in FIG. 2 The operation performed by the second device in the.
  • the embodiment of the present application also provides a second terminal.
  • the second terminal includes a second device, and the second device is used to perform operations performed by the second device in the embodiment shown in FIG. 2 above.
  • the second terminal is connected to the first device through a CAN line, and the first device is used to perform operations performed by the first device in the embodiment shown in FIG. 2.
  • the first terminal and the second terminal may be vehicles (such as smart vehicles), robots (such as express robots or smart robots), airplanes (such as express drones or smart airplanes), ships, and the like.
  • vehicles such as smart vehicles
  • robots such as express robots or smart robots
  • airplanes such as express drones or smart airplanes
  • ships and the like.
  • the disclosed system, device, and method can be implemented in other ways.
  • the device embodiments described above are merely illustrative, for example, the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components may be combined or It can be integrated into another system, or some features can be ignored or not implemented.
  • the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.
  • the units described 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 they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • the functional units in the various embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units may be integrated into one unit.
  • the above-mentioned integrated unit can be implemented in the form of hardware or software functional unit.
  • the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium.
  • the technical solution of the present application essentially or the part that contributes to the existing technology or all or 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 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 methods described in the various embodiments of the present application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), magnetic disks or optical disks and other media that can store program codes. .

Landscapes

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

Abstract

一种路径规划方法，例如智能驾驶或者自动驾驶过程中的路径规划。可以应用于智能车辆、智能机器人以及智能飞机等。第一装置（1000）可以向第二装置（1100）发送至少一个特征点（100）的第一索引（205），再接收来自第二装置（1100）的该至少一个特征点（100）的第二索引（207），并根据第二索引生成第一路径信息（208）。通过第一装置（1000）与第二装置（1100）传输特征点的索引的方式，使得第一装置（1000）根据特征点的索引生成第一路径信息，利用特征点的索引传输的时长小于地图传输的时长，避免由于地图传输的高时延带来终端位置误差大的问题。

