WO2022257488A1 - 基于自动驾驶的乘车方法、装置、设备和存储介质 - Google Patents

基于自动驾驶的乘车方法、装置、设备和存储介质 Download PDF

Info

Publication number
WO2022257488A1
WO2022257488A1 PCT/CN2022/075164 CN2022075164W WO2022257488A1 WO 2022257488 A1 WO2022257488 A1 WO 2022257488A1 CN 2022075164 W CN2022075164 W CN 2022075164W WO 2022257488 A1 WO2022257488 A1 WO 2022257488A1
Authority
WO
WIPO (PCT)
Prior art keywords
point
information
candidate
target
boarding
Prior art date
Application number
PCT/CN2022/075164
Other languages
English (en)
French (fr)
Inventor
张鑫
Original Assignee
北京百度网讯科技有限公司
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 北京百度网讯科技有限公司 filed Critical 北京百度网讯科技有限公司
Priority to KR1020227029593A priority Critical patent/KR20220166784A/ko
Priority to JP2022551665A priority patent/JP7478831B2/ja
Priority to US17/796,074 priority patent/US20240166243A1/en
Publication of WO2022257488A1 publication Critical patent/WO2022257488A1/zh

Links

Images

Classifications

    • 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
    • B60W60/0025—Planning or execution of driving tasks specially adapted for specific operations
    • B60W60/00253—Taxi operations
    • 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
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
    • 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
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/403—Image sensing, e.g. optical camera
    • 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
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/53—Road markings, e.g. lane marker or crosswalk
    • 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
    • B60W2554/404—Characteristics
    • B60W2554/4041—Position
    • 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
    • B60W2556/00—Input parameters relating to data
    • B60W2556/40—High definition maps
    • 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
    • B60W2556/45—External transmission of data to or from the vehicle
    • 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 present disclosure relates to the field of computer technology, to the field of automatic driving and deep learning technology, for example, to a car riding method, device, device and storage medium based on automatic driving.
  • Self-driving vehicles can use self-driving technology to achieve unmanned driving through computer systems.
  • the self-driving technology used by self-driving vehicles can be divided into five levels: L1-L5. As the level increases, the automatic driving function becomes more intelligent.
  • the present disclosure provides a car riding method, device, device and storage medium based on automatic driving.
  • a method of riding a car based on automatic driving including:
  • the vehicle auxiliary information of the candidate boarding point select the target boarding point for the target passenger from the candidate boarding point, wherein the vehicle auxiliary information of the candidate boarding point includes coordinate information and lane information of the candidate boarding point;
  • the self-driving vehicle is controlled to travel to the target boarding point according to the vehicle auxiliary information of the target boarding point.
  • an automatic driving-based ride-hailing device including:
  • the target boarding point selection module is configured to select a target boarding point for the target passenger from the candidate boarding points according to the vehicle auxiliary information of the candidate boarding points, wherein the vehicle auxiliary information of the candidate boarding points includes the candidate boarding point Point coordinate information and lane information;
  • the vehicle control module is configured to control the self-driving vehicle to drive to the target boarding point according to the vehicle auxiliary information of the target boarding point.
  • an electronic device including:
  • the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can perform the automatic driving based on any embodiment of the present disclosure. way of riding.
  • a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to make a computer execute the autonomous driving-based car ride provided by any embodiment of the present disclosure. method.
  • a computer program product including a computer program.
  • the computer program When the computer program is executed by a processor, the method for riding a car based on automatic driving provided by any embodiment of the present disclosure is implemented.
  • FIG. 1 is a schematic diagram of a car-riding method based on automatic driving provided according to an embodiment of the present disclosure
  • Fig. 2 is a schematic diagram of another method of taking a car based on automatic driving according to an embodiment of the present disclosure
  • Fig. 3a is a schematic diagram of another method of riding a car based on automatic driving according to an embodiment of the present disclosure
  • 3b-3d are schematic diagrams of a mapping point provided according to an embodiment of the present disclosure.
  • Fig. 4 is a schematic diagram of another method of riding a car based on automatic driving according to an embodiment of the present disclosure
  • Fig. 5 is a schematic diagram of a ride-hailing device based on automatic driving provided according to an embodiment of the present disclosure
  • FIG. 6 is a block diagram of an electronic device used to implement an automatic driving-based ride-hailing method according to an embodiment of the present disclosure.
  • Fig. 1 is a schematic diagram of a method for taking a car based on automatic driving according to an embodiment of the present disclosure, and the embodiment of the present disclosure is applicable to the situation of taking an automatic driving vehicle.
  • the method can be executed by a ride-hailing device based on automatic driving, which can be implemented in the form of hardware and/or software, and can be configured in electronic equipment.
  • the method includes the following operations.
  • the boarding point refers to the docking point between the passenger and the self-driving vehicle, that is, the passenger boards the vehicle at the boarding point, for example, the self-driving vehicle can wait for the passenger to board at the Waiting for the self-driving vehicle at the car point.
  • Candidate boarding points refer to boarding points available to passengers.
  • Information about candidate boarding points may include vehicle auxiliary information and semantic description information, wherein the vehicle auxiliary information is oriented to the self-driving vehicle, and is used for the self-driving vehicle to drive to the candidate riding point according to the vehicle auxiliary information, and the coordinate information in the vehicle auxiliary information
  • the error can be at the centimeter level, for example, obtained through the high-precision positioning equipment installed in the self-driving vehicle, and the lane information can also be obtained through high-precision positioning, such as the third lane of a certain road.
  • Semantic description information is oriented to passengers, and is used for passengers to walk to candidate boarding points through semantic description information.
  • the target boarding point can be selected for the target passenger from the candidate boarding points according to the initial location of the target passenger.
  • the vehicle auxiliary information of the target boarding point can be sent to the self-driving vehicle, so that the self-driving vehicle can drive to the target boarding point according to the coordinate information and lane information of the target boarding point, and can also be sent to the target passenger.
  • the semantic description information of the target boarding point enables the target passengers to move from the initial position to the target boarding point according to the semantic description information.
  • the vehicle can only obtain the coordinate information of the ride point, and the error range of the coordinate information of the ride point is large.
  • the coordinate information can be obtained through the Global Positioning System (Global Positioning System, GPS) positioning technology. It is not obtained through high-precision positioning.
  • the accuracy of the coordinate information of the boarding point is low.
  • the embodiments of the present disclosure provide the self-driving vehicle with high-precision coordinate information of the target boarding point, such as the lane information associated with the high-precision coordinate information, so that the self-driving vehicle can and lane information to accurately drive to the target boarding point.
  • the target passenger can accurately arrive at the target boarding point according to the semantic description information, that is, through the target boarding point’s
  • the vehicle auxiliary information and semantic description information can take into account the different needs of the self-driving vehicle and the target passenger for the boarding point, so that both the self-driving vehicle and the target passenger can move to the target boarding point, and can overcome the situation that there is no driver in the autonomous driving scene.
  • the problem of difficult docking of autonomous driving vehicles thereby improving the ride efficiency and success rate of rides in autonomous driving scenarios.
  • the technical solution of the embodiment of the present disclosure provides the target driving vehicle with the high-precision coordinate information and lane information of the target boarding point, and provides the target passenger with the semantic description information of the target boarding point, so that both the self-driving vehicle and the target passenger are accurate Moving to the target ride point can improve the ride efficiency and ride success rate of the autonomous driving scene.
  • Fig. 2 is a schematic diagram of another method of riding a car based on automatic driving according to an embodiment of the present disclosure.
  • This embodiment is an optional solution proposed on the basis of the foregoing embodiments.
  • the method for riding a car based on automatic driving provided in this embodiment includes the following operations.
  • S210 Screen the candidate boarding points according to the initial position of the target passenger and the vehicle auxiliary information of the candidate boarding points, wherein the vehicle auxiliary information of the candidate boarding points includes coordinate information and lanes of the candidate boarding points information.
  • the automatic driving feature can be determined according to the historical behavior data of the candidate riding point in the automatic driving scene.
  • the distance between the target passenger and the candidate ride point can be determined according to the initial location of the target passenger, the coordinate information of the candidate ride point and the lane information, and according to the distance
  • the candidate boarding points are screened to obtain at least two candidate boarding points, for example, a maximum of 50 candidate boarding points within 500 meters from the initial position may be selected.
  • the candidate boarding points can also be screened by combining the distance, the click-through rate of the candidate boarding points, and the popularity information of the candidate boarding points. Heat information is negatively correlated.
  • the candidate boarding points located in the legal autonomous driving area can also be eliminated, and the legal autonomous driving area is the legal driving area of the automatic driving area.
  • the automatic driving features of the candidate boarding points can be introduced to sort the screened candidate boarding points, and select the target boarding point for the target passengers according to the sorting results.
  • the candidate boarding point with the highest ranking score can be used as the target boarding point, or a fixed value (for example, 3) candidate boarding points with a relatively high ranking score can be provided to the target passenger, and the target passenger can choose the target according to individual needs ride point.
  • the target boarding point is selected for the target passenger, which can improve the matching degree between the target boarding point and the target passenger, thereby further improving the target passenger’s riding time. Car efficiency and ride success rate.
