WO2020107974A1 - 用于无人驾驶车的避障方法和装置 - Google Patents

用于无人驾驶车的避障方法和装置 Download PDF

Info

Publication number
WO2020107974A1
WO2020107974A1 PCT/CN2019/103253 CN2019103253W WO2020107974A1 WO 2020107974 A1 WO2020107974 A1 WO 2020107974A1 CN 2019103253 W CN2019103253 W CN 2019103253W WO 2020107974 A1 WO2020107974 A1 WO 2020107974A1
Authority
WO
WIPO (PCT)
Prior art keywords
obstacle
information
terminal device
category
preset
Prior art date
Application number
PCT/CN2019/103253
Other languages
English (en)
French (fr)
Inventor
王月
慎东辉
程烈
于高
李文博
薛晶晶
Original Assignee
百度在线网络技术（北京）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 百度在线网络技术（北京）有限公司 filed Critical 百度在线网络技术（北京）有限公司
Priority to EP19889463.6A priority Critical patent/EP3757875A4/en
Priority to JP2020550724A priority patent/JP7174063B2/ja
Publication of WO2020107974A1 publication Critical patent/WO2020107974A1/zh
Priority to US17/024,651 priority patent/US20210001841A1/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/09—Taking automatic action to avoid collision, e.g. braking and steering
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0015—Planning or execution of driving tasks specially adapted for safety
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W50/08—Interaction between the driver and the control system
    • B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
    • B60W2050/146—Display means
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2520/00—Input parameters relating to overall vehicle dynamics
    • B60W2520/06—Direction of travel
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2540/00—Input parameters relating to occupants
    • B60W2540/215—Selection or confirmation of options
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/402—Type
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/60—Traversable objects, e.g. speed bumps or curbs
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/80—Spatial relation or speed relative to objects
    • B60W2554/802—Longitudinal distance
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2556/00—Input parameters relating to data
    • B60W2556/10—Historical data
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2720/00—Output or target parameters relating to overall vehicle dynamics
    • B60W2720/10—Longitudinal speed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2756/00—Output or target parameters relating to data
    • B60W2756/10—Involving external transmission of data to or from the vehicle