Description

一种路径规划方法及相关设备
本申请要求于2020年2月12日提交中国专利局、申请号为202010088731.1、发明名称为“一种路径规划方法及相关设备”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及通信领域，特别涉及一种路径规划方法及相关设备。
背景技术
在自动驾驶或者智能驾驶领域中，汽车使用视频摄像头、雷达传感器、超声波传感器等感知模块来获取周围的交通状况。特别地，在自动泊车辅助系统(auto parking assist，APA)场景中，主要是由环视感知或超声波感知模块提供场景信息，这些场景信息以栅格地图的形式，为路径规划提供最初的判断依据。
现有技术中，感知模块向规划模块发送含有障碍物包络的栅格地图。感知模块将该栅格地图中的数据按照栅格索引分成N份数据，周期性向M帧报文中写入每份数据，总共N个周期发送完毕。规划模块根据该栅格地图规划路径，其中N或M为大于等于2的整数。
但是，当车辆行驶速度高时，由于栅格地图的数据庞大，传输时延大，导致规划模块根据收到的栅格地图再规划的路径与预想规划的路径有偏差，车辆位置误差较大。
发明内容
本申请实施例提供了一种路径规划方法及相关设备，利用特征点的索引传输的时长小于地图传输的时长，避免由于地图的传输的高时延带来的终端位置误差大问题。
本申请实施例第一方面提供了一种路径规划方法，该方法包括：第一装置向第二装置发送至少一个特征点的第一索引，该至少一个特征点为第一障碍物在第一地图中的特征点，第一索引用于指示至少一个特征点在第一地图中的位置。第一装置接收来自第二装置的至少一个特征点的第二索引，第二索引用于指示至少一个特征点在第二地图中的位置，第二地图的生成时刻晚于第一地图的生成时刻。第一装置根据第二索引生成第一路径信息，第一路径信息用于指示用于终端的第一路径。
本申请实施例中，第一装置向第二装置发送第一地图中特征点的第一索引，接收来自第二装置的特征点在第二地图中的第二索引，并根据第二索引生成第一路径信息，通过第一装置与第二装置传输特征点的索引的方式，使得第一装置根据特征点的索引生成第一路径信息，利用特征点的索引传输的时长小于地图传输的时长，避免由于地图的传输的高时延带来的终端位置误差大问题。
可选地，在第一方面的一种可能的实现方式中，上述步骤还包括：第一装置向第三装置发送控制信号或控制信息，该控制信号或控制信息用于控制终端根据第一路径信息进行运动。
该种可能的实现方式中，通过第一装置与第三装置的交互，使得终端根据第一路径信息进行运动。
可选地，在第一方面的一种可能的实现方式中，上述步骤：第一装置向第二装置发送第一地图中特征点的第一索引，包括：当确定终端的速度大于第一阈值时，第一装置向第二装置发送第一地图中特征点的第一索引。
该种可能的实现方式中，通过速度大于阈值时，第一装置向第二装置发送索引，避免由于地图的传输的高时延带来的终端位置误差大问题。
可选地，在第一方面的一种可能的实现方式中，上述步骤：第一装置向第二装置发送至少一个特征点的第一索引之前，还包括：第一装置向第二装置发送更新地图请求，并接收来自第二装置的第一地图。
该种可能的实现方式中，通过接收来自第二装置的第一地图，为后续第一装置发送第一索引提供一种可能。
可选地，在第一方面的一种可能的实现方式中，上述步骤：第一装置向第二装置发送更新地图请求，包括，当确定终端的速度小于第一阈值时，第一装置向第二装置发送更新地图请求。
该种可能的实现方式中，通过速度小于阈值时，第一装置向第二装置发送索引更新地图请求，避免了速度过快时，由于地图的传输的高时延带来的终端位置误差大问题。
可选地，在第一方面的一种可能的实现方式中，上述步骤：第一装置接收来自第二装置的第一地图之后，还包括：第一装置根据第一地图中的障碍物轮廓生成第二路径信息，第二路径信息用于指示用于终端的第二路径。
该种可能的实现方式中，第一装置根据地图生成第二路径信息，可以先为终端规划行驶的路径提供一种方案的可实现性。
可选地，在第一方面的一种可能的实现方式中，上述步骤：第一装置根据第二索引生成用于终端的第一路径信息之后，还包括：第一装置确定至少一个目标特征点，该至少一个目标特征点属于至少一个特征点，至少一个目标特征点与第一路径之间的距离小于第二阈值。
该种可能的实现方式中，第一装置可以确定需要追踪的特征点，降低了传输时延。
可选地，在第一方面的一种可能的实现方式中，上述步骤还包括：第一装置向第二装置发送至少一个目标特征点的第一目标索引，第一目标索引为至少一个目标特征点在第一地图中的位置信息。第一装置接收来自第二装置的至少一个目标特征点的第二目标索引，第二目标索引用于指示至少一个目标特征点在第三地图中的位置，第三地图的生成时刻晚于第二地图的生成时刻。第一装置根据第二目标索引生成第三路径信息，第三路径信息用于指示用于终端的第三路径。
该种可能的实现方式中，第一装置获取需要追踪特征点在新地图中的索引，生成了进一步优化的路径。
可选地，在第一方面的一种可能的实现方式中，上述步骤还包括：第一装置接收来自第二装置的告警信息，该告警信息用于指示终端的速度值小于第一阈值。
该种可能的实现方式中，第一装置通过接收来自第二装置的告警信息，通过告警信息使得终端减速至传输地图的速度，防止终端因为没有追踪的特征点发生撞击危险。
可选地，在第一方面的一种可能的实现方式中，上述步骤：第一地图与第二地图为栅格地图，或第一地图与第二地图为点云地图。
该种可能的实现方式提升了方案的可实现性。
可选地，在第一方面的一种可能的实现方式中，上述步骤：终端为智能车辆、智能飞机或智能机器人。
该种可能的实现方式提升了方案的可实现性。
本申请实施例第二方面提供一种路径规划方法，该方法包括：第二装置接收来自第一装置的至少一个特征点的第一索引，至少一个特征点为第一障碍物在第一地图中的特征点，第一索引用于指示至少一个特征点在第一地图中的位置。第二装置获取第二地图，第二地图的生成时刻晚于第一地图的生成时刻。第二装置向第一装置发送第二索引，第二索引用于指示至少一个特征点在第二地图中的位置以及第二索引用于指示用于终端的第一路径信息。
本申请实施例中，第二装置接收来自第一装置的至少一个特征点的第一索引，获取第二地图，并向第一装置发送第二索引，该第二索引用于指示用于终端的第一路径信息。利用特征点的索引传输的时长小于地图传输的时长，避免由于地图的传输的高时延带来的终端位置误差大问题。
可选地，在第二方面的一种可能的实现方式中，上述步骤：第二装置接收来自第一装置的至少一个特征点的第一索引之前，还包括：第二装置接收来自第一装置的更新地图请求；并根据更新地图请求向第一装置发送第一地图。
该种可能的实现方式中，第二装置根据第一装置的请求发送第一地图，可以先为第一装置的路径规划提供一种方案的可实现性。
可选地，在第二方面的一种可能的实现方式中，上述步骤：第二装置向第一装置发送第二索引之后，还包括：第二装置接收来自第一装置的至少一个目标特征点的第一目标索引，第一目标索引为至少一个目标特征点在第一地图中的位置信息。第二装置获取第三地图，第三地图的生成时刻晚于第二地图的生成时刻。第二装置向第一装置发送第二目标索引，第二目标索引用于指示至少一个目标特征点在第三地图中的位置以及第二目标索引用于指示用于终端的第三路径信息。
该种可能的实现方式中，第二装置向第一装置发送第一装置需要追踪特征点在新地图中的索引，生成了进一步优化的路径。
可选地，在第二方面的一种可能的实现方式中，上述步骤：第二装置获取第二地图之后，还包括：第二装置确定存在第二障碍物，第二障碍物存在于第二地图，第二障碍物不存在于第一地图。若第二障碍物的目标值满足预设条件，第二装置向第一装置发送告警信息，目标值用于指示第二障碍物与终端的靠近程度，告警信息用于指示终端的速度值小于第一阈值。
该种可能的实现方式中，若第二障碍物的目标值满足预设条件，第二装置向第一装置发送告警信息，通过告警信息使得终端减速至传输地图的速度，防止终端因为没有追踪的特征点发生撞击危险。
可选地，在第二方面的一种可能的实现方式中，上述步骤：第一地图与第二地图为栅格地图，或第一地图与第二地图为点云地图。
该种可能的实现方式提升了方案的可实现性。
可选地，在第二方面的一种可能的实现方式中，上述步骤：终端为智能车辆、智能飞机或智能机器人。
该种可能的实现方式提升了方案的可实现性。
本申请第三方面提供一种第一装置，用于执行上述第一方面或第一方面的任意可能的实现方式中的方法。具体地，该装置包括用于执行上述第一方面或第一方面的任意可能的实现方式中的方法的模块或单元。
本申请第四方面提供一种第二装置，用于执行上述第二方面或第二方面的任意可能的实现方式中的方法。具体地，该装置包括用于执行上述第二方面或第二方面的任意可能的实现方式中的方法的模块或单元。
本申请第五方面提供一种第一装置，该第一装置包括至少一个处理器以及至少一个通信接口。至少一个通信接口用于为至少一个处理器提供数据和/或信息的输入/输出；至少一个处理器用于处理数据和/或信息以使得第一装置实现第一方面或第一方面的任意可能的实现方式中的方法。
本申请第六方面提供一种第二装置，该第二装置包括至少一个处理器以及至少一个通信接口。至少一个通信接口用于为至少一个处理器提供数据和/或信息的输入/输出；至少一个处理器用于处理数据和/或信息以使得第一装置实现第二方面或第二方面的任意可能的实现方式中的方法。
本申请第七方面提供了一种计算机存储介质，该计算机存储介质中存储有指令，该指令在计算机上执行时，使得计算机执行前述第一方面或第一方面的任意可能的实现方式、第二方面或第二方面的任意可能的实现方式中的方法。
本申请第八方面提供了一种计算机程序产品，该计算机程序产品在计算机上执行时，使得计算机执行前述第一方面或第一方面的任意可能的实现方式、第二方面或第二方面的任意可能的实现方式中的方法。