  • the automatic driving feature includes at least one of the following: automatic driving success rate, road condition complexity, or passenger feedback information.
  • the success rate of automatic driving can refer to the successful docking rate of historical passengers and self-driving vehicles at candidate boarding points.
  • the complexity of road conditions can be determined according to the surrounding road level, the number of pedestrians, and the number of non-motorized vehicles.
  • Passenger feedback information can be Passenger's evaluation information on the difficulty of riding at the candidate boarding point.
  • the automatic driving success rate, road condition complexity, and passenger feedback information of multiple candidate riding points that have been screened can be used as the input of the ranking model, and the scores of multiple candidate riding points output by the ranking model can be obtained; the target riding point can be selected according to the score. car spot.
  • the embodiments of the present disclosure do not limit the network structure of the ranking model, for example, a logistic regression model, Pairwise (ranking model) or RankNet (ranking network), etc. may be used.
  • the candidate boarding points are screened by combining the initial position of the target passenger and the vehicle auxiliary information of the candidate boarding points, and the success rate of automatic driving, the complexity of the road conditions or passenger feedback information are introduced to filter the selected Sorting the candidate ride points can fully consider the characteristics of the autonomous driving ride scene and further improve the ride success rate.
  • Fig. 3a is a schematic diagram of another method of riding a car based on automatic driving according to an embodiment of the present disclosure.
  • This embodiment is an optional solution proposed on the basis of the foregoing embodiments.
  • the method for riding a car based on automatic driving provided in this embodiment includes the following operations.
  • the POI may be a POI visible along the street, such as an east gate of a certain community, a subway station, a bus station, and the like.
  • a POI visible along the street such as an east gate of a certain community, a subway station, a bus station, and the like.
  • the POI can be matched with the lane of the road in the road network to determine whether the POI is on the lane; if the POI is on the lane, use the POI itself as a mapping point (refer to Figure 3b); if the POI is not on the lane , then the point closest to the POI in the lane can be used as the mapping point (refer to Figure 3c).
  • mapping point belongs to the no-riding area. If the mapping point does not belong to the no-riding area, the mapping point can be directly used as the candidate boarding point, and the coordinate information and lane information of the mapping point can be used as the candidate boarding point. Coordinate information and lane information, and adjust the semantic description information of the POI according to the coordinate information of the mapping point and the coordinate information of the POI, to obtain the semantic description information of the mapping point (see Figure 3c).
  • the relative distance and direction between the mapping point and the POI can be determined according to the coordinate information of the mapping point and the coordinate information of the POI, and the semantic description information of the candidate boarding point can be obtained according to the relative distance, direction and the semantic description information of the POI.
  • the semantic description information of the POI is the east gate of a certain shopping mall
  • the semantic description information of the candidate boarding point is 30 meters to the west of the east gate of a certain shopping mall.
  • S330 may include: in the case that the mapping point belongs to a prohibited riding area, correcting the coordinate information and/or lane information of the mapping point to obtain the coordinate information of the candidate riding point and/or lane information, and adjust the semantic description information of the POI according to the coordinate information and/or lane information of the candidate boarding point to obtain the semantic description information of the candidate boarding point.
  • the correction point of the mapping point in the riding area can be obtained by correcting the coordinate information and/or lane information of the mapping point, and the correction point can be used as a candidate riding point , take the coordinate information and lane information of the correction point as the coordinate information and lane information of the candidate boarding point, and adjust the semantic description information of POI according to the coordinate information and lane information of the candidate boarding point to obtain the semantic description of the candidate boarding point information.
  • the semantic description information of POI is a certain bus station on a certain road.
  • the semantic description information of a candidate boarding point can be 30 meters north of a certain bus station on a certain road.
  • the lane information of the candidate riding point can be the third lane of a certain road.
  • a target boarding point for a target passenger before selecting a target boarding point for a target passenger from the candidate boarding points, it also includes: acquiring the coordinate information, semantic description information and historical Passenger’s movement trajectory before boarding; modify the coordinate information of the historical riding point according to the movement trajectory, and determine the coordinate information and lane information of the candidate riding point according to the correction result; according to the coordinate information of the candidate riding point Information, adjusting the semantic description information of the historical boarding point to obtain the semantic description information of the candidate boarding point.
  • historical riding points in non-autonomous driving scenarios can also be used to mine candidate riding points in automatic driving scenarios. Since the coordinates of historical boarding points in non-autonomous driving scenarios are obtained through the positioning equipment of historical passengers or drivers, rather than through high-precision positioning, the positioning error is on the order of meters or hundreds of meters.
  • the candidate By inferring the actual riding point coordinates of historical passengers and the lanes corresponding to the actual riding point coordinates according to the historical passenger's moving trajectory (such as walking trajectory) before boarding, as the coordinate information and lane information of the candidate riding point, the candidate The positioning accuracy of the boarding point can meet the high-precision positioning requirements of the self-driving vehicle, which is convenient for the self-driving vehicle to accurately locate the candidate boarding point.
  • the target passenger before selecting the target passenger from the candidate riding points, it also includes: using the actual riding points of historical passengers in the autonomous driving scene as the candidate riding points. point, and obtain the coordinate information, lane information and semantic description information of the candidate riding point.
  • the self-driving vehicle is equipped with high-precision positioning equipment
  • the coordinate information and lane information of the actual boarding point of the historical passenger can be collected through the high-precision positioning equipment, which can
  • the actual boarding point is used as a candidate boarding point; and the semantic description information of the actual boarding point can also be determined according to the coordinate information of the actual boarding point, the relationship between the lane information and the POI coordinates.
  • the POI information, the coordinate information of the historical boarding points in the non-autonomous driving scene, the movement track of the historical passengers before boarding, and the actual boarding points of the historical passengers in the automatic driving scene are mined
  • Candidate boarding points in the autonomous driving scene can obtain high-precision coordinate information and lane information of candidate boarding points, and can also obtain semantic description information of candidate boarding points, which is convenient for autonomous vehicles and passengers to accurately locate candidate boarding points. car points, thereby improving the success rate and efficiency of car rides in autonomous driving scenarios.
  • Fig. 4 is a schematic diagram of another method for riding a car based on automatic driving according to an embodiment of the present disclosure.
  • This embodiment is an optional solution proposed on the basis of the foregoing embodiments.
  • the method for riding a car based on automatic driving provided in this embodiment includes the following operations.
  • the self-driving vehicle arrives at the target boarding point, it can be checked whether the target passenger has arrived at the target boarding point, by checking whether the target passenger has already boarded the vehicle or collecting the vehicle information through the image collector of the self-driving vehicle Environmental images, and through face recognition technology to determine whether the target passenger has arrived.
  • the vehicle environment image can be sent to the electronic device held by the target passenger, so that the target passenger can determine the actual position of the self-driving vehicle according to the vehicle environment image, so that the target passenger can accurately and quickly locate the automatic vehicle drive the vehicle.
  • after controlling the self-driving vehicle to drive to the target boarding point according to the vehicle auxiliary information of the target boarding point further includes: when the self-driving vehicle arrives at the target boarding point and the target passenger In the case of the target boarding point, control the self-driving vehicle to interact with the target passenger, and generate candidate instructions according to the interaction information; send an inquiry message to the target passenger whether to execute the candidate instruction; after the target passenger confirms the execution, control the automatic The driving vehicle executes candidate instructions to adjust the actual location information of the autonomous vehicle.
  • the self-driving vehicle when the self-driving vehicle arrives at the target boarding point, and the target passenger does not arrive at the target boarding point, the self-driving vehicle can also interact with the user, such as voice interaction, video call interaction, etc.
  • the vehicle executes candidate instructions to adjust the actual location information of the autonomous vehicle.
  • the embodiments of the present disclosure do not limit the candidate instructions, for example, the candidate instructions may be adjusting to the opposite side of the road, turning around, and the like.
  • the adjustment of the position of the self-driving vehicle can solve the problems of inaccurate target boarding points and target passenger positioning travel deviations, improve the convenience and flexibility of the target passenger's ride, and further improve the success rate of the ride.
  • the self-driving vehicle arrives at the target boarding point, by sending the vehicle environment image to the target passenger, or by controlling the self-driving vehicle to adjust the actual situation of the self-driving vehicle according to the confirmation information of the candidate instruction by the target passenger.
  • Location information can make accurate recommendations for close-range self-driving vehicles and target passengers, thereby improving the success rate of target passengers arriving at self-driving vehicles.
  • Fig. 5 is a schematic diagram of a ride-on device based on automatic driving provided by an embodiment of the present disclosure. This embodiment is applicable to the situation of riding an automatic driving vehicle.