Definitions

  • the embodiments of the present application relate to the field of computer technology, specifically to the field of unmanned driving technology, and in particular, to an obstacle avoidance method and device for an unmanned vehicle.
  • the driverless car needs to perceive the environment while traveling.
  • detecting obstacles in front is an important part of environmental perception.
  • a camera installed in an unmanned vehicle is required to collect environmental images, and lidar is used to measure the distance of objects in front.
  • the on-board brain of a driverless car can analyze the environmental images collected by the camera to determine whether there are obstacles ahead, and the distance of the obstacles can be determined by the feedback data of the lidar.
  • the embodiment of the present application proposes a method and device for avoiding obstacles for driverless vehicles.
  • an embodiment of the present application provides an obstacle avoidance method for an unmanned vehicle.
  • the method includes: in response to determining that there is an obstacle in a preset driving path, sending obstacle information to a preset terminal device, So that the preset terminal device displays obstacle information on its display page, and the obstacle information includes the image and position information of the obstacle; receiving the type of obstacle input by the preset terminal device based on the displayed obstacle information Information, wherein the category information is used to indicate the category of the obstacle; according to the category of the obstacle indicated by the category information, the obstacle avoidance instruction of the unmanned vehicle is determined.
  • sending the obstacle information to the preset terminal device so that the preset terminal device displays the obstacle information in its display page includes: in response to the determination There are obstacles in the preset driving path. Use the pre-trained obstacle category recognition model to determine the reference category information of the obstacle.
  • the reference category information is used to indicate whether the obstacle is an ignorable obstacle; if the reference category information indicates that the obstacle is not It belongs to negligible obstacles, and sends the obstacle information to the preset terminal device, so that the preset terminal device displays the obstacle information on its display page; wherein the obstacle category recognition model is based on using multiple historical obstacle information and according to the The historical category information of the plurality of historical obstacles respectively set by the plurality of historical obstacle information is obtained by training the initial obstacle category recognition model, and is used to determine the reference category information of the obstacle according to the obstacle information.
  • the method further includes: if the reference category information indicates that the obstacle is not an ignorable obstacle, determine the distance between the obstacle and the driverless vehicle; if the distance is less than a preset distance threshold, then generate decelerating travel Instructions.
  • the method before receiving the category information of the obstacle input according to the obstacle information sent by the preset terminal device, the method further includes: sending to the preset terminal device for prompting that there is an obstacle in the preset driving path The prompt information of the object, so that the preset terminal device plays the prompt information.
  • the driving instruction of the driverless vehicle is determined according to the category of the obstacle indicated by the category information, including: if the category information indicates that the obstacle is not a negligible obstacle, the current state of the driverless vehicle
  • the information and obstacle information are input into a pre-trained obstacle avoidance model to generate an obstacle avoidance instruction.
  • the obstacle avoidance model is obtained by training the initial obstacle avoidance model based on using multiple historical obstacle avoidance records.
  • the method before sending the obstacle information to the preset terminal device in response to determining that there is an obstacle in the preset driving path, the method further includes: determining based on the acquired current environmental data of the driverless vehicle Whether there are obstacles in the preset driving path.
  • an embodiment of the present application provides an obstacle avoidance device for an unmanned vehicle, the device includes: a sending unit configured to send obstacle information in response to determining that there is an obstacle in a preset driving path To the preset terminal device, so that the preset terminal device displays obstacle information on its display page, and the obstacle information includes the image and position information of the obstacle; the receiving unit is configured to receive the Obstacle information displayed and the category information of the obstacle input, wherein the category information is used to indicate the category of the obstacle; the instruction generation unit is configured to determine the driverless vehicle’s type according to the category of the obstacle indicated by the category information Obstacle avoidance instructions.
  • the sending unit is further configured to: in response to determining that there is an obstacle in the preset driving path, use a pre-trained obstacle category recognition model to determine reference category information of the obstacle, where the reference category information is used to indicate the obstacle Whether the object is an ignorable obstacle; if the reference category information indicates that the obstacle is not an ignorable obstacle, send the obstacle information to the preset terminal device, so that the preset terminal device displays the obstacle information on its display page;
  • the obstacle category recognition model is based on the use of multiple historical obstacle information and the historical category information of the multiple historical obstacles respectively set according to the multiple historical obstacle information.
  • the initial obstacle category recognition model is trained and used to The information determines the reference category information of the obstacle.
  • the sending unit is further configured to: if the reference category information indicates that the obstacle is not a negligible obstacle, determine the distance between the obstacle and the driverless vehicle; if the distance If it is less than the preset distance threshold, a command to slow down is generated.
  • the apparatus further includes a prompt unit configured to: before the receiving unit receives the category information of the obstacle sent by the preset terminal device and input by the preset user according to the obstacle information, send a notification to the preset terminal The device sends prompt information for prompting that there is an obstacle in the preset driving path, so that the preset terminal device plays the prompt information.
  • the instruction generation unit is further configured to: if the category information indicates that the obstacle is not an ignorable obstacle, then input the current state information of the driverless vehicle and the obstacle information to the pre-trained obstacle avoidance model An obstacle avoidance instruction is generated, and the obstacle avoidance model is obtained by training the initial obstacle avoidance model based on using multiple historical obstacle avoidance records.
  • the apparatus further includes a determination unit configured to: according to the acquired information before the transmission unit sends the obstacle information to the preset terminal device in response to determining that there is an obstacle in the preset travel path The current environmental data of the driverless car determines whether there are obstacles in the preset driving path.
  • an embodiment of the present application provides an electronic device, the electronic device includes: one or more processors; a storage device, on which one or more programs are stored, when the one or more programs are When executed by one or more processors, the above one or more processors implement the method described in any one of the implementation manners of the first aspect.
  • an embodiment of the present application provides a computer-readable medium on which a computer program is stored, where the computer program is executed by a processor to implement the method described in any one of the implementation manners of the first aspect.
  • the obstacle avoidance method and device for an unmanned vehicle provided by the embodiments of the present application send obstacle information to a preset terminal device in response to determining that there is an obstacle in the preset driving path, so that the preset terminal device Obstacle information is displayed on its display page, after which, it receives the category information of obstacles input according to the obstacle information sent by the preset terminal device, and finally, determines the driverless car according to the category of obstacle indicated by the category information Obstacle avoidance instructions.
  • the preset terminal device as a human-machine interaction interface
  • the unmanned vehicle can receive the user's judgment on the obstacle category, and decide the obstacle avoidance strategy based on the user's judgment on the obstacle category.
  • the above method realizes the manual recognition of obstacles during the driving process of the driverless vehicle, and determines the obstacle avoidance instruction according to the above-mentioned auxiliary recognition results, which can reduce the deceleration and detours that are performed due to the avoidance of all obstacles. Operation such as driving or even parking, so that the phenomenon of prolonged driving time caused by decelerating driving, detouring or even parking due to avoiding obstacles can be improved.
  • FIG. 1 is an exemplary system architecture diagram in which an obstacle avoidance method for a driverless vehicle according to an embodiment of the present application can be applied;
  • FIG. 2 is a flowchart of an embodiment of an obstacle avoidance method for a driverless vehicle according to the present application
  • FIG. 3 is a schematic diagram of an application scenario of an obstacle avoidance method for a driverless vehicle according to the present application
  • FIG. 4 is a flowchart of still another embodiment of an obstacle avoidance method for a driverless vehicle according to the present application.
  • FIG. 5 is a schematic structural view of an embodiment of an obstacle avoidance device for a driverless vehicle according to the present application.
  • FIG. 6 is a schematic structural diagram of a computer system suitable for implementing an electronic device according to an embodiment of the present application.
  • FIG. 1 shows an exemplary system architecture 100 in which an obstacle avoidance method for an unmanned vehicle according to an embodiment of the present application can be applied.
  • the system architecture 100 may include an unmanned vehicle control system 101, a terminal device 102 and a user 103.
  • the terminal device 102 can communicate with the control system 101 via a network.
  • the above network may include various connection types, such as wired, wireless communication links, or fiber optic cables, and so on.
  • the control system 101 includes a perception unit and a driving decision unit.
  • the sensing unit includes multiple on-vehicle sensors, and the on-vehicle sensors can collect environmental data of the driverless vehicle in real time.
  • Vehicle-mounted sensors may include vehicle-mounted cameras, lidar sensors, millimeter-wave radar sensors, collision sensors, speed sensors, air pressure sensors, and the like.
  • the driving decision unit can be an ECU (Electronic Control Unit), or it can be an on-board computer or a remote server.
  • the driving decision unit can obtain the data collected by the vehicle sensors, process and respond to the data.
  • the control system 101 can send the environmental data of the driverless vehicle collected by the vehicle-mounted sensors to the terminal device 102 via the network.
  • the terminal device 102 may display the environment image in its display page.
  • the above environment image may include obstacle information.
  • the user 103 can use the terminal device 102 to interact with the control system 101 through the network to receive or send messages, and so on.
  • Various client applications may be installed on the terminal device 102, such as map applications, video playback applications, and the like.
  • the user 103 can judge whether the obstacle is negligible according to the image of the obstacle in the environment image displayed by the terminal device, and input the judgment result to the terminal device 102.
  • the terminal device 102 may send the above determination result to the above control system 101.
  • the terminal device 102 may be hardware or software.
  • the terminal device 104 When the terminal device 104 is hardware, it may be various electronic devices having a display screen and supporting map display, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and so on.
  • the terminal device 102 When the terminal device 102 is software, it can be installed in the electronic devices listed above. It can be implemented as multiple software or software modules (for example, software or software modules used to provide distributed services) or as a single software or software module. There is no specific limit here.
  • the terminal device 102 may be a terminal device provided on a remote server, and the user 103 may also be located on a remote server.
  • the terminal device may be a terminal device installed in an unmanned vehicle, and the user may also be located in an unmanned vehicle.
  • the obstacle avoidance method for unmanned vehicles provided by the embodiments of the present application is generally executed by the control system 103, and accordingly, the obstacle avoidance device for unmanned vehicles is generally provided in the control system 103.
  • FIG. 1 It should be understood that the number of terminal devices and control systems in FIG. 1 are only schematic. According to the implementation needs, there can be any number of terminal devices and control systems.
  • FIG. 2 shows a flow 200 of an embodiment of a method for avoiding obstacles for a driverless vehicle according to the present application.
  • the obstacle avoidance method for driverless vehicles includes the following steps:
  • step 201 in response to determining that there is an obstacle in the preset travel path, the obstacle information is sent to the preset terminal device, so that the preset terminal device displays the obstacle information in its display page.
  • the preset driving path may be a path to be driven by the unmanned vehicle planned in the planned path when the unmanned vehicle is at the current position.
  • the execution subject of the obstacle avoidance method for an unmanned vehicle may first determine whether there is an obstacle in the preset travel path by various methods. In response to determining that there is an obstacle in the preset travel path, the above-mentioned execution subject may send the obstacle information to a preset terminal device (such as the terminal device shown in FIG. 1 ).
  • the preset terminal device may display obstacle information on its display page.
  • the obstacle avoidance method for a driverless vehicle may further include: determining a preset driving path according to the obtained current environment data of the driverless vehicle Are there any obstacles?
  • an execution subject (such as the control system shown in FIG. 1) for the obstacle avoidance method of the unmanned vehicle can obtain the current environment data of the unmanned vehicle.
  • a driverless vehicle may include a sensing unit.
  • the sensing unit includes multiple on-board sensors. Multiple on-board sensors are used to collect environmental data.
  • the above environmental data includes the state information of the driverless vehicle itself and the state information around the driverless vehicle. Its own state information includes speed, acceleration, steering angle, position and other information.
  • the surrounding state information includes road location, road direction, surrounding objects, vehicles, pedestrians and other information.
  • an on-board camera installed at the front of the vehicle can collect images of the road environment in front of the driverless vehicle.
  • the lidar sensor can collect data such as the position, size, and external appearance of objects in the surrounding environment of the unmanned vehicle.
  • the above-mentioned execution subject may acquire environment data in real time during the above-mentioned unmanned vehicle travel process, so as to determine whether there are obstacles in the preset driving path of the unmanned vehicle according to the environment data.
  • the above obstacles may be vehicles, pedestrians, animals, plants, warning signs, etc.
  • the above-mentioned executive body can analyze the environmental data acquired in real time, and judge the surrounding environment according to the preset obstacle judgment conditions to determine whether there is an obstacle in the preset driving path of the unmanned vehicle.
  • the above-mentioned preset obstacle judgment condition may include that the height of the object on the ground is higher than the first preset height of the ground plane. Or the distance between the object hanging from the sky and the ground is less than the second preset height.
  • the first preset height here may be 10 cm, for example.
  • the second preset height may be, for example, the height of an unmanned vehicle.
  • the above-mentioned execution subject may input the environment data acquired in real time into a pre-trained obstacle judgment model to judge whether there is an obstacle in the preset driving path of the unmanned vehicle.
  • the above obstacle judgment model may be, for example, a support vector machine model, a naive Bayes model, a neural network model, or the like.
  • the above obstacle judgment model may be obtained by training the initial obstacle judgment model using a plurality of environmental data marked with obstacles and environmental data marked with obstacles.
  • the above obstacle information may include an image of the obstacle.
  • the image of the obstacle may be, for example, an image of an obstacle captured by an on-board camera, or an image of an obstacle generated based on the shape and size of the obstacle scanned by the on-board lidar sensor.
  • the position data of the obstacle can also be displayed on the display page of the preset terminal device.
  • the position data of the obstacle may include the coordinates of the obstacle, for example.
  • the foregoing preset terminal device may be set in an unmanned vehicle.
  • the above-mentioned preset terminal device may be set on the remote server.
  • Step 202 Receive obstacle type information that is input according to the displayed obstacle information and sent by a preset terminal device.
  • the above-mentioned execution subject may receive the category information of the obstacle input by the preset user and sent by the preset terminal device through the network.
  • the above category information is used to indicate the category of the obstacle.
  • the categories of obstacles include negligible obstacles and non-negligible obstacles.
  • the above category information may include numbers, symbols, or a combination of numbers and symbols. In other words, the obstacle is a negligible obstacle, or a non-negligible obstacle.
  • the control system may determine whether the vehicle needs to avoid obstacles according to the result of whether there is an obstacle in the determined preset travel path. Generally, when there is an obstacle in the preset driving path, an obstacle avoidance strategy needs to be implemented; when there is no obstacle, the unmanned vehicle can continue to drive according to the preset driving path.
  • the above obstacle avoidance strategies include changing the preset driving path, bypassing obstacles, slowing down or stopping.
  • the unmanned vehicle travels according to the preset travel path, which is also used as an obstacle avoidance strategy.
  • the preset user can observe the obstacle information on the screen of the preset terminal device. If the obstacle itself does not cause damage to the unmanned vehicle, and the unmanned vehicle passes thereon without causing major harm to the obstacle, the above obstacle may be a negligible obstacle. Otherwise, the obstacle cannot be ignored.
  • the above-mentioned obstacles may be, for example, grasses growing on the ground, or leaves, ribbons, etc. hanging down from a height.
  • the preset user may input the judgment result of the obstacle category into the preset terminal device.
  • the above judgment result can be input through a text input window or an audio input window.
  • the above judgment result can also be input by selecting according to the selection item of the obstacle category displayed on the screen of the preset terminal.
  • the preset terminal device may send the category information of the obstacle to the execution subject.
  • the preset user may be a user located in an unmanned vehicle, such as a vehicle safety officer.
  • the preset user may be a remote monitoring user located at a remote server.
  • Step 203 Determine an obstacle avoidance instruction for the unmanned vehicle according to the category of the obstacle indicated by the category information.
  • the obstacle avoidance instruction generated by the execution subject instructs the unmanned vehicle to continue driving along the preset driving path.
  • the obstacle avoidance instruction generated by the execution subject includes changing a detour travel path, a detour travel speed, etc. around which the preset travel path bypasses the obstacle.