本申请第九方面提供了一种车辆，该车辆包括第一装置以及第二装置，第一装置用于执行前述第一方面或第一方面的任意可能的实现方式中的方法，第二装置用于执行前述第二方面或第二方面的任意可能的实现方式中的方法。
其中，第三、第五、第七、第八方面或者其中任一种可能实现方式所带来的技术效果可参见第一方面或第一方面不同可能实现方式所带来的技术效果，此处不再赘述。
其中，第四、第六、第八、第八方面或者其中任一种可能实现方式所带来的技术效果可参见第二方面或第二方面不同可能实现方式所带来的技术效果，此处不再赘述。
附图说明
图1为本申请实施例中智能车辆系统架构示意图；
图2为本申请实施例中路径规划方法一个流程示意图；
图3为本申请实施例中第一地图的一个示意图；
图4为本申请实施例中第一地图中特征点的示意图；
图5为本申请实施例中第二地图的一个示意图；
图6为本申请实施例中第一装置一个结构示意图；
图7为本申请实施例中第一装置另一结构示意图；
图8为本申请实施例中第二装置一个结构示意图；
图9为本申请实施例中第二装置另一结构示意图；
图10为本申请实施例中第一装置另一结构示意图；
图11为本申请实施例中第二装置另一结构示意图。
具体实施方式
本申请实施例提供了一种路径规划方法及相关设备。基于该方法，第一装置与第二装置之间传输特征点的索引，有效的解决了由于地图传输的高时延带来的车辆位置误差大的问题。
下面将结合各个附图对本申请技术方案的实现原理、具体实施方式及其对应能够达到的有益效果进行详细的阐述。
本申请实施例中的路径规划方法可以应用于终端，其中，终端可以是智能车辆，也可以是智能飞机，还可以是智能机器人等，具体此处不做限定。
下面仅以终端为智能车辆为例进行示意性说明。
请参阅图1，本申请实施例中智能车辆系统架构包括：
图1是本申请实施例提供的一种示例智能车辆100(或者也可以称为车辆100)的一种系统架构示意图。智能车辆100中的组件可包括推进系统101、感知系统103、规划系统105、控制系统107、外围设备109、电源110、计算装置111以及用户接口112中的至少一个。
推进系统101主要的功能是向智能车辆100提供动力。如图1所示，推进系统101包括引擎/发动机118、能量源120、转动装置122和车胎/轮胎124。
引擎/发动机118可以是或包括内燃机、电动机、蒸汽机和斯特林发动机等的任意组合。其它发动机和引擎也是可能的、在一些示例中，推进系统101可包括多种类型的引擎和/或发动机。例如，电气混合轿车可包括汽油发动机和电动机。其它示例是可能的。
能量源120主要的功能是全部或部分向引擎/发动机118供能的能量的来源。也就是说，引擎/发动机118可用于为将能量源120转换为机械能。能量源120的示例包括汽油、柴油、其它基于石油的燃料、丙烷、其它基于压缩气体的燃料、乙醇、太阳能电池板、电池和其它电力来源。(一个或多个)能量源120可以额外地或可替换地包括燃料箱、电池、电容器和/或飞轮的任意组合。在一些示例中，能量源120也可以为智能车辆100的其它系统提供能量。
传动装置122主要的功能是把机械动力从引擎/发动机118传送到车轮/轮胎124。为此，传动装置122可包括变速箱、离合器、差速器、驱动轴和/或其它元件。在传动装置122包括驱动轴的示例中，驱动轴包括用于耦合到车轮/轮胎124的一个或多个轴。
智能车辆100的车轮/轮胎124可配置为各种形式，包括单轮车、自行车/摩托车、三轮车或者轿车/卡车四轮形式。其它车轮/轮胎形式也是可能的，诸如包括六个或更多个车轮的那些。智能车辆100的车轮/轮胎124可被配置为相对于其它车轮/轮胎124差速地旋转。在一些示例中，车轮/轮胎124可包括固定地附着到传动装置122的至少一个车轮和与驾驶表面接触的耦合到车轮的边缘的至少一个轮胎。车轮/轮胎124可包括金属和橡胶的任意组合，或者其它材料的组合。
推进系统101可以额外地或可替换地包括除了所示出的那些以外的组件。
感知系统103主要的功能是通过传感器、相机等设备对外界的环境和/或车辆自身的情况进行感知识别。
传感器可以包括全球定位系统(global positioning system，GPS)、惯性测量单元(inertial measurement unit，IMU)、无线电、雷达(radar)以及相机中至少一个。
GPS可以为用于估计智能车辆100的地理位置的任何传感器。为此，GPS可能包括收发器，基于卫星定位数据，估计智能车辆100相对于地球的位置。在示例中，计算装置111可用于结合地图数据116使用GPS来估计智能车辆100可在其上行驶的道路上的车道边界的位置。GPS也可采取其它形式。
IMU可以是用于基于惯性加速度及其任意组合来感测智能车辆100的位置和朝向变化。在一些示例中，传感器的组合可包括例如加速度计和陀螺仪。传感器的其它组合也是可能的。
雷达还包含激光雷达(laser radar，LIDAR)。LIDAR是可通过利用光照射目标来测量到目标的距离或目标的其它属性的光学遥感技术。作为示例，LIDAR可包括被配置为发射激光脉冲的激光源和/或激光扫描仪，和用于为接收激光脉冲的反射的检测器。例如，LIDAR可包括由转镜反射的激光测距仪，并且以一维或二维围绕数字化场景扫描激光，从而以指定角度间隔采集距离测量值。在示例中，LIDAR可包括诸如光(例如，激光)源、扫描仪和光学系统、光检测器和接收器电子器件之类的组件，以及位置和导航系统。
在示例中，LIDAR可被配置为使用紫外光(UV)、可见光或红外光对物体成像，并且可用于广泛的目标，包括非金属物体。在一个示例中，窄激光波束可用于以高分辨率对物体的物理特征进行地图绘制。
使用扫描LIDAR系统和非扫描LIDAR系统两者可实现三维(3D)成像。“3D选通观测激光RADAR(3D gated viewing laser radar)”是非扫描激光测距系统的示例，其应用脉冲激光和快速选通相机。成像LIDAR也可使用通常使用互补金属氧化物半导体(complementary metal oxide semiconductor，CMOS)和混合互补金属氧化物半导体/电荷耦合器件(charge coupled device，CCD)制造技术在单个芯片上构建的高速检测器阵列和调制敏感检测器阵列来执行。在这些装置中，每个像素可通过以高速解调或选通来被局部地处理，以使得阵列可被处理成表示来自相机的图像。使用此技术，可同时获取上千个像素以创建表示LIDAR检测到的物体或场景的3D点云。
点云可包括3D坐标系统中的一组顶点。这些顶点例如可由X、Y、Z坐标定义，并且可表示物体的外表面。LIDAR可被配置为通过测量物体的表面上的大量点来创建点云，并可将点云作为数据文件输出。作为通过LIDAR的对物体的3D扫描过程的结果，点云可用于识别并可视化物体。
在一个示例中，点云可被直接渲染以可视化物体。在另一示例中，点云可通过可被称为曲面重建的过程被转换为多边形或三角形网格模型。用于将点云转换为3D曲面的示例技术可包括德洛内三角剖分、阿尔法形状和旋转球。这些技术包括在点云的现有顶点上构建三角形的网络。其它示例技术可包括将点云转换为体积距离场，以及通过移动立方体算法重建这样定义的隐式曲面。
相机可以用于获取智能车辆100所位于的环境的图像的任何相机(例如，静态相机、视频相机等)。为此，相机可被配置为检测可见光，或可被配置为检测来自光谱的其它部分(诸如红外光或紫外光)的光。其它类型的相机也是可能的。相机可以是二维检测器，或可具有三维空间范围。在一些示例中，相机例如可以是距离检测器，其被配置为生成指示从相机到环 境中的若干点的距离的二维图像。为此，相机可使用一种或多种距离检测技术。例如，相机可被配置为使用结构光技术，其中智能车辆100利用预定光图案，诸如栅格或棋盘格图案，对环境中的物体进行照射，并且使用相机检测从物体的预定光图案的反射。基于反射的光图案中的畸变，智能车辆100可被配置为检测到物体上的点的距离。预定光图案可包括红外光或其它波长的光。
规划系统105主要的功能是在收到感知模块感知的信息基础上，规划智能车辆100的形式路径并向控制系统107发送控制指令。规划系统105可以包括避障系统，避障系统的主要功能是识别、评估和避免或者以其它方式越过智能车辆100所位于的环境中的障碍物。
控制系统107的主要功能是控制智能车辆100及其组件的操作以及接收规划系统105的控制指令。为此，控制系统107可包括转向126、油门128、制动130。
转向126的主要功能是调整智能车辆100的前进方向或方向。
油门128的主要功能是控制引擎/发动机118的操作速度和加速度并进而控制智能车辆100的速度和加速度。
制动130的主要功能是控制智能车辆100减速。例如，制动130可使用摩擦来减慢车轮/轮胎124。
控制系统107可以额外地或可替换地包括除了所示出的那些以外的组件。
外围设备109的主要功能是与外部传感器、其它车辆和/或用户交互。外围设备109可以包括例如无线通信系统132、触摸屏134、麦克风136以及扬声器138。
无线通信系统132可以是被配置为直接地或经由同喜窝囊罗无线耦合至一个或多个其它车辆、传感器或其它实体的任何系统。为此，无线通信系统132可包括用于直接或通过空中接口与其它车辆、传感器或其它实体通信的天线和芯片集。芯片集或整个无线通信系统132可被配置为根据一个或多个其它类型的无线通信来通信，无线通信诸如蓝牙、通信协议、蜂窝技术以及射频识别(radio frequency identification，RFID)通信等。
触摸屏134的主要功能是供用户向智能车辆100输入命令。为此，触摸屏134可被配置为经由电容感测、电阻感测或者表面声波过程等等来感测用户的手指的位置和移动中国的至少一者。触摸屏134可能够感测在与触摸屏表面平行或与触摸屏表面在同一平面内的方向上、在于触摸屏便面垂直的方向上或者在这两个方向上的手指移动，并且还可能感测施加到触摸屏表面的压力的水平。触摸屏134可由一个或多个半透明或透明绝缘层和一个或多个半透明或透明导电层形成。触摸屏134也可采取其它形式。