  • the device is configured in an electronic device and can implement any embodiment of the present disclosure.
  • the ride-on device 500 based on automatic driving includes the following modules.
  • the target boarding point selection module 501 is configured to select a target boarding point for the target passenger from the candidate boarding points according to the vehicle auxiliary information of the candidate boarding points, wherein the vehicle auxiliary information of the candidate boarding points includes the candidate boarding point Coordinate information and lane information of vehicle points;
  • the vehicle control module 502 is configured to control the self-driving vehicle to drive to the target boarding point according to the vehicle auxiliary information of the target boarding point.
  • the target riding point selection module 501 includes:
  • the target riding point screening unit is configured to filter the candidate riding points according to the initial position of the target passenger and the vehicle auxiliary information of the candidate riding points;
  • the target boarding point sorting unit is configured to sort the filtered candidate boarding points according to the automatic driving characteristics of the candidate boarding points, and select the target boarding point for the target passenger according to the sorting result.
  • the automatic driving feature includes at least one of the following: automatic driving success rate, road condition complexity, or passenger feedback information.
  • the ride device 500 based on automatic driving also includes a first candidate ride point module, and the first candidate ride point module includes:
  • a POI information acquisition unit is configured to acquire semantic description information and coordinate information of a point of interest POI
  • the POI matching unit is configured to match the coordinate information of the POI with the lane in the road network to obtain the mapping point of the POI on the lane;
  • the first candidate riding point unit is configured to determine the coordinate information and lane information of the candidate riding point according to the coordinate information and lane information of the mapping point, and determine the semantic description information of the candidate riding point according to the semantic description information of the POI .
  • the first candidate ride point unit is set to:
  • the coordinate information and/or lane information of the mapping point are corrected to obtain the coordinate information and/or lane information of the candidate riding point, and according to the candidate riding point
  • the coordinate information and/or lane information of the point adjust the semantic description information of the POI to obtain the semantic description information of the candidate boarding point.
  • the ride device 500 based on automatic driving also includes a second candidate ride point module, and the second candidate ride point module includes:
  • the historical passenger information unit is set to obtain the coordinate information, semantic description information and the moving track of the historical passengers before the ride of the historical passengers in the non-autonomous driving scene;
  • the coordinate correction unit is configured to correct the coordinate information of the historical boarding point according to the movement trajectory, and determine the coordinate information and lane information of the candidate boarding point according to the correction result;
  • the second candidate riding point unit is configured to adjust the semantic description information of the historical riding point to obtain the semantic description information of the candidate riding point according to the coordinate information of the candidate riding point.
  • the ride-on device 500 based on automatic driving also includes:
  • the third candidate boarding point module is configured to use the actual boarding point of historical passengers in the automatic driving scene as the candidate boarding point, and obtain the coordinate information, lane information and semantic description information of the candidate boarding point .
  • the ride-on device 500 based on automatic driving also includes:
  • the environment image sending module is configured to control the self-driving vehicle to collect the vehicle environment image and send the vehicle environment image to the target passenger when the self-driving vehicle arrives at the target boarding point and the target passenger does not arrive at the target boarding point, for Assisting target occupants in locating self-driving vehicles.
  • the ride-on device 500 based on automatic driving also includes an interaction module, and the interaction module includes:
  • the instruction generation unit is configured to control the automatic driving vehicle to interact with the target passenger when the self-driving vehicle arrives at the target boarding point and the target passenger does not arrive at the target boarding point, and generate candidate instructions according to the interaction information;
  • the inquiry unit is configured to send the inquiry information of whether to execute the candidate instruction to the target passenger;
  • the instruction execution unit is configured to control the self-driving vehicle to execute candidate instructions after the target passenger confirms the execution, so as to adjust the position information of the self-driving vehicle.
  • the technical solution of this embodiment aiming at the scene of autonomous driving, excavates candidate boarding points with high-precision coordinate information and lane information.
  • the self-driving vehicle arrives at the target ride point, it can also control the interaction between the self-driving vehicle and the target passenger, and make close-range and accurate recommendations for the self-driving vehicle and the target passenger, further improving the ride quality. Success rate and ride efficiency.
  • the present disclosure also provides an electronic device, a readable storage medium, and a computer program product.
  • FIG. 6 shows a schematic block diagram of an example electronic device 600 that may be used to implement embodiments of the present disclosure.
  • Electronic device is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other suitable computers.
  • Electronic devices may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smart phones, wearable devices, and other similar computing devices.
  • the components shown herein, their connections and relationships, and their functions, are by way of example only, and are not intended to limit implementations of the disclosure described and/or claimed herein.
  • the device 600 includes a computing unit 601, and the computing unit 601 can be loaded into a random access memory (Random Access Memory) according to a computer program stored in a read-only memory (Read-Only Memory, ROM) 602 or from a storage unit 608. , the computer program in RAM) 603 to perform various appropriate actions and processes. In the RAM 603, various programs and data necessary for the operation of the device 600 can also be stored.
  • the computing unit 601, ROM 602, and RAM 603 are connected to each other through a bus 604.
  • An input/output (Input/Output, I/O) interface 605 is also connected to the bus 604 .
  • the I/O interface 605 includes: an input unit 606, such as a keyboard, a mouse, etc.; an output unit 607, such as various types of displays, speakers, etc.; a storage unit 608, such as a magnetic disk, an optical disk, etc. ; and a communication unit 609, such as a network card, a modem, a wireless communication transceiver, and the like.
  • the communication unit 609 allows the device 600 to exchange information/data with other devices over a computer network such as the Internet and/or various telecommunication networks.
  • Computing unit 601 may be various general-purpose and/or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 601 include, but are not limited to, a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU), various dedicated artificial intelligence (Artificial Intelligence, AI) computing chips, various execution The computing unit of the machine learning model algorithm, the digital signal processor (Digital Signal Processor, DSP), and any appropriate processor, controller, microcontroller, etc.
  • the calculation unit 601 executes a plurality of methods and processes described above, such as a car riding method based on automatic driving.
  • the autonomous driving-based ride-hailing method may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as storage unit 608 .
  • part or all of the computer program may be loaded and/or installed on the device 600 via the ROM 602 and/or the communication unit 609.
  • the computing unit 601 may be configured in any other appropriate way (for example, by means of firmware) to execute a car-riding method based on automatic driving.
  • programmable processor can be special-purpose or general-purpose programmable processor, can receive data and instruction from storage system, at least one input device, and at least one output device, and transmit data and instruction to this storage system, this at least one input device, and this at least one output device an output device.
  • Program codes for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special purpose computer, or other programmable data processing devices, so that the program codes, when executed by the processor or controller, make the functions/functions specified in the flow diagrams and/or block diagrams Action is implemented.
  • the program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.
  • a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device.
  • a machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
  • a machine-readable medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing.
  • Machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, RAM, ROM, Erasable Programmable Read-Only Memory (EPROM), flash memory, optical fiber , Compact Disc Read Only Memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.
  • the storage medium may be a non-transitory storage medium.
  • the systems and techniques described herein can be implemented on a computer having a display device (e.g., a Cathode Ray Tube (CRT) or a Liquid Crystal Display (LCD)) for displaying information to the user.
  • a display device e.g., a Cathode Ray Tube (CRT) or a Liquid Crystal Display (LCD)
  • LCD Liquid Crystal Display
  • keyboard and pointing device e.g., a mouse or trackball
  • Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and can be in any form (including Acoustic input, speech input or, tactile input) to receive input from the user.
  • the systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., as a a user computer having a graphical user interface or web browser through which a user can interact with embodiments of the systems and techniques described herein), or including such backend components, middleware components, Or any combination of front-end components in a computing system.
  • the components of the system can be interconnected by any form or medium of digital data communication, eg, a communication network. Examples of communication networks include: Local Area Network (LAN), Wide Area Network (Wide Area Network, WAN), blockchain networks, and the Internet.
  • a computer system may include clients and servers.
  • Clients and servers are generally remote from each other and typically interact through a communication network.
  • the relationship of client and server arises by computer programs executing on the respective computers and having a client-server relationship to each other.
  • the server can be a cloud server, also known as cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the problems existing in traditional physical host and virtual private server (Virtual Private Server, VPS) services.
  • VPS Virtual Private Server
  • Steps can be reordered, added, or removed using the various forms of flow shown above.
  • steps described in the present disclosure may be executed in parallel, sequentially, or in a different order, as long as the desired result of the technical solution disclosed in the present disclosure can be achieved, no limitation is imposed herein.