  • the model generates an obstacle avoidance instruction, and the obstacle avoidance model is obtained by training an initial obstacle avoidance model based on using multiple historical obstacle avoidance records.
  • the above obstacle avoidance strategy model may be various existing obstacle avoidance strategy models, for example, a neural network based obstacle avoidance strategy model, a DRL (Deep Reinforcement Learning, deep reinforcement learning) obstacle avoidance strategy model, etc.
  • a neural network based obstacle avoidance strategy model for example, a neural network based obstacle avoidance strategy model, a DRL (Deep Reinforcement Learning, deep reinforcement learning) obstacle avoidance strategy model, etc.
  • DRL Deep Reinforcement Learning, deep reinforcement learning
  • the category information input by the preset user indicates that the obstacle is a non-negligible obstacle
  • relevant data such as the current state of the unmanned vehicle and the position of the obstacle may be input into a pre-trained obstacle avoidance strategy
  • obstacle avoidance instructions are generated.
  • the current state indicated by the current state information of the vehicle may include, for example, the current position of the vehicle, vehicle speed, acceleration, attitude angle, and the like.
  • the obstacle avoidance command may include, for example, a detour travel path, a detour travel speed, etc.
  • the obstacle avoidance command may also include a parking command.
  • the obstacle avoidance strategy model is used to generate obstacle avoidance instructions for non-negligible obstacles to avoid collisions between vehicles and obstacles, which can speed up the generation of obstacle avoidance instructions.
  • FIG. 3 is a schematic diagram of an application scenario 300 of the obstacle avoidance method for an unmanned vehicle according to this embodiment.
  • the on-board sensor on the driverless car 301 can collect environmental data of the driverless car 301 in real time.
  • the obstacle 303 may be grass, for example.
  • the in-vehicle control unit 302 determines that there is an obstacle 304 in the preset driving path of the unmanned vehicle according to the acquired environmental data of the unmanned vehicle in the current state.
  • the control unit 302 sends the obstacle information to the preset terminal device, so that the preset terminal device displays the obstacle information in its display page, so that The preset terminal device displays obstacle information 305 on its display page, and the above obstacle information includes an image of the obstacle and position information.
  • the control unit 302 receives the obstacle category information 306 sent by the preset terminal device and input by the preset user according to the obstacle image, where the obstacle category information is used to indicate that the obstacle is an ignorable obstacle.
  • the control unit 302 indicates that the obstacle is an ignorable obstacle according to the above-mentioned preset category information of the obstacle input by the user, and then generates an instruction 307 to continue driving along the preset path.
  • the method provided by the above embodiment of the present application by responding to determining that there is an obstacle in the preset travel path, sends the obstacle information to the preset terminal device, so that the preset terminal device displays the obstacle information on its display page, After that, it receives the category information of the obstacles sent by the preset user based on the obstacle information sent by the preset terminal device, and finally, determines the obstacle avoidance of the unmanned vehicle according to the category of the obstacle indicated by the category information instruction.
  • the above method uses the preset terminal device as a human-machine interaction interface, so that the unmanned vehicle can receive the user's judgment on the obstacle category, and decide the obstacle avoidance instruction according to the preset user's judgment on the obstacle category.
  • the above method realizes the manual recognition of obstacles during the driving process of the unmanned vehicle, and determines the obstacle avoidance instruction according to the above auxiliary recognition results, which can reduce the deceleration and detour due to the obstacles. Even parking and other operations can improve the phenomenon of extended driving time caused by avoiding all obstacles.
  • FIG. 4 shows a flow 400 of yet another embodiment of an obstacle avoidance method for driverless vehicles.
  • the process 400 of the obstacle avoidance method for driverless vehicles includes the following steps:
  • step 401 in response to determining that there is an obstacle in the preset travel path, a pre-trained obstacle category recognition model is used to determine the reference category information of the obstacle.
  • a pre-trained obstacle category recognition model may be set in an execution subject (for example, the control system shown in FIG. 1) of an obstacle avoidance method for an unmanned vehicle.
  • the above-mentioned executive body can communicate with the electronic device that sets the obstacle category recognition model through a wired network or a wireless network.
  • the above obstacle category recognition model is used to determine the reference category information of the obstacle according to the input obstacle information.
  • the above-mentioned pre-trained obstacle category recognition model may be obtained by training the initial obstacle category recognition model based on using multiple historical obstacle information to set the historical category information of the multiple historical obstacles according to the multiple historical obstacle information respectively of.
  • the aforementioned pre-trained obstacle category recognition model is used to determine the reference category information of the obstacle according to the obstacle information.
  • the above reference category information is used to indicate whether the obstacle belongs to a negligible obstacle.
  • the above obstacle class recognition model may be various machine learning models, such as artificial neural network membrane, convolutional neural network model, etc.
  • Step 402 If the reference category information indicates that the obstacle is not an ignorable obstacle, send the obstacle information to the preset terminal device, so that the preset terminal device displays the obstacle information on its display page.
  • the above-mentioned execution subject can ignore the above-mentioned obstacle, and the obstacle avoidance instruction generated by the above-mentioned execution subject indicates no The human-driven vehicle continues to drive according to the original driving path.
  • the above-mentioned execution subject may send the relevant data of the obstacle to the preset terminal device, so that the preset terminal device displays the above obstacle information on its display page.
  • the environment data is processed once using the obstacle category recognition model.
  • the workload of the preset user to identify the category information of the obstacle is reduced, which is beneficial to shorten the processing time for the preset user to process the displayed obstacle.
  • Step 403 Receive the obstacle category information sent by the preset terminal device and input by the preset user according to the displayed obstacle information.
  • step 403 is the same as step 202 in the embodiment shown in FIG. 2 and will not be repeated here.
  • Step 404 Determine the obstacle avoidance instruction for the unmanned vehicle according to the category of the obstacle indicated by the category information.
  • step 404 is the same as step 203 in the embodiment shown in FIG. 2 and will not be repeated here.
  • the process 400 of the obstacle avoidance method for driverless vehicles in this embodiment highlights the use of a pre-trained obstacle category recognition model to determine obstacles
  • the reference category information if the reference category information indicates that the obstacle is a non-negligible obstacle, then send the relevant data of the obstacle to the preset terminal device, so that the obstacle category recognition model can first be used to determine whether the obstacle can be ignored Judgment, and then judgment by the preset user.
  • it can reduce the workload of the preset user, on the other hand, it can further shorten the driving time of the driverless car.
  • step 403 before receiving the category information of the obstacle sent by the preset terminal device and input by the preset user according to the displayed obstacle information, it is used to
  • the obstacle avoidance method for unmanned vehicles also includes: if the reference category information indicates that the obstacle is not an ignorable obstacle, determine the distance between the obstacle and the unmanned vehicle; if the distance is less than the preset distance threshold, then generate a decelerating driving instruction.
  • the executive body of the obstacle avoidance method for the unmanned vehicle may further determine the distance between the obstacle and the unmanned vehicle.
  • the distance between the obstacle and the unmanned vehicle is less than the preset distance threshold, generating the deceleration driving instruction can make the unmanned vehicle decelerate driving, so that the preset user has enough time to display on the preset terminal device
  • the obstacle information on the system determines the category of the obstacle, so as to avoid the phenomenon that the unmanned vehicle collides with the obstacle due to the default user not judging the category of the obstacle in time.
  • the obstacle avoidance method for an unmanned vehicle may further include: sending prompt information for reminding that there is an obstacle in the preset path to the preset terminal device, so that the preset terminal device plays the above prompt information.
  • the above-mentioned executive body determines that there is an obstacle in the preset travel path, and sends obstacle information to the preset terminal device, so that the preset terminal device displays the obstacle information on its display page
  • the preset terminal device may be sent prompt information for indicating that there is an obstacle in the traveling direction, so that the preset terminal device plays the above prompt information.
  • the prompt information is used to prompt the preset user to judge the type of the obstacle according to the image and position information of the obstacle displayed on the display page of the preset terminal device.
  • the preset user does not need to observe the details of the environmental image displayed on the display page of the preset terminal device at all times, but only needs to judge the obstacle information displayed by the preset terminal device when receiving the prompt information to The type of obstacle in the preset travel path is determined.
  • the workload of the preset user can be reduced, and misjudgment and missed judgment caused by the fatigue of the preset user can be avoided.
  • the present application provides an embodiment of an obstacle avoidance device for an unmanned vehicle.
  • the device embodiment is the same as the method embodiment shown in FIG. 2.
  • the device can be specifically applied as shown in FIG. 5.
  • the obstacle avoidance device 500 for an unmanned vehicle in this embodiment includes a sending unit 501, a receiving unit 502 and an instruction generating unit 503.
  • the sending unit 501 is configured to, in response to determining that there is an obstacle in the preset travel path, send the obstacle information to the preset terminal device, so that the preset terminal device displays the obstacle on its display page Information, the obstacle information includes an image and position information of the obstacle;
  • the receiving unit 502 is configured to receive an obstacle sent by the preset terminal device and input by the preset user according to the displayed obstacle information Category information of objects, wherein the category information is used to indicate the category of the obstacle;
  • the instruction generation unit 503 is configured to determine the obstacle avoidance of the unmanned vehicle according to the category of the obstacle indicated by the category information instruction.
  • step 201, step 202 and step 203 the specific processing of the sending unit 501, the receiving unit 502, and the command generating unit 503 for the obstacle avoidance device 500 for an unmanned vehicle can be referred to the corresponding embodiment in FIG. 2 respectively
  • step 201, step 202 and step 203 the relevant descriptions of step 201, step 202 and step 203 will not be repeated here.
  • the sending unit 501 is further configured to: in response to determining that there is an obstacle in the preset driving path, use a pre-trained obstacle category recognition model to determine the reference category information of the obstacle ,
  • the reference category information is used to indicate whether the obstacle is an ignorable obstacle; if the reference category information indicates that the obstacle is not an ignorable obstacle, the obstacle information is sent to the preset terminal device so that the preset terminal device displays Obstacle information is displayed on the page;
  • the obstacle category recognition model is based on the use of multiple historical obstacle information and the preset historical obstacle information of the multiple historical obstacles set by the user according to the multiple historical obstacle information respectively.
  • the category recognition model is trained and used to determine the reference category information of the obstacle based on the obstacle information.
  • the sending unit 501 is further configured to: if the reference category information indicates that the obstacle does not belong to the negligible obstacle, determine the obstacle and the unmanned vehicle The distance between them; if the distance is less than the preset distance threshold, an instruction to slow down is generated.
  • the obstacle avoidance device 500 for an unmanned vehicle further includes a prompt unit (not shown in the figure).
  • the prompting unit is configured to: before the receiving unit receives the category information of the obstacle sent by the preset terminal device and input by the preset user according to the obstacle information, send the preset terminal device a reminder that the preset driving path has The prompt information of the obstacle, so that the preset terminal device plays the prompt information.
  • the instruction generation unit 503 is further configured to: if the category information indicates that the obstacle is not an ignorable obstacle, enter the current state information of the driverless vehicle and the obstacle information Go to the pre-trained obstacle avoidance model to generate obstacle avoidance instructions.
  • the obstacle avoidance model is based on training the initial obstacle avoidance model using multiple historical obstacle avoidance records.
  • the obstacle avoidance device 500 for an unmanned vehicle further includes a determination unit (not shown in the figure).
  • the determining unit is configured to: before the sending unit responds to determining that there is an obstacle in the preset driving path, before sending the obstacle information to the preset terminal device, determine the preset driving according to the acquired current environment data of the driverless vehicle Are there obstacles in the path?
  • FIG. 6 shows a schematic structural diagram of a computer system 600 suitable for implementing an electronic device according to an embodiment of the present application.
  • the electronic device shown in FIG. 6 is only an example, and should not bring any limitation to the functions and use scope of the embodiments of the present application.
  • the computer system 600 includes a central processing unit (CPU, Central Processing Unit) 601, which can be loaded into random access according to a program stored in a read-only memory (ROM, Read Only Memory) 602 or from the storage section 606
  • the program in the memory (RAM, Random Access) 603 executes various appropriate operations and processes.
  • RAM Random Access
  • various programs and data necessary for the operation of the system 600 are also stored.
  • the CPU 601, ROM 602, and RAM 603 are connected to each other through a bus 604.
  • An input/output (I/O, Input/Output) interface 605 is also connected to the bus 604.
  • the following components are connected to the I/O interface 605: a storage portion 606 including a hard disk and the like; and a communication portion 607 including a network interface card such as a LAN (Local Area Network) card, a modem, and the like.
  • the communication section 607 performs communication processing via a network such as the Internet.
  • the driver 608 is also connected to the I/O interface 605 as needed.
  • the process described above with reference to the flowchart may be implemented as a computer software program.
  • embodiments of the present disclosure include a computer program product that includes a computer program carried on a computer-readable medium, the computer program containing program code for performing the method shown in the flowchart.
  • the computer program may be downloaded and installed from the network through the communication section 607, and/or installed from the removable medium 609.
  • CPU central processing unit
  • the above-mentioned functions defined in the method of the present application are executed.
  • the computer-readable medium described in this application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two.
  • the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or device, or any combination of the above. More specific examples of computer readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable removable Programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.
  • the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.
  • the computer-readable signal medium may include a data signal that is propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried.
  • This propagated data signal can take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing.
  • the computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, and the computer-readable medium may send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. .
  • the program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the foregoing.
  • the computer program code for performing the operations of the present application can be written in one or more programming languages or a combination thereof.
  • the programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include the conventional process Programming language-such as "C" language or similar programming language.
  • the program code may be executed entirely on the user's computer, partly on the user's computer, as an independent software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server.
  • the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (for example, through an Internet service provider Internet connection).
  • LAN local area network
  • WAN wide area network
  • Internet service provider Internet connection for example, AT&T, MCI, Sprint, EarthLink, MSN, GTE, etc.
  • each block in the flowchart or block diagram may represent a module, program segment, or part of code that contains one or more logic functions Executable instructions.
  • the functions noted in the block may occur out of the order noted in the figures. For example, two blocks represented in succession may actually be executed in parallel, and they may sometimes be executed in reverse order, depending on the functions involved.
  • each block in the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts can be implemented with dedicated hardware-based systems that perform specified functions or operations Or, it can be realized by a combination of dedicated hardware and computer instructions.
  • the units described in the embodiments of the present application may be implemented in software or hardware.
  • the described unit may also be provided in the processor.
  • a processor includes a sending unit, a receiving unit, and an instruction generating unit.
  • the names of these units do not constitute a limitation on the unit itself under certain circumstances.
  • the sending unit may also be described as “in response to determining that there is an obstacle in the preset driving path, sending the obstacle information to the Set a terminal device so that the preset terminal device displays the obstacle information unit on its display page".
  • the present application also provides a computer-readable medium, which may be included in the device described in the foregoing embodiments; or may exist alone without being assembled into the device.
  • the computer-readable medium carries one or more programs, and when the one or more programs are executed by the device, the device is caused to: in response to determining that there is an obstacle in the preset travel path, send the obstacle information to the preset Terminal device, so that the preset terminal device displays obstacle information on its display page, and the obstacle information includes the image and position information of the obstacle; receiving the obstacle information sent by the preset terminal device and displayed by the preset user according to the displayed obstacle information
  • the input category information of the obstacle wherein the category information is used to indicate the category of the obstacle; according to the category of the obstacle indicated by the category information, the obstacle avoidance instruction of the unmanned vehicle is determined.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Traffic Control Systems (AREA)
  • Control Of Driving Devices And Active Controlling Of Vehicle (AREA)