麦克风136的主要功能是接收智能车辆100的用户音频(例如，声音命令或其它音频输入)。类似地，扬声器138可被配置为向智能车辆100的用户输出音频。
计算装置111可包括处理器113和存储器114。计算装置111可以是智能车辆100的控制器或控制器的一部分。存储器114可包括处理器113可运行的指令115，并且还可存储地图数据116，地图数据116可以为栅格地图、点云地图等地图，地图数据116也可采取其它形式。
智能车辆100的组件可被配置为以与彼此互联和/或与耦合到各系统的其它组件互联的工作方式。例如，电源110可向智能车辆100的所有组件提供电力。计算装置111可被配置为从推进系统101、感知系统103、规划系统105、控制系统107以及外围设备109接收数据并 对它们进行控制。计算装置111可被配置为用户接口112上生成图像的显示并从用户接口112接收输入。
可选地，智能车辆100可包括更多、更少或不同的系统或模块，并且每个系统/模块可包括更多、更少或不同的组件。此外，图1示出的系统/模块和组件可以按任意种的方式进行组合或划分，例如：感知系统103与规划系统105可以分别是独立的，也可以是集成到一个装置中。规划系统105与控制系统107可以分别是独立的，也可以是集成到一个装置中。
下面结合图1的系统框架，仅以终端为智能车辆为例进行示意性说明：
本申请实施例中，仅以智能车辆的行驶速度小于第一阈值为低速模式，行驶速度大于第一阈值为高速模式为例进行示意性说明。可以理解的是，低速模式可以为智能车辆的行驶速度小于或等于第一阈值，高速模式为智能车辆的行驶速度大于第一阈值。当然，低速模式可以为智能车辆的行驶速度小于第一阈值，高速模式为智能车辆的行驶速度大于或等于第一阈值。这里需要说明的是，上述第一阈值可以是预先配置的，也可以是根据实际需要提前设置的，或者是法律法规或者道路行驶规则所规定或者约束的，本申请不做具体限定。
本申请实施例中出现的“小于”可以为“小于”也可以为“小于或等于”。本申请实施例中出现的“大于”可以为“大于”，也可以为“大于或等于”。即：当“小于”为“小于”时，“大于”为“大于或等于”。当“小于”为“小于或等于”时，“大于”为“大于”。具体此处不做限定。
本申请实施例中的第一装置可以是规划系统，或者是规划系统中内部元件，例如芯片或者集成电路，第二装置可以是感知系统或者是感知系统中的内部元件，例如芯片或者集成电路，第三装置可以是控制系统或者是控制系统中的内部元件，例如芯片或者集成电路。
请参阅图2，本申请实施例中路径规划方法一个实施例包括：
201、第一装置向第二装置发送更新地图请求。该步骤为可选的。也可以理解为，第一装置可以不向第二装置发送更新地图请求。
本步骤的触发条件可以是多种方式，比如，可选地，在智能车辆的速度小于第一阈值时，第一装置向第二装置发送更新地图请求，也可以每隔一个周期触发第一装置向第二装置发送更新地图请求，可以理解的是，在实际应用中，还可以通过其他条件触发，其中，周期可以根据需要设置，可以为30分钟或1小时等，本步骤的触发条件和周期设置的方式具体此处不做限定。
可选地，在本步骤之前，第一装置可以获取智能车辆的速度，并判断智能车辆的速度与第一阈值的大小。在智能车辆的速度小于第一阈值时，执行本步骤。在智能车辆的速度大于第一阈值时，执行步骤205。
可选地，本申请实施例中，可以在智能车辆的速度小于或等于第一阈值时，执行本步骤，在智能车辆的速度大于第一阈值时，执行步骤205。也可以在智能车辆的速度小于第一阈值时，执行本步骤，在智能车辆的速度大于或等于第一阈值时，执行步骤205。具体此处不做限定。
本申请实施例中的，第一装置获取智能车辆的速度可以来自除了第一装置以外的测速装置测量的速度信息，比如：来自第二装置中的速度传感器感知的速度信息，可以理解的是，第一装置中也可以安装有检测速度信息的速度传感器，具体速度的确定方式此处不做限定。 当然，如果第一装置中安装有检测速度信息的速度传感器，第一装置可以通过速度传感器直接确定智能车辆的速度，也可以间接确定智能车辆的速度，比如：通过采集单位时间轮数脉冲数，还可以通过车轮轮速或发动机转速，具体此处不做限定。
本申请实施例中仅以第一阈值为10千米每小时(km/h)为例进行示意性说明，可以理解的是，在实际应用中，第一阈值根据实际需要设置，可以是20km/h或40km/h等，具体此处不做限定。
本申请实施例中的阈值(第一阈值、第二阈值以及预设条件)的设定可以有多种方式，比如，可以通过修改只读存储器(read only memory，ROM)中的配置文件，还可以通过控制器局域网络(controller area network，CAN)总线传输报文或固化在程序中，具体此处不做限定。
202、第二装置获取第一地图。
可选地，第二装置获取第一地图的时机，可以是在第二装置接收到第一装置发送的更新地图请求后，也可以是提前获取。可选地，在接收到更新地图请求后，第二装置获取第一地图，因为此时的第一地图是新的，有利于后续生成更优的第二路径信息。
本申请实施例中仅以第一地图为栅格地图为例进行示意性说明，可以理解的是，在实际应用中，第一地图也可以是点云地图或其他类型的地图，具体此处不做限定。
本申请实施例中第二装置获取第一地图可以通过智能车辆上的超声波传感器、GPS等其他设备，具体此处不做限定。
当然，可以理解的是，地图的获取由智能车辆上的超声波传感器或其他设备获取，因此智能车辆一直位于地图的中心位置。
203、第二装置向第一装置发送第一地图；该步骤为可选的。也可以理解为，第一装置可以通过其他可能的方式获取第一地图。
可选地，第二装置获取到第一地图后，向第一装置发送第一地图。
204、第一装置根据第一地图中的障碍物轮廓生成第二路径信息；该步骤为可选的。也可以理解为，所述第一装置可以通过其他方式生成第二路径信息。
可选地，第一装置在接收到第一地图后，根据第一地图中的障碍物轮廓，确定第二路径信息，智能车辆可以根据第二路径信息中的第二路径进行行驶。
示例性的，如图3所示，第一地图300为栅格地图，第一地图300中含有障碍物轮廓301。第一装置通过第一地图300中的障碍物轮廓301生成第二路径302。车辆根据第二路径302进行行驶，且不与障碍物轮廓301接触。
本申请实施例中的障碍物轮廓可以是由点构成的一条没有闭合的折线(如图3中上方301所示)表示，也可以是由多个线段形成闭合的图案(如图3中下方301所示)等，障碍物轮廓的具体形式此处不作限定。
可以理解的是，图3仅是举例描述第一地图300中含有障碍物轮廓301，具体的障碍物轮廓301及第一地图300中栅格的数量此处不做限定。
205、第一装置向第二装置发送至少一个特征点的第一索引；
本步骤的触发条件可以是多种方式，比如，在智能车辆的速度大于第一阈值时，触发第一装置向第二装置发送至少一个特征点的第一索引，也可以每隔一个周期触发第一装置向第 二装置发送至少一个特征点的第一索引，可以理解的是，在实际应用中，还可以通过其他条件触发，其中，周期可以根据需要设置，可以为30分钟或1小时等，本步骤的触发条件和周期设置的方式具体此处不做限定。
第一装置先根据第一地图中的第一障碍物轮廓确定凸包顶点，在凸包顶点中将具有代表性的凸包顶点作为特征点(如图4中所示的402)。
本申请涉及的凸包顶点可以是障碍物轮廓上的拐点(如图4中403所示)，也可以是障碍物轮廓上的任意一点，当然，当拐点在障碍物轮廓上为凸点时，有利于后续的路径规划，凸包顶点的具体形式此处不作限定。
如图4所示，第一装置根据第一地图中的障碍物轮廓线401确定多个凸包顶点，在将凸包顶点中与第二路径403的距离较近的凸包顶点402作为特征点，或者靠近智能车辆一侧的凸包顶点402作为特征点。
地图中的特征点与索引是一一对应的。示例性的，第一地图为20乘20的栅格地图(如图4所示)，以图4中的两个特征点402为例进行说明。两个特征点402的坐标分别为(5，-1)和(-4，-5)。(5，-1)表示该点在正五行负一列，(-4，-5)表示该点在负四行负五列。即两个坐标对应的第一索引分别为005101和104105。005101中的005表示该点在正五行，101表示该点在负一列。104105中的104表示该点在负四行，105表示该点在负五列。其余特征点对应的第一索引的确定方法类似，此处不再赘述。本申请实施例中特征点的数量根据实际情况不同可以有所不同，具体这里不做限定。
第一装置确定至少一个特征点对应的第一索引之后，第一装置向第二装置发送第一索引。
206、第二装置获取第二地图；
第二装置获取第二地图的时机可以在接收到第二装置发送的第一索引后，也可以在接收到第二装置发送的第一索引之前，发送第一地图之后，具体此处不做限定。当然，第二装置在接收到第二装置发送的第一索引后，再获取第二地图可以使得获取的第二地图为新地图，方案最优。
当第二装置收到第一装置发送的第一索引后，获取当前时刻的第二地图，即第二地图为新的地图，也即是第二地图的生成时刻晚于第一地图。
207、第二装置向第一装置发送至少一个特征点的第二索引；
第二装置获取第二地图之后，通过对比第一地图与第二地图，确定第一索引对应的特征点在第二地图中的第二索引，也即是更新特征点在新地图中的索引，第一索引为特征点在旧地图中的索引，第二索引为特征点在新地图中的索引。第二装置确定第二索引后，向第一装置发送第二索引。
下面结合图5与步骤205中的举例进行说明：两个特征点503在第一地图500中的第一索引分别为005101和104105。第二装置确定两个特征点503在第二地图502中的第二索引分别为007006和102002。
第二装置向第一装置发送第二索引之后，第二装置可以将第二地图标记为历史地图，方便后续持续更新特征点在新地图中的索引。
208、第一装置根据第二索引生成第一路径信息；