Landscapes

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

Abstract

基于自动驾驶的乘车方法、装置、设备和存储介质。该基于自动驾驶的乘车方法包括：根据候选乘车点的车辆辅助信息，从候选乘车点中为目标乘客选择目标乘车点；其中，所述候选乘车点的车辆辅助信息包括候选乘车点的坐标信息和车道信息；控制自动驾驶车辆根据目标乘车点的车辆辅助信息向所述目标乘车点行驶。

Description

基于自动驾驶的乘车方法、装置、设备和存储介质
本申请要求在2021年06月09日提交中国专利局、申请号为202110643898.4的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本公开涉及计算机技术领域，涉及自动驾驶和深度学习技术领域，例如涉及基于自动驾驶的乘车方法、装置、设备和存储介质。
背景技术
自动驾驶车辆可以通过计算机系统采用自动驾驶技术实现无人驾驶。自动驾驶车辆采用的自动驾驶技术可以划分为L1-L5五个等级。随着等级的升高，自动驾驶功能越智能化。
随着自动驾驶技术的发展，众多科技公司都在探索自动驾驶出租车(Robotaxi)方面的技术。在自动驾驶的乘车(即用户乘坐自动驾驶车辆)场景中，自动驾驶车辆如何顺利接到乘客是成单的关键。
发明内容
本公开提供了一种用于基于自动驾驶的乘车方法、装置、设备和存储介质。
根据本公开的一方面，提供了一种基于自动驾驶的乘车方法，包括：
根据候选乘车点的车辆辅助信息，从候选乘车点中为目标乘客选择目标乘车点，其中，所述候选乘车点的车辆辅助信息包括候选乘车点的坐标信息和车道信息；
控制自动驾驶车辆根据目标乘车点的车辆辅助信息向所述目标乘车点行驶。
根据本公开的又一方面，提供了一种基于自动驾驶的乘车装置，包括：
目标乘车点选择模块，设置为根据候选乘车点的车辆辅助信息，从候选乘车点中为目标乘客选择目标乘车点，其中，所述候选乘车点的车辆辅助信息包括候选乘车点的坐标信息和车道信息；
车辆控制模块，设置为控制自动驾驶车辆根据目标乘车点的车辆辅助信息向所述目标乘车点行驶。
根据本公开的又一方面，提供了一种电子设备，包括：
至少一个处理器；以及
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行本公开任意实施例所提供的基于自动驾驶的乘车方法。
根据本公开的又一方面，提供了一种存储有计算机指令的非瞬时计算机可读存储介质，其中，所述计算机指令用于使计算机执行本公开任意实施例所提供的基于自动驾驶的乘车方法。
根据本公开的又一方面，提供了一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现本公开任意实施例所提供的基于自动驾驶的乘车方法。
附图说明
图1是根据本公开实施例提供的一种基于自动驾驶的乘车方法的示意图；
图2是根据本公开实施例提供的另一种基于自动驾驶的乘车方法的示意图；
图3a是根据本公开实施例提供的又一种基于自动驾驶的乘车方法的示意图；
图3b-图3d分别是根据本公开实施例提供的一种映射点的示意图；
图4是根据本公开实施例提供的又一种基于自动驾驶的乘车方法的示意图；
图5是根据本公开实施例提供的一种基于自动驾驶的乘车装置的示意图；
图6是用来实现本公开实施例的基于自动驾驶的乘车方法的电子设备的框图。
具体实施方式
以下结合附图对本公开的示范性实施例做出说明，其中包括本公开实施例的多种细节以助于理解，应当将它们认为仅仅是示范性的。可以对这里描述的实施例做出多种改变和修改。以下的描述中省略了对公知功能和结构的描述。
以下结合附图，对本公开实施例提供的该方案进行说明。
图1是根据本公开实施例提供的一种基于自动驾驶的乘车方法的示意图，本公开实施例可适用于乘坐自动驾驶车辆的情况。该方法可由一种基于自动驾驶的乘车装置来执行，该装置可采用硬件和/或软件的方式来实现，可 配置于电子设备中。参考图1，该方法包括如下操作。
S110、根据候选乘车点的车辆辅助信息，从候选乘车点中为目标乘客选择目标乘车点，其中，所述候选乘车点的车辆辅助信息包括候选乘车点的坐标信息和车道信息。
S120、控制自动驾驶车辆根据目标乘车点的车辆辅助信息向所述目标乘车点行驶。
在本公开实施例中，乘车点是指乘客与自动驾驶车辆的对接点，即乘客在乘车点上车，例如自动驾驶车辆可以在乘车点处等待乘客上车，乘客也可以在乘车点处等待自动驾驶车辆。
候选乘车点是指可供乘客使用的乘车点。关于候选乘车点的信息可以包括车辆辅助信息和语义描述信息，其中，车辆辅助信息面向自动驾驶车辆，用于自动驾驶车辆根据车辆辅助信息向候选乘车点行驶，车辆辅助信息中的坐标信息的误差可以是厘米级别的，例如通过自动驾驶车辆中设置的高精度定位设备得到，车道信息也可以通过高精度定位得到，例如某某路的第3车道。语义描述信息面向乘客，用于乘客通过语义描述信息步行到候选乘车点。
在目标乘客需要乘坐自动驾驶车辆的情况下，可以根据目标乘客的初始位置从候选乘车点中为目标乘客选择目标乘车点。选择目标乘车点后，可以向自动驾驶车辆发送目标乘车点的车辆辅助信息，使自动驾驶车辆根据目标乘车点的坐标信息和车道信息向目标乘车点行驶，还可以向目标乘客发送目标乘车点的语义描述信息，使目标乘客根据语义描述信息由初始位置移动到目标乘车点处。
在非自动驾驶场景中，车辆只能获得乘车点的坐标信息，并且乘车点的坐标信息的误差范围较大，例如坐标信息可以通过全球定位系统(Global Positioning System，GPS)定位技术得到，而不是通过高精定位得到。在非自动驾驶场景中，乘车点的坐标信息精度较低，在车辆到达乘车点后，司机可以结合地图导航和经验常识，观测环境门牌标牌信息，与乘客通过语音电话等方式找到乘客的实际乘车位置。
本公开实施例在自动驾驶场景中，通过向自动驾驶车辆提供目标乘车点的高精度坐标信息，例如高精度坐标信息所关联的车道信息，使自动驾驶车辆可以根据目标乘车点的坐标信息和车道信息准确行驶到目标乘车点，通过向目标乘客提供目标乘车点的语义描述信息，使目标乘客可以根据语义描述信息准确到达目标乘车点，也就是说，通过目标乘车点的车辆辅助信息和语义描述信息，能够兼顾自动驾驶车辆和目标乘客对乘车点的不同需求，使自 动驾驶车辆和目标乘客均移动到目标乘车点，能够克服自动驾驶场景中没有司机导致乘客与自动驾驶车辆对接难的问题，从而提高自动驾驶场景的乘车效率和乘车成功率。
本公开实施例的技术方案，通过向目标驾驶车辆提供目标乘车点的高精度坐标信息和车道信息，向目标乘客提供目标乘车点的语义描述信息，使自动驾驶车辆和目标乘客均准确的移动到目标乘车点，能够提高自动驾驶场景的乘车效率和乘车成功率。
图2是根据本公开实施例提供的另一种基于自动驾驶的乘车方法的示意图。本实施例是在上述实施例的基础上提出的一种可选方案。参见图2，本实施例提供的基于自动驾驶的乘车方法包括以下操作。
S210、根据目标乘客的初始位置和所述候选乘车点的车辆辅助信息，对候选乘车点进行筛选，其中，所述候选乘车点的车辆辅助信息包括候选乘车点的坐标信息和车道信息。
S220、根据候选乘车点的自动驾驶特征，对经筛选的候选乘车点进行排序，并根据排序结果为目标乘客选择目标乘车点。
S230、控制自动驾驶车辆根据目标乘车点的车辆辅助信息向所述目标乘车点行驶。
其中，自动驾驶特征可以根据候选乘车点在自动驾驶场景中的历史行为数据确定。响应于包括目标乘客的初始位置的自动驾驶乘车请求，可以根据目标乘客的初始位置、候选乘车点的坐标信息和车道信息，确定目标乘客与候选乘车点之间的距离，并根据距离对候选乘车点进行筛选得到经筛选的至少两个候选乘车点，例如可以选择在初始位置500米以内的最多50个候选乘车点。另外，还可以结合距离、候选乘车点的点击率、候选乘车点的热度信息对候选乘车点进行筛选，其中候选乘车点被滤除的概率可以与候选乘车点的点击率、热度信息呈负相关。在对经筛选的候选乘车点进行排序之前还可以剔除位于合法自动驾驶乘车区域的候选乘车点，合法自动驾驶乘车区域即自动驾驶乘车的合法行驶区域。
可以引入候选乘车点的自动驾驶特征对经筛选的候选乘车点进行排序，并根据排序结果为目标乘客选择目标乘车点。可以将排序得分最高的候选乘车点作为目标乘车点，也可以将排序得分相对较高的固定数值(例如3)个候选乘车点提供给目标乘客，由目标乘客根据个性化需求选择目标乘车点。通过结合目标乘客的初始位置、候选乘车点的车辆辅助信息和自动驾驶特征， 为目标乘客选择目标乘车点，能够提高目标乘车点与目标乘客的匹配度，从而进一步提高目标乘客的乘车效率和乘车成功率。
本公开的技术方案中，所涉及的乘客个人信息的获取，存储和应用等，均符合相关法律法规的规定，且不违背公序良俗。
在一种可选实施方式中，所述自动驾驶特征包括如下至少一项：自动驾驶成功率、路况复杂度或乘客反馈信息。
其中，自动驾驶成功率可以是指在候选乘车点处历史乘客与自动驾驶车辆的成功对接率，路况复杂度可以根据周边道路等级、行人数量、非机动车数量等确定，乘客反馈信息可以是乘客对候选乘车点处乘车难易程度的评价信息。
可以将经筛选的多个候选乘车点的自动驾驶成功率、路况复杂度、乘客反馈信息作为排序模型的输入，并获取排序模型输出的多个候选乘车点的得分；根据得分选择目标乘车点。本公开实施例对排序模型的网络结构不做限定，如可以采用逻辑回归模型、Pairwise(排序模型)或RankNet(排序网络)等。通过引入自动驾驶成功率、路况复杂度或乘客反馈信息对经筛选的候选乘车点进行排序，能够进一步提高目标乘车点与自动驾驶场景之间的匹配度，从而提高乘车成功率。
本公开实施例的技术方案，通过结合目标乘客的初始位置、候选乘车点的车辆辅助信息对候选乘车点进行筛选，并引入自动驾驶成功率、路况复杂度或乘客反馈信息对经筛选的候选乘车点进行排序，能够充分考虑自动驾驶乘车场景的特性，进一步提高乘车成功率。