Abstract

本申请实施例公开了用于无人驾驶车的避障方法和装置。该方法的一具体实施方式包括：响应于确定预设行驶路径中有障碍物，将障碍物信息发送至预设终端设备，以使预设终端设备在其展示页面中展示障碍物信息，障碍物信息包括障碍物的图像以及位置信息；接收预设终端设备发送的、根据所展示的障碍物信息而输入的障碍物的类别信息；根据类别信息所指示的障碍物的类别，确定无人驾驶车的避障指令。该实施方式减少了由于对障碍物进行躲避而执行减速行驶、绕行甚至停车等操作，改善了由于避障引起的驾驶时间延长的现象。

Description

用于无人驾驶车的避障方法和装置
本申请要求于2018年11月30日提交的、申请号为201811458406.9、申请人为百度在线网络技术(北京)有限公司、发明名称为“用于无人驾驶车的避障方法和装置”的中国专利申请的优先权，该申请的全文以引用的方式并入本申请中。
技术领域
本申请实施例涉及计算机技术领域，具体涉及无人驾驶技术领域，尤其涉及用于无人驾驶车的避障方法和装置。
背景技术
无人驾驶车在行进过程中，需要对环境进行感知。在对环境进行感知时，检测前方的障碍物是环境感知的一个重要部分。
通常需要设置在无人驾驶车上的相机采集环境图像，并使用激光雷达来测量前方物体的距离。无人驾驶车的车载大脑可以对相机所采集的环境图像进行分析，以确定前方是否存在障碍物，以及通过激光雷达的反馈数据确定障碍物的距离。
发明内容
本申请实施例提出了一种用于无人驾驶车的避障方法和装置。
第一方面，本申请实施例提供了一种用于无人驾驶车的避障方法，该方法包括：响应于确定预设行驶路径中有障碍物，将障碍物信息发送至预设终端设备，以使预设终端设备在其展示页面中展示障碍物信息，障碍物信息包括障碍物的图像以及位置信息；接收预设终端设备发送的、根据所展示的障碍物信息而输入的障碍物的类别信息，其中，类别信息用于指示障碍物的类别；根据类别信息所指示的障碍物的类别，确定无人驾驶车的避障指令。
在一些实施例中，响应于确定预设行驶路径中有障碍物，将障碍物信息发送至预设终端设备，以使预设终端设备在其展示页面中展示障碍物信息，包括：响应于确定预设行驶路径中有障碍物，利用预先训练的障碍物类别识别模型，确定障碍物的参考类别信息，参考类别信息用于指示障碍物是否属于可忽略障碍物；若参考类别信息指示障碍物不属于可忽略障碍物，将障碍物信息发送至预设终端设备，以使预设终端设备在其展示页面中展示障碍物信息；其中障碍物类别识别模型基于使用多个历史障碍物信息以及根据该多个历史障碍物信息分别设置的该多个历史障碍物的历史类别信息对初始障碍物类别识别模型训练得到，用于根据障碍物信息确定障碍物的参考类别信息。
在一些实施例中，该方法还包括：若参考类别信息指示障碍物不属于可忽略障碍物，确定障碍物与无人驾驶车之间的距离；若距离小于预设距离阈值，则生成减速行驶的指令。
在一些实施例中，在接收预设终端设备发送的、根据障碍物信息而输入的障碍物的类别信息之前，该方法还包括：向预设终端设备发送用于提示预设行驶路径中有障碍物的提示信息，以使预设终端设备播放提示信息。
在一些实施例中，根据类别信息所指示的障碍物的类别，确定无人驾驶车的行车指令，包括：若类别信息指示障碍物不属于可忽略障碍物，则将无人驾驶车的当前状态信息以及障碍物信息输入到预先训练的避障模型生成避障指令，避障模型基于使用多个历史避障记录对初始避障模型训练得到。
在一些实施例中，在响应于确定预设行驶路径中有障碍物，将障碍物信息发送至预设终端设备之前，该方法还包括：根据所获取的无人驾驶车的当前环境数据，确定预设行驶路径中是否有障碍物。
第二方面，本申请实施例提供了一种用于无人驾驶车的避障装置，该装置包括：发送单元，被配置成响应于确定预设行驶路径中有障碍物，将障碍物信息发送至预设终端设备，以使预设终端设备在其展示页面中展示障碍物信息，障碍物信息包括障碍物的图像以及位置信息；接收单元，被配置成接收预设终端设备发送的、根据所展示的障碍物 信息而输入的障碍物的类别信息，其中，类别信息用于指示障碍物的类别；指令生成单元，被配置成根据类别信息所指示的障碍物的类别，确定无人驾驶车的避障指令。
在一些实施例中，发送单元进一步被配置成：响应于确定预设行驶路径中有障碍物，利用预先训练的障碍物类别识别模型，确定障碍物的参考类别信息，参考类别信息用于指示障碍物是否属于可忽略障碍物；若参考类别信息指示障碍物不属于可忽略障碍物，将障碍物信息发送至预设终端设备，以使预设终端设备在其展示页面中展示障碍物信息；其中障碍物类别识别模型基于使用多个历史障碍物信息以及根据该多个历史障碍物信息分别设置的该多个历史障碍物的历史类别信息对初始障碍物类别识别模型训练得到，用于根据障碍物信息确定障碍物的参考类别信息。
在一些实施例中，发送单元进一步被配置成：若所述参考类别信息指示障碍物不属于可忽略障碍物，确定所述障碍物与所述无人驾驶车之间的距离；若所述距离小于预设距离阈值，则生成减速行驶的指令。
在一些实施例中，该装置还包括提示单元，被配置成：在接收单元接收预设终端设备发送的、由预设用户根据障碍物信息而输入的障碍物的类别信息之前，向预设终端设备发送用于提示预设行驶路径中有障碍物的提示信息，以使预设终端设备播放提示信息。
在一些实施例中，指令生成单元，进一步被配置成：若类别信息指示障碍物不属于可忽略障碍物，则将无人驾驶车的当前状态信息以及障碍物信息输入到预先训练的避障模型生成避障指令，避障模型基于使用多个历史避障记录对初始避障模型训练得到。
在一些实施例中，该装置还包括确定单元，确定单元被配置成：在发送单元响应于确定预设行驶路径中有障碍物，将障碍物信息发送至预设终端设备之前，根据所获取的无人驾驶车的当前环境数据，确定预设行驶路径中是否有障碍物。
第三方面，本申请实施例提供了一种电子设备，该电子设备包括：一个或多个处理器；存储装置，其上存储有一个或多个程序，当上述 一个或多个程序被上述一个或多个处理器执行时，使得上述一个或多个处理器实现如第一方面中任一实现方式描述的方法。
第四方面，本申请实施例提供了一种计算机可读介质，其上存储有计算机程序，其中，该计算机程序被处理器执行时实现如第一方面中任一实现方式描述的方法。
本申请实施例提供的用于无人驾驶车的避障方法和装置，通过响应于确定预设行驶路径中有障碍物，将障碍物信息发送至预设终端设备，以使预设终端设备在其展示页面中展示障碍物信息，之后，接收预设终端设备发送的、根据障碍物信息而输入的障碍物的类别信息，最后，根据类别信息所指示的障碍物的类别，确定无人驾驶车的避障指令。通过将预设终端设备作为人机交互接口，从而使得无人驾驶车可以接收用户对障碍物类别的判断，并根据用户对障碍物类别的判断来决策避障策略。上述方法实现了在无人驾驶车行进过程中，由人工对障碍物进行辅助识别，并根据上述辅助识别结果来确定避障指令，可以减少由于对全部障碍物进行躲避而执行的减速行驶、绕行甚至停车等操作，从而可以改善由于对障碍物进行躲避而执行的减速行驶、绕行甚至停车引起的驾驶时间延长的现象。
附图说明
通过阅读参照以下附图所作的对非限制性实施例所作的详细描述，本申请的其它特征、目的和优点将会变得更明显：
图1是本申请的一个实施例的用于无人驾驶车的避障方法可以应用于其中的示例性系统架构图；
图2是根据本申请的用于无人驾驶车的避障方法的一个实施例的流程图；
图3是根据本申请的用于无人驾驶车的避障方法的一个应用场景的示意图；
图4是根据本申请的用于无人驾驶车的避障方法的又一个实施例的流程图；
图5是根据本申请的用于无人驾驶车的避障装置的一个实施例的 结构示意图；
图6是适于用来实现本申请实施例的电子设备的计算机系统的结构示意图。
具体实施方式
下面结合附图和实施例对本申请作进一步的详细说明。可以理解的是，此处所描述的具体实施例仅仅用于解释相关发明，而非对该发明的限定。另外还需要说明的是，为了便于描述，附图中仅示出了与有关发明相关的部分。
需要说明的是，在不冲突的情况下，本申请中的实施例及实施例中的特征可以相互组合。下面将参考附图并结合实施例来详细说明本申请。
图1示出了本申请的一个实施例的用于无人驾驶车的避障方法可以应用于其中的示例性系统架构100。
如图1所示，系统架构100可以包括无人驾驶车的控制系统101、终端设备102和用户103。终端设备102可以通过网络与控制系统101进行通信连接。上述网络可以包括各种连接类型，例如有线、无线通信链路或者光纤电缆等等。
控制系统101包括感知单元和驾驶决策单元。感知单元包括多个车载传感器，车载传感器可以实时采集无人驾驶车的环境数据。车载传感器可以包括车载摄像机、激光雷达传感器、毫米波雷达传感器、碰撞传感器、速度传感器、空气压力传感器等。
驾驶决策单元可以为ECU(Electronic Control Unit,电子控制单元)，或者可以为车载电脑，还可以为远程服务器。驾驶决策单元可以获取车载传感器采集的数据，对数据进行处理并响应。
控制系统101可以将车载传感器采集的无人驾驶车的环境数据通过网络发送至终端设备102。终端设备102可以在其展示页面中展示环境图像。上述环境图像中可以包括障碍物信息。
用户103可以使用终端设备102通过网络与控制系统101交互，以接收或发送消息等。终端设备102上可以安装有各种客户端应用， 例如地图类应用、视频播放类应用等。用户103可以根据终端设备上述显示的环境图像中的障碍物的图像对障碍物是否可忽略进行判断，并向终端设备102输入判断结果。终端设备102可以将上述判断结果发送至上述控制系统101。
终端设备102可以是硬件，也可以是软件。当终端设备104为硬件时，可以是具有显示屏并且支持地图显示的各种电子设备，包括但不限于智能手机、平板电脑、膝上型便携计算机和台式计算机等等。当终端设备102为软件时，可以安装在上述所列举的电子设备中。其可以实现成多个软件或软件模块(例如用来提供分布式服务的软件或软件模块)，也可以实现成单个软件或软件模块。在此不做具体限定。
在一些应用场景中，上述终端设备102可以是设置在远程服务端的终端设备，上述用户103也可以位于远程服务端。
在另外一些应用场景中，上述终端设备可以是设置在无人驾驶车内的终端设备，上述用户也可以位于无人驾驶车内。
需要说明的是，本申请实施例所提供的用于无人驾驶车的避障方法一般由控制系统103执行，相应地，用于无人驾驶车的避障装置一般设置于控制系统103中。
应该理解，图1中的终端设备、控制系统的数目仅仅是示意性的。根据实现需要，可以具有任意数目的终端设备和控制系统。
继续参考图2，其示出了根据本申请的用于无人驾驶车的避障方法的一个实施例的流程200。该用于无人驾驶车的避障方法，包括以下步骤：
步骤201，响应于确定预设行驶路径中有障碍物，将障碍物信息发送至预设终端设备，以使预设终端设备在其展示页面中展示障碍物信息。
通常，在无人驾驶车上路行驶之前，需要预先规划无人驾驶车的行驶路径。在本实施例中，上述预设行驶路径可以为在无人驾驶车位于当前位置时，上述规划路径中所规划的无人驾驶车下一段待行驶的路径。
在本实施例中，用于无人驾驶车的避障方法的执行主体可以首先 通过各种方法确定预设行驶路径中是否有障碍物。响应于确定预设行驶路径中有障碍物，上述执行主体可以将障碍物信息发送至预设终端设备(例如图1所示的终端设备)。上述预设终端设备可以在其展示页面展示障碍物信息。
在本实施例的一些可选的实现方式中，在步骤201之前，用于无人驾驶车的避障方法还可以包括：根据所获取的无人驾驶车的当前环境数据，确定预设行驶路径中是否有障碍物。
在这些可选的实现方式中，用于无人驾驶车的避障方法的执行主体(例如图1所示的控制系统)可以获取无人驾驶车的当前环境数据。
通常，无人驾驶车上可以包括感知单元。感知单元包括多个车载传感器。多个车载传感器用于采集环境数据。上述环境数据包括无人驾驶车自身的状态信息以及无人驾驶车周围的状态信息。自身的状态信息包括速度、加速度、转向角度、所处位置等信息。周围状态信息包括道路位置、道路方向、周围的物体、车辆、行人等信息。
例如，设置在车辆前端的车载摄像头可以采集无人驾驶车前方道路环境的图像。激光雷达传感器可以采集无人驾驶车周围环境中的物体的位置、大小、外部形貌等数据。
在一些应用场景中，上述执行主体可以在上述无人驾驶车行进过程中实时获取环境数据，从而根据环境数据判断无人驾驶车预设行驶路径中是否有障碍物存在。
上述障碍物可以为车辆、行人、动物、植物、警示标志等。
通常，上述执行主体可以对实时获取到的环境数据进行分析，根据预设障碍物判断条件对周围环境进行判断，以确定无人驾驶车的预设行驶路径中是否有障碍物。例如上述预设障碍物判断条件可以包括地面上物体的高度高于地平面的第一预设高度以上。或者从天空中垂下的物体与地面之间的距离小于第二预设高度。这里的第一预设高度例如可以为10厘米。第二预设高度例如可以为无人驾驶车的高度。
在一些应用场景中，上述执行主体可以将实时获取到的环境数据输入到预先训练的障碍物判断模型中，来判断无人驾驶车的预设行驶路径中是否有障碍物。上述障碍物判断模型例如可以是支持向量机模 型、朴素贝叶斯模型、神经网络模型等。
上述障碍物判断模型可以是使用多个标记有障碍物的环境数据和标记无障碍物的环境数据，对初始障碍物判断模型进行训练得到的。
上述障碍物信息可以包括障碍物的图像。障碍物的图像例如可以是由车载摄像机拍摄到的障碍物的图像，或者可以是根据车载激光雷达传感器扫描到的障碍物的形状、大小等生成的障碍物的图像等。
进一步地，在上述预设终端设备的展示页面中还可以展示障碍物的位置数据。障碍物的位置数据例如可以包括障碍物的坐标。
在一些应用场景中，上述预设终端设备可以设置在无人驾驶车内。
在另外一些应用场景中，上述预设终端设备可以设置在远程服务端。
步骤202，接收预设终端设备发送的、根据所展示的障碍物信息而输入的障碍物的类别信息。
上述执行主体可以通过网络接收预设终端设备发送的、由预设用户输入的障碍物的类别信息。上述类别信息用于指示障碍物的类别。障碍物的类别包括可忽略障碍物和不可忽略障碍物。上述类别信息可以包括数字、符号或者数字和符号的组合等。也就是说，障碍物属于可忽略障碍物，或者属于不可忽略障碍物。
可以由控制系统根据所确定的预设行驶路径中是否有障碍物的结果来确定车辆是否需要进行避障。通常当预设行驶路径中有障碍物时，需要实施避障策略；没有障碍物时，无人驾驶车可以按照预设行驶路径继续行驶。上述避障策略包括改变预设行驶路径，对障碍物绕行，减速行驶或者停车等。
在本实施例中，将对于可忽略的障碍物，无人驾驶车按照预设行驶路径行驶，也作为一种避障策略。
由于控制系统并不能对全部的障碍物是否为可忽略障碍物进行准确判断，如果出现将可忽略障碍物误判为不可忽略障碍物，则会发生无人驾驶车辆在行驶过程中由于采取对障碍物绕行，减速行驶或绕行等避障策略而引起行驶时间延长的现象。
上述预设用户可以在预设终端设备的屏幕中观察到上述障碍物信 息。如果障碍物本身对无人驾驶车不会造成损伤，以及无人驾驶车在其上经过也不会对障碍物造成重大危害，则上述障碍物可以为可忽略障碍物。否则，障碍物为不可忽略障碍物。上述障碍物例如可以为在地面上生长的草，或者高空垂下的树叶、丝带等。
预设用户可以将对障碍物类别的判断结果，输入到预设终端设备中。例如可以通过文字输入窗口或者音频输入窗口输入上述判断结果。还可以根据预设终端设屏幕展示的障碍物类别的选择项进行选择来输入上述判断结果。
上述预设终端设备可以将障碍物的类别信息发送给上述执行主体。
在一些应用场景中，上述预设用户可以是位于无人驾驶车内的用户，例如车辆安全员等。
在另外一些应用场景中，上述预设用户可以是位于远程服务端的远程监控用户等。
步骤203，根据类别信息所指示的障碍物的类别，确定无人驾驶车的避障指令。
在本实施例中，若上述类别信息指示障碍物属于可忽略障碍物，上述执行主体所生成的避障指令指示无人驾驶车沿预设行驶路径继续行驶。
若上述类别信息指示障碍物属于不可忽略障碍物，上述执行主体生成的避障指令包括改变预设行驶路径对障碍物绕行的绕行行驶路径、绕行行驶速度等。
在本实施例的一些可选的实现方式中，若所述类别信息指示所述障碍物属于不可忽略障碍物，则将无人驾驶车的当前状态信息以及障碍物信息输入到预先训练的避障模型生成避障指令，所述避障模型基于使用多个历史避障记录对初始避障模型训练得到。
上述避障策略模型可以是现有的各种避障策略模型，例如基于神经网络的避障策略模型、基于DRL(Deep Reinforcement Learning，深度增强学习)的避障策略模型等。
在这些实施方式中，在由预设用户输入的类别信息指示障碍物属 于不可忽略障碍物时，可以将无人驾驶车的当前状态、障碍物的位置等相关数据输入到预先训练的避障策略模型中，生成避障指令。车辆的当前状态信息所指示的当前状态例如可以包括车辆当前位置、车辆速度、加速度、姿态角等。上述避障指令例如可以包括绕行行驶路径、绕行行驶速度等，此外，避障指令还可以包括停车指令等。
在这些可选的实现方式中，使用避障策略模型对不可忽略的障碍物生成避障指令，避免车辆与障碍物碰撞，可以加快生成避障指令的速度。
继续参见图3，图3是根据本实施例的用于无人驾驶车的避障方法的应用场景300的一个示意图。在图3的应用场景中，无人驾驶车301的上的车载传感器可以实时采集无人驾驶车301的环境数据。在无人驾驶车301的预设行驶路径中有障碍物303。上述障碍物303例如可以为草。车载控制单元302根据所获取的无人驾驶车在当前状态下的环境数据，确定无人驾驶车的预设行驶路径中有障碍物304。之后，响应于确定在无人驾驶车的行进方向上有障碍物，控制单元302将障碍物信息发送至预设终端设备，以使预设终端设备在其展示页面中展示障碍物信息，以使预设终端设备在其展示页面中展示障碍物信息305，上述障碍物信息包括障碍物的图像以及位置信息。接着，控制单元302接收预设终端设备发送的、由预设用户根据障碍物的图像而输入的障碍物的类别信息306，这里障碍物的类别信息用于指示障碍物是可忽略障碍物。最后，控制单元302根据上述预设用户输入的障碍物的类别信息指示障碍物为可忽略障碍物，则生成沿预设路径继续行驶的指令307。
本申请的上述实施例提供的方法，通过响应于确定预设行驶路径中有障碍物，将障碍物信息发送至预设终端设备，以使预设终端设备在其展示页面中展示障碍物信息，之后，接收预设终端设备发送的、由预设用户根据障碍物信息而输入的障碍物的类别信息，最后，根据所述类别信息所指示的障碍物的类别，确定无人驾驶车的避障指令。
上述方法通过将预设终端设备作为人机交互接口，从而使得无人驾驶车可以接收用户对障碍物类别的判断，并根据预设用户对障碍物 类别的判断来决策避障指令。上述方法实现了在无人驾驶车的行进过程中，由人工对障碍物进行辅助识别，并根据上述辅助识别结果来确定避障指令，可以减少由于对障碍物进行躲避而执行减速行驶、绕行甚至停车等操作，从而可以改善由于对所有障碍物进行躲避而引起的驾驶时间延长的现象。
进一步参考图4，其示出了用于无人驾驶车的避障方法的又一个实施例的流程400。该用于无人驾驶车的避障方法的流程400，包括以下步骤：
步骤401，响应于确定预设行驶路径中有障碍物，利用预先训练的障碍物类别识别模型，确定障碍物的参考类别信息。
在本实施例中，用于无人驾驶车的避障方法的执行主体(例如图1所示的控制系统)内可以设置预先训练的障碍物类别识别模型。或者上述执行主体可以通过有线网络或无线网络与设置障碍物类别识别模型的电子设备通信。上述障碍物类别识别模型用于根据输入的障碍物信息确定障碍物的参考类别信息。
上述预先训练的障碍物类别识别模型可以是基于使用多个历史障碍物信息以根据该多个历史障碍物信息分别设置的该多个历史障碍物的历史类别信息对初始障碍物类别识别模型训练得到的。上述预先训练的障碍物类别识别模型用于根据障碍物信息确定障碍物的参考类别信息。
上述参考类别信息用于指示障碍物是否属于可忽略障碍物。
上述障碍物类别识别模型可以是各种机器学习模型，例如人工神经网络膜、卷积神经网络模型等。
步骤402，若参考类别信息指示障碍物不属于可忽略障碍物，将障碍物信息发送至预设终端设备，以使预设终端设备在其展示页面中展示障碍物信息。
在本实施例中，若在步骤402中得到障碍物物的参考类别信息所指示的障碍物属于可忽略障碍物，则上述执行主体可以忽略上述障碍物，上述执行主体生成的避障指令指示无人驾驶车按照原定行驶路径 行驶继续行驶。
若参考类别信息指示障碍物不属于可忽略障碍物，则上述执行主体可以将障碍物的相关数据发送至预设终端设备，以使预设终端设备在其展示页面中展示上述障碍物信息。
在本实施例中，由于在将障碍物的相关数据发送给预设终端设备进行展示之前，采用障碍物类别识别模型对环境数据进行了一次处理。减少了预设用户识别障碍物的类别信息的工作量，有利于缩短预设用户处理所展示的障碍物进行处理的时间。
步骤403，接收预设终端设备发送的、由预设用户根据所展示的障碍物信息而输入的障碍物的类别信息。
在本实施例中，步骤403与图2所示实施例的步骤202相同，此处不赘述。
步骤404，根据类别信息所指示的障碍物的类别，确定无人驾驶车的避障指令。
在本实施例中，步骤404与图2所示实施例的步骤203相同，此处不赘述。
从图4中可以看出，与图2对应的实施例相比，本实施例中的用于无人驾驶车的避障方法的流程400突出了采用预先训练的障碍物类别识别模型确定障碍物的参考类别信息，若参考类别信息指示障碍物为不可忽略障碍物，再将障碍物的相关数据发送至预设终端设备的步骤，从而可以首先由障碍物类别识别模型对障碍物是否可忽略进行判断，然后再由预设用户进行判断。一方面可以减少预设用户的工作量，另一方面还可以进一步缩短无人驾驶车的行驶时间。
在本实施例的一些可选的实现方式中，在步骤403的接收预设终端设备发送的、由预设用户根据所展示的障碍物信息而输入的所述障碍物的类别信息之前，用于无人车的避障方法还包括：若参考类别信息指示障碍物不属于可忽略障碍物，确定障碍物与无人驾驶车之间的距离；若距离小于预设距离阈值，则生成减速行驶的指令。
在这些可选的实现方式中，由于参考类别信息指示障碍物不属于可忽略障碍物，用于无人车的避障方法的执行主体可以进一步确定障 碍物与无人驾驶车之间的距离。当障碍物与无人驾驶车之间的距离小于预设距离阈值时，生成减速行驶的指令可以使无人驾驶车减速行驶，从而使得预设用户有足够的时间来根据展示在预设终端设备上的障碍物信息判断障碍物的类别，以避免由于预设用户未及时对障碍物的类别作出判断，而引起的无人驾驶车与障碍物碰撞的现象。
在本申请的用于无人驾驶车的避障方法各实施例的一些可选的实现方式中，在图2所示实施例的步骤203和图4所示实施例的步骤404之前，用于无人驾驶车的避障方法可以进一步包括：向预设终端设备发送用于提示预设路径中有障碍物的提示信息，以使预设终端设备播放上述提示信息。
在这些可选的实现方式中，上述执行主体在确定了预设行驶路径中有障碍物，向预设终端设备发送障碍物信息，以使预设终端设备在其展示页面中展示障碍物信息的同时，可以向预设终端设备发送用于提示行驶方向上有障碍物的提示信息，以使预设终端设备播放上述提示信息。这些提示信息用来提示预设用户根据预设终端设备的展示页面中所展示的障碍物的图像和位置信息对障碍物的类别进行判断。
这样一来，预设用户不用时刻观察预设终端设备的展示页面中所展示的环境图像的细节，仅需要在接收到提示信息时对预设终端设备所展示的障碍物信息进行判断，来对预设行驶路径中的障碍物的类别进行判断。可以减少预设用户的工作量，避免预设用户疲劳而引起的误判、漏判等。
进一步参考图5，作为对上述各图所示方法的实现，本申请提供了一种用于无人驾驶车的避障装置的一个实施例，该装置实施例与图2所示的方法实施例相对应，该装置具体可以应用于如图5所示，本实施例的用于无人驾驶车的避障装置500包括：发送单元501、接收单元502和指令生成单元503。其中，发送单元501，被配置成响应于确定预设行驶路径中有障碍物，将障碍物信息发送至预设终端设备，以使所述预设终端设备在其展示页面中展示所述障碍物信息，所述障碍物信息包括所述障碍物的图像以及位置信息；接收单元502，被配 置成接收所述预设终端设备发送的、由预设用户根据所展示的障碍物信息而输入的障碍物的类别信息，其中，所述类别信息用于指示所述障碍物的类别；指令生成单元503，被配置成根据所述类别信息所指示的障碍物的类别，确定无人驾驶车的避障指令。
在本实施例中，用于无人驾驶车的避障装置500的发送单元501、接收单元502和指令生成单元503的具体处理及其所带来的技术效果可分别参考图2对应实施例中步骤201、步骤202和步骤203的相关说明，在此不再赘述。
在本实施例的一些可选的实现方式中，发送单元501进一步被配置成：响应于确定预设行驶路径中有障碍物，利用预先训练的障碍物类别识别模型，确定障碍物的参考类别信息，参考类别信息用于指示障碍物是否属于可忽略障碍物；若参考类别信息指示障碍物不属于可忽略障碍物，将障碍物信息发送至预设终端设备，以使预设终端设备在其展示页面中展示障碍物信息；其中障碍物类别识别模型基于使用多个历史障碍物信息以及预设用户根据该多个历史障碍物信息分别设置的该多个历史障碍物的历史类别信息对初始障碍物类别识别模型训练得到，用于根据障碍物信息确定障碍物的参考类别信息。
在本实施例的一些可选的实现方式中，发送单元501进一步被配置成：若所述参考类别信息指示障碍物不属于可忽略障碍物，确定所述障碍物与所述无人驾驶车之间的距离；若所述距离小于预设距离阈值，则生成减速行驶的指令。
在本实施例的一些可选的实现方式中，用于无人驾驶车的避障装置500还包括提示单元(图中未示出)。提示单元被配置成：在接收单元接收预设终端设备发送的、由预设用户根据障碍物信息而输入的障碍物的类别信息之前，向预设终端设备发送用于提示预设行驶路径中有障碍物的提示信息，以使预设终端设备播放提示信息。
在本实施例的一些可选的实现方式中，指令生成单元503进一步被配置成：若类别信息指示障碍物不属于可忽略障碍物，则将无人驾驶车的当前状态信息以及障碍物信息输入到预先训练的避障模型生成避障指令，避障模型基于使用多个历史避障记录对初始避障模型训练 得到。
在本实施例的一些可选的实现方式中，用于无人驾驶车的避障装置500还包括确定单元(图中未示出)。确定单元被配置成：在发送单元响应于确定预设行驶路径中有障碍物，将障碍物信息发送至预设终端设备之前，根据所获取的无人驾驶车的当前环境数据，确定预设行驶路径中是否有障碍物。
下面参考图6，其示出了适于用来实现本申请实施例的电子设备的计算机系统600的结构示意图。图6示出的电子设备仅仅是一个示例，不应对本申请实施例的功能和使用范围带来任何限制。
如图6所示，计算机系统600包括中央处理单元(CPU，Central Processing Unit)601，其可以根据存储在只读存储器(ROM，Read Only Memory)602中的程序或者从存储部分606加载到随机访问存储器(RAM，Random Access Memory)603中的程序而执行各种适当的动作和处理。在RAM 603中，还存储有系统600操作所需的各种程序和数据。CPU 601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(I/O，Input/Output)接口605也连接至总线604。
以下部件连接至I/O接口605：包括硬盘等的存储部分606；以及包括诸如LAN(局域网，Local Area Network)卡、调制解调器等的网络接口卡的通信部分607。通信部分607经由诸如因特网的网络执行通信处理。驱动器608也根据需要连接至I/O接口605。可拆卸介质609，诸如磁盘、光盘、磁光盘、半导体存储器等等，根据需要安装在驱动器608上，以便于从其上读出的计算机程序根据需要被安装入存储部分606。
特别地，根据本公开的实施例，上文参考流程图描述的过程可以被实现为计算机软件程序。例如，本公开的实施例包括一种计算机程序产品，其包括承载在计算机可读介质上的计算机程序，该计算机程序包含用于执行流程图所示的方法的程序代码。在这样的实施例中，该计算机程序可以通过通信部分607从网络上被下载和安装，和/或从可拆卸介质609被安装。在该计算机程序被中央处理单元(CPU)601 执行时，执行本申请的方法中限定的上述功能。需要说明的是，本申请所述的计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本申请中，计算机可读存储介质可以是任何包含或存储程序的有形介质，该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本申请中，计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于：无线、电线、光缆、RF等等，或者上述的任意合适的组合。
可以以一种或多种程序设计语言或其组合来编写用于执行本申请的操作的计算机程序代码，程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
附图中的流程图和框图，图示了按照本申请各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上，流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分，该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意，在有些作为替换的实现中，方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如，两个接连地表示的方框实际上可以基本并行地执行，它们有时也可以按相反的顺序执行，这依所涉及的功能而定。也要注意的是，框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合，可以用执行规定的功能或操作的专用的基于硬件的系统来实现，或者可以用专用硬件与计算机指令的组合来实现。
描述于本申请实施例中所涉及到的单元可以通过软件的方式实现，也可以通过硬件的方式来实现。所描述的单元也可以设置在处理器中，例如，可以描述为：一种处理器包括发送单元、接收单元和指令生成单元。其中，这些单元的名称在某种情况下并不构成对该单元本身的限定，例如，发送单元还可以被描述为“响应于确定预设行驶路径中有障碍物，将障碍物信息发送至预设终端设备，以使所述预设终端设备在其展示页面中展示所述障碍物信息的单元”。
作为另一方面，本申请还提供了一种计算机可读介质，该计算机可读介质可以是上述实施例中描述的装置中所包含的；也可以是单独存在，而未装配入该装置中。上述计算机可读介质承载有一个或者多个程序，当上述一个或者多个程序被该装置执行时，使得该装置：响应于确定预设行驶路径中有障碍物，将障碍物信息发送至预设终端设备，以使预设终端设备在其展示页面中展示障碍物信息，障碍物信息包括障碍物的图像以及位置信息；接收预设终端设备发送的、由预设用户根据所展示的障碍物信息而输入的障碍物的类别信息，其中，类别信息用于指示障碍物的类别；根据类别信息所指示的障碍物的类别，确定无人驾驶车的避障指令。
以上描述仅为本申请的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解，本申请中所涉及的发明范围，并不限 于上述技术特征的特定组合而成的技术方案，同时也应涵盖在不脱离上述发明构思的情况下，由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本申请中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。

Claims (14)

  1. 一种用于无人驾驶车的避障方法，包括：
    响应于确定预设行驶路径中有障碍物，将障碍物信息发送至预设终端设备，以使所述预设终端设备在其展示页面中展示所述障碍物信息，所述障碍物信息包括所述障碍物的图像以及位置信息；
    接收所述预设终端设备发送的、根据所展示的所述障碍物信息而输入的所述障碍物的类别信息，其中，所述类别信息用于指示所述障碍物的类别；
    根据所述类别信息所指示的所述障碍物的类别，确定所述无人驾驶车的避障指令。
  2. 根据权利要求1所述的方法，其中，所述响应于确定预设行驶路径中有障碍物，将障碍物信息发送至预设终端设备，以使所述预设终端设备在其展示页面中展示所述障碍物信息，包括：
    响应于确定所述预设行驶路径中有障碍物，利用预先训练的障碍物类别识别模型，确定所述障碍物的参考类别信息，所述参考类别信息用于指示所述障碍物是否属于可忽略障碍物；
    响应于所述参考类别信息指示所述障碍物不属于可忽略障碍物，将障碍物信息发送至所述预设终端设备，以使所述预设终端设备在其展示页面中展示所述障碍物信息；其中
    所述障碍物类别识别模型基于使用多个历史障碍物信息以及根据所述多个历史障碍物信息分别设置的所述多个历史障碍物的历史类别信息对初始障碍物类别识别模型训练得到，用于根据障碍物信息确定障碍物的参考类别信息。
  3. 根据权利要求2所述的方法，其中，在所述接收所述预设终端设备发送的、根据所展示的障碍物信息而输入的所述障碍物的类别信息之前，所述方法还包括：
    响应于所述参考类别信息指示障碍物不属于可忽略障碍物，确定 所述障碍物与所述无人驾驶车之间的距离；
    若所述距离小于预设距离阈值，则生成减速行驶的指令。
  4. 根据权利要求1所述的方法，其中，在所述接收所述预设终端设备发送的、根据所述障碍物信息而输入的所述障碍物的类别信息之前，所述方法还包括：
    向所述预设终端设备发送用于提示预设行驶路径中有障碍物的提示信息，以使所述预设终端设备播放所述提示信息。
  5. 根据权利要求1所述的方法，其中，所述根据所述类别信息所指示的障碍物的类别，确定无人驾驶车的避障指令，包括：
    响应于所述类别信息指示所述障碍物不属于可忽略障碍物，则将所述无人驾驶车的当前状态信息以及障碍物信息输入到预先训练的避障模型生成避障指令，所述避障模型基于使用多个历史避障记录对初始避障模型训练得到。
  6. 根据权利要求1所述的方法，其中，在所述响应于确定预设行驶路径中有障碍物，将障碍物信息发送至预设终端设备之前，所述方法还包括：
    根据所获取的无人驾驶车的当前环境数据，确定预设行驶路径中是否有障碍物。
  7. 一种用于无人驾驶车的避障装置，包括：
    发送单元，被配置成响应于确定预设行驶路径中有障碍物，将障碍物信息发送至预设终端设备，以使所述预设终端设备在其展示页面中展示所述障碍物信息，所述障碍物信息包括所述障碍物的图像以及位置信息；
    接收单元，被配置成接收所述预设终端设备发送的、根据所展示的所述障碍物信息而输入的所述障碍物的类别信息，其中，所述类别信息用于指示所述障碍物的类别；
    指令生成单元，被配置成根据所述类别信息所指示的所述障碍物的类别，确定所述无人驾驶车的避障指令。
  8. 根据权利要求7所述的装置，其中，所述发送单元进一步被配置成：
    响应于确定所述预设行驶路径中有障碍物，利用预先训练的障碍物类别识别模型，确定所述障碍物的参考类别信息，所述参考类别信息用于指示所述障碍物是否属于可忽略障碍物；
    响应于所述参考类别信息指示所述障碍物不属于可忽略障碍物，将障碍物信息发送至所述预设终端设备，以使所述预设终端设备在其展示页面中展示所述障碍物信息；其中
    所述障碍物类别识别模型基于使用多个历史障碍物信息以及根据所述多个历史障碍物信息分别设置的所述多个历史障碍物的历史类别信息对初始障碍物类别识别模型训练得到，用于根据障碍物信息确定障碍物的参考类别信息。
  9. 根据权利要求8所述的装置，其中，所述发送单元进一步被配置成：
    响应于所述参考类别信息指示障碍物不属于可忽略障碍物，确定所述障碍物与所述无人驾驶车之间的距离；
    响应于所述距离小于预设距离阈值，则生成减速行驶的指令。
  10. 根据权利要求7所述的装置，其中，所述装置还包括提示单元，被配置成：
    在所述接收单元接收所述预设终端设备发送的、根据所述障碍物信息而输入的所述障碍物的类别信息之前，向所述预设终端设备发送用于提示预设行驶路径中有障碍物的提示信息，以使所述预设终端设备播放所述提示信息。
  11. 根据权利要求7所述的装置，其中，所述指令生成单元，进 一步被配置成：
    响应于所述类别信息指示所述障碍物不属于可忽略障碍物，则将所述无人驾驶车的当前状态信息以及障碍物信息输入到预先训练的避障模型生成避障指令，所述避障模型基于使用多个历史避障记录对初始避障模型训练得到。
  12. 根据权利要求7所述的装置，其中，所述装置还包括确定单元，所述确定单元被配置成：
    在所述发送单元响应于确定预设行驶路径中有障碍物，将障碍物信息发送至预设终端设备之前，根据所获取的无人驾驶车的当前环境数据，确定预设行驶路径中是否有障碍物。
  13. 一种电子设备，包括：
    一个或多个处理器；
    存储装置，其上存储有一个或多个程序，
    当所述一个或多个程序被所述一个或多个处理器执行，使得所述一个或多个处理器实现如权利要求1-6中任一所述的方法。
  14. 一种计算机可读介质，其上存储有计算机程序，其中，该程序被处理器执行时实现如权利要求1-6中任一所述的方法。
PCT/CN2019/103253 2018-11-30 2019-08-29 用于无人驾驶车的避障方法和装置 WO2020107974A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
EP19889463.6A EP3757875A4 (en) 2018-11-30 2019-08-29 METHOD AND DEVICE FOR AVOIDING OBSTACLES TO DRIVERLESS VEHICLES
JP2020550724A JP7174063B2 (ja) 2018-11-30 2019-08-29 無人運転車用の障害物回避方法及び装置
US17/024,651 US20210001841A1 (en) 2018-11-30 2020-09-17 Obstacle Avoidance Method and Apparatus for Autonomous Driving Vehicle

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201811458406.9 2018-11-30
CN201811458406.9A CN109583384A (zh) 2018-11-30 2018-11-30 用于无人驾驶车的避障方法和装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/024,651 Continuation US20210001841A1 (en) 2018-11-30 2020-09-17 Obstacle Avoidance Method and Apparatus for Autonomous Driving Vehicle

Publications (1)

Publication Number Publication Date
WO2020107974A1 true WO2020107974A1 (zh) 2020-06-04

Family

ID=65925922

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/103253 WO2020107974A1 (zh) 2018-11-30 2019-08-29 用于无人驾驶车的避障方法和装置

Country Status (5)

Country Link
US (1) US20210001841A1 (zh)
EP (1) EP3757875A4 (zh)
JP (1) JP7174063B2 (zh)
CN (1) CN109583384A (zh)
WO (1) WO2020107974A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111857135A (zh) * 2020-06-30 2020-10-30 北京百度网讯科技有限公司 用于车辆的避障方法、装置、电子设备和计算机存储介质
CN112269379A (zh) * 2020-10-14 2021-01-26 北京石头世纪科技股份有限公司 障碍物识别信息反馈方法
CN113496213A (zh) * 2021-06-29 2021-10-12 中汽创智科技有限公司 一种目标感知数据的确定方法、装置、系统及存储介质

Families Citing this family (31)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109583384A (zh) * 2018-11-30 2019-04-05 百度在线网络技术（北京）有限公司 用于无人驾驶车的避障方法和装置
CN110320910B (zh) * 2019-07-01 2023-10-10 阿波罗智能技术(北京)有限公司 车辆的避让控制方法、装置、电子设备与存储介质
CN114026961A (zh) 2019-07-04 2022-02-08 昕诺飞控股有限公司 用于照明的控制设备
CN112346445A (zh) * 2019-08-07 2021-02-09 坎德拉（深圳）科技创新有限公司 一种配送机器人及其避障方法、计算机存储介质
CN114291082A (zh) * 2019-10-09 2022-04-08 北京百度网讯科技有限公司 用于控制车辆的方法和装置
CN110827578B (zh) * 2019-10-23 2022-05-10 江苏广宇协同科技发展研究院有限公司 一种基于车路协同的车辆防碰撞提示方法、装置及系统
CN112749595A (zh) * 2019-10-31 2021-05-04 北京沃东天骏信息技术有限公司 一种确定行驶路径的方法和装置
CN110879560B (zh) * 2019-12-23 2022-02-25 北京百度网讯科技有限公司 控制车辆的方法、装置、设备和存储介质
CN110989623A (zh) * 2019-12-25 2020-04-10 广州极飞科技有限公司 地面无人作业设备及控制其移动的方法和装置、存储介质
CN111724598B (zh) * 2020-06-29 2022-04-05 北京百度网讯科技有限公司 用于自动驾驶规划路径的方法、装置、设备以及存储介质
CN111982137B (zh) 2020-06-30 2022-08-12 阿波罗智能技术(北京)有限公司 生成路线规划模型的方法、装置、设备和存储介质
CN111959526B (zh) * 2020-06-30 2022-02-15 北京百度网讯科技有限公司 基于无人车的控制方法、装置、无人车和电子设备
CN112078593B (zh) * 2020-07-24 2021-12-21 西安电子科技大学 基于多种网络协同模型的自动驾驶系统及方法
CN112077840B (zh) * 2020-08-08 2022-02-15 浙江科聪控制技术有限公司 一种防爆巡检机器人的避障方法及应用于该方法的机器人
CN111879184A (zh) * 2020-08-27 2020-11-03 航天科工智能机器人有限责任公司 移动靶车系统
CN112168074B (zh) * 2020-09-14 2022-06-24 上海思寒环保科技有限公司 一种智能清洁机器人的清洁方法及系统
CN112540365B (zh) * 2020-12-10 2022-07-12 中国第一汽车股份有限公司 一种评估方法、装置、设备及存储介质
CN112651359A (zh) * 2020-12-30 2021-04-13 深兰科技（上海）有限公司 障碍物检测方法、装置、电子设备和存储介质
CN113819915A (zh) * 2021-03-03 2021-12-21 京东鲲鹏(江苏)科技有限公司 无人车路径规划方法及相关设备
CN113128419B (zh) * 2021-04-23 2023-12-05 京东鲲鹏(江苏)科技有限公司 一种障碍物识别方法和装置、电子设备及存储介质
CN113156954B (zh) * 2021-04-25 2023-03-24 电子科技大学 一种基于增强学习的多智能体集群避障方法
JP7349472B2 (ja) 2021-06-07 2023-09-22 本田技研工業株式会社 警告制御装置、移動体、警告制御方法及びプログラム
CN113325826B (zh) * 2021-06-08 2022-08-30 矿冶科技集团有限公司 一种井下车辆控制方法、装置、电子设备及存储介质
CN113650607B (zh) * 2021-07-20 2023-06-06 江铃汽车股份有限公司 一种低速场景自动驾驶方法、系统及汽车
CN113734164B (zh) * 2021-09-07 2022-04-19 北京三快在线科技有限公司 无人车的控制方法、装置、存储介质及电子设备
CN114415726B (zh) * 2022-01-18 2023-01-03 江苏锐天智能科技股份有限公司 一种基于图像分析的无人机避障控制系统及方法
JP2024005701A (ja) * 2022-06-30 2024-01-17 ヤンマーホールディングス株式会社 自動走行方法、自動走行システム、及び自動走行プログラム
CN115329024B (zh) * 2022-08-18 2023-09-26 北京百度网讯科技有限公司 一种地图数据更新方法、装置、电子设备及存储介质
CN115489522B (zh) * 2022-11-18 2023-04-07 东风悦享科技有限公司 一种应用于平行辅助驾驶系统的避障目标识别方法及系统
CN115535004B (zh) * 2022-11-21 2023-03-10 小米汽车科技有限公司 距离生成方法、装置、存储介质及车辆
CN115593397B (zh) * 2022-11-29 2023-03-21 小米汽车科技有限公司 车辆控制方法、装置、存储介质与芯片

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105261224A (zh) * 2015-09-02 2016-01-20 奇瑞汽车股份有限公司 智能车辆控制方法和装置
CN108521809A (zh) * 2017-12-18 2018-09-11 深圳市大疆创新科技有限公司 障碍物信息提示方法、系统、设备、装置及记录介质
WO2018195857A1 (zh) * 2017-04-27 2018-11-01 深圳市大疆创新科技有限公司 无人机的控制方法、设备及障碍物的提示方法、设备
CN109583384A (zh) * 2018-11-30 2019-04-05 百度在线网络技术（北京）有限公司 用于无人驾驶车的避障方法和装置

Family Cites Families (16)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2000305625A (ja) 1999-04-16 2000-11-02 Honda Motor Co Ltd 自動走行車
JP5293321B2 (ja) 2009-03-23 2013-09-18 株式会社豊田中央研究所 対象物識別装置及びプログラム
US9052714B2 (en) 2013-07-12 2015-06-09 Jaybridge Robotics, Inc. Computer-implemented method and system for controlling operation of an autonomous driverless vehicle in response to obstacle detection
JP6558731B2 (ja) * 2015-04-21 2019-08-14 パナソニックＩｐマネジメント株式会社 運転支援方法およびそれを利用した運転支援装置、運転制御装置、車両、運転支援プログラム
KR102366402B1 (ko) * 2015-05-21 2022-02-22 엘지전자 주식회사 운전자 보조 장치 및 그 제어방법
KR101730321B1 (ko) * 2015-08-03 2017-04-27 엘지전자 주식회사 운전자 보조 장치 및 그 제어방법
JP6747044B2 (ja) 2016-05-11 2020-08-26 株式会社豊田中央研究所 走行経路生成装置、モデル学習装置、及びプログラム
WO2018045577A1 (zh) * 2016-09-09 2018-03-15 深圳市大疆创新科技有限公司 显示无人飞行器的障碍检测的方法和系统
CN106713879A (zh) * 2016-11-25 2017-05-24 重庆杰夫与友文化创意有限公司 避障投影方法及其装置
JP6930152B2 (ja) 2017-03-14 2021-09-01 トヨタ自動車株式会社 自動運転システム
JP6523361B2 (ja) * 2017-03-30 2019-05-29 本田技研工業株式会社 車両制御システム、車両制御方法、および車両制御プログラム
CN106970395B (zh) * 2017-05-08 2019-12-03 奇瑞汽车股份有限公司 确定障碍物位置的方法和装置
CN106959696B (zh) * 2017-05-10 2020-03-03 北京京东尚科信息技术有限公司 运动目标的控制方法和装置
CN107491072B (zh) * 2017-09-05 2021-03-30 百度在线网络技术（北京）有限公司 车辆避障方法和装置
CN108521808B (zh) * 2017-10-31 2021-12-07 深圳市大疆创新科技有限公司 一种障碍信息显示方法、显示装置、无人机及系统
CN109084794B (zh) * 2018-08-09 2021-05-07 北京智行者科技有限公司 一种路径规划方法

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105261224A (zh) * 2015-09-02 2016-01-20 奇瑞汽车股份有限公司 智能车辆控制方法和装置
WO2018195857A1 (zh) * 2017-04-27 2018-11-01 深圳市大疆创新科技有限公司 无人机的控制方法、设备及障碍物的提示方法、设备
CN108521809A (zh) * 2017-12-18 2018-09-11 深圳市大疆创新科技有限公司 障碍物信息提示方法、系统、设备、装置及记录介质
CN109583384A (zh) * 2018-11-30 2019-04-05 百度在线网络技术（北京）有限公司 用于无人驾驶车的避障方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3757875A4

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111857135A (zh) * 2020-06-30 2020-10-30 北京百度网讯科技有限公司 用于车辆的避障方法、装置、电子设备和计算机存储介质
US11807269B2 (en) 2020-06-30 2023-11-07 Beijing Baidu Netcom Science And Technology Co., Ltd. Method for vehicle avoiding obstacle, electronic device, and computer storage medium
CN112269379A (zh) * 2020-10-14 2021-01-26 北京石头世纪科技股份有限公司 障碍物识别信息反馈方法
CN112269379B (zh) * 2020-10-14 2024-02-27 北京石头创新科技有限公司 障碍物识别信息反馈方法
CN113496213A (zh) * 2021-06-29 2021-10-12 中汽创智科技有限公司 一种目标感知数据的确定方法、装置、系统及存储介质
CN113496213B (zh) * 2021-06-29 2024-05-28 中汽创智科技有限公司 一种目标感知数据的确定方法、装置、系统及存储介质

Also Published As

Publication number Publication date
JP7174063B2 (ja) 2022-11-17
EP3757875A4 (en) 2021-12-01
JP2022507995A (ja) 2022-01-19
EP3757875A1 (en) 2020-12-30
US20210001841A1 (en) 2021-01-07
CN109583384A (zh) 2019-04-05

Similar Documents

Publication Publication Date Title
WO2020107974A1 (zh) 用于无人驾驶车的避障方法和装置
CN109455180B (zh) 用于控制无人车的方法和装置
US10457294B1 (en) Neural network based safety monitoring system for autonomous vehicles
WO2017130482A1 (ja) 報知制御装置及び報知制御方法
US11592570B2 (en) Automated labeling system for autonomous driving vehicle lidar data
US20180348763A1 (en) Utilizing rule-based and model-based decision systems for autonomous driving control
US10850739B2 (en) Automatic lane change with lane-biased strategy
CN106292432B (zh) 信息处理方法、装置和电子设备
CN111527013A (zh) 车辆变道预测
US11332165B2 (en) Human trust calibration for autonomous driving agent of vehicle
CN113205088B (zh) 障碍物图像展示方法、电子设备和计算机可读介质
CN110696826B (zh) 用于控制车辆的方法和装置
JPWO2020116195A1 (ja) 情報処理装置、情報処理方法、プログラム、移動体制御装置、及び、移動体
US11904853B2 (en) Apparatus for preventing vehicle collision and method thereof
US10118612B2 (en) Vehicles, electronic control units, and methods for effecting vehicle changes based on predicted actions of target vehicles
EP3588007B1 (en) Information processing method and information processing device
JP2021006448A (ja) 単一車両走行用に設計された自動運転システムでの車両隊列実施
WO2021241260A1 (ja) 情報処理装置、および情報処理方法、情報処理システム、並びにプログラム
KR102433345B1 (ko) 차량 카메라를 이용한 정보 제공 서비스 방법 및 장치
WO2022004448A1 (ja) 情報処理装置、および情報処理方法、情報処理システム、並びにプログラム
CN111341134A (zh) 车道线向导提示方法、云端服务器及车辆
US20230289980A1 (en) Learning model generation method, information processing device, and information processing system
CN114771533A (zh) 自动驾驶车辆的控制方法、装置、设备、车辆及介质
CN113393687B (zh) 驾驶辅助装置、驾驶辅助方法、车辆和介质
CN114511834A (zh) 一种确定提示信息的方法、装置、电子设备及存储介质

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: 19889463

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020550724

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2019889463

Country of ref document: EP

Effective date: 20200923

NENP Non-entry into the national phase

Ref country code: DE