第一装置接收到第二装置发送的第二索引后，根据第二索引映射为平面坐标。
下面继续以步骤205与步骤207中的举例进行说明，当第一装置收到第二索引007006与102002后，根据第二索引映射平面坐标。即007006中的007表示该点在正七行，006表示该点在正六列，即该点对应的坐标值为(7，6)。102002中的102表示该点在负二行，002表示该点在正二列，即该点对应的坐标值为(-2，2)。
第一装置根据映射出来的坐标值生成第一路径信息，智能车辆可以根据第一路径信息中的第一路径进行行驶。
209、第一装置向第三装置发送控制信号或者控制信息；
第一装置生成第一路径信息后，可以向第三装置发送控制信号或者控制信息，该控制信号或者控制信息用于控制智能车辆根据第一路径进行行驶。
210、第一装置确定至少一个目标特征点；
第一装置生成第一路径后，判断与第一路径505距离小于第二阈值的目标特征点。即确定需要继续追踪的特征点，可以减少不重要特征点的数据传输。
本申请实施例中的第二阈值根据实际需要设置，例如，设置为1米或0.5米。具体此处不做限定。
示例性的，第二阈值为1米，图五中位于智能车辆右侧的特征点503，与第一路径505的距离小于1米，则第一装置确定位于智能车辆右侧的特征点503为目标特征点，并确定该目标特征点对应的目标索引，由于上面步骤208分析过，此处不再赘述，即目标索引为102002。
可选地，判断第一路径与目标特征点的距离，可以是目标特征点到第一路径的垂直距离，也可以是目标特征点与当前时刻智能车辆所在点的距离，具体此处不做限定，以能体现特征点于路径之间的距离关系为准。
211、第一装置向第二装置发送至少一个目标特征点的第一目标索引；
第一装置确定目标特征点之后，向第二装置发送目标特征点的第一目标索引。
212、第二装置获取第三地图；
第二装置获取第三地图的时机可以在接收到第二装置发送的第一目标索引后，也可以在接收到第二装置发送的第一目标索引之前，具体此处不做限定。当然，第二装置在接收到第二装置发送的第一目标索引后，再获取第三地图可以使得获取的第三地图为最新地图，方案最优。
当第二装置收到第一装置发送的第一索引后，获取当前时刻的第三地图，即第三地图为新的地图，也即是第三地图的生成时刻晚于第二地图。
213、第二装置向第一装置发送至少一个目标特征点的第二目标索引；
第二装置获取第三地图之后，通过对比最新地图(第三地图)与历史地图(第一地图)，确定第一目标索引对应的目标特征点在第三地图中的第二目标索引，也即是更新特征点的索引，第一索引为特征点在旧地图中的索引，第二索引为特征点在新地图中的索引。第二装置确定第二索引后，向第一装置发送第二索引。
下面结合图5与步骤205中的举例进行说明：两个特征点503在第一地图500中的第一索引分别为005101和104105。第二装置确定两个特征点503在第二地图502中的第二索引分别为007006和102002。
第二装置向第一装置发送第二索引之后，第二装置可以将第二地图标记为历史地图，方便后续持续更新特征在新地图中的索引。
214、第一装置根据第二目标索引生成第三路径信息；
第一装置接收到第二装置发送的第二目标索引后，根据第二目标索引映射为平面坐标。具体可以参考步骤208中的第一装置根据第二索引生成第一路径信息，此处不再赘述。
可以理解的是，本步骤生成的第三路径信息相较于步骤208中第二路径信息是优化的。
步骤211至步骤214也即是重复刷新需要追踪特征点在最新地图中的索引，并生成路径信息。
可选地，重复执行步骤211至214不断更新需要追踪的目标特征点在最新地图中的新索引，可以减少不重要特征点的数据传输，减小时延。
215、第二装置确定存在第二障碍物；
本步骤可以在步骤214之前，也可以在步骤212之后，只要在步骤206之后即可。
如果步骤是在212之后，第二装置在获取第三地图后，对比第三地图与第二地图，可以判断出第三地图中新增的第二障碍物。
如果是在步骤206之后，第二装置在获取第二地图后，第二装置对比第二地图与第一地图，可以判断出第二地图中新增的第二障碍物。
如果新增有第二障碍物(如图5中所示的504)，第二装置基于车姿判断第二障碍物靠近路径的目标值。下面仅以目标值为概率或距离进行示意性说明，可以理解的是，目标值还可以是其他参数，具体此处不做限定。
示例性的，目标值为90％。即第二装置判断出如果该智能车辆按照规划路径继续行驶，将会有90％的概率撞上第二障碍物。
示例性的，目标值为0.1米。即根据历史行驶情况分析第二障碍物靠近路径的距离为0.1米的情况下，智能车辆继续行驶，将会撞上第二障碍物。
如果本步骤在步骤208之后，规划路径为第一路径。如果本步骤在步骤208之前，规划路径为第二路径。
216、若第二障碍物的目标值满足预设条件，第二装置向第一装置发送告警信息；
本申请实施例中的预设条件可以是预先配置的，或者，根据实际需要设置，例如，结合历史路径得出30％是对于智能车辆是有危险的，则预设条件为如果该智能车辆按照规划路径继续行驶，将会有30％的概率撞上新增障碍物。具体数值此处不做限定。
目标值用于指示第二障碍物与智能车辆的靠近程度。目标值和预设条件可以为概率，也可以为距离或差值等参数，具体此处不做限定。
可选地，预设条件为大于第三阈值，假设目标值为90％，若目标值大于第三阈值(即目标值为90％大于30％，图5中智能车辆按照规划路径继续行驶，将会有90％的概率撞上第二障碍物)，第二装置向第一装置发送告警信息。
可选地，预设条件为小于第四阈值，第二装置可以确定当前时刻的第二障碍物与智能车辆的距离D1，在确定之前的时刻，第二障碍物与智能车辆的距离D2，如果D1-D2的差值小于等于0(相当于当前时刻智能车辆与第二障碍物的距离小于上一时刻智能车辆与第二障碍物的距离，即，第二障碍物与智能车辆越来越近)，并且D1小于第四阈值的距离，则第二装置 向第一装置发送告警信息。
可选地，第二装置也可以根据智能车辆的历史轨迹等信息，先定义一个参考点，也即是第二装置根据历史轨迹和车姿推测出下一个智能车辆所在的位置信息，再确定第二障碍物与该位置信息的距离，如果该距离小于某个数值，可以确定该第二障碍物有潜在危险。
217、第一装置向第三装置发送减速信号。
第一装置接收来自第二装置的告警信息后，可以向第三装置发送减速信号，第三装置控制智能车辆减速至小于10km/h，即防止智能车辆行驶出第一地图后，没有目标特征点反馈，此时减速至小于10km/h，进而实现第二装置和第一装置传输地图。
本申请实施例中，步骤201至204可以称为低速模式，步骤205至208或步骤205至209可以称为高速模式，步骤215与步骤216或步骤215至步骤217可以称为预警模式。本申请实施例可以应用在“高速”模式、“高速-预警”模式、“低速-高速”模式、“低速-高速-预警”模式、“低速-高速-预警-低速”模式或“低速-高速-预警-低速-高速”模式等。
本申请实施例中的步骤209可以在步骤210之后，也可以在步骤214之后。步骤201至步骤204的低速模式也可以在步骤205至208之后(即低速模式可以在高速模式后，也可以在高速模式前)，具体此处不做限定。
本申请实施例中的第一装置与第二装置是单独的两个装置(两个装置可以通过CAN总线或者无线连接进行数据传输)。第一装置与第三装置可以是单独的两个装置，也可以是集成的一个装置(规划控制装置)。比如，第一装置为多域控制器(multi domain controller，MDC)或者智能驾驶域控制器，或者第一装置与第三装置都可以属于MDC的一部分。
本申请实施例中，当终端的行驶速度小于第一阈值时，通过第二装置与第一装置传输地图的方式，使得第一装置根据地图生成第二路径。当终端的行驶速度大于第一阈值时，通过第二装置与第一装置传输特征点的方式，使得第一装置根据特征点生成第一路径，利用特征点传输的时长小于第一地图传输的时长，避免由于传输第一地图的高时延带来的终端位置误差大的问题。并通过预警模式使得终端减速至传输地图的速度，防止终端因为没有追踪的特征点发生撞击危险。
上面对本申请实施例中的路径规划方法进行了描述，下面对本申请实施例中的第一装置和第二装置分别进行描述，请参阅图6，本申请实施例中第一装置一个实施例包括：
发送单元601，用于向第二装置发送至少一个特征点的第一索引，至少一个特征点为第一障碍物在第一地图中的特征点，第一索引用于指示至少一个特征点在第一地图中的位置。
接收单元602，用于接收来自第二装置的至少一个特征点的第二索引，第二索引用于指示至少一个特征点在第二地图中的位置，第二地图的生成时刻晚于第一地图的生成时刻。
生成单元603，用于根据第二索引生成第一路径信息，第一路径信息用于指示用于终端的第一路径。
本实施例中，第一装置中各单元所执行的操作与前述图2所示实施例中描述的类似，此处不再赘述。
本实施例中，发送单元601向第二装置发送第一地图中特征点的第一索引，接收单元602接收来自第二装置的特征点在第二地图中的第二索引，生成单元603并根据第二索引生成第一路径信息，通过发送单元601、接收单元602与第二装置传输特征点的索引的方式， 使得生成单元603根据特征点的索引生成第一路径信息，利用特征点的索引传输的时长小于地图传输的时长，避免由于地图的传输的高时延带来的终端位置误差大问题。
请参阅图7，本申请实施例中第一装置另一实施例包括：
发送单元701，用于向第二装置发送至少一个特征点的第一索引，至少一个特征点为第一障碍物在第一地图中的特征点，第一索引用于指示至少一个特征点在第一地图中的位置。
接收单元702，用于接收来自第二装置的至少一个特征点的第二索引，第二索引用于指示至少一个特征点在第二地图中的位置，第二地图的生成时刻晚于第一地图的生成时刻。
生成单元703，用于根据第二索引生成第一路径信息，第一路径信息用于指示用于终端的第一路径。
本实施例中的第一装置还包括：
第一确定单元704，用于确定终端的速度大于第一阈值。
第二确定单元705，用于确定终端的速度小于第一阈值。
第三确定单元706，用于确定至少一个目标特征点，至少一个目标特征点属于至少一个特征点，至少一个目标特征点与第一路径之间的距离小于第二阈值。
发送单元701，还用于向第三装置发送控制信号，控制信号用于控制终端根据第一路径信息进行运动；向第二装置发送更新地图请求；向第二装置发送至少一个目标特征点的第一目标索引，第一目标索引为至少一个目标特征点在第一地图中的位置信息。
接收单元702，还用于接收来自第二装置的第一地图；接收来自第二装置的至少一个目标特征点的第二目标索引，第二目标索引用于指示至少一个目标特征点在第三地图中的位置，第三地图的生成时刻晚于第二地图的生成时刻；还用于接收来自第二装置的告警信息，告警信息用于指示终端的速度值小于第一阈值。
生成单元703，还用于根据第一地图中的障碍物轮廓生成第二路径信息，第二路径信息用于指示用于终端的第二路径；根据第二目标索引生成第三路径信息，第三路径信息用于指示用于终端的第三路径。
本实施例中，第一装置中各单元所执行的操作与前述图2所示实施例中描述的类似，此处不再赘述。
本实施例中的第一确定单元704、第二确定单元705以及第三确定单元706可以是同一确定单元，也可以是不同的确定单元，具体此处不作限定。
本实施例中，当终端的行驶速度小于第一阈值时，通过发送单元701、接收单元702与第二装置传输地图的方式，使得生成单元703根据地图生成第二路径。当终端的行驶速度大于第一阈值时，通过发送单元701、接收单元702与第二装置传输特征点的方式，使得生成单元703根据特征点生成第一路径，利用特征点传输的时长小于第一地图传输的时长，避免由于传输第一地图的高时延带来的终端位置误差大的问题。并通过接收单元702接收第二装置的告警信息来减速，从而保证终端的安全。
下面对本申请实施例中的第二装置进行描述，请参阅图8，本申请实施例中第二装置一个实施例包括：
接收单元801，用于接收来自第一装置的至少一个特征点的第一索引，至少一个特征点为第一障碍物在第一地图中的特征点，第一索引用于指示至少一个特征点在第一地图中的位 置。
获取单元802，用于获取第二地图，第二地图的生成时刻晚于第一地图的生成时刻。
发送单元803，用于向第一装置发送第二索引，第二索引用于指示至少一个特征点在第二地图中的位置以及第二索引用于指示用于终端的第一路径信息。
本实施例中，第二装置中各单元所执行的操作与前述图2所示实施例中描述的类似，此处不再赘述。
本实施例中的接收单元801与获取单元802可以是同一个单元，也可以是不同单元，具体此处不作限定。
本实施例中，接收单元801接收来自第一装置的至少一个特征点的第一索引，获取单元802获取第二地图，发送单元803向第一装置发送第二索引，以使得第一装置根据第二索引生成第一路径信息。通过接收单元801、发送单元803与第一装置传输特征点的索引的方式，使得第一装置根据特征点的索引生成第一路径信息，利用特征点的索引传输的时长小于地图传输的时长，避免由于地图的传输的高时延带来的终端位置误差大问题。
请参阅图9，本申请实施例中第二装置另一实施例包括：
接收单元901，用于接收来自第一装置的至少一个特征点的第一索引，至少一个特征点为第一障碍物在第一地图中的特征点，第一索引用于指示至少一个特征点在第一地图中的位置。
获取单元902，用于获取第二地图，第二地图的生成时刻晚于第一地图的生成时刻。
发送单元903，用于向第一装置发送第二索引，第二索引用于指示至少一个特征点在第二地图中的位置以及第二索引用于指示用于终端的第一路径信息。
本实施例中的第二装置还包括：
确定单元904，用于确定存在第二障碍物，第二障碍物存在于第二地图，第二障碍物不存在于第一地图。
接收单元901，还用于接收来自第一装置的更新地图请求；接收来自第一装置的至少一个目标特征点的第一目标索引，第一目标索引为至少一个目标特征点在第一地图中的位置信息。
获取单元902，还用于获取第三地图，第三地图的生成时刻晚于第二地图的生成时刻；
发送单元903，还用于向第一装置发送第二目标索引，第二目标索引用于指示至少一个目标特征点在第三地图中的位置以及第二目标索引用于指示用于终端的第三路径信息；还用于若第二障碍物的目标值满足预设条件，向第一装置发送告警信息，目标值用于指示第二障碍物与终端的靠近程度，告警信息用于指示终端的速度值小于第一阈值。
本实施例中，第二装置中各单元所执行的操作与前述图2所示实施例中描述的类似，此处不再赘述。
本实施例中，一方面：接收单元901接收来自第一装置的至少一个特征点的第一索引，获取单元902获取第二地图，发送单元903向第一装置发送第二索引，以使得第一装置根据第二索引生成第一路径信息。通过接收单元901、发送单元903与第一装置传输特征点的索引的方式，使得第一装置根据特征点的索引生成第一路径信息，利用特征点的索引传输的时长小于地图传输的时长，避免由于地图的传输的高时延带来的终端位置误差大问题。另一方 面，通过确定单元904确定第二障碍物，若第二障碍物的目标值满足预设条件，发送单元903向第一装置发送告警信息，以使得第一装置减速，从而保证终端的安全。
图10是本申请实施例提供的一种第一装置结构示意图，该第一装置1000包括至少一个处理器1001以及至少一个通信接口(即图10中的输入输出接口1003)。输入输出接口1003用于为处理器1001提供数据和/或信息的输入/输出，处理器1001用于处理该数据和/或信息。
可选地，第一装置1000还包括存储器1004，处理器1001与存储器1004和输入输出接口1003耦合。该存储器1004中可以存储有一个或一个以上的应用程序、数据和/或信息。其中，存储器1004可以是易失性存储或持久存储。存储在存储器1004的程序可以包括一个或一个以上模块，每个模块可以包括对服务器中的一系列指令操作。更进一步地，处理器1001可以设置为与存储器1004通信，在第一装置1000上执行存储器1004中的一系列指令操作。
可选地，存储器1004用于存储路径信息以及配置文件，处理器1001用于处理前述图2所示实施例中的确定速度、确定目标特征点以及生成路径。输入输出接口1003用于前述图2所示实施例中第一装置的发送和接收数据。
第一装置1000还可以包括一个或一个以上电源1002。
进一步地，第一装置1000还可以包括至少一个有线或无线网络接口，和/或，至少一个以上操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM等。
该处理器1001可以执行前述图2所示实施例中第一装置所执行的操作，具体此处不再赘述。
图11是本申请实施例提供的一种第二装置结构示意图，该第二装置1100包括至少一个处理器1101以及至少一个通信接口(即图11中的输入输出接口1104)。输入输出接口1104用于为处理器1101提供数据和/或信息的输入/输出，处理器1101用于处理该数据和/或信息。
可选地，第二装置1100还包括存储器1105，处理器1101与存储器1105和输入输出接口1104耦合。存储器1105可以是易失性存储或持久存储。存储在存储器1105的程序可以包括一个或一个以上模块，每个模块可以包括对服务器中的一系列指令操作。更进一步地，处理器1101可以设置为与存储器1105通信，在第二装置1100上执行存储器1105中的一系列指令操作。
可选地，存储器1105用于存储第一地图、第二地图、第三地图以及配置文件，处理器1101用于处理前述图2所示实施例中的确定第二障碍物。输入输出接口1104用于前述图2所示实施例中第二装置的发送和接收数据。
第二装置1100还可以包括至少一个电源1102，至少一个有线或无线网络接口1103，和/或，至少一个操作系统，例如Windows ServerTM，Mac OS XTM，UnixTM,LinuxTM，FreeBSDTM等。
该处理器1101可以执行前述图2所示实施例中第二装置所执行的操作，具体此处不再赘述。
本申请实施例还提供一种第一终端。该第一终端包括第一装置以及第二装置，其中，第一装置用于执行前述图2所示实施例中第一装置所执行的操作，第二装置用于执行前述图2所示实施例中第二装置所执行的操作。
本申请实施例还提供一种第二终端。该第二终端包括第二装置，第二装置用于执行前述 图2所示实施例中第二装置所执行的操作。该第二终端通过CAN线与第一装置连接，第一装置用于执行前述图2所示实施例中第一装置所执行的操作。
可选的，所述第一终端与第二终端可以为车辆(比如智能车辆)、机器人(比如：快递机器人或智能机器人)、飞机(比如：快递无人机或智能飞机)以及船舶等。
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，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，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，机械或其它的形式。
所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。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元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全部或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所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(ROM，read-only memory)、随机存取存储器(RAM，random access memory)、磁碟或者光盘等各种可以存储程序代码的介质。

Claims (38)

  1. 一种路径规划方法，其特征在于，所述方法包括：
    向第二装置发送至少一个特征点的第一索引，所述至少一个特征点为第一障碍物在第一地图中的特征点，所述第一索引用于指示所述至少一个特征点在所述第一地图中的位置；
    接收来自所述第二装置的所述至少一个特征点的第二索引，所述第二索引用于指示所述至少一个特征点在第二地图中的位置，所述第二地图的生成时刻晚于所述第一地图的生成时刻；
    根据所述第二索引生成第一路径信息，所述第一路径信息用于指示用于终端的第一路径。
  2. 根据权利要求1所述的路径规划方法，其特征在于，所述方法还包括：
    向第三装置发送控制信号，所述控制信号用于控制所述终端根据所述第一路径信息进行运动。
  3. 根据权利要求1所述的路径规划方法，其特征在于，所述向第二装置发送至少一个特征点的第一索引之前，所述方法还包括：
    确定所述终端的速度大于第一阈值。
  4. 根据权利要求1至3中任一项所述的路径规划方法，其特征在于，所述向第二装置发送至少一个特征点的第一索引之前，所述方法还包括：
    向所述第二装置发送更新地图请求；
    接收来自所述第二装置的所述第一地图。
  5. 根据权利要求4所述的路径规划方法，其特征在于，所述向第二装置发送更新地图请求之前，所述方法还包括：
    确定所述终端的速度小于第一阈值。
  6. 根据权利要求4所述的路径规划方法，其特征在于，所述接收来自所述第二装置的所述第一地图之后，所述方法还包括：
    根据所述第一地图中的障碍物轮廓生成第二路径信息，所述第二路径信息用于指示用于所述终端的第二路径。
  7. 根据权利要求1至6中任一项所述的路径规划方法，其特征在于，所述根据所述第二索引生成用于终端的第一路径信息之后，所述方法还包括：
    确定至少一个目标特征点，所述至少一个目标特征点属于所述至少一个特征点，所述至少一个目标特征点与所述第一路径之间的距离小于第二阈值。
  8. 根据权利要求7所述的路径规划方法，其特征在于，所述方法还包括：
    向所述第二装置发送所述至少一个目标特征点的第一目标索引，所述第一目标索引为所述至少一个目标特征点在所述第一地图中的位置信息；
    接收来自所述第二装置的所述至少一个目标特征点的第二目标索引，所述第二目标索引用于指示所述至少一个目标特征点在第三地图中的位置，所述第三地图的生成时刻晚于所述第二地图的生成时刻；
    根据所述第二目标索引生成第三路径信息，所述第三路径信息用于指示用于所述终端的第三路径。
  9. 根据权利要求1至6中任一项所述的路径规划方法，其特征在于，所述方法还包括：
    接收来自所述第二装置的告警信息，所述告警信息用于指示所述终端的速度值小于所述第一阈值。
  10. 根据权利要求1至6中任一项所述的路径规划方法，其特征在于，所述第一地图与所述第二地图为栅格地图，或所述第一地图与所述第二地图为点云地图。
  11. 根据权利要求1至6中任一项所述的路径规划方法，其特征在于，所述终端为智能车辆、智能飞机或智能机器人。
  12. 一种路径规划方法，其特征在于，所述方法包括：
    接收来自第一装置的至少一个特征点的第一索引，所述至少一个特征点为第一障碍物在第一地图中的特征点，所述第一索引用于指示所述至少一个特征点在所述第一地图中的位置；
    获取第二地图，所述第二地图的生成时刻晚于所述第一地图的生成时刻；
    向所述第一装置发送第二索引，所述第二索引用于指示所述至少一个特征点在所述第二地图中的位置以及所述第二索引用于指示用于终端的第一路径信息。
  13. 根据权利要求12所述的路径规划方法，其特征在于，所述接收来自第一装置的至少一个特征点的第一索引之前，所述方法还包括：
    接收来自所述第一装置的更新地图请求；
    根据所述更新地图请求向所述第一装置发送所述第一地图。
  14. 根据权利要求12或13所述的路径规划方法，其特征在于，所述向所述第一装置发送所述第二索引之后，所述方法还包括：
    接收来自所述第一装置的至少一个目标特征点的第一目标索引，所述第一目标索引为所述至少一个目标特征点在所述第一地图中的位置信息；
    获取第三地图，所述第三地图的生成时刻晚于所述第二地图的生成时刻；
    向所述第一装置发送第二目标索引，所述第二目标索引用于指示所述至少一个目标特征点在所述第三地图中的位置以及所述第二目标索引用于指示用于所述终端的第三路径信息。
  15. 根据权利要求12至14中任一项所述的路径规划方法，其特征在于，所述获取第二地图之后，所述方法还包括：
    确定存在第二障碍物，所述第二障碍物存在于所述第二地图，所述第二障碍物不存在于所述第一地图；
    若所述第二障碍物的目标值满足预设条件，向第一装置发送告警信息，所述目标值用于指示所述第二障碍物与所述终端的靠近程度，所述告警信息用于指示所述终端的速度值小于第一阈值。
  16. 根据权利要求12至14中任一项所述的路径规划方法，其特征在于，所述第一地图与所述第二地图为栅格地图，或所述第一地图与所述第二地图为点云地图。
  17. 根据权利要求12至14中任一项所述的路径规划方法，其特征在于，所述终端为智能车辆、智能飞机或智能机器人。
  18. 一种第一装置，其特征在于，包括：
    发送单元，用于向第二装置发送至少一个特征点的第一索引，所述至少一个特征点为第一障碍物在第一地图中的特征点，所述第一索引用于指示所述至少一个特征点在所述第一地图中的位置；
    接收单元，用于接收来自所述第二装置的所述至少一个特征点的第二索引，所述第二索引用于指示所述至少一个特征点在第二地图中的位置，所述第二地图的生成时刻晚于所述第一地图的生成时刻；
    生成单元，用于根据所述第二索引生成第一路径信息，所述第一路径信息用于指示用于终端的第一路径。
  19. 根据权利要求18所述的第一装置，其特征在于，所述发送单元，还用于向第三装置发送控制信号，所述控制信号用于控制所述终端根据所述第一路径信息进行运动。
  20. 根据权利要求18所述的第一装置，其特征在于，所述第一装置还包括：
    第一确定单元，用于确定所述终端的速度大于第一阈值。
  21. 根据权利要求18至20中任一项所述的第一装置，其特征在于，所述发送单元，还用于向所述第二装置发送更新地图请求；
    所述接收单元，还用于接收来自所述第二装置的所述第一地图。
  22. 根据权利要求21所述的第一装置，其特征在于，所述第一装置还包括：
    第二确定单元，用于确定所述终端的速度小于第一阈值。
  23. 根据权利要求21所述的第一装置，其特征在于，所述生成单元，还用于根据所述第一地图中的障碍物轮廓生成第二路径信息，所述第二路径信息用于指示用于所述终端的第二路径。
  24. 根据权利要求18至23中任一项所述的第一装置，其特征在于，所述第一装置还包括：
    第三确定单元，用于确定至少一个目标特征点，所述至少一个目标特征点属于所述至少一个特征点，所述至少一个目标特征点与所述第一路径之间的距离小于第二阈值。
  25. 根据权利要求24所述的第一装置，其特征在于，所述发送单元，还用于向所述第二装置发送所述至少一个目标特征点的第一目标索引，所述第一目标索引为所述至少一个目标特征点在所述第一地图中的位置信息；
    所述接收单元，还用于接收来自所述第二装置的所述至少一个目标特征点的第二目标索引，所述第二目标索引用于指示所述至少一个目标特征点在第三地图中的位置，所述第三地图的生成时刻晚于所述第二地图的生成时刻；
    所述生成单元，还用于根据所述第二目标索引生成第三路径信息，所述第三路径信息用于指示用于所述终端的第三路径。
  26. 根据权利要求18至23中任一项所述的第一装置，其特征在于，所述接收单元，还用于接收来自所述第二装置的告警信息，所述告警信息用于指示所述终端的速度值小于所述第一阈值。
  27. 根据权利要求18至23中任一项所述的第一装置，其特征在于，所述第一地图与所述第二地图为栅格地图，或所述第一地图与所述第二地图为点云地图。
  28. 根据权利要求18至23中任一项所述的第一装置，其特征在于，所述终端为智能车辆、智能飞机或智能机器人。
  29. 一种第二装置，其特征在于，包括：
    接收单元，用于接收来自第一装置的至少一个特征点的第一索引，所述至少一个特征点 为第一障碍物在第一地图中的特征点，所述第一索引用于指示所述至少一个特征点在所述第一地图中的位置；
    获取单元，用于获取第二地图，所述第二地图的生成时刻晚于所述第一地图的生成时刻；
    发送单元，用于向所述第一装置发送第二索引，所述第二索引用于指示所述至少一个特征点在所述第二地图中的位置以及所述第二索引用于指示用于终端的第一路径信息。
  30. 根据权利要求29所述的第二装置，其特征在于，所述接收单元，还用于接收来自所述第一装置的更新地图请求；
    所述发送单元，还用于根据所述更新地图请求向所述第一装置发送所述第一地图。
  31. 根据权利要求29或30所述的第二装置，其特征在于，所述接收单元，还用于接收来自所述第一装置的至少一个目标特征点的第一目标索引，所述第一目标索引为所述至少一个目标特征点在所述第一地图中的位置信息；
    所述获取单元，还用于获取第三地图，所述第三地图的生成时刻晚于所述第二地图的生成时刻；
    所述发送单元，还用于向所述第一装置发送第二目标索引，所述第二目标索引用于指示所述至少一个目标特征点在所述第三地图中的位置以及所述第二目标索引用于指示用于所述终端的第三路径信息。
  32. 根据权利要求29至31中任一项所述的第二装置，其特征在于，所述第二装置还包括：
    确定单元，用于确定存在第二障碍物，所述第二障碍物存在于所述第二地图，所述第二障碍物不存在于所述第一地图；
    所述发送单元，还用于若所述第二障碍物的目标值满足预设条件，向第一装置发送告警信息，所述目标值用于指示所述第二障碍物与所述终端的靠近程度，所述告警信息用于指示所述终端的速度值小于第一阈值。
  33. 根据权利要求29至31中任一项所述的第二装置，其特征在于，所述第一地图与所述第二地图为栅格地图，或所述第一地图与所述第二地图为点云地图。
  34. 根据权利要求29至31中任一项所述的第二装置，其特征在于，所述终端为智能车辆、智能飞机或智能机器人。
  35. 一种第一装置，其特征在于，包括：
    至少一个处理器以及至少一个通信接口；
    所述至少一个通信接口用于为所述至少一个处理器提供数据和/或信息的输入/输出；
    所述至少一个处理器用于处理所述数据和/或信息以使得所述第一装置实现权利要求1-11任一项所述的方法。
  36. 一种第二装置，其特征在于，包括：
    至少一个处理器以及至少一个通信接口；
    所述至少一个通信接口用于为所述至少一个处理器提供数据和/或信息的输入/输出；
    所述至少一个处理器用于处理所述数据和/或信息以使得所述第一装置实现权利要求12-17任一项所述的方法。
  37. 一种计算机存储介质，其特征在于，所述计算机存储介质中存储有指令，所述指令 在计算机上执行时，使得所述计算机执行如权利要求1至17中任一项所述的方法。
  38. 一种计算机程序产品，其特征在于，所述计算机程序产品在计算机上执行时，使得所述计算机执行如权利要求1至17中任一项所述的方法。
PCT/CN2021/071212 2020-02-12 2021-01-12 一种路径规划方法及相关设备 WO2021159901A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010088731.1A CN113252034A (zh) 2020-02-12 2020-02-12 一种路径规划方法及相关设备
CN202010088731.1 2020-02-12

Publications (1)

Publication Number Publication Date
WO2021159901A1 true WO2021159901A1 (zh) 2021-08-19

Family

ID=77219657

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/071212 WO2021159901A1 (zh) 2020-02-12 2021-01-12 一种路径规划方法及相关设备

Country Status (2)

Country Link
CN (1) CN113252034A (zh)
WO (1) WO2021159901A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116125995A (zh) * 2023-04-04 2023-05-16 华东交通大学 一种高铁巡检机器人的路径规划方法及系统
CN116880513A (zh) * 2023-09-06 2023-10-13 广州慧洋信息科技有限公司 基于数据分析的水下机器人运行监控管理系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040111213A1 (en) * 2002-11-11 2004-06-10 Kazuaki Iwamura Map generating system and map management system
CN103884330A (zh) * 2012-12-21 2014-06-25 联想(北京)有限公司 信息处理方法、可移动电子设备、引导设备和服务器
CN104142971A (zh) * 2013-05-07 2014-11-12 三星泰科威株式会社 用于构建用于移动机器人的地图的方法和设备
CN104992466A (zh) * 2015-06-26 2015-10-21 四川赛迪智科技有限公司 一种三维场景的即时寻径方法
CN108007470A (zh) * 2017-11-30 2018-05-08 深圳市隐湖科技有限公司 一种移动机器人地图文件格式和路径规划系统及其方法
CN109737974A (zh) * 2018-12-14 2019-05-10 中国科学院深圳先进技术研究院 一种3d导航语义地图更新方法、装置及设备

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106647742B (zh) * 2016-10-31 2019-09-20 纳恩博（北京）科技有限公司 移动路径规划方法及装置
CN108303098B (zh) * 2018-02-09 2018-09-25 上海思岚科技有限公司 机器人路径规划方法及设备
US11530921B2 (en) * 2018-09-28 2022-12-20 Intel Corporation Method of generating a collision free path of travel and computing system
CN110220524A (zh) * 2019-04-23 2019-09-10 炬星科技（深圳）有限公司 路径规划方法、电子设备、机器人及计算机可读存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20040111213A1 (en) * 2002-11-11 2004-06-10 Kazuaki Iwamura Map generating system and map management system
CN103884330A (zh) * 2012-12-21 2014-06-25 联想(北京)有限公司 信息处理方法、可移动电子设备、引导设备和服务器
CN104142971A (zh) * 2013-05-07 2014-11-12 三星泰科威株式会社 用于构建用于移动机器人的地图的方法和设备
CN104992466A (zh) * 2015-06-26 2015-10-21 四川赛迪智科技有限公司 一种三维场景的即时寻径方法
CN108007470A (zh) * 2017-11-30 2018-05-08 深圳市隐湖科技有限公司 一种移动机器人地图文件格式和路径规划系统及其方法
CN109737974A (zh) * 2018-12-14 2019-05-10 中国科学院深圳先进技术研究院 一种3d导航语义地图更新方法、装置及设备

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116125995A (zh) * 2023-04-04 2023-05-16 华东交通大学 一种高铁巡检机器人的路径规划方法及系统
CN116880513A (zh) * 2023-09-06 2023-10-13 广州慧洋信息科技有限公司 基于数据分析的水下机器人运行监控管理系统
CN116880513B (zh) * 2023-09-06 2023-11-17 广州慧洋信息科技有限公司 基于数据分析的水下机器人运行监控管理系统

Also Published As

Publication number Publication date
CN113252034A (zh) 2021-08-13

Similar Documents

Publication Publication Date Title
JP6441993B2 (ja) レーザー点クラウドを用いる物体検出のための方法及びシステム
US9207680B1 (en) Estimating multi-vehicle motion characteristics by finding stable reference points
US9063548B1 (en) Use of previous detections for lane marker detection
CN109844562B (zh) 用于自主车辆感知和计划的雷达生成的占用网格
US9315192B1 (en) Methods and systems for pedestrian avoidance using LIDAR
US9080866B1 (en) Methods and systems for detection of reflective markers at long range
JP5912200B2 (ja) 複数のセンサーを用いる物体検出方法及びシステム
US8989944B1 (en) Methods and devices for determining movements of an object in an environment
US9052721B1 (en) Method for correcting alignment of vehicle mounted laser scans with an elevation map for obstacle detection
US9285230B1 (en) Methods and systems for detecting road curbs
US9342074B2 (en) Systems and methods for transitioning control of an autonomous vehicle to a driver
US9783172B2 (en) Methods and systems for steering-based oscillatory vehicle braking
CN113792566B (zh) 一种激光点云的处理方法及相关设备
US20180329423A1 (en) System To Optimize Sensor Parameters In An Autonomous Vehicle
US10712556B2 (en) Image information processing method and augmented reality AR device
US11592524B2 (en) Computation of the angle of incidence of laser beam and its application on reflectivity estimation
US10094670B1 (en) Condensing sensor data for transmission and processing
WO2021159901A1 (zh) 一种路径规划方法及相关设备
WO2023070113A1 (en) Validating an sfm map using lidar point clouds
CN109906657B (zh) 资源复用方法、终端和相关设备
JP2022528382A (ja) 検出信号に基づくレンジング方法及び装置
CN115082886B (zh) 目标检测的方法、装置、存储介质、芯片及车辆
WO2024138508A1 (zh) 一种障碍物检测方法及相关装置

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: 21753773

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 21753773

Country of ref document: EP

Kind code of ref document: A1