图3a是根据本公开实施例提供的又一种基于自动驾驶的乘车方法的示意图。本实施例是在上述实施例的基础上提出的一种可选方案。参见图3a，本实施例提供的基于自动驾驶的乘车方法包括以下操作。
S310、获取兴趣点(Point of Interest，POI)的语义描述信息和坐标信息。
S320、将POI的坐标信息与路网中车道进行匹配，得到POI在车道上的映射点。
S330、根据映射点的坐标信息和车道信息，确定候选乘车点的坐标信息和车道信息，以及根据所述POI的语义描述信息确定候选乘车点的语义描述信息。
S340、根据候选乘车点的车辆辅助信息，从候选乘车点中为目标乘客选 择目标乘车点，其中，所述候选乘车点的车辆辅助信息包括候选乘车点的坐标信息和车道信息。
S350、控制自动驾驶车辆根据目标乘车点的车辆辅助信息向所述目标乘车点行驶。
其中，POI可以为沿街可视的POI，例如某某小区东门、地铁站、公交站等。通过根据沿街可视的POI挖掘候选乘车点，提高乘客的乘车便捷性。
可以根据POI的坐标信息，将POI与路网中道路的车道进行匹配，确定POI是否在车道上；若POI在车道上，则将POI本身作为映射点(参考图3b)；若POI不在车道上，则可以将车道中距POI最近的点作为映射点(参考图3c)。
还确定映射点是否属于禁止乘车区域，在映射点不属于禁止乘车区域的情况下，可以直接将映射点作为候选乘车点，将映射点的坐标信息、车道信息作为候选乘车点的坐标信息和车道信息，并且根据映射点的坐标信息和POI的坐标信息对POI的语义描述信息进行调整，得到映射点的语义描述信息(参考图3c)。可以根据映射点的坐标信息和POI的坐标信息确定映射点与POI的相对距离和方向，且根据相对距离、方向和POI的语义描述信息，得到候选乘车点的语义描述信息。参考图3c，POI的语义描述信息为某某商场东门，而候选乘车点的语义描述信息为某某商场东门往西30米。通过确定POI在车道上的映射点，且在映射点不属于禁止乘车区域的情况下，可以将映射点作为候选乘车点，并得到候选乘车点的坐标信息、车道信息和语义描述信息，便于自动驾驶车辆根据候选乘车点的坐标信息、车道信息准确定位候选乘车点，以及便于乘客根据语义描述信息准确定位候选乘车点，从而提高乘车成功率。
在一种可选实施方式中，S330可以包括：在所述映射点属于禁止乘车区域的情况下，对所述映射点的坐标信息和/或车道信息进行修正得到候选乘车点的坐标信息和/或车道信息，且根据所述候选乘车点的坐标信息和/或车道信息对POI的语义描述信息进行调整得到候选乘车点的语义描述信息。
在映射点属于禁止乘车区域的情况下，可以通过对所述映射点的坐标信息和/或车道信息进行修正得到映射点在可乘车区域中的修正点，将修正点作为候选乘车点，将修正点的坐标信息、车道信息作为候选乘车点的坐标信息、车道信息，并且根据候选乘车点的坐标信息、车道信息对POI的语义描述信息进行调整得到候选乘车点的语义描述信息。参考图3d，POI的语义描述信息为某路某某公交站，由于公交站为自动驾驶车辆的禁止乘车区域，候选乘车点的语义描述信息可以为某路某某公交站往北30米，候选乘车点的车道信息可以为某路第3车道。在映射点属于禁止乘车区域的情况下，可以确定映 射点在除禁止乘车区域之外的修正点，将修正点作为候选乘车点，不仅能够提高乘车成功率，还能够避免在候选乘车点上车过程中自动驾驶车辆违反交规，提高稳定性。
在一种可选实施方式中，从候选乘车点中为目标乘客选择目标乘车点之前，还包括：获取非自动驾驶场景中历史乘客的历史乘车点的坐标信息、语义描述信息和历史乘客在乘车前的移动轨迹；根据所述移动轨迹对所述历史乘车点的坐标信息进行修正，且根据修正结果确定候选乘车点的坐标信息和车道信息；根据候选乘车点的坐标信息，对所述历史乘车点的语义描述信息进行调整得到候选乘车点的语义描述信息。
在本公开实施例中，还可以采用非自动驾驶场景中的历史乘车点挖掘自动驾驶场景中的候选乘车点。由于非自动驾驶场景中的历史乘车点坐标通过历史乘客或司机的定位设备得到，而非通过高精度定位得到，定位误差在米或百米量级。通过根据历史乘客在乘车前的移动轨迹(例如步行轨迹)推测出历史乘客的实际乘车点坐标和实际乘车点坐标对应的车道，作为候选乘车点的坐标信息和车道信息，使候选乘车点的定位精度能够满足自动驾驶车辆的高精度定位要求，便于自动驾驶车辆准确定位候选乘车点。
在一种可选实施方式中，在所述从候选乘车点中为目标乘客选择目标乘车点之前，还包括：将自动驾驶乘车场景中历史乘客的实际乘车点作为所述候选乘车点，且得到所述候选乘车点的坐标信息、车道信息和语义描述信息。
在本公开实施例中，由于自动驾驶车辆设置有高精定位设备，在历史乘客乘坐自动驾驶车辆过程中，可以通过高精定位设备采集历史乘客的实际乘车点的坐标信息和车道信息，可以将实际乘车点作为候选乘车点；并且，还可以根据实际乘车点的坐标信息、车道信息与POI坐标之间的关系，确定实际乘车点的语义描述信息。通过将高精度定位设备采集的历史乘客的实际乘车点作为候选乘车点，便于自动驾驶车辆准确定位候选乘车点，能够提高乘车成功率。
本公开实施例的技术方案，通过根据POI信息、非自动驾驶场景中历史乘车点的坐标信息和历史乘客在乘车前的移动轨迹、自动驾驶乘车场景中历史乘客的实际乘车点挖掘自动驾驶乘车场景中的候选乘车点，能够得到高精度的候选乘车点的坐标信息和车道信息，还能够得到候选乘车点的语义描述信息，便于自动驾驶车辆和乘客准确定位候选乘车点，从而提高自动驾驶场景中的乘车成功率和乘车效率。
图4是根据本公开实施例提供的又一种基于自动驾驶的乘车方法的示意图。本实施例是在上述实施例的基础上提出的一种可选方案。参见图4，本实施例提供的基于自动驾驶的乘车方法包括以下操作。
S410、根据候选乘车点的车辆辅助信息，从候选乘车点中为目标乘客选择目标乘车点，其中，所述候选乘车点的车辆辅助信息包括候选乘车点的坐标信息和车道信息。
S420、控制自动驾驶车辆根据目标乘车点的车辆辅助信息向所述目标乘车点行驶。
S430、在自动驾驶车辆到达目标乘车点，且目标乘客未到达目标乘车点的情况下，控制自动驾驶车辆采集车辆环境图像，且向目标乘客发送车辆环境图像，用于辅助目标乘客定位自动驾驶车辆。
在乘客实际乘车过程中，在自动驾驶车辆到达目标乘车点时，可以检查目标乘客是否到达目标乘车点，可以通过检查目标乘客是否已乘车或者通过自动驾驶车辆的图像采集器采集车辆环境图像，并通过人脸识别技术确定目标乘客是否到达。在目标乘客未到达目标乘车点的情况下，可以向目标乘客持有的电子设备发送车辆环境图像，使目标乘客根据车辆环境图像确定自动驾驶车辆的实际位置，便于目标乘客准确、快速定位自动驾驶车辆。
在一种可选实施方式中，控制自动驾驶车辆根据目标乘车点的车辆辅助信息向所述目标乘车点行驶之后，还包括：在自动驾驶车辆到达目标乘车点，且目标乘客未到达目标乘车点的情况下，控制自动驾驶车辆与目标乘客进行交互，并根据交互信息生成候选指令；向目标乘客发送是否执行候选指令的问询信息；在目标乘客确认执行后，控制所述自动驾驶车辆执行候选指令，以调整自动驾驶车辆的实际位置信息。
在本公开实施例中，在自动驾驶车辆到达目标乘车点，且目标乘客未到达目标乘车点的情况下，自动驾驶车辆还可以与用户进行交互，如进行语音交互，视频通话交互等，根据交互信息确定自动驾驶车辆与目标乘客之间的相对位置信息如确定相对距离、相对方位，还根据相对位置信息生成对自动驾驶车辆的候选指令，在目标乘客对候选指令确认后，控制自动驾驶车辆执行候选指令，以调整自动驾驶车辆的实际位置信息。本公开实施例对候选指令不做限定，如候选指令可以为调整到马路对面、掉头等。
在乘车过程中，通过根据自动驾驶车辆与目标乘客的交互信息生成候选指令，并根据目标乘客对候选指令的确认信息控制自动驾驶车辆执行候选指令，例如适用于目标乘客发现自动驾驶车辆后控制自动驾驶车辆调整位置的 情况，能够解决目标乘车点不精确、目标乘客定位出行偏差等问题，能够提高目标乘客的乘车便捷度与乘车灵活性，进一步提高乘车成功率。
本公开实施例的技术方案，在自动驾驶车辆到达目标乘车点后，通过将车辆环境图像发送给目标乘客，或者通过根据目标乘客对候选指令的确认信息控制自动驾驶车辆调整自动驾驶车辆的实际位置信息，能够对近距离的自动驾驶车辆和目标乘客进行精确推荐，从而提高目标乘客到达自动驾驶车辆的成功率。
图5是根据本公开实施例提供的一种基于自动驾驶的乘车装置的示意图，本实施例可适用于乘坐自动驾驶车辆的情况，该装置配置于电子设备中，可实现本公开任意实施例所述的基于自动驾驶的乘车方法。参考图5，该基于自动驾驶的乘车装置500包括如下模块。
目标乘车点选择模块501，设置为根据候选乘车点的车辆辅助信息，从候选乘车点中为目标乘客选择目标乘车点，其中，所述候选乘车点的车辆辅助信息包括候选乘车点的坐标信息和车道信息；
车辆控制模块502，设置为控制自动驾驶车辆根据目标乘车点的车辆辅助信息向所述目标乘车点行驶。
在一种可选实施方式中，所述目标乘车点选择模块501包括：
目标乘车点筛选单元，设置为根据目标乘客的初始位置和所述候选乘车点的车辆辅助信息，对候选乘车点进行筛选；
目标乘车点排序单元，设置为根据候选乘车点的自动驾驶特征，对经筛选的候选乘车点进行排序，并根据排序结果为目标乘客选择目标乘车点。
在一种可选实施方式中，所述自动驾驶特征包括如下至少一项：自动驾驶成功率、路况复杂度或乘客反馈信息。
在一种可选实施方式中，该基于自动驾驶的乘车装置500还包括第一候选乘车点模块，所述第一候选乘车点模块包括：
POI信息获取单元，设置为获取兴趣点POI的语义描述信息和坐标信息；
POI匹配单元，设置为将POI的坐标信息与路网中车道进行匹配，得到POI在车道上的映射点；
第一候选乘车点单元，设置为根据映射点的坐标信息和车道信息，确定候选乘车点的坐标信息和车道信息，以及根据所述POI的语义描述信息确定候选乘车点的语义描述信息。
在一种可选实施方式中，所述第一候选乘车点单元是设置为：
在所述映射点属于禁止乘车区域的情况下，对所述映射点的坐标信息和/或车道信息进行修正得到候选乘车点的坐标信息和/或车道信息，且根据所述候选乘车点的坐标信息和/或车道信息对POI的语义描述信息进行调整得到候选乘车点的语义描述信息。
在一种可选实施方式中，该基于自动驾驶的乘车装置500还包括第二候选乘车点模块，所述第二候选乘车点模块包括：
历史乘客信息单元，设置为获取非自动驾驶场景中历史乘客的历史乘车点的坐标信息、语义描述信息和历史乘客在乘车前的移动轨迹；
坐标修正单元，设置为根据所述移动轨迹对所述历史乘车点的坐标信息进行修正，且根据修正结果确定候选乘车点的坐标信息和车道信息；
第二候选乘车点单元，设置为根据候选乘车点的坐标信息，对所述历史乘车点的语义描述信息进行调整得到候选乘车点的语义描述信息。
在一种可选实施方式中，该基于自动驾驶的乘车装置500还包括：
第三候选乘车点模块，设置为将自动驾驶乘车场景中历史乘客的实际乘车点作为所述候选乘车点，且得到所述候选乘车点的坐标信息、车道信息和语义描述信息。
在一种可选实施方式中，该基于自动驾驶的乘车装置500还包括：
环境图像发送模块，设置为在自动驾驶车辆到达目标乘车点，且目标乘客未到达目标乘车点的情况下，控制自动驾驶车辆采集车辆环境图像，且向目标乘客发送车辆环境图像，用于辅助目标乘客定位自动驾驶车辆。
在一种可选实施方式中，该基于自动驾驶的乘车装置500还包括交互模块，所述交互模块包括：
指令生成单元，设置为在自动驾驶车辆到达目标乘车点，且目标乘客未到达目标乘车点的情况下，控制自动驾驶车辆与目标乘客进行交互，并根据交互信息生成候选指令；
问询单元，设置为向目标乘客发送是否执行候选指令的问询信息；
指令执行单元，设置为在目标乘客确认执行后，控制所述自动驾驶车辆执行候选指令，以调整自动驾驶车辆的位置信息。
本实施例的技术方案，针对自动驾驶乘车场景，挖掘具有高精度坐标信息和车道信息的候选乘车点，候选乘车点还具有面向乘客的语义描述信息，能够提高自动驾驶场景中的乘车成功率和乘车效率；并且，在自动驾驶车辆 到达目标乘车点之后，还可以控制自动驾驶车辆与目标乘客交互，对自动驾驶车辆、目标乘客进行近距离的精准推荐，进一步提高乘车成功率和乘车效率。
根据本公开的实施例，本公开还提供了一种电子设备、一种可读存储介质和一种计算机程序产品。
图6示出了可以用来实施本公开的实施例的示例电子设备600的示意性框图。电子设备旨在表示多种形式的数字计算机，诸如，膝上型计算机、台式计算机、工作台、个人数字助理、服务器、刀片式服务器、大型计算机、和其它适合的计算机。电子设备还可以表示多种形式的移动装置，诸如，个人数字处理、蜂窝电话、智能电话、可穿戴设备和其它类似的计算装置。本文所示的部件、它们的连接和关系、以及它们的功能仅仅作为示例，并且不意在限制本文中描述的和/或者要求的本公开的实现。
如图6所示，设备600包括计算单元601，计算单元601可以根据存储在只读存储器(Read-Only Memory，ROM)602中的计算机程序或者从存储单元608加载到随机访问存储器(Random Access Memory，RAM)603中的计算机程序，来执行多种适当的动作和处理。在RAM 603中，还可存储设备600操作所需的多种程序和数据。计算单元601、ROM 602以及RAM 603通过总线604彼此相连。输入/输出(Input/Output，I/O)接口605也连接至总线604。
设备600中的多个部件连接至I/O接口605，包括：输入单元606，例如键盘、鼠标等；输出单元607，例如多种类型的显示器、扬声器等；存储单元608，例如磁盘、光盘等；以及通信单元609，例如网卡、调制解调器、无线通信收发机等。通信单元609允许设备600通过诸如因特网的计算机网络和/或多种电信网络与其他设备交换信息/数据。
计算单元601可以是多种具有处理和计算能力的通用和/或专用处理组件。计算单元601的一些示例包括但不限于中央处理单元(Central Processing Unit，CPU)、图形处理单元(Graphics Processing Unit，GPU)、多种专用的人工智能(Artificial Intelligence，AI)计算芯片、多种执行机器学习模型算法的计算单元、数字信息处理器(Digital Signal Processor，DSP)、以及任何适当的处理器、控制器、微控制器等。计算单元601执行上文所描述的多个方法和处理，例如基于自动驾驶的乘车方法。例如，在一些实施例中，基于自动驾驶的乘车方法可被实现为计算机软件程序，其被有形地包含于机器可读介质，例如存储单元608。在一些实施例中，计算机程序的部分或者 全部可以经由ROM 602和/或通信单元609而被载入和/或安装到设备600上。当计算机程序加载到RAM 603并由计算单元601执行时，可以执行上文描述的基于自动驾驶的乘车方法的一个或多个步骤。备选地，在其他实施例中，计算单元601可以通过其他任何适当的方式(例如，借助于固件)而被配置为执行基于自动驾驶的乘车方法。
本文中以上描述的系统和技术的多种实施方式可以在数字电子电路系统、集成电路系统、场可编程门阵列(Field Programmable Gate Array，FPGA)、专用集成电路(Application Specific Integrated Circuit，ASIC)、专用标准产品(Application Specific Standard Parts，ASSP)、芯片上系统的系统(System on Chip，SOC)、负载可编程逻辑设备(Complex Programmable Logic Device，CPLD)、计算机硬件、固件、软件、和/或它们的组合中实现。这些多种实施方式可以包括：实施在一个或者多个计算机程序中，该一个或者多个计算机程序可在包括至少一个可编程处理器的可编程系统上执行和/或解释，该可编程处理器可以是专用或者通用可编程处理器，可以从存储系统、至少一个输入装置、和至少一个输出装置接收数据和指令，并且将数据和指令传输至该存储系统、该至少一个输入装置、和该至少一个输出装置。
用于实施本公开的方法的程序代码可以采用一个或多个编程语言的任何组合来编写。这些程序代码可以提供给通用计算机、专用计算机或其他可编程数据处理装置的处理器或控制器，使得程序代码当由处理器或控制器执行时使流程图和/或框图中所规定的功能/操作被实施。程序代码可以完全在机器上执行、部分地在机器上执行，作为独立软件包部分地在机器上执行且部分地在远程机器上执行或完全在远程机器或服务器上执行。
在本公开的上下文中，机器可读介质可以是有形的介质，其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备，或者上述内容的任何合适组合。机器可读存储介质包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、RAM、ROM、可擦除可编程只读存储器(Erasable Programmable Read-Only Memory，EPROM)、快闪存储器、光纤、便捷式紧凑盘只读存储器(Compact Disc Read Only Memory，CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。存储介质可以是非暂态(non-transitory)存储介质。
为了提供与用户的交互，可以在计算机上实施此处描述的系统和技术，该计算机具有：用于向用户显示信息的显示装置(例如，阴极射线管(Cathode  Ray Tube，CRT)或者液晶显示器(Liquid Crystal Display，LCD)监视器)；以及键盘和指向装置(例如，鼠标或者轨迹球)，用户可以通过该键盘和该指向装置来将输入提供给计算机。其它种类的装置还可以用于提供与用户的交互；例如，提供给用户的反馈可以是任何形式的传感反馈(例如，视觉反馈、听觉反馈、或者触觉反馈)；并且可以用任何形式(包括声输入、语音输入或者、触觉输入)来接收来自用户的输入。
可以将此处描述的系统和技术实施在包括后台部件的计算系统(例如，作为数据服务器)、或者包括中间件部件的计算系统(例如，应用服务器)、或者包括前端部件的计算系统(例如，具有图形用户界面或者网络浏览器的用户计算机，用户可以通过该图形用户界面或者该网络浏览器来与此处描述的系统和技术的实施方式交互)、或者包括这种后台部件、中间件部件、或者前端部件的任何组合的计算系统中。可以通过任何形式或者介质的数字数据通信(例如，通信网络)来将系统的部件相互连接。通信网络的示例包括：局域网(Local Area Network，LAN)、广域网(Wide Area Network，WAN)、区块链网络和互联网。
计算机系统可以包括客户端和服务器。客户端和服务器一般远离彼此并且通常通过通信网络进行交互。通过在相应的计算机上执行并且彼此具有客户端-服务器关系的计算机程序来产生客户端和服务器的关系。服务器可以是云服务器，又称为云计算服务器或云主机，是云计算服务体系中的一项主机产品，以解决了传统物理主机与虚拟专用服务器(Virtual Private Server，VPS)服务中，存在的管理难度大，业务扩展性弱的缺陷。
可以使用上面所示的多种形式的流程，重新排序、增加或删除步骤。例如，本发公开中记载的多个步骤可以并行地执行也可以顺序地执行也可以不同的次序执行，只要能够实现本公开公开的技术方案所期望的结果，本文在此不进行限制。

Claims (21)

  1. 一种基于自动驾驶的乘车方法，包括：
    根据候选乘车点的车辆辅助信息，从所述候选乘车点中为目标乘客选择目标乘车点，其中，所述候选乘车点的车辆辅助信息包括所述候选乘车点的坐标信息和车道信息；
    控制自动驾驶车辆根据所述目标乘车点的车辆辅助信息向所述目标乘车点行驶。
  2. 根据权利要求1所述的方法，其中，所述根据候选乘车点的车辆辅助信息，从所述候选乘车点中为目标乘客选择目标乘车点，包括：
    根据所述目标乘客的初始位置和所述候选乘车点的车辆辅助信息，对所述候选乘车点进行筛选；
    根据所述候选乘车点的自动驾驶特征，对经筛选的候选乘车点进行排序，并根据排序结果为所述目标乘客选择所述目标乘车点。
  3. 根据权利要求2所述的方法，其中，所述自动驾驶特征包括如下至少一项：自动驾驶成功率、路况复杂度或乘客反馈信息。
  4. 根据权利要求1-3中任一项所述的方法，在所述从所述候选乘车点中为目标乘客选择目标乘车点之前，还包括：
    获取兴趣点POI的语义描述信息和坐标信息；
    将所述POI的坐标信息与路网中车道进行匹配，得到所述POI在车道上的映射点；
    根据所述映射点的坐标信息和车道信息，确定所述候选乘车点的坐标信息和车道信息，以及根据所述POI的语义描述信息确定所述候选乘车点的语义描述信息。
  5. 根据权利要求4所述的方法，其中，所述根据所述映射点的坐标信息和车道信息，确定所述候选乘车点的坐标信息和车道信息，以及根据所述POI的语义描述信息确定所述候选乘车点的语义描述信息，包括：
    在所述映射点属于禁止乘车区域的情况下，对所述映射点的坐标信息或车道信息中至少之一进行修正得到所述候选乘车点的以下至少之一：坐标信息、或车道信息，且根据所述候选乘车点的以下至少之一对所述POI的语义描述信息进行调整得到所述候选乘车点的语义描述信息：坐标信息、或车道信息。
  6. 根据权利要求1-3中任一项所述的方法，在所述从所述候选乘车点中为目标乘客选择目标乘车点之前，还包括：
    获取非自动驾驶场景中历史乘客的历史乘车点的坐标信息、语义描述信息和历史乘客在乘车前的移动轨迹；
    根据所述移动轨迹对所述历史乘车点的坐标信息进行修正，且根据修正结果确定所述候选乘车点的坐标信息和车道信息；
    根据所述候选乘车点的坐标信息，对所述历史乘车点的语义描述信息进行调整得到所述候选乘车点的语义描述信息。
  7. 根据权利要求1-3中任一项所述的方法，在所述从所述候选乘车点中为目标乘客选择目标乘车点之前，还包括：
    将自动驾驶乘车场景中历史乘客的实际乘车点作为所述候选乘车点，且得到所述候选乘车点的坐标信息、车道信息和语义描述信息。
  8. 根据权利要求1所述的方法，在所述控制自动驾驶车辆根据所述目标乘车点的车辆辅助信息向所述目标乘车点行驶之后，还包括：
    在所述自动驾驶车辆到达所述目标乘车点，且所述目标乘客未到达所述目标乘车点的情况下，控制所述自动驾驶车辆采集车辆环境图像，且向所述目标乘客发送所述车辆环境图像，用于辅助所述目标乘客定位所述自动驾驶车辆。
  9. 根据权利要求1所述的方法，在所述控制自动驾驶车辆根据所述目标乘车点的车辆辅助信息向所述目标乘车点行驶之后，还包括：
    在所述自动驾驶车辆到达所述目标乘车点，且所述目标乘客未到达所述目标乘车点的情况下，控制所述自动驾驶车辆与所述目标乘客进行交互，并根据交互信息生成候选指令；
    向所述目标乘客发送是否执行所述候选指令的问询信息；
    在所述目标乘客确认执行后，控制所述自动驾驶车辆执行所述候选指令，以调整所述自动驾驶车辆的位置信息。
  10. 一种基于自动驾驶的乘车装置，包括：
    目标乘车点选择模块，设置为根据候选乘车点的车辆辅助信息，从所述候选乘车点中为目标乘客选择目标乘车点，其中，所述候选乘车点的车辆辅助信息包括所述候选乘车点的坐标信息和车道信息；
    车辆控制模块，设置为控制自动驾驶车辆根据所述目标乘车点的车辆辅助信息向所述目标乘车点行驶。
  11. 根据权利要求10所述的装置，其中，所述目标乘车点选择模块包括：
    目标乘车点筛选单元，设置为根据所述目标乘客的初始位置和所述候选乘 车点的车辆辅助信息，对所述候选乘车点进行筛选；
    目标乘车点排序单元，设置为根据所述候选乘车点的自动驾驶特征，对经筛选的候选乘车点进行排序，并根据排序结果为所述目标乘客选择所述目标乘车点。
  12. 根据权利要求11所述的装置，其中，所述自动驾驶特征包括如下至少一项：自动驾驶成功率、路况复杂度或乘客反馈信息。
  13. 根据权利要求10-12中任一项所述的装置，还包括第一候选乘车点模块，所述第一候选乘车点模块包括：
    兴趣点POI信息获取单元，设置为获取POI的语义描述信息和坐标信息；
    POI匹配单元，设置为将所述POI的坐标信息与路网中车道进行匹配，得到所述POI在车道上的映射点；
    第一候选乘车点单元，设置为根据所述映射点的坐标信息和车道信息，确定所述候选乘车点的坐标信息和车道信息，以及根据所述POI的语义描述信息确定所述候选乘车点的语义描述信息。
  14. 根据权利要求13所述的装置，其中，所述第一候选乘车点单元是设置为：
    在所述映射点属于禁止乘车区域的情况下，对所述映射点的坐标信息或车道信息中至少之一进行修正得到所述候选乘车点的以下至少之一：坐标信息、或车道信息，且根据所述候选乘车点的以下至少之一对所述POI的语义描述信息进行调整得到所述候选乘车点的语义描述信息：坐标信息、或车道信息。
  15. 根据权利要求10-12中任一项所述的装置，还包括第二候选乘车点模块，所述第二候选乘车点模块包括：
    历史乘客信息单元，设置为获取非自动驾驶场景中历史乘客的历史乘车点的坐标信息、语义描述信息和历史乘客在乘车前的移动轨迹；
    坐标修正单元，设置为根据所述移动轨迹对所述历史乘车点的坐标信息进行修正，且根据修正结果确定所述候选乘车点的坐标信息和车道信息；
    第二候选乘车点单元，设置为根据所述候选乘车点的坐标信息，对所述历史乘车点的语义描述信息进行调整得到所述候选乘车点的语义描述信息。
  16. 根据权利要求10-12中任一项所述的装置，还包括：
    第三候选乘车点模块，设置为将自动驾驶乘车场景中历史乘客的实际乘车点作为所述候选乘车点，且得到所述候选乘车点的坐标信息、车道信息和语义描述信息。
  17. 根据权利要求10所述的装置，还包括：
    环境图像发送模块，设置为在所述自动驾驶车辆到达所述目标乘车点，且所述目标乘客未到达所述目标乘车点的情况下，控制所述自动驾驶车辆采集车辆环境图像，且向所述目标乘客发送所述车辆环境图像，用于辅助所述目标乘客定位所述自动驾驶车辆。
  18. 根据权利要求10所述的装置，还包括交互模块，所述交互模块包括：
    指令生成单元，设置为在所述自动驾驶车辆到达所述目标乘车点，且所述目标乘客未到达所述目标乘车点的情况下，控制所述自动驾驶车辆与所述目标乘客进行交互，并根据交互信息生成候选指令；
    问询单元，设置为向所述目标乘客发送是否执行所述候选指令的问询信息；
    指令执行单元，设置为在所述目标乘客确认执行后，控制所述自动驾驶车辆执行所述候选指令，以调整所述自动驾驶车辆的位置信息。
  19. 一种电子设备，包括：
    至少一个处理器；以及
    与所述至少一个处理器通信连接的存储器；其中，
    所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行权利要求1-9中任一项所述的基于自动驾驶的乘车方法。
  20. 一种存储有计算机指令的非瞬时计算机可读存储介质，其中，所述计算机指令用于使计算机执行权利要求1-9中任一项所述的基于自动驾驶的乘车方法。
  21. 一种计算机程序产品，包括计算机程序，所述计算机程序在被处理器执行时实现根据权利要求1-9中任一项所述的基于自动驾驶的乘车方法。
PCT/CN2022/075164 2021-06-09 2022-01-30 基于自动驾驶的乘车方法、装置、设备和存储介质 WO2022257488A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
KR1020227029593A KR20220166784A (ko) 2021-06-09 2022-01-30 자율주행에 기반한 승차 방법, 장치, 설비 및 저장매체
JP2022551665A JP7478831B2 (ja) 2021-06-09 2022-01-30 自動運転に基づく乗車方法、装置、機器および記憶媒体
US17/796,074 US20240166243A1 (en) 2021-06-09 2022-01-30 Automatic driving-based riding method, apparatus and device, and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110643898.4 2021-06-09
CN202110643898.4A CN113276888B (zh) 2021-06-09 2021-06-09 基于自动驾驶的乘车方法、装置、设备和存储介质

Publications (1)

Publication Number Publication Date
WO2022257488A1 true WO2022257488A1 (zh) 2022-12-15

Family

ID=77283992

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/075164 WO2022257488A1 (zh) 2021-06-09 2022-01-30 基于自动驾驶的乘车方法、装置、设备和存储介质

Country Status (5)

Country Link
US (1) US20240166243A1 (zh)
JP (1) JP7478831B2 (zh)
KR (1) KR20220166784A (zh)
CN (1) CN113276888B (zh)
WO (1) WO2022257488A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113276888B (zh) * 2021-06-09 2022-10-21 北京百度网讯科技有限公司 基于自动驾驶的乘车方法、装置、设备和存储介质

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150219464A1 (en) * 2014-02-04 2015-08-06 Here Global B.V. Method and apparatus for providing passenger embarkation points for points of interests
CN105677793A (zh) * 2015-12-31 2016-06-15 百度在线网络技术（北京）有限公司 地点数据库的建立和候选乘车地点的推荐方法及装置
CN109445434A (zh) * 2018-11-16 2019-03-08 广州汽车集团股份有限公司 无人驾驶汽车的控制方法、装置、设备和存储介质
WO2020201802A1 (ja) * 2019-04-03 2020-10-08 日産自動車株式会社 配車サービス乗車地決定方法及び配車サービス乗車地決定システム
CN112686461A (zh) * 2021-01-06 2021-04-20 南京领行科技股份有限公司 一种乘车信息处理方法、装置、计算机设备及存储介质
CN113276888A (zh) * 2021-06-09 2021-08-20 北京百度网讯科技有限公司 基于自动驾驶的乘车方法、装置、设备和存储介质

Family Cites Families (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5085970B2 (ja) * 2007-04-23 2012-11-28 パイオニア株式会社 情報処理装置、情報処理方法、情報処理プログラムおよびコンピュータに読み取り可能な記録媒体
CN106843219B (zh) * 2017-02-20 2020-07-10 北京百度网讯科技有限公司 无人驾驶车辆选择接泊点的方法、装置、设备及存储介质
JP6724832B2 (ja) 2017-03-17 2020-07-15 株式会社デンソー 走行制御システム、走行制御プログラム及び自動走行車両
BR112020015141A2 (pt) 2018-01-25 2021-01-05 Nissan Motor Co., Ltd. Método de gerenciamento de veículo e aparelho de gerenciamento de veículo
JP7036690B2 (ja) 2018-08-20 2022-03-15 ヤフー株式会社 情報処理装置、情報処理方法および情報処理プログラム
CN109115237B (zh) * 2018-08-27 2021-05-07 阿里巴巴（中国）有限公司 一种乘车位置推荐方法及服务器
JP7192569B2 (ja) 2019-02-26 2022-12-20 トヨタ自動車株式会社 運行支援装置及び車両
JP7172777B2 (ja) 2019-03-19 2022-11-16 トヨタ自動車株式会社 情報処理システム、サーバ、及びプログラム
CN111859180A (zh) * 2020-05-21 2020-10-30 北京嘀嘀无限科技发展有限公司 一种上车点推荐方法和系统

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150219464A1 (en) * 2014-02-04 2015-08-06 Here Global B.V. Method and apparatus for providing passenger embarkation points for points of interests
CN105677793A (zh) * 2015-12-31 2016-06-15 百度在线网络技术（北京）有限公司 地点数据库的建立和候选乘车地点的推荐方法及装置
CN109445434A (zh) * 2018-11-16 2019-03-08 广州汽车集团股份有限公司 无人驾驶汽车的控制方法、装置、设备和存储介质
WO2020201802A1 (ja) * 2019-04-03 2020-10-08 日産自動車株式会社 配車サービス乗車地決定方法及び配車サービス乗車地決定システム
CN112686461A (zh) * 2021-01-06 2021-04-20 南京领行科技股份有限公司 一种乘车信息处理方法、装置、计算机设备及存储介质
CN113276888A (zh) * 2021-06-09 2021-08-20 北京百度网讯科技有限公司 基于自动驾驶的乘车方法、装置、设备和存储介质

Also Published As

Publication number Publication date
KR20220166784A (ko) 2022-12-19
JP2023534336A (ja) 2023-08-09
JP7478831B2 (ja) 2024-05-07
CN113276888A (zh) 2021-08-20
US20240166243A1 (en) 2024-05-23
CN113276888B (zh) 2022-10-21

Similar Documents

Publication Publication Date Title
CN110377025A (zh) 用于自动驾驶车辆的传感器聚合框架
US11222530B2 (en) Driving intention determining method and apparatus
EP3933345A2 (en) Road event detection method, apparatus, device and storage medium
CN110386142A (zh) 用于自动驾驶车辆的俯仰角校准方法
CN109725635A (zh) 自动驾驶车辆
CN111985662B (zh) 网络约车方法、装置、电子设备和存储介质
CN111694973A (zh) 自动驾驶场景的模型训练方法、装置、电子设备
CN110617826B (zh) 车辆导航中高架桥区识别方法、装置、设备和存储介质
EP4068811A1 (en) Method and apparatus for pushing information, device and storage medium
CN111563450A (zh) 数据处理方法、装置、设备及存储介质
JP7258938B2 (ja) 交差点仮想レーンをマークする方法、交差点仮想レーンをマークする装置、電子機器、コンピュータ可読記憶媒体及びコンピュータプログラム
WO2022257488A1 (zh) 基于自动驾驶的乘车方法、装置、设备和存储介质
US20220204000A1 (en) Method for determining automatic driving feature, apparatus, device, medium and program product
CN108286973B (zh) 一种行驶数据校验方法及装置、及混合导航系统
WO2024037487A1 (zh) 应用于车辆中的路径修正方法、装置及电子设备
WO2024093641A1 (zh) 多模态融合的高精地图要素识别方法、装置、设备及介质
WO2021104325A1 (zh) 一种偏航识别的方法和系统
CN113139139A (zh) 用于确定上车点的方法、装置、电子设备和介质
US11657268B1 (en) Training neural networks to assign scores
CN113011298A (zh) 截断物体样本生成、目标检测方法、路侧设备和云控平台
US20220165155A1 (en) Parking Guidance Method Based on Temporal and Spatial Features and Its Device, Equipment, and Storage Medium
US20230194268A1 (en) Longitudinal-limited lane marking localizer
CN114659537A (zh) 导航起点道路确定方法、装置、设备及存储介质
CN112785072B (zh) 路线规划和模型训练方法、装置、设备及存储介质
CN114581869A (zh) 确定目标对象位置的方法、装置、电子设备和存储介质

Legal Events

Date Code Title Description
WWE Wipo information: entry into national phase

Ref document number: 17796074

Country of ref document: US

ENP Entry into the national phase

Ref document number: 2022551665

Country of ref document: JP

Kind code of ref document: A

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

Ref document number: 22819095

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE