WO2021168660A1 - 特殊路况的识别方法、装置、电子设备和存储介质 - Google Patents

特殊路况的识别方法、装置、电子设备和存储介质 Download PDF

Info

Publication number
WO2021168660A1
WO2021168660A1 PCT/CN2020/076654 CN2020076654W WO2021168660A1 WO 2021168660 A1 WO2021168660 A1 WO 2021168660A1 CN 2020076654 W CN2020076654 W CN 2020076654W WO 2021168660 A1 WO2021168660 A1 WO 2021168660A1
Authority
WO
WIPO (PCT)
Prior art keywords
road
vehicle
special
area
road area
Prior art date
Application number
PCT/CN2020/076654
Other languages
English (en)
French (fr)
Inventor
马鹏飞
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP20922073.0A priority Critical patent/EP4099293B1/en
Priority to PCT/CN2020/076654 priority patent/WO2021168660A1/zh
Priority to KR1020227031702A priority patent/KR20220140813A/ko
Priority to JP2022550856A priority patent/JP7462778B2/ja
Priority to CN202080004502.5A priority patent/CN112585656B/zh
Priority to EP24171746.1A priority patent/EP4425463A2/en
Priority to CN202210659439.XA priority patent/CN115188183A/zh
Publication of WO2021168660A1 publication Critical patent/WO2021168660A1/zh
Priority to US17/892,449 priority patent/US20220397406A1/en

Links

Images

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • G01C21/3453Special cost functions, i.e. other than distance or default speed limit of road segments
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/01Detecting movement of traffic to be counted or controlled
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W40/00Estimation 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
    • B60W40/02Estimation 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
    • B60W40/06Road conditions
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W40/00Estimation 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
    • B60W40/10Estimation 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 vehicle motion
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W60/00Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001Planning or execution of driving tasks
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W60/00Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001Planning or execution of driving tasks
    • B60W60/0015Planning or execution of driving tasks specially adapted for safety
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/26Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
    • G01C21/34Route searching; Route guidance
    • G01C21/36Input/output arrangements for on-board computers
    • G01C21/3626Details of the output of route guidance instructions
    • G01C21/3647Guidance involving output of stored or live camera images or video streams
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804Creation or updating of map data
    • G01C21/3807Creation or updating of map data characterised by the type of data
    • G01C21/3815Road data
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/21Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N20/00Machine learning
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06QINFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00Administration; Management
    • G06Q10/04Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G06Q10/047Optimisation of routes or paths, e.g. travelling salesman problem
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/70Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/77Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
    • G06V10/774Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/50Context or environment of the image
    • G06V20/56Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/588Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/01Detecting movement of traffic to be counted or controlled
    • G08G1/0104Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125Traffic data processing
    • G08G1/0129Traffic data processing for creating historical data or processing based on historical data
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/01Detecting movement of traffic to be counted or controlled
    • G08G1/0104Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/01Detecting movement of traffic to be counted or controlled
    • G08G1/0104Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0137Measuring and analyzing of parameters relative to traffic conditions for specific applications
    • G08G1/0141Measuring and analyzing of parameters relative to traffic conditions for specific applications for traffic information dissemination
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/09Arrangements for giving variable traffic instructions
    • G08G1/0962Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0967Systems involving transmission of highway information, e.g. weather, speed limits
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/09Arrangements for giving variable traffic instructions
    • G08G1/0962Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0967Systems involving transmission of highway information, e.g. weather, speed limits
    • G08G1/096708Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control
    • G08G1/096725Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control where the received information generates an automatic action on the vehicle control
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/09Arrangements for giving variable traffic instructions
    • G08G1/0962Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0967Systems involving transmission of highway information, e.g. weather, speed limits
    • G08G1/096766Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission
    • G08G1/096775Systems involving transmission of highway information, e.g. weather, speed limits where the system is characterised by the origin of the information transmission where the origin of the information is a central station
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/09Arrangements for giving variable traffic instructions
    • G08G1/0962Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0968Systems involving transmission of navigation instructions to the vehicle
    • G08G1/096833Systems involving transmission of navigation instructions to the vehicle where different aspects are considered when computing the route
    • G08G1/096844Systems involving transmission of navigation instructions to the vehicle where different aspects are considered when computing the route where the complete route is dynamically recomputed based on new data
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/09Arrangements for giving variable traffic instructions
    • G08G1/0962Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0968Systems involving transmission of navigation instructions to the vehicle
    • G08G1/0969Systems involving transmission of navigation instructions to the vehicle having a display in the form of a map
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W2556/00Input parameters relating to data
    • B60W2556/10Historical data
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60WCONJOINT 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
    • B60W2556/00Input parameters relating to data
    • B60W2556/40High definition maps
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01CMEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/38Electronic maps specially adapted for navigation; Updating thereof
    • G01C21/3804Creation or updating of map data
    • G01C21/3807Creation or updating of map data characterised by the type of data
    • G01C21/3815Road data
    • G01C21/3822Road feature data, e.g. slope data
    • GPHYSICS
    • G07CHECKING-DEVICES
    • G07CTIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C5/00Registering or indicating the working of vehicles
    • G07C5/008Registering or indicating the working of vehicles communicating information to a remotely located station
    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/09Arrangements for giving variable traffic instructions
    • G08G1/0962Arrangements for giving variable traffic instructions having an indicator mounted inside the vehicle, e.g. giving voice messages
    • G08G1/0967Systems involving transmission of highway information, e.g. weather, speed limits
    • G08G1/096708Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control
    • G08G1/096716Systems involving transmission of highway information, e.g. weather, speed limits where the received information might be used to generate an automatic action on the vehicle control where the received information does not generate an automatic action on the vehicle control

Definitions

  • the embodiments of the present application relate to the Internet of Vehicles technology, and in particular, to a method, device, electronic device, and storage medium for identifying special road conditions.
  • the vehicle can collect images around the vehicle during driving, compare and recognize the collected images according to preset images of special road conditions, and remind the driver when it recognizes that the image contains special road conditions, or According to the special road conditions, the corresponding driving instruction is sent to the autonomous vehicle. If there is a pit in the front, the driving instruction can control the vehicle to slow down, turn right to the right lane, and so on.
  • the method in the prior art has the problem of low real-time performance. For example, when the image of the special road condition is recognized, the vehicle may have driven through the special road condition at high speed, and the special road condition cannot be recognized in time.
  • the embodiments of the present application provide a method, device, electronic device, and storage medium for identifying special road conditions, which can obtain areas of special road conditions in advance based on map data at the current moment, with high real-time performance.
  • a method for identifying special road conditions is provided.
  • the method is applied to a terminal device and can also be applied to a chip in the terminal device.
  • the method is described below by taking the application to a terminal device as an example.
  • the terminal device obtains map data at the current moment from a server, and the map data includes: the first road area at the current moment, and the first road area Is the road area where the special road condition is located, the first road area is obtained from the road condition model and the vehicle parameters in the preset time period before the current moment, and the road condition model is used to characterize the characteristics and special characteristics of the vehicle parameters.
  • the road condition model can identify whether there are special road conditions in a certain road section area based on the vehicle parameters of a certain road section area within a period of time; according to the planned route of the vehicle, judge whether there is a second road area in the planned route of the vehicle , The second road area is a road area in the first road area.
  • the terminal device may periodically report vehicle parameters to the server, and the vehicle parameters include dynamic parameters and static parameters of the vehicle.
  • the dynamic parameters of the vehicle include the position of the vehicle, the image or video taken by the vehicle, and the driving data of the vehicle.
  • the driving data of the vehicle can be the speed, acceleration, and driving actions such as steering and braking of the vehicle.
  • the static parameters of the vehicle are attribute data of the vehicle.
  • the attribute data of the vehicle may include data such as the weight, length, width, and height, and shock absorption of the vehicle. It is worth noting that when the vehicle reports the vehicle parameters for the first time, the dynamic parameters and static parameters of the vehicle are reported, and the dynamic parameters are reported when the vehicle parameters are subsequently reported.
  • the terminal device in the embodiment of the present application can obtain the map data at the current moment from the server in real time.
  • the map data is different from the existing map data in that the map data at the current moment includes the first road in a special road condition.
  • Area, and the first road area is obtained by the server according to the reported vehicle parameters and the above-mentioned road condition model, and is marked on the map.
  • the reported vehicle parameters are massive data reported by multiple vehicles in real time
  • the accuracy and real-time performance of the first road area obtained can be improved, and the terminal device can obtain the latest road information representing special road conditions in real time through the server. Information about a road area.
  • the terminal device can perform the driving application of the vehicle according to the map data at the current moment.
  • the vehicle is an autonomous driving vehicle, and there is a second road area in the planned route of the vehicle. Since the self-driving vehicle is not driven by the user, in the embodiment of the present application, a driving instruction (driving decision) may be generated to control the driving behavior of the vehicle. Among them, when the vehicle travels to the second road area, the vehicle is controlled to travel according to the driving instruction. Or, when the vehicle travels to a preset distance from the second road area, the vehicle may be controlled to travel according to the driving instruction, thereby effectively guiding the driving action decision.
  • driving decision driving decision
  • the driving instruction may be generated according to the map data at the current moment.
  • the map data further includes: description information of a special road condition of the first road area, and the description information is used to describe a scene type of the special road condition.
  • the driving instruction may be generated according to the description information of the special road condition of the second road area.
  • the driving behavior indicated by the characteristics of the historical vehicle parameters obtained from the target road condition model may be used as the driving instruction, and the target road condition model is a model for determining that the second road area is a special road condition.
  • Another scenario is: the vehicle is a non-autonomous driving vehicle, and there is a second road area in the planned route of the vehicle.
  • reminding information can be generated in the embodiment of this application to remind the user that there is a special road condition in the second road area, so that when the vehicle is about to drive to the second road area, push The reminding information further serves the purpose of reminding special road conditions in advance.
  • the driving instruction may be generated according to the map data at the current moment.
  • the map data at the current moment further includes: description information and/or target image of the special road condition of the first road area, the description information is used to describe the scene type of the special road condition, and the information of the first road area
  • the target image is: the vehicle parameter includes an image of the special road condition of the first road area.
  • description information and/or target images of special road conditions in the second road area may be used as the reminder information.
  • the description information of the special road condition of the second road area is played, and/or the target image of the special road condition of the second road area is displayed.
  • the terminal device may send a route planning request to the server, so that the server obtains the planned route, and then sends the planned route to the terminal device.
  • the server can avoid planning routes that include special road conditions when designing and planning routes, and can prevent vehicles from driving to special road conditions that require a lot of time to pass, thereby improving traffic efficiency and user experience.
  • the map of the terminal device displays the identification of the special road conditions of each of the first road areas, and receives the user's selection instruction for the identification of the special road conditions of any first road area, and displays the user's selection Descriptive information of special road conditions in the first road area.
  • the user can view the information of any special road condition in the map, so that the user can actively choose the driving route, which improves the user experience.
  • a method for identifying special road conditions is provided.
  • the method is applied to a server.
  • the method includes: the server obtains the first road at the current time according to the road condition model and vehicle parameters in a preset time period before the current time. Area, and mark the first road area on the map data or remove the invalid first road area to obtain the map data at the current moment.
  • the first region is a specific road traffic in which the road area, the traffic model is used to characterize a correspondence relationship vehicle parameters and special features of the road.
  • the server can periodically update the map data according to the reported vehicle parameters to ensure the real-time performance of the first road area in the map, so that the terminal device can obtain the latest map data in real time to achieve Pre-identification and reminding of special road conditions.
  • the vehicle parameters of at least one vehicle received within the preset time period may be preprocessed to determine the initial road area, and then the initial road area is determined.
  • the vehicle parameters corresponding to the road area are used as the vehicle parameters in the preset time period before the current time.
  • the initial road area may be determined by the area where the location in the vehicle parameter does not match the feature of the road at the location of the vehicle in the map data.
  • the vehicle parameter that does not match the characteristics of the road at the location of the vehicle in the map data is used as the vehicle parameter in the preset time period before the current time.
  • the road condition model in the embodiment of the present application is obtained using multiple historical vehicle parameters as training parameters.
  • the historical vehicle parameter is a vehicle parameter from at least one vehicle received before the preset time period.
  • the multiple historical vehicle parameters may be divided into N training data sets in this embodiment of the application, and each training data set is used as training data for training a road condition model to obtain
  • the characteristics of the vehicle parameters in each training data set are the same, and N is an integer greater than 1.
  • the vehicle parameters in the preset time period before the current moment may be input to the at least one road condition model to obtain the first road area.
  • the characteristic type of the first road area of the special road condition can be obtained, but the special road condition of the first road area cannot be determined.
  • Scene type In a possible design, the image or video shot by the vehicle in the reported vehicle parameters can be combined to determine the scene type of the special road condition in the first road area.
  • the target image of the first road area may be acquired, and the target image of the first road area is: the vehicle parameters include the image of the special road condition of the first road area, and the target image is the target image of the first road area.
  • the description information of the special road condition of the first road area may be generated according to the target image of the first road area, and the description information is used to describe the scene type of the special road condition.
  • the method of generating the description information of the special road conditions of the first road area may be: an identification model may be pre-stored in the server in the embodiment of the present application, and the identification model is used to characterize the characteristics of the image and the scene type of the special road condition.
  • the corresponding relationship is that the image is input into the recognition model, and the recognition model can recognize whether the image is an image containing pixel blocks of special road conditions, so as to determine the scene type of the special road conditions. Further, in the embodiment of the present application, description information and/or target images of special road conditions of the first road area may be added to the map data.
  • the duration of the special road condition in the first road area is determined according to the scene type of the special road condition characterized by the description information of the special road condition in the first road area;
  • the special road condition duration of the first road area is added to the map data.
  • the embodiment of the application can determine the target image containing the special road condition according to the image or video in the vehicle parameters to generate the description information of the special road condition, and it can also determine according to the scene type of the special road condition The duration of special road conditions, and then add this information to the map data, so that the terminal device can generate driving decisions, reminder information, or plan a preset route for the vehicle after obtaining the map data at the current moment.
  • the server when the terminal device requests the server to obtain the planned route of the vehicle, the server can receive the route planning request from the terminal device, according to the starting and ending points and the special characteristics of the first road area.
  • the duration of the road condition and the scene type of the special road condition in the first road area obtain a planned route, and the route planning request includes the starting and ending points; and the planned route is pushed to the terminal device.
  • a device for identifying special road conditions including:
  • the processing module is configured to obtain map data at the current moment, where the map data includes: the first road area at the current moment, and according to the planned route of the vehicle, it is judged whether there is a second road area in the planned route of the vehicle,
  • the second road area is a road area in the first road area
  • the first road area is a road area where a special road condition is located
  • the first road area is determined by a road condition model and a road area before the current time.
  • the vehicle parameters in a preset time period are obtained, and the road condition model is used to characterize the correspondence between the characteristics of the vehicle parameters and the special road conditions.
  • the processing module is further configured to generate a driving instruction if the second road area exists in the planned route of the vehicle, and when the vehicle travels to the destination In the second road area, the driving of the vehicle is controlled according to the driving instruction, and the driving instruction is used to instruct the driving behavior of the vehicle.
  • the map data further includes: description information of a special road condition of the first road area, and the description information is used to describe a scene type of the special road condition.
  • the processing module is specifically configured to generate the driving instruction according to the description information of the special road condition of the second road area, and the driving behavior indicated by the driving instruction is related to obtaining the historical vehicle parameters of the target road condition model.
  • the driving behavior indicated by the feature is the same, and the target road condition model is a model for determining that the second road area is a special road condition.
  • the vehicle is a non-autonomous driving vehicle
  • the processing module is further configured to generate reminder information if the second road area exists in the planned route of the vehicle, and when the vehicle is about to drive to In the second road area, the reminder information is pushed, and the reminder information is used to indicate that there is a special road condition in the second road area.
  • the map data further includes: description information and/or target images of special road conditions in the first road area, where the description information is used to describe the scene type of the special road conditions, and the first road area
  • the target image of is: the vehicle parameter includes an image of the special road condition of the first road area.
  • the processing module is specifically configured to use description information and/or target images of special road conditions in the second road area as the reminder information.
  • the playing module is used to play the description information of the special road conditions in the second road area; and/or,
  • the display module is used to display a target image of a special road condition in the second road area.
  • the map data further includes: the duration of the special road condition of the first road area.
  • the display module is also used to display the identifier of the special road condition of each of the first road areas on the map.
  • the transceiving module is used to receive a user's selection instruction for the identification of the special road conditions in any first road area; correspondingly, the display module is also used to display the description information of the special road conditions in the first road area selected by the user.
  • the transceiver module is further configured to send a route planning request to the server and receive the planned route sent by the server.
  • the transceiver module is further configured to report vehicle parameters to the server.
  • vehicle parameters include the location of the vehicle, images or videos taken by the vehicle, and attribute data and driving data of the vehicle.
  • a device for identifying special road conditions including:
  • the processing module is used to obtain the first road area at the current time according to the road condition model and the vehicle parameters in the preset time period before the current time, and mark the first road area on the map data to obtain the current
  • the first road area is the road area where the special road condition is located
  • the road condition model is used to characterize the correspondence between the characteristics of the vehicle parameter and the special road condition.
  • the vehicle parameter includes the location of the vehicle.
  • the transceiver module is configured to receive at least one vehicle parameter reported by the vehicle within the preset time period.
  • the processing module is further configured to determine the vehicle parameters in the preset time period before the current time according to the vehicle parameters of the at least one vehicle, and the vehicles in the preset time period before the current time
  • the parameter is: a vehicle parameter that does not match the characteristics of the road at the location of the vehicle in the map data.
  • the processing module is further configured to use multiple historical vehicle parameters as training parameters to obtain the road condition model, and the historical vehicle parameters are received before the preset time period from at least one The vehicle parameters of the vehicle.
  • the processing module is specifically configured to divide the multiple historical vehicle parameters into N training data sets, and use each training data set as training data for training a road condition model to obtain the at least one road condition model, wherein: The characteristics of the vehicle parameters in each training data set are the same, and N is an integer greater than 1.
  • the processing module is specifically configured to input vehicle parameters in a preset time period before the current moment into the at least one road condition model to obtain the first road area.
  • the vehicle parameters include: images or videos taken by the vehicle.
  • the processing module is also used to obtain a target image of the first road area, and according to the target image of the first road area, generate description information of a special road condition of the first road area, and display it on the map.
  • Descriptive information and/or target images of the special road conditions of the first road area are added to the data, and the target image of the first road area is: the vehicle parameters include the images of the special road conditions of the first road area
  • the target image is an image taken by the vehicle or a video frame in the video, and the description information is used to describe the scene type of the special road condition.
  • the processing module is further configured to determine the duration of the special road condition in the first road area according to the scene type of the special road condition characterized by the description information of the special road condition in the first road area, and the The special road condition duration of the first road area is added to the map data.
  • the processing module is further configured to, if a route planning request from a terminal device is received, according to the starting and ending points, the duration of the special road conditions of the first road area and the special road conditions of the first road area.
  • the scene type of the road condition, the planned route is obtained, and the route planning request includes the start and end points;
  • the transceiver module is also used to push the planned route to the terminal device.
  • the vehicle parameters include attribute data and driving data of the vehicle.
  • an electronic device including: a processor, a memory, and a transceiver; the transceiver is coupled to the processor, the processor controls the transceiver actions of the transceiver, and the processor executes the third For the actions performed by the processing module of the third aspect or the fourth aspect, the transceiver performs the actions performed by the transceiving module of the third aspect or the fourth aspect.
  • the memory is used to store computer executable program code, and the program code includes instructions; when the processor executes the instructions, the instructions cause the terminal device to execute the method provided in the first aspect or the second aspect.
  • a computer program product containing instructions which when run on a computer, causes the computer to execute the method of the first aspect or the second aspect.
  • a computer-readable storage medium stores instructions that, when run on a computer, cause the computer to execute the method of the first aspect or the second aspect.
  • the embodiments of the application provide a method, device, electronic device, and storage medium for identifying special road conditions.
  • the server can determine the first road area where the special road conditions are located based on the massive vehicle parameters reported, and then update the map data to obtain the current time Map data.
  • the map data at the current time includes the first road area, and the terminal device can identify whether the planned route of the vehicle contains special road conditions after acquiring the map data at the current time, so as to identify the special road conditions in the planned route in advance , Can improve the real-time recognition of special road conditions.
  • FIG. 1 is a schematic diagram of a scenario where the method for identifying special road conditions provided by an embodiment of the application is applicable;
  • FIG. 2 is a first schematic flowchart of a method for identifying special road conditions provided by an embodiment of this application;
  • FIG. 3 is a schematic diagram 1 of a map provided by an embodiment of this application.
  • Fig. 4 is a second schematic diagram of a map provided by an embodiment of the application.
  • FIG. 5 is a second schematic flowchart of a method for identifying special road conditions provided by an embodiment of this application.
  • FIG. 6 is a schematic diagram of a process for obtaining a road condition model provided by an embodiment of the application.
  • FIG. 7 is a schematic diagram 1 of interface changes of the terminal device provided by an embodiment of the application.
  • FIG. 8 is a second schematic diagram of interface changes of the terminal device provided by an embodiment of the application.
  • FIG. 9 is a first structural diagram of a device for special road condition recognition provided by an embodiment of the application.
  • FIG. 10 is a second schematic structural diagram of a device for identifying special road conditions provided by an embodiment of this application.
  • FIG. 11 is a first structural diagram of an electronic device provided by an embodiment of this application.
  • FIG. 12 is a second structural diagram of an electronic device provided by an embodiment of this application.
  • the recognition of special road conditions during the driving of a vehicle is mainly based on navigation prompts, recognition of sensors on the vehicle to assist driving, or user recognition.
  • the existing navigation can only prompt for special road conditions such as road construction, traffic congestion, etc., and cannot provide information on missing manhole covers, uneven manhole covers, road depressions, road flooding, high speed bumps, lanes or temporary road sections.
  • Special road conditions such as closures, traffic accidents, etc. are prompted, so the types of special road conditions indicated by the navigation are not comprehensive.
  • the navigation cannot provide prompts for sudden special road conditions, such as sudden obstacles, car accidents, or mudslides in a certain lane, which cannot prompt promptly, and the real-time performance is low.
  • the driving-assisted sensors rely on lidar to identify special road conditions with obstacles on the road.
  • Special road conditions such as road depressions, missing manhole covers, and road water cannot be recognized, so The types of special road conditions recognized by the driving-assisting sensors are not comprehensive.
  • the user needs to rely on the user's driving experience to recognize special road conditions, and the user's carelessness or slow response will lead to the inability to recognize and avoid the special road conditions.
  • the special road conditions in the embodiments of the present application may include: missing manhole covers, uneven manhole covers, road depressions and potholes, road water, high speed bumps, lane closure construction, temporary closure of lanes or road sections, traffic accidents, Traffic jam and so on.
  • the prior art provides a method for identifying special road conditions by using images collected during the driving of the vehicle.
  • the vehicle compares and recognizes the images collected during driving with various pre-set images of various special road conditions, and reminds the user when it is determined that the collected images include special road conditions.
  • this method has the problem of low real-time performance.
  • the vehicle travels at a high speed.
  • the image is collected and the image is recognized as containing special road conditions, the vehicle may have driven through the special road conditions at high speed and cannot be reminded in time.
  • this method relies on a single image collected by the vehicle to recognize special road conditions, and there is a problem of low recognition accuracy.
  • the server in the prior art may receive images of the special road conditions and the location of the special road conditions uploaded by the user, and then alert vehicles passing the location of the special road conditions.
  • this method still has the problem of low real-time performance, and if the image of the special road condition is not uploaded by the user, the server cannot remind the special road condition.
  • an embodiment of the present application provides a method for identifying special road conditions.
  • massive vehicle parameters reported by the vehicle in real time various types of special road conditions are identified and marked on the map. Remind the driving vehicles in real time.
  • real-time and massive vehicle parameters reported by vehicles during driving are used in the embodiments of the present application to identify special road conditions, the recognition accuracy and real-time performance of special road conditions can be ensured, thereby supporting real-time reminders.
  • FIG. 1 is a schematic diagram of a scenario where the method for identifying special road conditions provided by an embodiment of the application is applicable.
  • this scenario includes: a terminal device and a server.
  • the terminal device is connected to the server wirelessly.
  • the server may be a cloud server for the Internet of Vehicles.
  • the terminal device may be a vehicle, or an in-vehicle terminal in the vehicle, or the like.
  • FIG. 2 is a schematic flowchart 1 of a method for identifying special road conditions provided by an embodiment of this application.
  • the method for identifying special road conditions provided by the embodiment of the present application may include:
  • the server obtains the first road area at the current time according to the road condition model and the vehicle parameters in the preset time period before the current time. Correspondence between characteristics and special road conditions.
  • S202 The server marks the first road area on the map data to obtain the map data at the current moment.
  • S203 The terminal device obtains the map data at the current moment.
  • S204 The terminal device judges whether there is a second road area in the planned route of the vehicle according to the planned route of the vehicle, and the second road area is a road area in the first road area.
  • traffic parameters for a particular vehicle model may be based on a time segment regions identify the segment area exists Special road conditions.
  • the road condition model in the embodiment of the present application is obtained by using a clustering algorithm or an AI algorithm such as machine learning based on historically obtained vehicle parameters.
  • AI algorithms can be decision trees, random forests, logistic regression, support vector machines, naive Bayes or neural networks.
  • the type of AI algorithm used to obtain the road condition model is not limited.
  • the preset time period before the current time is a predefined time period.
  • the vehicle parameters of the preset time period before the current time may be periodically used to obtain the special road conditions.
  • the road area at the location Exemplarily, if the current time is 8:00, the vehicle parameters in the preset time period before the current time may be the vehicle parameters in the time period of 7:50-8:00.
  • the vehicle parameters in the time period of 7:50-8:00 can be used to input into the road condition model to obtain the road area where the special road condition at 8:00 is located.
  • the vehicle parameters of the preset time period before the current time in the embodiment of the present application may be: the vehicle parameters reported by the vehicle to the server during the preset time period before the current time. It should be understood that the vehicle parameters may be reported periodically during the driving of the vehicle.
  • Vehicle parameters include dynamic parameters and static parameters of the vehicle.
  • the dynamic parameters of the vehicle include the position of the vehicle, the image or video taken by the vehicle, and the driving data of the vehicle.
  • the driving data of the vehicle can be the speed, acceleration, and driving actions such as steering and braking of the vehicle.
  • the static parameters of the vehicle are attribute data of the vehicle.
  • the attribute data of the vehicle may include data such as the weight, length, width, and height, and shock absorption of the vehicle. It is worth noting that when the vehicle reports the vehicle parameters for the first time, the dynamic parameters and static parameters of the vehicle are reported, and the dynamic parameters are reported when the vehicle parameters are subsequently reported.
  • the road area where the special road condition at the current moment is located is taken as the first road area.
  • the first road area is a lane-level road area.
  • the special road condition is traffic jam
  • the first road area may be three lanes between XX road and XX road.
  • the special road condition is missing manhole cover
  • the first road area can be the area of the left lane on XX road.
  • vehicle parameter in the preset time period before the current moment may be a vehicle parameter reported by at least one vehicle within the preset time period.
  • the vehicle parameters of at least one vehicle received within the preset time period may be preprocessed to determine the initial road area, and then correspond to the initial road area.
  • the vehicle parameters of is used as the vehicle parameters in the preset time period before the current time.
  • the initial road area is the road area where the special road conditions are preliminarily determined
  • the vehicle parameters corresponding to the initial road area are: the vehicle position in the vehicle parameters of at least one vehicle received within the preset time period is within the initial road area Vehicle parameters.
  • area 1 is determined as the initial road area, and then the vehicle parameters of the vehicle's position in area 1 are acquired from the vehicle parameters of the N vehicles, as the above
  • the vehicle parameters in the preset time period before the current moment that is, the vehicle parameters input to the road condition model.
  • the initial road area may be determined by the area where the location in the vehicle parameter does not match the feature of the road at the location of the vehicle in the map data.
  • the vehicle parameter that does not match the characteristics of the road at the location of the vehicle in the map data is used as the vehicle parameter in the preset time period before the current time.
  • the characteristic of the road in area 1 in the map data is a straight lane and the minimum vehicle speed is 60Km/h, and according to the vehicle parameters, it is determined that the vehicle speed in the vehicle parameters reported by the vehicles in the area 1 is 10Km/h, 0Km/h.
  • the vehicle parameters in this area 1 do not match the characteristics of the road in area 1, and there may be special road conditions in this area 1, such as traffic jam.
  • the parameter of the vehicle located in the area 1 is taken as the parameter of the vehicle in the preset time period before the current moment.
  • the first road area may be marked on the map data, and the map data may be updated to obtain the map data at the current moment. It should be understood that marking the first road area on the map data may be: marking a special road condition at a location corresponding to the first road area on the map, and then the updated map data at the current moment may be marked with the first road area.
  • FIG. 3 is a schematic diagram 1 of a map provided by an embodiment of this application. As shown in Figure 1, the map is marked with the first road area at three locations (such as A, B, and C). Among them, FIG. 3 exemplarily represents the first road area in the form of an "exclamation mark".
  • the map data can also be updated for the elimination of special road conditions.
  • the characteristics of the road in area 1 in the above map data are straight lanes and the vehicle speed is less than 60Km/h, while the vehicle parameters reported by vehicles in area 1 at the previous time are 10Km/h, 0Km/h Etc., then the area 1 is marked as the first road area in the map data at the previous time.
  • the map data can be updated to obtain the map data at the current moment.
  • the specific method for updating the map data is: deleting the area 1 marked as the first road area on the map.
  • Fig. 4 is a second schematic diagram of a map provided by an embodiment of this application. Compared with FIG. 3, the special road condition at location A in FIG. 4 is eliminated, and the updated map at the current moment is shown in FIG. 4. In FIG. 4, the first road area is marked at location B and location C.
  • the terminal device may obtain the map data at the current moment in the server.
  • an application program that displays a map is installed in the terminal device, such as a navigation application program, an autonomous driving map application program, etc.
  • the terminal device can obtain the map data at the current moment to update the map data in the terminal device application.
  • the terminal device can obtain the map data at the current moment, so that the autonomous vehicle can obtain the first road area in advance.
  • the terminal device can display the first road area in the map, so that the user can learn the first road area. That is to say, in the embodiment of the present application, both the autonomous driving vehicle and the non-autonomous driving vehicle can obtain the first road area in advance according to the map data at the current moment, which solves the real-time problem in the prior art.
  • the terminal device can determine whether there is a second road area in the planned route of the vehicle according to the planned route of the vehicle, that is, it can identify special road conditions in the planned route in advance.
  • the second road area is a road area in the first road area, that is, in the embodiment of the present application, it can be judged in advance whether there is a road area where a special road condition exists in the planned route of the vehicle. If there is a second road area in the planned route of the vehicle, a driving decision can be made in advance (for autonomous vehicles, see S508 in the following embodiments for details) or advance reminders (for non-autonomous vehicles), And then realize timely reminding.
  • the planned route in the embodiment of the present application may be obtained by the terminal device according to the start and end points input by the user, or may be obtained by the terminal device requesting the server to obtain it.
  • the server obtains the area where the special road condition at the current moment is located, that is, the first road area, according to the reported vehicle parameters and road condition model, to update the map data to obtain the map data at the current moment.
  • the map data includes the first road area.
  • the terminal device can identify whether the planned route of the vehicle contains special road conditions, so as to identify the special road conditions in the planned route in advance, which can improve the real-time recognition of special road conditions.
  • FIG. 5 is a second schematic flowchart of a method for identifying a special road condition provided by an embodiment of this application.
  • the method for identifying special road conditions provided by the embodiment of the present application may include:
  • S501 The server inputs vehicle parameters in a preset time period before the current moment into at least one road condition model to obtain a first road area.
  • the server acquires a target image of the first road area, the target image of the first road area is: the vehicle parameters include an image of the special road condition of the first road area, and the target image is an image taken by the vehicle or a video frame in the video .
  • S503 The server generates description information of a special road condition in the first road area according to the target image of the first road area, where the description information is used to describe a scene type of the special road condition.
  • the server determines the duration of the special road condition in the first road area according to the scene type of the special road condition characterized by the description information of the special road condition in the first road area.
  • S505 The server marks the first road area on the map data, and adds the description information and/or target image of the special road condition of the first road area and the special road condition duration of the first road area to the map data to obtain the current time Map data.
  • S506 The terminal device obtains the map data at the current moment.
  • S507 The terminal device judges whether there is a second road area in the planned route of the vehicle according to the planned route of the vehicle.
  • the terminal device If the vehicle is an autonomous driving vehicle and there is a second road area in the planned route of the vehicle, the terminal device generates a driving instruction, and the driving instruction is used to instruct the driving behavior of the vehicle.
  • the terminal device If the vehicle is a non-autonomous driving vehicle and there is a second road area in the planned route of the vehicle, the terminal device generates reminder information, and the reminder information is used to indicate that there is a special road condition in the second road area.
  • each road condition model is used to identify vehicle parameters with different characteristics as vehicle parameters corresponding to special road conditions.
  • the road condition model 1 is used to identify special road conditions with a lack of manhole cover
  • the road condition model 2 is used to identify special road conditions where roads are blocked
  • the road condition model 3 is used to identify special road conditions where the vehicle is slipping.
  • the vehicle parameters in the preset time period before the current time may be input into at least one road condition model to obtain the first road area.
  • the output result of road condition model 1 may be that the vehicle parameter is not a vehicle parameter corresponding to a special road condition, but it is input to road condition model 2, and the output result of road condition model 2 may be a vehicle parameter It is a vehicle parameter corresponding to a special road condition, and then it can be determined that the vehicle parameter is a vehicle parameter corresponding to a blocked road.
  • the method of obtaining the first road area in the embodiment of the present application may be: according to at least one road condition model, the vehicle parameter output as the vehicle parameter corresponding to the special road condition can be obtained. Since the vehicle parameter includes the position of the vehicle, the implementation of this application is In the example, an area including a preset number of vehicle parameters corresponding to special road conditions may be used as the first road area. Exemplarily, if the vehicle parameters reported by 10 vehicles in area 1 are all determined to be vehicle parameters corresponding to special road conditions, then area 1 may be used as the first road area.
  • the method of obtaining the first road area in the embodiment of the present application may also be: the vehicle parameters in the preset time period before the current moment may be input into at least one road condition model to obtain the first road area as a special road condition , Without going through the vehicle parameter analysis process of the vehicle parameters corresponding to the above special road conditions.
  • Fig. 6 is a schematic diagram of a process for acquiring a road condition model provided by an embodiment of the application. As shown in FIG. 6, the method for obtaining a road condition model in the embodiment of the present application includes:
  • S601 Divide the multiple historical vehicle parameters into N training data sets.
  • Each historical vehicle parameter may include the location of the vehicle, the image or video taken by the vehicle, and the attribute data and driving data of the vehicle.
  • attribute data and driving data please refer to the relevant description in S201 above.
  • the characteristics of the vehicle parameters in each training data set are the same, and N is an integer greater than or equal to 1.
  • special road conditions of different characteristic types can be obtained in advance.
  • the special road conditions of different feature types can be features that affect the vehicle to produce different vehicle parameters.
  • the characteristic types of special road conditions are: blocked roads, missing manhole covers, icing roads, speed bumps, etc.
  • the embodiment of the present application may be divided into N training data sets according to the characteristics of the historical vehicle parameters.
  • the characteristics of the vehicle parameters in each training data set are the same, that is, the vehicle parameters in each training data set are generated by a characteristic type of special road conditions.
  • the characteristics of the generated vehicle parameters such as road barriers may be: turning right after decelerating, turning left after decelerating, turning around after decelerating, and so on.
  • the characteristics of the vehicle parameters generated by the deceleration zone may be: vehicle body vibration after deceleration, etc.
  • the degree of distinction between deceleration, vehicle body vibration, and turning can also be determined to determine the characteristic types of special road conditions corresponding to historical vehicle parameters, so as to classify the training data set where the historical vehicle parameters are located.
  • deceleration can include slow deceleration, rapid deceleration, etc.
  • body vibration can include body vibration as small amplitude vibration, large amplitude vibration (for example, the amplitude of the body vibration can be discretized into different integer values, such as 0-10 to achieve amplitude division), etc.
  • turning It can include sharp turns and slow turns.
  • S602 Use each training data set as training data for training a road condition model to obtain the at least one road condition model.
  • each training data set may be used as training data for training one road condition model, one road condition model is trained, and N training data sets are trained to obtain at least one road condition model.
  • N that is, at least one
  • the vehicle parameters are labeled, for example, the vehicle parameter corresponding to the deceleration part of the vehicle parameters is marked as "deceleration”, and the vehicle parameter corresponding to the left turn part is marked as "left turn”.
  • the above S201 describes that a road condition model can be used to obtain the first road area.
  • the road condition model in the above embodiment can be a model that integrates at least one road condition model in the embodiment of the present application, so as to realize the comparison of different road conditions. Characteristic vehicle parameters are used to identify special road conditions.
  • the characteristic type of the first road area of the special road condition can be obtained, but the scene type of the special road condition of the first road area cannot be determined.
  • the characteristic types of the above-mentioned special road conditions are: “road blocked”, “road bumpy”, and “road congested”.
  • the scene type of the special road condition in the first road area may also be obtained based on the vehicle parameters, so as to obtain more detailed information about the special road condition in the first road area.
  • the vehicle parameters reported by the vehicle include images or videos taken by the vehicle.
  • the vehicle parameters reported by the vehicle in the first road area can be obtained according to the first road area and the position of the vehicle in the vehicle parameters. Then, the image or video shot by the vehicle is obtained from the vehicle parameters reported in the first road area.
  • the vehicle parameters reported in the first road area are referred to as target vehicle parameters in the following description.
  • the target image of the first road area can be obtained from the target vehicle parameters. It should be understood that there may be multiple target vehicle parameters, and correspondingly, there may also be multiple images or videos in the target vehicle parameters.
  • the method of acquiring the target image in the target vehicle parameters may be: taking an image or video frame of a special road condition containing the first road area as a candidate image, and then acquiring the target image in the candidate image. It should be understood that the video in the target vehicle parameter may include multiple video frames.
  • the server in the embodiment of the present application may pre-store a recognition model, and the recognition model is used to characterize the correspondence between the characteristics of the image and the scene type of the special road condition, that is, the image is input into the recognition model, and the recognition model can recognize Whether the image is an image containing pixel blocks of special road conditions, so as to determine the scene type of the special road conditions.
  • images or video frames in the target vehicle parameters can be input to the recognition model, and images or video frames containing special road conditions are used as candidate images.
  • the recognition model can also output the similarity of the candidate images to characterize the accuracy of the particular road conditions included in the candidate images.
  • the target image may be determined according to the image clarity and similarity, for example, the candidate image with the highest image clarity is used as the target image, or the candidate image with the highest similarity is used as the target image.
  • the recognition model in the embodiment of the present application may be obtained by training in a machine learning manner using multiple types of images containing special road conditions as a training data set.
  • the machine learning method for training the recognition model can be the same as the method for training the road condition model described above.
  • the description information of the special road condition in the embodiment of the present application is used to describe the scene type of the special road condition.
  • the scene types of special road conditions can be traffic jams, missing manhole covers, and unequal manhole covers.
  • the type of special road conditions in the first road area can be determined according to the target image of the first road area, so as to generate description information of the special road conditions in the first road area according to the scene type of the special road conditions in the first road area .
  • the type of the special road condition in the first road area is missing manhole cover
  • the description information of the special road condition in the first road area may be a detailed description of the scene type of the special road condition in the first road area, such as the first road area
  • the description information of the special road conditions can be: the manhole cover of the first lane on the left in the eastbound direction of Road XX is missing.
  • one way to determine the type of the special road condition in the first road area in the embodiment of the present application may be: the above-mentioned recognition model is used to characterize the correspondence between the characteristics of the image and the scene type of the special road condition, that is, the image is input to the recognition model , That is, you can get the scene type of the special road condition in the image.
  • another way of determining the type of the special road condition of the first road area may be: there may be multiple recognition models. Among them, each recognition model is used to characterize the corresponding relationship between the special road conditions of a scene type and the features of the image.
  • images or video frames in the target vehicle parameters can be input to multiple recognition models, and the input image is the special road condition scene type represented by the special road condition recognition model, which is the scene type of the special road condition contained in the image.
  • the recognition model 1 is used to characterize the correspondence between the missing manhole cover and the feature of the image, that is, it is used to identify the image containing the missing manhole cover;
  • the recognition model 2 is used to characterize the correspondence between the traffic jam and the feature of the image, that is, the identification contains There is an image of a traffic jam;
  • the recognition model 3 is used to characterize the correspondence between the speed bump and the characteristics of the image, that is, it is used to identify the image containing the speed bump.
  • the machine learning method used when training each recognition model can be the same as the method for training the recognition model described above.
  • training each recognition model is different from the training data for training the recognition model described above.
  • the training data when training each recognition model is an image containing special road conditions of the same scene type
  • the training data of the above-mentioned training recognition model is an image containing special road conditions of various scene types.
  • the training data for training the recognition model 1 in the embodiment of the present application may be multiple images containing missing manhole covers.
  • the duration of the special road condition in the first road area refers to the time from the current moment to the elimination of the first road area. It should be understood that the duration of the special road condition in the first road area may be determined based on the empirical average value of statistics based on big data, or may refer to the time from the appearance of the special road condition to the elimination of the special road condition.
  • the embodiment of the present application may determine the duration of the special road condition in the first road area according to the scene type of the special road condition in the first road area.
  • the server stores an empirical value of the duration of special road conditions of each scene type, and the empirical value may be input by a user (technician) or obtained by the server according to the duration of historical special road conditions.
  • the server may use the average value, maximum value, or minimum value of the duration of the historical special road condition as the duration of the special road condition of the same type as the scene type of the historical special road condition.
  • the duration of the special road condition that the manhole cover is missing is 1 day, and the duration of the special road condition that the debris flow is 4 hours, etc.
  • the embodiment of the present application may mark on the map data
  • the first road area, and the description information and/or the target image of the special road condition of the first road area, and the special road condition duration of the first road area are added to the map data. That is, the current map data includes the first road area, the description information and/or the target image of the special road condition of the first road area, and the special road condition duration of the first road area.
  • a driving decision that is, a driving instruction
  • the driving instruction is used to instruct the vehicle's Driving behavior.
  • the driving instruction may be an instruction instructing the vehicle to slow down and turn right, or slow down.
  • the embodiment of the application can generate driving instructions according to the description information of the special road conditions in the second road area.
  • the driving behavior indicated by the driving instruction is the same as the driving behavior indicated by the characteristic of acquiring the historical vehicle parameters of the target road condition model, and the target road condition model is a model for determining that the second road area is a special road condition.
  • the model in which the input second road area is a special road condition is used as the target road condition model, and the driving behavior indicated by the characteristics of the historical vehicle parameters trained on the target road condition model is used as the driving instruction.
  • the second road area is a missing manhole cover
  • the model that outputs the second road area as a special road condition is road condition model 2
  • the historical vehicle parameter of the training road condition model 2 is characterized by first decelerating and then turning right. Turn right after deceleration as the driving instruction for the second road area.
  • the terminal device controls the vehicle to travel according to the driving instruction.
  • the driving instruction for the autonomous vehicle in the second road area can be generated in advance, and the autonomous vehicle can be reminded in advance, so that when the autonomous vehicle is driving to the second road area, it can Drive according to driving instructions.
  • the driving instruction in the second road area is to decelerate first and then turn right
  • the autonomous vehicle may decelerate first and then turn right when driving to the second road area.
  • the driving instruction may be executed at a preset distance before the self-driving vehicle travels to the second road area.
  • a preset distance exemplary, when there is 1 meter away from the second road area, first slow down and then turn right.
  • reminding information may be generated in the embodiment of the present application to remind the user driving the vehicle. Since the map data also includes the description information and/or target image of the special road conditions in the first road area, the reminder information generated in the embodiment of the present application may use the description information and/or target image of the special road conditions in the second road area as a reminder information.
  • the terminal device may push reminder information when the vehicle is about to drive to the second road area.
  • the way of pushing the reminder information may be to play the description information of the special road condition in the second road area, and/or display the target image of the special road condition in the second road area.
  • the description information of the special road condition of the first road area may be: the manhole cover of the first lane on the left in the eastbound direction of Road XX is missing.
  • This embodiment of the application can play the reminder message of "the manhole cover of the first lane on the left of the eastbound direction of XX Road is missing" when the vehicle is about to drive to the second road area (for example, there is still a preset distance from the second road area) , And display the target image of the special road condition of the second road area on the display screen of the terminal device.
  • FIG. 7 is a schematic diagram 1 of interface changes of the terminal device provided by an embodiment of the application.
  • the navigation interface of the vehicle is displayed on the interface 701.
  • the interface 701 can jump to the interface 702, and the second road is displayed on the interface 702.
  • what is displayed on the interface 702 is an image of "missing manhole cover" at the second road area.
  • the terminal device is an in-vehicle terminal as an example for description.
  • FIG. 8 is a second schematic diagram of interface changes of the terminal device provided by an embodiment of the application. As shown in the interface 801 in FIG. 8, the interface 801 displays the identifier of the special road condition of the first road area on the navigation interface of the vehicle displayed on the interface 701.
  • the identifiers of the special road conditions in the first road area may be the same, for example, both are icons of exclamation points.
  • the identifier of the special road condition in the first road area may characterize the scene type of the special road condition in the first road area. As shown in the interface 801 of FIG. 8, when the special road conditions of the first road area include missing manhole covers, uneven manhole covers, and mudslides, corresponding signs may be displayed on the corresponding positions of the first road area on the map.
  • the position A is marked with a mark 1 which characterizes the missing manhole cover
  • the position B is marked with a mark 2 which characterizes the unevenness of the manhole cover
  • the position C is marked with a mark 3 which characterizes the missing manhole cover.
  • the terminal device receives the user's selection instruction for the identification of the special road condition in any first road area, and displays the description information of the special road condition in the first road area selected by the user, so that the user can obtain the selected first road area.
  • the scene type of the special road conditions in the road area Exemplarily, if the user selects the logo 1 by clicking, the above interface 801 jumps to the interface 802, and the interface 802 displays the description information of the special road condition at the position A, such as: the left side of the eastbound direction of the XX road The first lane manhole cover is missing.
  • S508-S509 and S510-S511 are steps to be executed alternatively. It should be understood that S508-S509 are steps executed when the vehicle is an autonomous driving vehicle, and S510-S511 are steps executed when the vehicle is a non-autonomous driving vehicle.
  • the above S507-S511 are scenes in the process of driving the vehicle.
  • the map data also includes: the duration of the special road conditions in the first road area, if there is a second road area in the planned route of the vehicle, and the special road conditions in the second road area have a preset scene type , And the time the vehicle travels to the second road area is less than the duration of the special road conditions in the second road area, the server may be requested to update the planned route of the vehicle to obtain the updated planned route.
  • the preset scene type is a pre-appointed scene type, which may be a scene type of special road conditions where vehicles cannot pass quickly, such as traffic jams, mudslides, etc.
  • the server may be requested to update the planned route of the vehicle to avoid the second road area, obtain the updated planned route, and then display the updated planned route on the terminal device.
  • the reason for updating the planned route can also be displayed on the terminal device, such as a text reminder message of "There is a mudslide ahead, the route has been updated for you".
  • the above-mentioned planned route of the vehicle may be obtained by the terminal device requesting the server.
  • the terminal device may send the route planning request to the server.
  • the server receives the route planning request from the terminal device, and can obtain the planned route according to the start and end points, the duration of the special road conditions in the first road area, and the scene type of the special road conditions in the first road area.
  • the server can avoid planning routes that include special road conditions with preset scene types when designing and planning routes.
  • the road condition model in the embodiment of the present application is obtained after training from a large amount of historical vehicle parameters. Therefore, using the road condition model to identify the first road area at the current moment has high accuracy.
  • the terminal device may generate driving decision or reminder information in advance based on current map data, so as to provide advance reminders to autonomous vehicles and non-autonomous vehicles, thereby improving user experience.
  • the terminal device can also update the preset route planned in advance according to the current map data, or set a preset route for the vehicle, which can further improve the user experience.
  • FIG. 9 is a first structural diagram of an apparatus for special road condition recognition provided by an embodiment of this application.
  • the device for identifying special road conditions may be the terminal device in the foregoing embodiment.
  • the device 900 for identifying special road conditions includes: a processing module 901, a playing module 902, a display module 903, and a transceiver module 904.
  • the processing module 901 is configured to obtain map data at the current moment, the map data including: the first road area at the current moment, and according to the planned route of the vehicle, determine whether there is a second road area in the planned route of the vehicle ,
  • the second road area is a road area in the first road area
  • the first road area is a road area where a special road condition is located
  • the first road area is determined by the road condition model and the current time before
  • the road condition model is used to characterize the correspondence between the characteristics of the vehicle parameters and the special road conditions.
  • the processing module 901 is further configured to generate a driving instruction if the second road area exists in the planned route of the vehicle, and when the vehicle travels to In the second road area, the driving of the vehicle is controlled according to the driving instruction, and the driving instruction is used to instruct the driving behavior of the vehicle.
  • the map data further includes: description information of a special road condition of the first road area, and the description information is used to describe a scene type of the special road condition.
  • the processing module 901 is specifically configured to generate the driving instruction according to the description information of the special road condition of the second road area, the driving behavior indicated by the driving instruction and the historical vehicle parameters for obtaining the target road condition model
  • the driving behavior indicated by the characteristics of is the same
  • the target road condition model is a model for determining that the second road area is a special road condition.
  • the vehicle is a non-autonomous driving vehicle
  • the processing module 901 is further configured to generate reminder information if the second road area exists in the planned route of the vehicle, and when the vehicle is about to drive When the second road area is reached, the reminder information is pushed, and the reminder information is used to indicate that there is a special road condition in the second road area.
  • the map data further includes: description information and/or target images of special road conditions in the first road area, where the description information is used to describe the scene type of the special road conditions, and the first road area
  • the target image of is: the vehicle parameter includes an image of the special road condition of the first road area.
  • the processing module 901 is specifically configured to use description information and/or target images of special road conditions in the second road area as the reminder information.
  • the playing module 902 is used to play the description information of the special road conditions in the second road area; and/or,
  • the display module 903 is configured to display target images of special road conditions in the second road area.
  • the map data further includes: the duration of the special road condition of the first road area.
  • the display module 903 is further configured to display the identifier of the special road condition of each first road area on the map.
  • the transceiving module 904 is used to receive a user's selection instruction for the identification of special road conditions in any first road area; correspondingly, the display module 903 is also used to display the description information of the special road conditions in the first road area selected by the user .
  • the transceiver module 904 is further configured to send a route planning request to the server, and receive the planned route sent by the server.
  • the map data further includes: the duration of the special road condition of the first road area.
  • the transceiver module 904 is further configured to report vehicle parameters to the server.
  • vehicle parameters include the location of the vehicle, images or videos taken by the vehicle, and attribute data and driving data of the vehicle.
  • FIG. 10 is a second structural diagram of the device for special road condition recognition provided by an embodiment of this application.
  • the device for identifying special road conditions may be the server in the foregoing embodiment.
  • the device 1000 for identifying special road conditions includes a processing module 1001 and a transceiver module 1002.
  • the processing module 1001 is configured to obtain the first road area at the current time according to the road condition model and the vehicle parameters in the preset time period before the current time, and mark the first road area on the map data to obtain the In the map data at the current moment, the first road area is a road area where a special road condition is located, and the road condition model is used to characterize the correspondence between the characteristics of the vehicle parameter and the special road condition.
  • the vehicle parameter includes the location of the vehicle.
  • the transceiver module 1002 is configured to receive at least one vehicle parameter reported by the vehicle within the preset time period.
  • the processing module 1001 is further configured to determine the vehicle parameters in the preset time period before the current time according to the vehicle parameters of the at least one vehicle, and the vehicle parameters in the preset time period before the current time
  • the vehicle parameter is: a vehicle parameter that does not match the characteristics of the road at the location of the vehicle in the map data.
  • the processing module 1001 is further configured to use multiple historical vehicle parameters as training parameters to obtain the road condition model, and the historical vehicle parameters are received before the preset time period from at least The vehicle parameters of a vehicle.
  • the processing module 1001 is specifically configured to divide the multiple historical vehicle parameters into N training data sets, the characteristics of the vehicle parameters in each training data set are the same, and N is an integer greater than 1, and each training data set As training data for training a road condition model to obtain the at least one road condition model.
  • the processing module 1001 is specifically configured to input vehicle parameters in a preset time period before the current moment into the at least one road condition model to obtain the first road area.
  • the vehicle parameters include: images or videos taken by the vehicle.
  • the processing module 1001 is further configured to obtain a target image of the first road area, and generate description information of a special road condition in the first road area according to the target image of the first road area, and Descriptive information and/or target images of the special road conditions of the first road area are added to the map data, and the target image of the first road area is: the vehicle parameters include the special road conditions of the first road area An image, the target image is an image taken by the vehicle or a video frame in a video, and the description information is used to describe the scene type of the special road condition.
  • the processing module 1001 is further configured to determine the duration of the special road condition in the first road area according to the scene type of the special road condition characterized by the description information of the special road condition in the first road area, and The special road condition duration of the first road area is added to the map data.
  • the processing module 1001 is further configured to, if a route planning request from a terminal device is received, according to the starting and ending points, the duration of the special road conditions of the first road area and the time of the first road area For the scene type of the special road condition, obtain the planned route, and the route planning request includes the start and end points;
  • the transceiver module 1002 is also used to push the planned route to the terminal device.
  • the vehicle parameters include attribute data and driving data of the vehicle.
  • FIG. 11 is a first structural diagram of an electronic device provided by an embodiment of this application.
  • the electronic device may be the terminal device in FIG. 9 described above, and the electronic device may include: a processor 1101, a player 1102, a display 1103, a transceiver 1104, and a memory 1105.
  • the processor 1101 executes the actions of the aforementioned processing module 901
  • the player 1102 executes the actions of the aforementioned playing module 902
  • the display 1103 executes the actions of the aforementioned display module 903
  • the transceiver 1104 executes the actions of the aforementioned transceiver module 904.
  • the memory 1105 can store various instructions for completing various processing functions and implementing the method steps of the present application.
  • transceiver 1104 is coupled to the processor 1101, and the processor 1101 controls the transceiver 1104 (1202)
  • the memory 1105 may include high-speed random-access memory (random-access memory, RAM), or may also include non-volatile memory (NVM), such as at least one disk memory.
  • the electronic device involved in the present application may further include: a power supply 1106, a communication bus 1107, and a communication port 1108.
  • the transceiver 1104 may be integrated in the transceiver of the terminal device, or may be an independent transceiver antenna on the terminal device.
  • the communication bus 1107 is used to implement communication connections between components.
  • the aforementioned communication port 1108 is used to implement connection and communication between the terminal device and other peripherals.
  • the display 1103 may be connected to the processor 1101 to display the setting interface in the foregoing embodiment under the control of the processor 1101.
  • the above-mentioned memory 1105 is used to store computer executable program code, and the program code includes instructions; when the processor 1101 executes the instructions, the instructions cause the processor 1101 of the terminal device to execute the processing of the terminal device in the above method embodiment.
  • the operation causes the transceiver 1104 to perform the receiving and sending actions of the terminal device in the foregoing method embodiment.
  • FIG. 12 is a second structural diagram of an electronic device provided by an embodiment of this application.
  • the electronic device may be the server in FIG. 10, and the electronic device may include: a processor 1201, a transceiver 1202, and a memory 1203.
  • the processor 1201 executes the actions of the aforementioned processing module 1001
  • the transceiver 1202 executes the actions of the aforementioned transceiver module 1002.
  • Various instructions can be stored in the memory 1203 to complete various processing functions and implement the method steps of the present application.
  • the above-mentioned transceiver 1202 is coupled to the processor 1201, and the processor 1201 controls the transceiver 1202 (1202) to send and receive actions;
  • the processor 1203 may include a high-speed random access memory (random-access memory, RAM), or may also include non-volatile memory.
  • the electronic device involved in the present application may further include: a power supply 1204, a communication bus 1205, and a communication port 1206.
  • the transceiver 1202 may be integrated in the transceiver of the terminal device, or may be an independent transceiver antenna on the terminal device.
  • the communication bus 1205 is used to implement communication connections between components.
  • the aforementioned communication port 1206 is used to implement connection and communication between the terminal device and other peripherals.
  • the display 1103 may be connected to the processor 1201 to display the setting interface in the foregoing embodiment under the control of the processor 1201.
  • the above-mentioned processor 1203 is used to store computer executable program code, and the program code includes instructions; when the processor 1201 executes the instructions, the instructions cause the processor 1201 of the terminal device to execute the terminal device in the above method embodiment.
  • the processing action enables the transceiver 1202 to perform the transceiving action of the terminal device in the foregoing method embodiment.
  • the implementation principle and technical effect are similar, and will not be repeated here.
  • the above embodiments it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof.
  • software it can be implemented in the form of a computer program product in whole or in part.
  • the computer program product includes one or more computer instructions.
  • the computer program instructions When the computer program instructions are loaded and executed on the computer, the processes or functions according to the embodiments of the present application are generated in whole or in part.
  • the computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.
  • Computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium.
  • computer instructions may be transmitted from a website, computer, server, or data center through a cable (such as Coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) to transmit to another website site, computer, server or data center.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center integrated with one or more available media.
  • the usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, and a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)).
  • plural herein refers to two or more.
  • the term “and/or” in this article is only an association relationship describing the associated objects, which means that there can be three relationships, for example, A and/or B, which can mean: A alone exists, A and B exist at the same time, exist alone B these three situations.
  • the character "/" in this article generally indicates that the associated objects before and after are in an "or” relationship; in the formula, the character "/" indicates that the associated objects before and after are in a "division" relationship.
  • the size of the sequence numbers of the foregoing processes does not mean the order of execution.
  • the execution order of the processes should be determined by their functions and internal logic, and should not be used for the implementation of this application.
  • the implementation process of the example constitutes any limitation.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Theoretical Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Software Systems (AREA)
  • Analytical Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Mathematical Physics (AREA)
  • Mechanical Engineering (AREA)
  • Transportation (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Computation (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Business, Economics & Management (AREA)
  • Computing Systems (AREA)
  • Medical Informatics (AREA)
  • Atmospheric Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Human Computer Interaction (AREA)
  • Strategic Management (AREA)
  • Economics (AREA)
  • Health & Medical Sciences (AREA)
  • Databases & Information Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Bioinformatics & Cheminformatics (AREA)

Abstract

一种特殊路况的识别方法、装置、电子设备和存储介质,该方法基于海量车辆实时上传到服务器的海量车辆参数,利用提前训练好的特殊路况的识别模型,基于车辆参数的大数据,实时识别出存在特殊路况的道路区域,进一步根据车辆实时上传的包含了特殊路况内容的图片或者视频帧,利用图片特征和特殊路况场景的特征模型,识别出特殊路况的场景类型;并将特殊路况的特征类型、场景类型和基于大数据分析统计出的该场景类型的特殊路况的持续时间等特殊路况信息标注到地图数据上,支撑车辆依据的地图数据的导航路径规划、临近特殊路况的提醒、途径特殊路况的驾驶决策;确保了特殊路况识别的实时性和准确性,有效提升车辆行驶的效率和安全性。

Description

特殊路况的识别方法、装置、电子设备和存储介质 技术领域
本申请实施例涉及车联网技术,尤其涉及一种特殊路况的识别方法、装置、电子设备和存储介质。
背景技术
随着经济水平的发展,车辆保有量逐步提升。车辆在行驶过程中可能会遇到各种特殊路况,如凹坑、井盖松动、无井盖、减速带、车道限制通行等,驾驶人员有时可能无法避让,进而造成驾驶体验低甚至发生危险。因此如何有效提醒,使得车辆可以安全通过特殊路况的路段尤为重要。
现有技术中,车辆可以采集行驶过程中车辆周围的图像,根据预先设置的特殊路况的图像对该采集到的图像进行比对识别,在识别出图像中包含有特殊路况时提醒驾驶人员,或者根据该特殊路况向自动驾驶车辆发送对应的驾驶指令,如前方有凹坑,该驾驶指令可以控制车辆减速、右拐至右方车道等。
但现有技术中的方式存在实时性不高的问题,如在识别出特殊路况的图像时该车辆可能已经高速行驶过了该特殊路况,不能对特殊路况进行及时地识别。
发明内容
本申请实施例提供一种特殊路况的识别方法、装置、电子设备和存储介质,能够根据当前时刻的地图数据,预先获取特殊路况的区域,实时性高。
第一方面,提供一种特殊路况的识别方法,该方法应用于终端设备,也可以应用于终端设备中的芯片。下面以应用于终端设备为例对该方法进行描述,该方法中终端设备从服务器获取当前时刻的地图数据,所述地图数据包括:所述当前时刻的第一道路区域,所述第一道路区域为特殊路况所处的道路区域,所述第一道路区域是由路况模型和所述当前时刻之前的预设时间段内的车辆参数获取的,所述路况模型用于表征车辆参数的特征和特殊路况的对应关系,即路况模型能够基于一段时间内某个路段区域的车辆参数识别出该路段区域是否存在特殊路况;根据车辆的规划路线,判断所述车辆的规划路线中是否存在第二道路区域,所述第二道路区域为所述第一道路区域中的道路区域。应理解,终端设备可以周期性的向服务器上报车辆参数,车辆参数包括车辆的动态参数和静态参数。其中,车辆的动态参数包括车辆的位置、车辆拍摄的图像或视频,以及车辆的行驶数据,车辆的行驶数据可以为车辆的速度、加速度,以及转向、刹车等驾驶动作。车辆的静态参数为车辆的属性数据。车辆的属性数据可以包括车辆的重量、长宽高、减震性等数据。值得注意的是,车辆在第一次上报车辆参数时,上报车辆的动态参数和静态参数,在后续上报车辆参数时上报动态参数。
可以理解,本申请实施例中的终端设备可以从服务器实时获取当前时刻的地图数据, 该地图数据与现有的地图数据不同的是,该当前时刻的地图数据中包括为特殊路况的第一道路区域,且该第一道路区域是服务器根据上报的车辆参数和上述路况模型获取、且标注在地图中的。鉴于上报的车辆参数为多个车辆实时上报的海量的数据,因此可以提高获取的第一道路区域的准确性和实时性,且终端设备可以通过服务器实时获取最新的道路上的表征特殊路况的第一道路区域的信息。
在一种可能的设计中,终端设备可以根据当前时刻的地图数据进行车辆的驾驶应用。
一方面,在车辆行驶过程中,可以根据当前时刻的地图数据判断车辆的规划路线中是否存在特殊路况的第二道路区域。其中,下述分为两种可能的方式对车辆的规划路线中存在特殊路况的场景进行说明:
一种场景为:车辆为自动驾驶车辆,且车辆的规划路线中存在第二道路区域。鉴于自动驾驶车辆非用户自己驾驶,本申请实施例中可以生成驾驶指令(驾驶决策),以控制车辆的驾驶行为。其中,在车辆行驶至第二道路区域时,根据驾驶指令控制车辆行驶。或者,在车辆行驶至距离第二道路区域预设距离处时,可以根据驾驶指令控制车辆行驶,进而起到有效指导驾驶动作决策的目的。
其中,本申请实施例中可以根据当前时刻的地图数据生成驾驶指令。其中,地图数据还包括:所述第一道路区域的特殊路况的描述信息,所述描述信息用于描述所述特殊路况的场景类型。可选的,所述路况模型为多个,本申请实施例中可以将根据所述第二道路区域的特殊路况的描述信息,生成所述驾驶指令。具体的,可以将获取目标路况模型的历史的车辆参数的特征指示的驾驶行为作为驾驶指令,所述目标路况模型为确定所述第二道路区域为特殊路况的模型。
另一种场景为:车辆为非自动驾驶车辆,且车辆的规划路线中存在第二道路区域。鉴于非自动驾驶车辆是用户自己驾驶,本申请实施例中可以生成提醒信息,以提醒用户所述第二道路区域存在特殊路况,使得当所述车辆即将行驶至所述第二道路区域时,推送所述提醒信息,进而起到预先对特殊路况提醒的目的。
其中,本申请实施例中可以根据当前时刻的地图数据生成驾驶指令。其中,当前时刻的地图数据还包括:所述第一道路区域的特殊路况的描述信息和/或目标图像,所述描述信息用于描述所述特殊路况的场景类型,所述第一道路区域的目标图像为:所述车辆参数中包含有所述第一道路区域的特殊路况的图像。
可选的,本申请实施例中可以将所述第二道路区域的特殊路况的描述信息和/或目标图像作为所述提醒信息。具体的在当所述车辆即将行驶至所述第二道路区域时,播放所述第二道路区域的特殊路况的描述信息,和/或显示所述第二道路区域的特殊路况的目标图像。
另一方面,本申请实施例中还可以根据当前时刻的地图数据为车辆进行预设线路的规划。具体的,终端设备可以向服务器发送路线规划请求,以使得服务器获取规划路线,进而将规划路线发送给终端设备。其中,服务器在设计规划线路时可以避免规划包括有特殊路况的路线,可以避免车辆行驶至需要大量时间才能通过的特殊路况,提高了通行效率和用户体验。
在一种可能的设计中,终端设备的地图上显示每个所述第一道路区域的特殊路况的标识,且接收用户对任一个第一道路区域的特殊路况的标识的选择指令,显示用户选择的第一道路区域的特殊路况的描述信息。
在该种设计中,用户可以对地图中的任意一个特殊路况的信息进行查看,以便于用户可以主动选择行驶路线,提高了用户体验。
第二方面,提供一种特殊路况的识别方法,该方法应用于服务器,该方法包括:服务器根据路况模型和当前时刻之前的预设时间段内的车辆参数,获取所述当前时刻的第一道路区域,以及将在地图数据上标注所述第一道路区域或去掉已经失效的第一道路区域,得到所述当前时刻的地图数据。其中,所述第一道路区域为特殊路况所处的道路区域,所述路况模型用于表征车辆参数的 特征和特殊路况的对应关系。
本申请实施例中服务器可以周期性的根据上报的车辆参数对地图数据进行更新,以保证地图中的第一道路区域的实时性,进而能够使得终端设备可以实时获取最新的地图数据,以实现对特殊路况的预先识别和提醒。
在一种可能的设计中,为了减少服务器的数据处理量,本申请实施例中可以对该预设时间段内接收的至少一个车辆的车辆参数进行预处理,确定初始道路区域,进而将该初始道路区域对应的车辆参数作为上述当前时刻之前的预设时间段内的车辆参数。其中,本申请实施例中可以将与地图数据中车辆的位置处的道路的特征不匹配的车辆参数中的位置所在的区域,确定初始道路区域。对应的,将该与地图数据中车辆的位置处的道路的特征不匹配的车辆参数,作为当前时刻之前的预设时间段内的车辆参数。
应注意,本申请实施例中的路况模型是以多个历史的车辆参数为训练参数获取的。其中,所述历史的车辆参数为所述预设时间段之前接收到的、来自至少一个车辆的车辆参数。
在一种可能的设计中,鉴于经过不同的特殊路况所处的道路区域时,不同的车辆上报的车辆参数不同,因此本申请实施例中针对不同的特殊路况,可以训练不同的路况模型,以提高特殊路况识别的准确性。据此,本申请实施例中的所述路况模型为多个。
其中,在训练上述多个路况模型时,本申请实施例中可以将所述多个历史的车辆参数分成N个训练数据集,将每个训练数据集作为训练一个路况模型的训练数据,以得到所述至少一个路况模型,其中,每个训练数据集中的车辆参数的特征相同,N为大于1的整数。对应的,可以将所述当前时刻之前的预设时间段内的车辆参数输入至所述至少一个路况模型,得到所述第一道路区域。
上述的方法中根据至少一个路况模型和当前时刻之前的预设时间段内的车辆参数,可以得到特殊路况的所述第一道路区域的特征类型,但并不能确定第一道路区域的特殊路况的场景类型。在一种可能的设计中,可以结合上报的车辆参数中的车辆拍摄的图像或视频,确定第一道路区域的特殊路况的场景类型。
其中,可以获取所述第一道路区域的目标图像,所述第一道路区域的目标图像为:所述车辆参数中包含有所述第一道路区域的特殊路况的图像,所述目标图像为所述车辆拍摄的图像或视频中的一个视频帧。本申请实施例中,可以根据所述第一道路区域的目标图像,生成所述第一道路区域的特殊路况的描述信息,所述描述信息用于描述所述特殊路况的场景类型。具体的,生成所述第一道路区域的特殊路况的描述信息的方式可以为:本申请实施例中的服务器中可以预先存储有识别模型,识别模型用于表征图像的特征和特殊路况的场景类型的对应关系,即将图像输入至识别模型中,该识别模型可以识别图像是否为包含有特殊路况的像素块的图像,从而判定特殊路况的场景类型。进一步的,本申请实施例中可以在所述地图数据中添加所述第一道路区域的特殊路况的描述信息和/或目标图像。
在一种可能的设计中,本申请实施例中根据所述第一道路区域的特殊路况的描述信息表征的特殊路况的场景类型,确定所述第一道路区域的特殊路况的持续时间;在所述地图数据中添加所述第一道路区域的特殊路况持续时间。
在上述两种设计中,本申请实施例中可以根据车辆参数中的图像或视频,确定包含有特殊路况的目标图像,以生成特殊路况的描述信息,且还能够根据特殊路况的场景类型,确定特殊路况的持续时间,进而将这些信息添加至地图数据中,进而可以使得终端设备在获取当前时刻的地图数据后,可以生成驾驶决策、或提醒信息、或为车辆进行预设路线的规划。
与上述第一方面相对应的,在车辆的规划路线是由终端设备请求服务器获取的时,服务器可以接收到来自终端设备的路线规划请求,则根据起止点、以及所述第一道路区域的特殊路况的持续时间和所述第一道路区域的特殊路况的场景类型,获取规划路线,所述路线规划请求中包括所述起止点;向所述终端设备推送所述规划路线。
第三方面,提供一种特殊路况的识别装置,包括:
处理模块,用于获取当前时刻的地图数据,所述地图数据包括:所述当前时刻的第一道路区域,且根据车辆的规划路线,判断所述车辆的规划路线中是否存在第二道路区域,所述第二道路区域为所述第一道路区域中的道路区域,所述第一道路区域为特殊路况所处的道路区域,所述第一道路区域是由路况模型和所述当前时刻之前的预设时间段内的车辆参数获取的,所述路况模型用于表征车辆参数的特征和特殊路况的对应关系。
可选的,若所述车辆为自动驾驶车辆,所述处理模块,还用于若所述车辆的规划路线中存在所述第二道路区域,则生成驾驶指令,以及当所述车辆行驶至所述第二道路区域时,根据所述驾驶指令控制所述车辆行驶,所述驾驶指令用于指示所述车辆的驾驶行为。
可选的,所述路况模型为多个,所述地图数据还包括:所述第一道路区域的特殊路况的描述信息,所述描述信息用于描述所述特殊路况的场景类型。
对应的,所述处理模块,具体用于根据所述第二道路区域的特殊路况的描述信息,生成所述驾驶指令,所述驾驶指令指示的驾驶行为与获取目标路况模型的历史的车辆参数的特征指示的驾驶行为相同,所述目标路况模型为确定所述第二道路区域为特殊路况的模型。
可选的,所述车辆为非自动驾驶车辆,所述处理模块,还用于若所述车辆的规划路线中存在所述第二道路区域,则生成提醒信息,且当所述车辆即将行驶至所述第二道路区域时,推送所述提醒信息,所述提醒信息用于指示所述第二道路区域存在特殊路况。
可选的,所述地图数据还包括:所述第一道路区域的特殊路况的描述信息和/或目标图像,所述描述信息用于描述所述特殊路况的场景类型,所述第一道路区域的目标图像为:所述车辆参数中包含有所述第一道路区域的特殊路况的图像。
对应的,所述处理模块,具体用于将所述第二道路区域的特殊路况的描述信息和/或目标图像作为所述提醒信息。
所述播放模块,用于播放所述第二道路区域的特殊路况的描述信息;和/或,
所述显示模块,用于显示所述第二道路区域的特殊路况的目标图像。
可选的,所述地图数据还包括:所述第一道路区域的特殊路况的持续时间。
可选的,所述第一道路区域为多个。所述显示模块,还用于在地图上显示每个所述第一道路区域的特殊路况的标识。
收发模块,用于接收用户对任一个第一道路区域的特殊路况的标识的选择指令;对应的,所述显示模块,还用于显示用户选择的第一道路区域的特殊路况的描述信息。
可选的,所述收发模块,还用于向服务器发送路线规划请求,以及接收所述服务器发送的所述规划路线。
可选的,所述收发模块,还用于向服务器上报车辆参数,所述车辆参数包括车辆的位置、车辆拍摄的图像或视频,以及所述车辆的属性数据、行驶数据。
上述第三方面提供的特殊路况的识别装置,其有益效果可以参见上述第一方面以及各可能的设计中所带来的有益效果,在此不加赘述。
第四方面,提供一种特殊路况的识别装置,包括:
处理模块,用于根据路况模型和当前时刻之前的预设时间段内的车辆参数,获取所述当前时刻的第一道路区域,且在地图数据上标注所述第一道路区域,得到所述当前时刻的地图数据,所述第一道路区域为特殊路况所处的道路区域,所述路况模型用于表征车辆参数的特征和特殊路况的对应关系。
可选的,所述车辆参数包括车辆的位置。
收发模块,用于在所述预设时间段内,接收至少一个车辆上报的车辆参数。
对应的,所述处理模块,还用于根据所述至少一个车辆的车辆参数,确定所述当前时刻之前的预设时间段内的车辆参数,所述当前时刻之前的预设时间段内的车辆参数为:与所述地图数据中所述车辆的位置处的道路的特征不匹配的车辆参数。
可选的,所述处理模块,还用于以多个历史的车辆参数为训练参数,获取所述路况模型,所述历史的车辆参数为所述预设时间段之前接收到的、来自至少一个车辆的车辆参数。
可选的,所述路况模型为多个。
所述处理模块,具体用于将所述多个历史的车辆参数分成N个训练数据集,将每个训练数据集作为训练一个路况模型的训练数据,以得到所述至少一个路况模型,其中,每个训练数据集中的车辆参数的特征相同,N为大于1的整数;。
可选的,所述处理模块,具体用于将所述当前时刻之前的预设时间段内的车辆参数输入至所述至少一个路况模型,得到所述第一道路区域。
可选的,所述车辆参数包括:车辆拍摄的图像或视频。
所述处理模块,还用于获取所述第一道路区域的目标图像,且根据所述第一道路区域的目标图像,生成所述第一道路区域的特殊路况的描述信息,以及在所述地图数据中添加所述第一道路区域的特殊路况的描述信息和/或目标图像,所述第一道路区域的目标图像为:所述车辆参数中包含有所述第一道路区域的特殊路况的图像,所述目标图像为所述车辆拍摄的图像或视频中的一个视频帧,所述描述信息用于描述所述特殊路况的场景类型。
可选的,所述处理模块,还用于根据所述第一道路区域的特殊路况的描述信息表征的特殊路况的场景类型,确定所述第一道路区域的特殊路况的持续时间,以及在所述地图数据中添加所述第一道路区域的特殊路况持续时间。
可选的,所述处理模块,还用于若接收到来自终端设备的路线规划请求,则根据起止点、以及所述第一道路区域的特殊路况的持续时间和所述第一道路区域的特殊路况的场景类型,获取规划路线,所述路线规划请求中包括所述起止点;
所述收发模块,还用于向所述终端设备推送所述规划路线。
可选的,所述车辆参数包括车辆的属性数据、行驶数据。
上述第四方面提供的特殊路况的识别装置,其有益效果可以参见上述第二方面以及各可能的设计中所带来的有益效果,在此不加赘述。
第五方面,提供一种电子设备,包括:处理器、存储器、收发器;所述收发器耦合至所述处理器,所述处理器控制所述收发器的收发动作,处理器执行上述第三方面或第四方面的处理模块执行的动作,收发器执行上述第三方面或第四方面的收发模块执行的动作。
其中,存储器用于存储计算机可执行程序代码,程序代码包括指令;当处理器执行指令时,指令使所述终端设备执行如第一方面或第二方面所提供的方法。
第六方面,提供一种包含指令的计算机程序产品,当其在计算机上运行时,使得计算机执行上述第一方面或第二方面的方法。
第七方面,提供一种计算机可读存储介质,所述计算机可读存储介质中存储有指令,当其在计算机上运行时,使得计算机执行上述第一方面或第二方面的方法。
本申请实施例提供一种特殊路况的识别方法、装置、电子设备和存储介质,服务器能够根据上报的海量的车辆参数,确定特殊路况所处的第一道路区域,进而更新地图数据,获取当前时刻的地图数据。应理解,该当前时刻的地图数据中包括第一道路区域,终端设备在获取当前时刻的地图数据后可以识别车辆的规划线路中是否包含有特殊路况,以预先对规划路线中的特殊路况进行识别,能够提高对特殊路况识别的实时性。
附图说明
图1为本申请实施例提供的特殊路况的识别方法适用的场景示意图;
图2为本申请实施例提供的特殊路况的识别方法的流程示意图一;
图3为本申请实施例提供的地图的示意图一;
图4为本申请实施例提供的地图的示意图二;
图5为本申请实施例提供的特殊路况的识别方法的流程示意图二;
图6为本申请实施例提供的获取路况模型的流程示意图;
图7为本申请实施例提供的终端设备的界面变化示意图一;
图8为本申请实施例提供的终端设备的界面变化示意图二;
图9为本申请实施例提供的特殊路况识别的装置的结构示意图一;
图10为本申请实施例提供的特殊路况识别的装置的结构示意图二;
图11为本申请实施例提供的电子设备的结构示意图一;
图12为本申请实施例提供的电子设备的结构示意图二。
具体实施方式
目前,车辆在行驶过程中对特殊路况的识别主要依据导航提示,车辆上辅助驾驶的传感器的识别,或者用户识别。但现有的导航中仅能够对道路施工、交通拥堵等类型的特殊路况进行提示,不能对井盖缺失、井盖不平、道路凹陷坑洼、道路积水、高度较大的减速带、车道或路段临时封闭、发生交通事故等特殊路况进行提示,因此导航提示的特殊路况的类型不全面。且导航对于突发的特殊路况不能进行提示,如某一车道上突发性出现障碍 物、发生车祸或出现泥石流等不能进行及时提示,实时性低。对于采用辅助驾驶的传感器识别特殊路况的方式,辅助驾驶的传感器是依靠激光雷达来识别道路上存在障碍物的特殊路况,对于道路凹陷坑洼、井盖缺失、道路积水等特殊路况无法识别,因此辅助驾驶的传感器识别的特殊路况的类型也不全面。用户识别特殊路况,需要依靠用户的驾驶经验,用户粗心或者反应慢均会导致无法对特殊路况进行识别和避让。应理解,本申请实施例中的特殊路况可以包括:井盖缺失、井盖不平、道路凹陷坑洼、道路积水、高度较大的减速带、车道封闭施工、车道或路段临时封闭、发生交通事故、堵车等。
为了解决上述问题,现有技术中提供了一种采用车辆在行驶过程中采集的图像识别特殊路况的方法。其中,车辆根据行驶过程中采集的图像与预先设置的各种特殊路况的图像进行比对识别,在确定采集的图像中包括特殊路况时对用户进行提醒。但该方法存在实时性不高的问题,车辆的行驶速度较大,在采集图像以及识别出图像中包含有特殊路况时该车辆可能已经高速行驶过了该特殊路况,不能及时地进行提醒。另,该方法依靠车辆采集的单张图像识别特殊路况,还存在识别准确性低的问题。
为了解决上述识别特殊路况准确性低的问题,现有技术中服务器可以通过接收用户上传的特殊路况的图像和特殊路况的位置,进而向经过该特殊路况的位置的车辆进行提醒。但该方法仍然存在实时性不高的问题,且若特殊路况的图像没有用户上传,则服务器不能对特殊路况进行提醒。
近年来,随着车联网技术和通信技术的发展,车辆可以实时上报车辆参数至车联网云端服务器。在此基础上,为了解决现有技术中的问题,本申请实施例提供一种特殊路况的识别方法,通过车辆实时上报的海量的车辆参数,识别各类型的特殊路况且标注在地图上,进而实时地对行驶车辆进行提醒。鉴于本申请实施例中采用实时的、海量的车辆在行驶过程中上报的车辆参数对特殊路况进行识别,可以保证特殊路况的识别准确性和实时性,从而支持提醒的实时性。
图1为本申请实施例提供的特殊路况的识别方法适用的场景示意图。如图1所示,该场景中包括:终端设备和服务器。终端设备通过无线的方式与服务器相连。其中,服务器可以为车联网云端服务器。终端设备可以为车辆、或车辆中的车载终端等。
下面结合具体的实施例对本申请提供的特殊路况的识别方法进行说明。下面这几个实施例可以相互结合,对于相同或相似的概念或过程可能在某些实施例不再赘述。
图2中以服务器和终端设备交互的角度对本申请实施例提供的特殊路况的识别方法进行说明。图2为本申请实施例提供的特殊路况的识别方法的流程示意图一。如图2所示,本申请实施例提供的特殊路况的识别方法可以包括:
S201,服务器根据路况模型和当前时刻之前的预设时间段内的车辆参数,获取当前时刻的第一道路区域,第一道路区域为特殊路况所处的道路区域,路况模型用于表征车辆参数的特征和特殊路况的对应关系。
S202,服务器在地图数据上标注第一道路区域,得到当前时刻的地图数据。
S203,终端设备获取当前时刻的地图数据。
S204,终端设备根据车辆的规划路线,判断车辆的规划路线中是否存在第二道路区域,第二道路区域为第一道路区域中的道路区域。
上述S201中,路况模型用于表征车辆参数的 特征和特殊路况的对应关系,即将车辆 参数输入至路况模型中,路况模型可以基于一段时间内某个路段区域的车辆参数识别出该路段区域是否存在特殊路况。可选的,本申请实施例中的路况模型是根据历史获取的车辆参数采用聚类算法,或者机器学习等AI算法获取的。其中,AI算法可以为决策树、随机森林、逻辑回归、支持向量机、朴素贝叶斯或神经网络等算法。本申请实施例中对获取路况模型采用的AI算法的类型不做限制。
当前时刻之前的预设时间段为预定义的时间段,本申请实施例中为了保证获取的特殊路况的实时性,可以周期性的采用当前时刻之前的预设时间段的车辆参数获取特殊路况所处的道路区域。示例性的,如当前时刻为8:00,则当前时刻之前的预设时间段内的车辆参数可以为7:50-8:00该时间段内的车辆参数。可以采用该7:50-8:00该时间段内的车辆参数输入至路况模型中,获取8:00的特殊路况所处的道路区域。
本申请实施例中的当前时刻之前的预设时间段的车辆参数可以为:在当前时刻之前的预设时间段内车辆上报至服务器的车辆参数。应理解,车辆在行驶的过程中可以周期性上报车辆参数。车辆参数包括车辆的动态参数和静态参数。其中,车辆的动态参数包括车辆的位置、车辆拍摄的图像或视频,以及车辆的行驶数据,车辆的行驶数据可以为车辆的速度、加速度,以及转向、刹车等驾驶动作。车辆的静态参数为车辆的属性数据。车辆的属性数据可以包括车辆的重量、长宽高、减震性等数据。值得注意的是,车辆在第一次上报车辆参数时,上报车辆的动态参数和静态参数,在后续上报车辆参数时上报动态参数。
本申请实施例中将当前时刻的特殊路况所处的道路区域作为第一道路区域。第一道路区域为车道级别的道路区域。示例性的,如特殊路况为堵车,则第一道路区域可以为XX路至XX路之间的三个车道。如特殊路况为井盖缺失,则第一道路区域可以为XX路上左侧车道的区域。
应理解,上述的“当前时刻之前的预设时间段内的车辆参数”可以为在预设时间段内,至少一个车辆上报的车辆参数。
可选的,为了减少路况模型的数据处理量,本申请实施例中可以对该预设时间段内接收的至少一个车辆的车辆参数进行预处理,确定初始道路区域,进而将该初始道路区域对应的车辆参数作为上述当前时刻之前的预设时间段内的车辆参数。其中,初始道路区域为初步确定的为特殊路况所处的道路区域,初始道路区域对应的车辆参数为:预设时间段内接收的至少一个车辆的车辆参数中的车辆位置在初始道路区域内的车辆参数。示例性的,根据预设时间段内接收的N个车辆的车辆参数,确定区域1为初始道路区域,进而在N个车辆的车辆参数中获取车辆的位置在区域1内的车辆参数,作为上述当前时刻之前的预设时间段内的车辆参数,即输入路况模型的车辆参数。
其中,本申请实施例中可以将与地图数据中车辆的位置处的道路的特征不匹配的车辆参数中的位置所在的区域,确定初始道路区域。对应的,将该与地图数据中车辆的位置处的道路的特征不匹配的车辆参数,作为当前时刻之前的预设时间段内的车辆参数。示例性的,若地图数据中区域1内的道路的特征为直行车道、最低车速为60Km/h,而根据车辆参数,确定该区域1内车辆上报的车辆参数中车速为10Km/h、0Km/h等,则可以确定该区域1内的车辆参数与区域1内道路的特征不匹配,则该区域1内可能存在特殊路况,如堵车,则可以将区域1作为初始道路区域,进而将车辆的位置处于区域1内的车辆参数作为当前时刻之前的预设时间段内的车辆参数。
上述S202中,本申请实施例中可以在地图数据上标注第一道路区域,对地图数据进行更新,得到当前时刻的地图数据。应理解,在地图数据上标注第一道路区域可以为:在地图上第一道路区域对应的位置上标注特殊路况,进而可以得到更新得到的当前时刻的地图数据上标注有第一道路区域。
图3为本申请实施例提供的地图的示意图一。如图1所示,该地图上在3个位置(如A、B和C)标注有第一道路区域。其中,图3以“感叹号”的形式示例性地表征第一道路区域。
应注意,本申请实施例中还可以对特殊路况的消除进行地图数据的更新。示例性的,如上述地图数据中区域1内的道路的特征为直行车道、车速为小于60Km/h,而上一时刻的区域1内车辆上报的车辆参数中车速为10Km/h、0Km/h等,则在上一时刻地图数据中标注区域1为第一道路区域。而根据当前时刻的预设时间段内的车辆参数,确定该区域1内车辆上报的车辆参数中车速最低为60Km/h等,则还可以确定该区域1内上一时刻的特殊路况消失,则可以对地图数据进行更新,获取当前时刻的地图数据。其中,对地图数据进行更新的具体方式为:在地图上将标注为第一道路区域的区域1删除。
图4为本申请实施例提供的地图的示意图二。与图3比对,图4中的位置A处的特殊路况消除,则得到更新的当前时刻的地图如图4所示,图4中在位置B和位置C处标注有第一道路区域。
上述S203中,终端设备可以在服务器中获取当前时刻的地图数据。可选的,终端设备中安装有显示地图的应用程序,如导航应用程序,自动驾驶地图应用程序等。终端设备可以获取当前时刻的地图数据,以更新终端设备应用程序中的地图数据。
上述S204中,依据上述S203,终端设备可以获取当前时刻的地图数据,进而可以使得自动驾驶车辆能够预先获取第一道路区域。对应的,终端设备可以显示地图中的第一道路区域,使得用户能够获知第一道路区域。也就是说,本申请实施例中,自动驾驶车辆或非自动驾驶车辆,均可以根据当前时刻的地图数据,预先获取第一道路区域,解决了现有技术中的实时性的问题。
本申请实施例中,若车辆正在按照规划线路行驶,则终端设备可以根据车辆的规划路线,判断车辆的规划路线中是否存在第二道路区域,即可以预先对规划路线中的特殊路况进行识别。其中,第二道路区域为第一道路区域中的道路区域,也就是说本申请实施例中可以预先判断车辆的规划路线中是否存在特殊路况所处的道路区域。若在车辆的规划路线中存在第二道路区域,则可以预先进行驾驶决策(对自动驾驶车辆而言,具体可见下述实施例中的S508)或预先提醒(对非自动驾驶车辆而言),进而实现及时地提醒。
本申请实施例中的规划线路可以是终端设备根据用户输入的起止点获取的,也可以是终端设备请求服务器获取的。
本申请实施例中,服务器根据上报的车辆参数和路况模型,获取当前时刻的特殊路况所处的区域,即第一道路区域,以对地图数据进行更新,得到当前时刻的地图数据,该当前时刻的地图数据中包括第一道路区域。对应的,终端设备在服务器获取当前时刻的地图数据后,可以识别车辆的规划线路中是否包含有特殊路况,以预先对规划路线中的特殊路况进行识别,能够提高对特殊路况识别的实时性。
在上述实施例的基础上,图5为本申请实施例提供的特殊路况的识别方法的流程示意图二。如图5所示,本申请实施例提供的特殊路况的识别方法可以包括:
S501,服务器将当前时刻之前的预设时间段内的车辆参数输入至少一个路况模型,得到第一道路区域。
S502,服务器获取第一道路区域的目标图像,第一道路区域的目标图像为:车辆参数中包含有第一道路区域的特殊路况的图像,目标图像为车辆拍摄的图像或视频中的一个视频帧。
S503,服务器根据第一道路区域的目标图像,生成第一道路区域的特殊路况的描述信息,描述信息用于描述特殊路况的场景类型。
S504,服务器根据第一道路区域的特殊路况的描述信息表征的特殊路况的场景类型,确定第一道路区域的特殊路况的持续时间。
S505,服务器在地图数据上标注第一道路区域,且在地图数据中添加第一道路区域的特殊路况的描述信息和/或目标图像,以及第一道路区域的特殊路况持续时间,得到当前时刻的地图数据。
S506,终端设备获取当前时刻的地图数据。
S507,终端设备根据车辆的规划路线,判断车辆的规划路线中是否存在第二道路区域。
S508,若车辆为自动驾驶车辆,且车辆的规划路线中存在第二道路区域,则终端设备生成驾驶指令,驾驶指令用于指示车辆的驾驶行为。
S509,当车辆行驶至第二道路区域时,终端设备根据驾驶指令控制车辆行驶。
S510,若车辆为非自动驾驶车辆,且车辆的规划路线中存在第二道路区域,则终端设备生成提醒信息,提醒信息用于指示第二道路区域存在特殊路况。
S511,当车辆即将行驶至第二道路区域时,终端设备推送提醒信息。
在上述S501中,本申请实施例中的路况模型为多个。其中,每个路况模型用于识别不同特征的车辆参数为特殊路况对应的车辆参数。示例性的,路况模型1用于识别缺井盖的特殊路况,路况模型2用于识别道路不通的特殊路况,路况模型3用于识别车辆打滑的特殊路况。
鉴于经过不同的特殊路况所处的道路区域时,不同的车辆上报的车辆参数不同,因此针对不同的特殊路况,可以训练不同的路况模型,以提高特殊路况识别的准确性。本申请实施例中可以将当前时刻之前的预设时间段内的车辆参数输入至少一个路况模型,得到第一道路区域。对于一个车辆参数而言,其输入至路况模型1,路况模型1输出的结果可以为车辆参数并非特殊路况对应的车辆参数,但其输入至路况模型2,路况模型2输出的结果可能为车辆参数为特殊路况对应的车辆参数,进而可以判定该车辆参数为道路不通对应的车辆参数。
应理解,本申请实施例中获取第一道路区域的方式可以为:根据至少一个路况模型,可以得到输出为特殊路况对应的车辆参数的车辆参数,鉴于车辆参数中包括车辆的位置,本申请实施例中可以将包括预设数量个特殊路况对应的车辆参数的区域作为第一道路区域。示例性的,如区域1内,10个车辆上报的车辆参数均被确定为是特殊路况对应的车辆参数,则可以将该区域1作为第一道路区域。
或者,本申请实施例中获取第一道路区域的方式还可以为:可以将当前时刻之前的预 设时间段内的车辆参数输入至少一个路况模型中,即可获取为特殊路况的第一道路区域,不用经过上述特殊路况对应的车辆参数的车辆参数的分析过程。
本申请实施例中可以以多个历史的车辆参数为训练参数,获取路况模型。其中,历史的车辆参数为预设时间段之前接收到的、来自至少一个车辆的车辆参数。下面结合图6对获取路况模型的方法进行具体说明。图6为本申请实施例提供的获取路况模型的流程示意图。如图6所示,本申请实施例中获取路况模型的方法包括:
S601,将所述多个历史的车辆参数分成N个训练数据集。
每个历史的车辆参数中可以包括车辆的位置、车辆的拍摄的图像或视频,以及车辆的属性数据、行驶数据。其中,属性数据、行驶数据具体可以参照上述S201中的相关描述。其中,每个训练数据集中的车辆参数的特征相同,N为大于或等于1的整数。
本申请实施例中,可以预先获取不同特征类型的特殊路况。不同特征类型的特殊路况可以为影响车辆产生不同的车辆参数的特征。如特殊路况的特征类型为:道路不通、缺井盖、道路结冰、减速带等。
鉴于车辆在遇到不同特征类型的特殊路况时的车辆参数不同,因此本申请实施例中可以根据历史的车辆参数的特征,分成N个训练数据集。其中,每个训练数据集中的车辆参数的特征相同,即每个训练数据集中的车辆参数均是由一种特征类型的特殊路况影响生成的。示例性的,如道路不通影响生成的车辆参数的特征可以为:减速后右转弯、或者减速后左转弯、减速后掉头等。减速带影响生成的车辆参数的特征可以为:减速后车身震动等。
另,本申请实施例中还可以对减速、车身震动和拐弯等区分程度,以确定历史的车辆参数对应的特殊路况的特征类型,以划分历史的车辆参数所在的训练数据集。其中,减速可以包括缓慢减速、急减速等,车身震动可以包括车身震动为小幅度震动、大幅度震动(如可以车身震动幅度离散成不同的整数值,如0-10实现幅度划分)等,拐弯可以包括急拐弯和缓慢拐弯等。
S602,将每个训练数据集作为训练一个路况模型的训练数据,以得到所述至少一个路况模型。
本申请实施例中,可以以每个训练数据集作为训练一个路况模型的训练数据,训练一个路况模型,进而对N个训练数据集训练,以得到至少一个路况模型。
其中,在对一个训练数据集进行训练得到路况模型时,可以该训练数据集中的车辆参数打标签,进而对打标签后的训练数据集作为训练一个路况模型的训练数据,训练一个路况模型。对应的,本申请实施例中对N个训练数据集进行训练,可以获取N个(即至少一下个)路况模型。应理解,对车辆参数进行打标签,例如,将车辆参数中减速部分对应的车辆参数的标识为“减速”,将左转弯部分对应的车辆参数的标识为“左转弯”。
应理解,上述S201中讲述了可以采用路况模型获取第一道路区域,应理解,上述实施例中的路况模型可以为一个综合本申请实施例中的至少一个路况模型的模型,进而能够实现对不同特征的车辆参数进行特殊路况的识别。
上述S502中,依据上述S501在得到第一道路区域后,可以得到特殊路况的所述第一道路区域的特征类型,但并不能确定第一道路区域的特殊路况的场景类型。示例性的,上述特殊路况的特征类型如:“道路不通”、“道路颠簸”、“道路拥堵”。但并不能确定特殊路况的场景类型,如“车祸引起的道路不通”、“道路积水引起的道路不通”。
据此,本申请实施例中还可以基于车辆参数获取第一道路区域的特殊路况的场景类型,以获取更为详细的第一道路区域的特殊路况的信息。其中,车辆上报的车辆参数中包括车辆拍摄的图像或视频,本申请实施例中可以根据第一道路区域,以及车辆参数中的车辆的位置,获取车辆在第一道路区域内上报的车辆参数,进而在该第一道路区域内上报的车辆参数中获取车辆拍摄的图像或视频。为了便于说明,下述描述中将在该第一道路区域内上报的车辆参数称为目标车辆参数。
本申请实施例中可以在目标车辆参数中获取第一道路区域的目标图像。应理解,目标车辆参数可以为多个,对应的,目标车辆参数中的图像或视频也为多个。其中,在目标车辆参数中获取目标图像的方式可以为:将包含有第一道路区域的特殊路况的图像或视频帧作为待选图像,进而在待选图像中获取目标图像。应理解,目标车辆参数中的视频可以包括多个视频帧。
可选的,本申请实施例中的服务器中可以预先存储有识别模型,识别模型用于表征图像的特征和特殊路况的场景类型的对应关系,即将图像输入至识别模型中,该识别模型可以识别图像是否为包含有特殊路况的像素块的图像,从而判定特殊路况的场景类型。本申请实施例中可以将目标车辆参数中的图像或视频帧输入至识别模型,将包含有特殊路况的图像或视频帧作为待选图像。进一步的,该识别模型还可以输出待选图像相似度,以表征待选图像中包含有特殊路况的准确度。本申请实施例中可以在待选图像中,根据图像清晰度、相似度确定目标图像,如将图像清晰度最高的待选图像作为目标图像,或者将相似度最高的待选图像作为目标图像。
应理解,本申请实施例中的识别模型可以是以多种类型的包含有特殊路况的图像作为训练数据集,采用机器学习的方式训练得到的。其中,训练识别模型的机器学习方法可以与上述训练路况模型的方法相同。
上述S503中,本申请实施例中的特殊路况的描述信息用于描述特殊路况的场景类型。如特殊路况的场景类型可以为堵车、井盖缺失、井盖不平等。
本申请实施例中可以根据第一道路区域的目标图像,确定第一道路区域的特殊路况的类型,以根据第一道路区域的特殊路况的场景类型,生成第一道路区域的特殊路况的描述信息。示例性的,第一道路区域的特殊路况的类型为井盖缺失,则第一道路区域的特殊路况的描述信息可以为对第一道路区域的特殊路况的场景类型的细致描述,如第一道路区域的特殊路况的描述信息可以为:XX路的东行方向左侧第一车道井盖缺失。
其中,本申请实施例中确定第一道路区域的特殊路况的类型的一种方式可以为:上述的识别模型用于表征图像的特征和特殊路况的场景类型的对应关系,即将图像输入至识别模型,即可以获取图像中的特殊路况的场景类型。
其中,确定第一道路区域的特殊路况的类型的另一种方式可以为:识别模型可以为多个。其中,每个识别模型用于表征一种场景类型的特殊路况与图像的特征的对应关系。本申请实施例中可以将目标车辆参数中的图像或视频帧输入至多个识别模型,输入图像为特殊路况的识别模型表征的特殊路况的场景类型即为图像中包含的特殊路况的场景类型。示例性的,如识别模型1用于表征井盖缺失与图像的特征的对应关系,即用于识别包含有井盖缺失的图像;识别模型2用于表征堵车与图像的特征的对应关系,即识别包含有堵车的图像;识别模型3用于表征减速带与图像的特征的对应关系,即用于识别包含有减速带的 图像。
该种方式中,在训练每个识别模型时采用的机器学习方法可以与上述训练识别模型的方法相同。但应注意,训练每个识别模型与上述训练识别模型的训练数据不同。该方法中训练每个识别模型时的训练数据为包含有相同场景类型的特殊路况的图像,而上述训练识别模型的训练数据为包含有各种场景类型的特殊路况的图像。示例性的,本申请实施例中训练识别模型1的训练数据可以为包含有井盖缺失的多个图像。
上述S504中,第一道路区域的特殊路况的持续时间,指的是第一道路区域从当前时刻至消除的时间。应理解,该第一道路区域的特殊路况的持续时间可以为根据大数据进行统计的经验均值确定,也可以指从特殊路况出现到消除的时间。本申请实施例可以根据第一道路区域的特殊路况的场景类型,确定第一道路区域的特殊路况的持续时间。可选的,服务器中存储有每种场景类型的特殊路况的持续时间的经验值,该经验值可以为用户(技术人员)输入的,或者服务器根据历史的特殊路况的持续时间获取的。示例性的,如服务器可以将历史的特殊路况的持续时间的均值、最大值或最小值,作为与历史的特殊路况的场景类型相同的特殊路况的持续时间。示例性的,如特殊路况为井盖缺失的持续时间为1天,特殊路况为泥石流的持续时间为4小时等。
上述S505中,本申请实施例在获取第一道路区域,以及第一道路区域的特殊路况的描述信息和/或目标图像、第一道路区域的特殊路况持续时间后,可以将在地图数据上标注第一道路区域,且在地图数据中添加第一道路区域的特殊路况的描述信息和/或目标图像,以及第一道路区域的特殊路况持续时间。也就是说,当前的地图数据中包括第一道路区域,以及第一道路区域的特殊路况的描述信息和/或目标图像、第一道路区域的特殊路况持续时间。
应理解,本申请实施例中的S506-S507中的实施方式可以参照上述实施例中S203-S204中的相关描述,在此不做赘述。
上述S508中,若车辆为自动驾驶车辆,且车辆的规划路线中存在第二道路区域,则本申请实施例中可以为自动驾驶车辆生成驾驶决策,即驾驶指令,该驾驶指令用于指示车辆的驾驶行为。示例性的,如驾驶指令可以为指示车辆减速且右拐,或者减速等指令。
鉴于本申请实施例中的路况模型为多个,且地图数据还包括第一道路区域的特殊路况的描述信息,本申请实施例中可以根据第二道路区域的特殊路况的描述信息,生成驾驶指令。应理解,驾驶指令指示的驾驶行为与获取目标路况模型的历史的车辆参数的特征指示的驾驶行为相同,目标路况模型为确定第二道路区域为特殊路况的模型。也就是说,本申请实施例中将输入第二道路区域为特殊路况的模型作为目标路况模型,且将训练该目标路况模型的历史的车辆参数的特征指示的驾驶行为作为驾驶指令。示例性的,第二道路区域为井盖缺失,输出第二道路区域为特殊路况的模型为路况模型2,而训练路况模型2的历史的车辆参数的特征为先减速后右拐,则可以将先减速后右拐作为第二道路区域的驾驶指令。
上述S509中,在自动驾驶车辆行驶至第二道路区域时,终端设备根据驾驶指令控制车辆行驶。具体的,本申请实施例中,上述S508中可以预先生成自动驾驶车辆在第道路区域的驾驶指令,可以对自动驾驶车辆进行预先提醒,以使自动驾驶车辆在行驶至第二道路区域时,可以根据驾驶指令行驶。示例性的,如第二道路区域的驾驶指令为先减速后右 拐,则自动驾驶车辆在行驶至第二道路区域时可以先减速后右拐。
可选的,为了进一步提高自动驾驶车辆的安全性,本申请实施例中还可以在自动驾驶车辆行驶至第二道路区域前预设距离处,执行该驾驶指令。示例性的,如在距离第二道路区域还有1米时先减速后右拐。
上述S510中,若车辆为非自动驾驶车辆,且车辆的规划路线中存在第二道路区域,则本申请实施例中可以生成提醒信息,以对驾驶车辆的用户进行提醒。鉴于地图数据还包括第一道路区域的特殊路况的描述信息和/或目标图像,本申请实施例中生成的提醒信息中可以将第二道路区域的特殊路况的描述信息和/或目标图像作为提醒信息。
上述S511中,为了预先对第二道路区域的特殊路况进行提醒,可以在当车辆即将行驶至第二道路区域时,终端设备推送提醒信息。具体的,推送提醒信息的方式可以为播放第二道路区域的特殊路况的描述信息,和/或显示第二道路区域的特殊路况的目标图像。
示例性的,如第一道路区域的特殊路况的场景类型为井盖缺失,第一道路区域的特殊路况的描述信息可以为:XX路的东行方向左侧第一车道井盖缺失。本申请实施例可以在当车辆即将行驶至第二道路区域(如在距离第二道路区域还有预设距离)时,播放“XX路的东行方向左侧第一车道井盖缺失”的提醒信息,以及在终端设备的显示屏幕上显示第二道路区域的特殊路况的目标图像。
图7为本申请实施例提供的终端设备的界面变化示意图一。如图7中的界面701所示,该界面701上显示为车辆的导航界面,在车辆即将行驶至第二道路区域时,界面701可以跳转至界面702,该界面702上显示有第二道路区域的特殊路况的目标图像。示例性的,如界面702上显示的为第二道路区域处“井盖缺失”的图像。应理解,本申请实施例中以终端设备为车载终端为例进行说明。
可选的,本申请实施例中的第一道路区域为多个,且还可以在地图上显示每个第一道路区域的特殊路况的标识。图8为本申请实施例提供的终端设备的界面变化示意图二。如图8中的界面801所示,该界面801在界面701显示的车辆的导航界面上显示有第一道路区域的特殊路况的标识。
示例性的,第一道路区域的特殊路况的标识可以相同,如均为感叹号的图标。或者第一道路区域的特殊路况的标识可以表征第一道路区域的特殊路况的场景类型。如图8界面801所示,第一道路区域的特殊路况包括井盖缺失、井盖不平和泥石流时,可以在地图的第一道路区域对应的位置上显示有对应的标识。如位置A处标注有表征井盖缺失的标识1,在位置B处标注有表征井盖不平的标识2,在位置C处标注有表征井盖缺失的标识3。
本申请实施例中,在终端设备接收用户对任一个第一道路区域的特殊路况的标识的选择指令,显示用户选择的第一道路区域的特殊路况的描述信息,以使用户获取选择的第一道路区域的特殊路况的场景类型。示例性的,如用户以点击的方式选择标识1,则上述界面801跳转至界面802,该界面802上显示有位置A处的特殊路况的描述信息,如:XX路的东行方向左侧第一车道井盖缺失。
应理解,上述S508-S509和S510-S511是择一执行的步骤。应理解,S508-S509是车辆为自动驾驶车辆时执行的步骤,S510-S511是车辆为非自动驾驶车辆时执行的步骤。
其中,上述S507-S511为车辆在行驶的过程中的场景。在该场景下,鉴于地图数据还包括:第一道路区域的特殊路况的持续时间,若车辆的规划路线中存在第二道路区域,且 第二道路区域的特殊路况的场景类型为预设场景类型,以及车辆行驶至第二道路区域的时间小于第二道路区域的特殊路况的持续时间,则可以请求服务器更新车辆的规划路线,得到更新后的规划路线。可选的,预设场景类型为预先约定的场景类型,可以为车辆不能快速通过的特殊路况的场景类型,如堵车、泥石流等。
示例性的,若车辆的规划路线中存在第二道路区域,且第二道路区域的特殊路况的场景类型为泥石流,且车辆行驶至第二道路区域的时间需要30分钟,而该第二道路区域的泥石流的持续时间为4小时,则可以请求服务器更新车辆的规划路线,以避免该第二道路区域,得到更新后的规划路线,进而在终端设备上显示更新后的规划路线。可选的,还可以在终端设备上显示更新规划路线的原因,如“前方有泥石流,已为您更新路线”的文字提醒信息。
上述的车辆的规划路线可以为终端设备请求服务器获取的。其中,终端设备在接收到用户输入的路线规划请求时,可以将该路线规划请求发送给服务器。在服务器接收到来自终端设备的路线规划请求,可以根据起止点、以及第一道路区域的特殊路况的持续时间和第一道路区域的特殊路况的场景类型,获取规划路线。其中,服务器在设计规划线路时可以避免规划包括有预设场景类型的特殊路况的路线。
本申请实施例中的路况模型是由历史的海量车辆参数经训练后得到的,因此采用该路况模型对当前时刻的第一道路区域进行识别具有较高的准确性。且本申请实施例中,终端设备可以根据当前的地图数据,可以预先生成驾驶决策或提醒信息,以对自动驾驶车辆和非自动驾驶车辆进行预先提醒,提高了用户体验。另终端设备还可以根据当前的地图数据对预先规划的预设线路进行更新,或者为车辆设置预设线路,能够进一步提高用户体验。
图9为本申请实施例提供的特殊路况识别的装置的结构示意图一。如图9所示,该特殊路况识别的装置可以为上述实施例中的终端设备。其中,特殊路况识别的装置900中包括:处理模块901、播放模块902、显示模块903和收发模块904。
处理模块901,用于获取当前时刻的地图数据,所述地图数据包括:所述当前时刻的第一道路区域,且根据车辆的规划路线,判断所述车辆的规划路线中是否存在第二道路区域,所述第二道路区域为所述第一道路区域中的道路区域,所述第一道路区域为特殊路况所处的道路区域,所述第一道路区域是由路况模型和所述当前时刻之前的预设时间段内的车辆参数获取的,所述路况模型用于表征车辆参数的特征和特殊路况的对应关系。
可选的,若所述车辆为自动驾驶车辆,所述处理模块901,还用于若所述车辆的规划路线中存在所述第二道路区域,则生成驾驶指令,以及当所述车辆行驶至所述第二道路区域时,根据所述驾驶指令控制所述车辆行驶,所述驾驶指令用于指示所述车辆的驾驶行为。
可选的,所述路况模型为多个,所述地图数据还包括:所述第一道路区域的特殊路况的描述信息,所述描述信息用于描述所述特殊路况的场景类型。
对应的,所述处理模块901,具体用于根据所述第二道路区域的特殊路况的描述信息,生成所述驾驶指令,所述驾驶指令指示的驾驶行为与获取目标路况模型的历史的车辆参数的特征指示的驾驶行为相同,所述目标路况模型为确定所述第二道路区域为特殊路况的模型。
可选的,所述车辆为非自动驾驶车辆,所述处理模块901,还用于若所述车辆的规划 路线中存在所述第二道路区域,则生成提醒信息,且当所述车辆即将行驶至所述第二道路区域时,推送所述提醒信息,所述提醒信息用于指示所述第二道路区域存在特殊路况。
可选的,所述地图数据还包括:所述第一道路区域的特殊路况的描述信息和/或目标图像,所述描述信息用于描述所述特殊路况的场景类型,所述第一道路区域的目标图像为:所述车辆参数中包含有所述第一道路区域的特殊路况的图像。
对应的,所述处理模块901,具体用于将所述第二道路区域的特殊路况的描述信息和/或目标图像作为所述提醒信息。
所述播放模块902,用于播放所述第二道路区域的特殊路况的描述信息;和/或,
所述显示模块903,用于显示所述第二道路区域的特殊路况的目标图像。
可选的,所述地图数据还包括:所述第一道路区域的特殊路况的持续时间。
可选的,所述第一道路区域为多个。所述显示模块903,还用于在地图上显示每个所述第一道路区域的特殊路况的标识。
收发模块904,用于接收用户对任一个第一道路区域的特殊路况的标识的选择指令;对应的,所述显示模块903,还用于显示用户选择的第一道路区域的特殊路况的描述信息。
可选的,所述收发模块904,还用于向服务器发送路线规划请求,以及接收所述服务器发送的所述规划路线。
可选的,所述地图数据还包括:所述第一道路区域的特殊路况的持续时间。
可选的,所述收发模块904,还用于向服务器上报车辆参数,所述车辆参数包括车辆的位置、车辆拍摄的图像或视频,以及所述车辆的属性数据、行驶数据。
本申请实施例提供的特殊路况识别的装置,其有益效果可以参见上述特殊路况的识别方法中的有益效果,在此不加赘述。
图10为本申请实施例提供的特殊路况识别的装置的结构示意图二。如图10所示,该特殊路况识别的装置可以为上述实施例中的服务器。其中,特殊路况识别的装置1000中包括:处理模块1001、收发模块1002。
处理模块1001,用于根据路况模型和当前时刻之前的预设时间段内的车辆参数,获取所述当前时刻的第一道路区域,且在地图数据上标注所述第一道路区域,得到所述当前时刻的地图数据,所述第一道路区域为特殊路况所处的道路区域,所述路况模型用于表征车辆参数的特征和特殊路况的对应关系。
可选的,所述车辆参数包括车辆的位置。
收发模块1002,用于在所述预设时间段内,接收至少一个车辆上报的车辆参数。
对应的,所述处理模块1001,还用于根据所述至少一个车辆的车辆参数,确定所述当前时刻之前的预设时间段内的车辆参数,所述当前时刻之前的预设时间段内的车辆参数为:与所述地图数据中所述车辆的位置处的道路的特征不匹配的车辆参数。
可选的,所述处理模块1001,还用于以多个历史的车辆参数为训练参数,获取所述路况模型,所述历史的车辆参数为所述预设时间段之前接收到的、来自至少一个车辆的车辆参数。
可选的,所述路况模型为多个。
所述处理模块1001,具体用于将所述多个历史的车辆参数分成N个训练数据集,每个 训练数据集中的车辆参数的特征相同,N为大于1的整数;将每个训练数据集作为训练一个路况模型的训练数据,以得到所述至少一个路况模型。
可选的,所述处理模块1001,具体用于将所述当前时刻之前的预设时间段内的车辆参数输入至所述至少一个路况模型,得到所述第一道路区域。
可选的,所述车辆参数包括:车辆拍摄的图像或视频。
所述处理模块1001,还用于获取所述第一道路区域的目标图像,且根据所述第一道路区域的目标图像,生成所述第一道路区域的特殊路况的描述信息,以及在所述地图数据中添加所述第一道路区域的特殊路况的描述信息和/或目标图像,所述第一道路区域的目标图像为:所述车辆参数中包含有所述第一道路区域的特殊路况的图像,所述目标图像为所述车辆拍摄的图像或视频中的一个视频帧,所述描述信息用于描述所述特殊路况的场景类型。
可选的,所述处理模块1001,还用于根据所述第一道路区域的特殊路况的描述信息表征的特殊路况的场景类型,确定所述第一道路区域的特殊路况的持续时间,以及在所述地图数据中添加所述第一道路区域的特殊路况持续时间。
可选的,所述处理模块1001,还用于若接收到来自终端设备的路线规划请求,则根据起止点、以及所述第一道路区域的特殊路况的持续时间和所述第一道路区域的特殊路况的场景类型,获取规划路线,所述路线规划请求中包括所述起止点;
所述收发模块1002,还用于向所述终端设备推送所述规划路线。
可选的,所述车辆参数包括车辆的属性数据、行驶数据。
本申请实施例提供的特殊路况识别的装置,其有益效果可以参见上述特殊路况的识别方法中的有益效果,在此不加赘述。
图11为本申请实施例提供的电子设备的结构示意图一。如图11所示,该电子设备可以为上述图9中的终端设备,该电子设备可以包括:处理器1101、播放器1102、显示器1103、收发器1104和存储器1105。应理解,处理器1101执行上述处理模块901的动作,播放器1102执行上述播放模块902的动作,显示器1103执行上述显示模块903的动作,以及收发器1104执行上述收发模块904的动作。存储器1105中可以存储各种指令,以用于完成各种处理功能以及实现本申请的方法步骤。
其中,上述收发器1104耦合至处理器1101,处理器1101控制收发器1104(1202)
的收发动作;存储器1105可能包含高速随机存取存储器(random-access memory,RAM),也可能还包括非易失性存储器(non-volatile memory,NVM),例如至少一个磁盘存储器。可选的,本申请涉及的电子设备还可以包括:电源1106、通信总线1107以及通信端口1108。收发器1104可以集成在终端设备的收发信机中,也可以为终端设备上独立的收发天线。通信总线1107用于实现元件之间的通信连接。上述通信端口1108用于实现终端设备与其他外设之间进行连接通信。其中,显示器1103可以与处理器1101连接,以在处理器1101的控制下显示上述实施例中的设置界面。
在本申请实施例中,上述存储器1105用于存储计算机可执行程序代码,程序代码包括指令;当处理器1101执行指令时,指令使终端设备的处理器1101执行上述方法实施例中终端设备的处理动作,使收发器1104执行上述方法实施例中终端设备的收发动作,其实现原理和技术效果类似,在此不再赘述。
图12为本申请实施例提供的电子设备的结构示意图二。如图12所示,该电子设备可以为上述图10中的服务器,该电子设备可以包括:处理器1201、收发器1202和存储器1203。应理解,处理器1201执行上述处理模块1001的动作,以及收发器1202执行上述收发模块1002的动作。存储器1203中可以存储各种指令,以用于完成各种处理功能以及实现本申请的方法步骤。
其中,上述收发器1202耦合至处理器1201,处理器1201控制收发器1202(1202)的收发动作;处理器1203可能包含高速随机存取存储器(random-access memory,RAM),也可能还包括非易失性存储器(non-volatile memory,NVM),例如至少一个磁盘存储器。可选的,本申请涉及的电子设备还可以包括:电源1204、通信总线1205以及通信端口1206。收发器1202可以集成在终端设备的收发信机中,也可以为终端设备上独立的收发天线。通信总线1205用于实现元件之间的通信连接。上述通信端口1206用于实现终端设备与其他外设之间进行连接通信。其中,显示器1103可以与处理器1201连接,以在处理器1201的控制下显示上述实施例中的设置界面。
在本申请实施例中,上述处理器1203用于存储计算机可执行程序代码,程序代码包括指令;当处理器1201执行指令时,指令使终端设备的处理器1201执行上述方法实施例中终端设备的处理动作,使收发器1202执行上述方法实施例中终端设备的收发动作,其实现原理和技术效果类似,在此不再赘述。
在上述实施例中,可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时,可以全部或部分地以计算机程序产品的形式实现。计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行计算机程序指令时,全部或部分地产生按照本申请实施例的流程或功能。计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。计算机指令可以存储在计算机可读存储介质中,或者从一个计算机可读存储介质向另一个计算机可读存储介质传输,例如,计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。可用介质可以是磁性介质,(例如,软盘、硬盘、磁带)、光介质(例如,DVD)、或者半导体介质(例如固态硬盘Solid State Disk(SSD))等。
本文中的术语“多个”是指两个或两个以上。本文中术语“和/或”,仅仅是一种描述关联对象的关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B这三种情况。另外,本文中字符“/”,一般表示前后关联对象是一种“或”的关系;在公式中,字符“/”,表示前后关联对象是一种“相除”的关系。
可以理解的是,在本申请的实施例中涉及的各种数字编号仅为描述方便进行的区分,并不用来限制本申请的实施例的范围。
可以理解的是,在本申请的实施例中,上述各过程的序号的大小并不意味着执行顺序的先后,各过程的执行顺序应以其功能和内在逻辑确定,而不应对本申请的实施例的实施 过程构成任何限定。

Claims (21)

  1. 一种特殊路况的识别方法,应用于终端设备,其特征在于,包括:
    获取当前时刻的地图数据,所述地图数据包括:所述当前时刻的第一道路区域,所述第一道路区域为特殊路况所处的道路区域,所述第一道路区域是由路况模型和所述当前时刻之前的预设时间段内的车辆参数获取的,所述路况模型用于表征车辆参数的特征和特殊路况的对应关系;
    根据车辆的规划路线,判断所述车辆的规划路线中是否存在第二道路区域,所述第二道路区域为所述第一道路区域中的道路区域。
  2. 根据权利要求1所述的方法,其特征在于,若所述车辆为自动驾驶车辆,所述方法还包括:
    若所述车辆的规划路线中存在所述第二道路区域,则生成驾驶指令,所述驾驶指令用于指示所述车辆的驾驶行为;
    当所述车辆行驶至所述第二道路区域时,根据所述驾驶指令控制所述车辆行驶。
  3. 根据权利要求2所述的方法,其特征在于,所述路况模型为多个,所述地图数据还包括:所述第一道路区域的特殊路况的描述信息,所述描述信息用于描述所述特殊路况的场景类型,所述生成驾驶指令,包括:
    根据所述第二道路区域的特殊路况的描述信息,生成所述驾驶指令,所述驾驶指令指示的驾驶行为与获取目标路况模型的历史的车辆参数的特征指示的驾驶行为相同,所述目标路况模型为确定所述第二道路区域为特殊路况的模型。
  4. 根据权利要求1所述的方法,其特征在于,所述车辆为非自动驾驶车辆,所述方法还包括:
    若所述车辆的规划路线中存在所述第二道路区域,则生成提醒信息,所述提醒信息用于指示所述第二道路区域存在特殊路况;
    当所述车辆即将行驶至所述第二道路区域时,推送所述提醒信息。
  5. 根据权利要求4所述的方法,其特征在于,所述地图数据还包括:所述第一道路区域的特殊路况的描述信息和/或目标图像,所述描述信息用于描述所述特殊路况的场景类型,所述第一道路区域的目标图像为:所述车辆参数中包含有所述第一道路区域的特殊路况的图像;所述生成提醒信息,包括:
    将所述第二道路区域的特殊路况的描述信息和/或目标图像作为所述提醒信息;
    所述推送所述提醒信息,包括:
    播放所述第二道路区域的特殊路况的描述信息,和/或显示所述第二道路区域的特殊路况的目标图像。
  6. 根据权利要求5所述的方法,其特征在于,所述第一道路区域为多个,所述方法还包括:
    在地图上显示每个所述第一道路区域的特殊路况的标识;
    接收用户对任一个第一道路区域的特殊路况的标识的选择指令,显示用户选择的第一道路区域的特殊路况的描述信息。
  7. 根据权利要求1-6任一项所述的方法,其特征在于,所述方法还包括:
    向服务器发送路线规划请求;
    接收所述服务器发送的所述规划路线。
  8. 根据权利要求1-6任一项所述的方法,其特征在于,所述方法还包括:
    向服务器上报车辆参数,所述车辆参数包括车辆的位置、车辆拍摄的图像或视频,以及所述车辆的属性数据、行驶数据。
  9. 一种特殊路况的识别方法,应用于服务器,其特征在于,包括:
    根据路况模型和当前时刻之前的预设时间段内的车辆参数,获取所述当前时刻的第一道路区域,所述第一道路区域为特殊路况所处的道路区域,所述路况模型用于表征车辆参数的特征和特殊路况的对应关系;
    在地图数据上标注所述第一道路区域,得到所述当前时刻的地图数据。
  10. 根据权利要求9所述的方法,其特征在于,所述车辆参数包括车辆的位置,所述获取所述当前时刻的第一道路区域之前,还包括:
    在所述预设时间段内,接收至少一个车辆上报的车辆参数;
    根据所述至少一个车辆的车辆参数,确定所述当前时刻之前的预设时间段内的车辆参数,所述当前时刻之前的预设时间段内的车辆参数为:与所述地图数据中所述车辆的位置处的道路的特征不匹配的车辆参数。
  11. 根据权利要求9或10所述的方法,其特征在于,所述方法还包括:
    以多个历史的车辆参数为训练参数,获取所述路况模型,所述历史的车辆参数为所述预设时间段之前接收到的、来自至少一个车辆的车辆参数。
  12. 根据权利要求11所述的方法,其特征在于,所述路况模型为多个,所述以多个历史的车辆参数为训练参数,获取所述路况模型,包括:
    将所述多个历史的车辆参数分成N个训练数据集,每个训练数据集中的车辆参数的特征相同,N为大于1的整数;
    将每个训练数据集作为训练一个路况模型的训练数据,以得到所述至少一个路况模型。
  13. 根据权利要求12所述的方法,其特征在于,所述根据路况模型和当前时刻之前的预设时间段内的车辆参数,获取所述当前时刻的第一道路区域,包括:
    将所述当前时刻之前的预设时间段内的车辆参数输入至所述至少一个路况模型,得到所述第一道路区域。
  14. 根据权利要求9-13任一项所述的方法,其特征在于,所述车辆参数包括:车辆拍摄的图像或视频,所述方法还包括:
    获取所述第一道路区域的目标图像,所述第一道路区域的目标图像为:所述车辆参数中包含有所述第一道路区域的特殊路况的图像,所述目标图像为所述车辆拍摄的图像或视频中的一个视频帧;
    根据所述第一道路区域的目标图像,生成所述第一道路区域的特殊路况的描述信息,所述描述信息用于描述所述特殊路况的场景类型;
    在所述地图数据中添加所述第一道路区域的特殊路况的描述信息和/或目标图像。
  15. 根据权利要求14所述的方法,其特征在于,所述方法还包括:
    根据所述第一道路区域的特殊路况的描述信息表征的特殊路况的场景类型,确定所述第一道路区域的特殊路况的持续时间;
    在所述地图数据中添加所述第一道路区域的特殊路况持续时间。
  16. 根据权利要求15所述的方法,其特征在于,所述方法还包括:
    若接收到来自终端设备的路线规划请求,则根据起止点、以及所述第一道路区域的特殊路况的持续时间和所述第一道路区域的特殊路况的场景类型,获取规划路线,所述路线规划请求中包括所述起止点;
    向所述终端设备推送所述规划路线。
  17. 根据权利要求9-13任一项所述的方法,其特征在于,所述车辆参数包括车辆的属性数据、行驶数据。
  18. 一种特殊路况识别的装置,其特征在于,包括:
    处理模块,用于获取当前时刻的地图数据,所述地图数据包括:所述当前时刻的第一道路区域,且根据车辆的规划路线,判断所述车辆的规划路线中是否存在第二道路区域,所述第二道路区域为所述第一道路区域中的道路区域,所述第一道路区域为特殊路况所处的道路区域,所述第一道路区域是由路况模型和所述当前时刻之前的预设时间段内的车辆参数获取的,所述路况模型用于表征车辆参数的特征和特殊路况的对应关系。
  19. 一种特殊路况识别的装置,其特征在于,包括:
    处理模块,用于根据路况模型和当前时刻之前的预设时间段内的车辆参数,获取所述当前时刻的第一道路区域,且在地图数据上标注所述第一道路区域,得到所述当前时刻的地图数据,所述第一道路区域为特殊路况所处的道路区域,所述路况模型用于表征车辆参数的特征和特殊路况的对应关系。
  20. 一种电子设备,其特征在于,所述电子设备上存储有计算机程序,在所述计算机程序被所述电子设备执行时,实现如权利要求1-17中任一项所述的方法。
  21. 一种计算机可读存储介质,其特征在于,所述计算机可读存储介质中存储有计算机程序或指令,当所述计算机程序或指令被运行时,实现如权利要求1-17中任一项所述的方法。
PCT/CN2020/076654 2020-02-25 2020-02-25 特殊路况的识别方法、装置、电子设备和存储介质 WO2021168660A1 (zh)

Priority Applications (8)

Application Number Priority Date Filing Date Title
EP20922073.0A EP4099293B1 (en) 2020-02-25 2020-02-25 Method and apparatus for identifying special road conditions, electronic device, and storage medium
PCT/CN2020/076654 WO2021168660A1 (zh) 2020-02-25 2020-02-25 特殊路况的识别方法、装置、电子设备和存储介质
KR1020227031702A KR20220140813A (ko) 2020-02-25 2020-02-25 특수 도로 상태들을 식별하기 위한 방법 및 장치, 전자 디바이스, 및 저장 매체
JP2022550856A JP7462778B2 (ja) 2020-02-25 2020-02-25 特殊な道路条件を認識するための方法および装置、電子デバイス、ならびに記憶媒体
CN202080004502.5A CN112585656B (zh) 2020-02-25 2020-02-25 特殊路况的识别方法、装置、电子设备和存储介质
EP24171746.1A EP4425463A2 (en) 2020-02-25 2020-02-25 Method and apparatus for recognizing special road condition, electronic device, and storage medium
CN202210659439.XA CN115188183A (zh) 2020-02-25 2020-02-25 特殊路况的识别方法、装置、电子设备和存储介质
US17/892,449 US20220397406A1 (en) 2020-02-25 2022-08-22 Method and apparatus for recognizing special road condition, electronic device, and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/076654 WO2021168660A1 (zh) 2020-02-25 2020-02-25 特殊路况的识别方法、装置、电子设备和存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/892,449 Continuation US20220397406A1 (en) 2020-02-25 2022-08-22 Method and apparatus for recognizing special road condition, electronic device, and storage medium

Publications (1)

Publication Number Publication Date
WO2021168660A1 true WO2021168660A1 (zh) 2021-09-02

Family

ID=75145439

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/076654 WO2021168660A1 (zh) 2020-02-25 2020-02-25 特殊路况的识别方法、装置、电子设备和存储介质

Country Status (6)

Country Link
US (1) US20220397406A1 (zh)
EP (2) EP4425463A2 (zh)
JP (1) JP7462778B2 (zh)
KR (1) KR20220140813A (zh)
CN (2) CN112585656B (zh)
WO (1) WO2021168660A1 (zh)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113928331A (zh) * 2021-12-07 2022-01-14 成都车晓科技有限公司 一种商用车可视化监控系统
CN114078328A (zh) * 2021-12-02 2022-02-22 中国联合网络通信集团有限公司 路况确定方法、装置及计算机可读存储介质
CN114299739A (zh) * 2021-12-21 2022-04-08 中国电信股份有限公司 目标路段的通过方法、系统、存储介质及电子装置
CN114463970A (zh) * 2022-01-11 2022-05-10 北京中交兴路信息科技有限公司 自动检测卡口封闭的方法、装置、设备及存储介质

Families Citing this family (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113267197A (zh) * 2021-05-19 2021-08-17 重庆蓝岸通讯技术有限公司 一种大数据以及统计解决道路拥挤的导航系统和算法
CN113160453A (zh) * 2021-05-19 2021-07-23 重庆蓝岸通讯技术有限公司 一种辅助驾驶行为提醒系统
CN113240682B (zh) * 2021-05-31 2022-06-21 华中科技大学 用于履带式起重机的防倾覆施工驾驶地图生成方法及系统
CN113361423A (zh) * 2021-06-11 2021-09-07 上海追势科技有限公司 一种主动悬架调整方法
CN113515580B (zh) * 2021-06-22 2022-03-01 智己汽车科技有限公司 车辆数据处理方法和设备
CN113479197A (zh) * 2021-06-30 2021-10-08 银隆新能源股份有限公司 车辆的控制方法及其装置、计算机可读存储介质
CN113997951B (zh) * 2021-08-17 2024-06-04 北京百度网讯科技有限公司 车辆的行驶轨迹的确定方法、装置及自动驾驶车辆
CN113727071A (zh) * 2021-08-30 2021-11-30 合众新能源汽车有限公司 路况显示方法和系统
CN115731732A (zh) * 2021-09-01 2023-03-03 博泰车联网(南京)有限公司 路况分享方法、系统、介质及装置
CN113778086B (zh) * 2021-09-03 2024-06-18 上海擎朗智能科技有限公司 地图构建和使用方法、机器人及存储介质
CN113859264B (zh) * 2021-09-17 2023-12-22 阿波罗智联(北京)科技有限公司 车辆控制方法、装置、电子设备及存储介质
CN116311015A (zh) * 2021-12-21 2023-06-23 北京嘀嘀无限科技发展有限公司 道路场景识别方法、装置、服务器、存储介质和程序产品
CN114777806B (zh) * 2022-04-14 2024-05-31 上海极豆科技有限公司 一种行驶路线绘制方法、装置、电子设备及存储介质
CN115273508A (zh) * 2022-06-17 2022-11-01 智道网联科技(北京)有限公司 车辆行驶引导方法、装置、电子设备及存储介质
CN114783189A (zh) * 2022-06-20 2022-07-22 安徽交欣科技股份有限公司 基于ai和gis的智慧预警及路径规划交通系统
CN116189133B (zh) * 2023-04-26 2023-07-28 宜宾闪马智通科技有限公司 道路巡检判定方法及装置
CN116881831B (zh) * 2023-09-07 2023-12-01 湖南省国土资源规划院 基于遥感技术的道路识别方法、系统及存储介质
CN117870713B (zh) * 2024-03-11 2024-05-31 武汉视普新科技有限公司 基于大数据车载影像的路径规划方法及系统

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010198533A (ja) * 2009-02-27 2010-09-09 Nissan Motor Co Ltd 路面情報提供装置及び路面状態判断方法
CN105355039A (zh) * 2015-10-23 2016-02-24 张力 路况信息处理方法及设备
CN105427606A (zh) * 2015-12-24 2016-03-23 重庆云途交通科技有限公司 路面状况信息采集及发布方法
CN107003429A (zh) * 2014-10-06 2017-08-01 株式会社普利司通 路面状态判断系统
CN107038884A (zh) * 2017-05-17 2017-08-11 北汽福田汽车股份有限公司 推送路况的方法、装置和系统
CN108513676A (zh) * 2018-04-25 2018-09-07 深圳市锐明技术股份有限公司 一种路况识别方法、装置及设备
US20190118813A1 (en) * 2017-10-20 2019-04-25 International Business Machines Corporation Road condition prediction
CN109754594A (zh) * 2017-11-01 2019-05-14 腾讯科技(深圳)有限公司 一种路况信息获取方法及其设备、存储介质、终端
CN110660141A (zh) * 2019-09-06 2020-01-07 杭州博信智联科技有限公司 路面状况检测方法、装置、电子设备及可读存储介质

Family Cites Families (40)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE69333916T2 (de) * 1992-07-23 2006-07-06 Aisin AW Co., Ltd., Anjo Navigationsgerät für Fahrzeuge zur Bestimmung eines neuen Leitwegs, wenn ein Fahrzeug von seinem Leitweg abweicht
DE69831623T2 (de) * 1997-04-25 2006-07-13 Hitachi, Ltd. Steuerverfahren und Vorrichtung für Kraftfahrzeug
JP4815943B2 (ja) * 2005-08-19 2011-11-16 株式会社デンソー 危険箇所情報表示装置
CN101549683B (zh) * 2009-04-23 2011-09-28 上海交通大学 自动识别道路深坑与障碍物的车辆智能方法
JP2012003408A (ja) * 2010-06-15 2012-01-05 Rohm Co Ltd ドライブレコーダ
GB201018815D0 (en) * 2010-11-08 2010-12-22 Tomtom Int Bv High-definition weather for improved routing and navigation systems
US20130127113A1 (en) * 2011-11-18 2013-05-23 George Davenport Card game
CN102799173B (zh) * 2012-08-03 2016-03-30 深圳市格美特科技有限公司 停车场、道路的收费及通道管理系统的智能化故障诊断装置
US9335178B2 (en) * 2014-01-28 2016-05-10 GM Global Technology Operations LLC Method for using street level images to enhance automated driving mode for vehicle
CN104899818B (zh) * 2014-03-03 2020-08-14 清华大学 一种区域性车载现场查验方法和系统
CN104865857B (zh) * 2015-05-04 2018-02-02 小米科技有限责任公司 启动饭煲的方法及装置
US9784589B1 (en) * 2016-11-16 2017-10-10 Aimotive Kft Electronic route navigation method in a road network on a map
US10332391B2 (en) * 2016-12-06 2019-06-25 Here Global B.V. Split lane traffic jam detection and remediation
JP6798032B2 (ja) * 2016-12-29 2020-12-09 華為技術有限公司Huawei Technologies Co.,Ltd. 地面環境検出方法及び機器
WO2018159259A1 (ja) * 2017-03-01 2018-09-07 パナソニックIpマネジメント株式会社 車両
CN107038478B (zh) * 2017-04-20 2023-10-27 百度在线网络技术(北京)有限公司 路况预测方法及装置、计算机设备与可读介质
US10930157B2 (en) * 2017-04-26 2021-02-23 Dropoff, Inc. Systems and methods for automated real-time and advisory routing within a fleet of geographically distributed drivers
DE102017207243A1 (de) * 2017-04-28 2018-10-31 Continental Automotive Gmbh Verfahren und Einrichtung zum Erzeugen von dynamischen Hinweisen über eine Änderung einer Routenführung
CN109803583A (zh) * 2017-08-10 2019-05-24 北京市商汤科技开发有限公司 驾驶状态监控方法、装置和电子设备
CN109919347B (zh) * 2017-12-13 2022-01-18 腾讯科技(深圳)有限公司 路况生成方法、相关装置和设备
CN108692733A (zh) * 2018-03-13 2018-10-23 四川斐讯信息技术有限公司 一种基于神经网络的地图建立方法和地图建立系统
JP2019168607A (ja) * 2018-03-23 2019-10-03 パイオニア株式会社 地図データ構造、情報処理装置及び地図データ生成装置
CN108764042B (zh) * 2018-04-25 2021-05-28 深圳市科思创动科技有限公司 一种异常路况信息识别方法、装置及终端设备
CN108827337B (zh) * 2018-05-25 2020-07-24 吉利汽车研究院(宁波)有限公司 导航路径显示方法及导航系统
CN110148294B (zh) * 2018-06-07 2021-08-03 腾讯大地通途(北京)科技有限公司 路况状态确定方法及装置
CN109035239A (zh) * 2018-08-03 2018-12-18 北京智行者科技有限公司 基于自动驾驶技术的道路设施检查方法和车辆
CN109101022A (zh) * 2018-08-09 2018-12-28 北京智行者科技有限公司 一种作业路径更新方法
CN109191911A (zh) * 2018-10-09 2019-01-11 湖南车路协同智能科技有限公司 一种隧道路况预警系统、方法及计算机可读存储介质
CN111413957B (zh) * 2018-12-18 2021-11-02 北京航迹科技有限公司 用于确定自动驾驶中的驾驶动作的系统和方法
GB2622969B (en) * 2019-02-14 2024-07-03 Mobileye Vision Technologies Ltd Systems and methods for vehicle navigation
CN109974734A (zh) * 2019-04-02 2019-07-05 百度在线网络技术(北京)有限公司 一种用于ar导航的事件上报方法、装置、终端及存储介质
CN110047306A (zh) * 2019-04-23 2019-07-23 杜泽臣 一种智能交通网络
CN110298311B (zh) * 2019-06-28 2021-05-07 北京智行者科技有限公司 路面积水检测方法及装置
US11593344B2 (en) * 2019-07-02 2023-02-28 Nvidia Corporation Updating high definition maps based on age of maps
US11774250B2 (en) * 2019-07-05 2023-10-03 Nvidia Corporation Using high definition maps for generating synthetic sensor data for autonomous vehicles
CN110335488A (zh) * 2019-07-24 2019-10-15 深圳成谷科技有限公司 一种基于车路协同的车辆自动驾驶方法和装置
JP7238729B2 (ja) * 2019-10-24 2023-03-14 トヨタ自動車株式会社 冠水検知装置、冠水検知システム、及び冠水検知プログラム
US11548505B2 (en) * 2019-12-09 2023-01-10 Magna Electronics Inc. Vehicular speed control system with automatic setting parameters
US12083955B2 (en) * 2019-12-30 2024-09-10 Gm Cruise Holdings Llc Dynamic inter-vehicle communication regarding risk detected based on vehicle sensor measurements
GB202001468D0 (en) * 2020-02-04 2020-03-18 Tom Tom Navigation B V Navigation system

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2010198533A (ja) * 2009-02-27 2010-09-09 Nissan Motor Co Ltd 路面情報提供装置及び路面状態判断方法
CN107003429A (zh) * 2014-10-06 2017-08-01 株式会社普利司通 路面状态判断系统
CN105355039A (zh) * 2015-10-23 2016-02-24 张力 路况信息处理方法及设备
CN105427606A (zh) * 2015-12-24 2016-03-23 重庆云途交通科技有限公司 路面状况信息采集及发布方法
CN107038884A (zh) * 2017-05-17 2017-08-11 北汽福田汽车股份有限公司 推送路况的方法、装置和系统
US20190118813A1 (en) * 2017-10-20 2019-04-25 International Business Machines Corporation Road condition prediction
CN109754594A (zh) * 2017-11-01 2019-05-14 腾讯科技(深圳)有限公司 一种路况信息获取方法及其设备、存储介质、终端
CN108513676A (zh) * 2018-04-25 2018-09-07 深圳市锐明技术股份有限公司 一种路况识别方法、装置及设备
CN110660141A (zh) * 2019-09-06 2020-01-07 杭州博信智联科技有限公司 路面状况检测方法、装置、电子设备及可读存储介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4099293A4 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114078328A (zh) * 2021-12-02 2022-02-22 中国联合网络通信集团有限公司 路况确定方法、装置及计算机可读存储介质
CN113928331A (zh) * 2021-12-07 2022-01-14 成都车晓科技有限公司 一种商用车可视化监控系统
CN114299739A (zh) * 2021-12-21 2022-04-08 中国电信股份有限公司 目标路段的通过方法、系统、存储介质及电子装置
CN114463970A (zh) * 2022-01-11 2022-05-10 北京中交兴路信息科技有限公司 自动检测卡口封闭的方法、装置、设备及存储介质

Also Published As

Publication number Publication date
EP4099293B1 (en) 2024-04-24
KR20220140813A (ko) 2022-10-18
EP4099293A4 (en) 2023-01-25
EP4425463A2 (en) 2024-09-04
CN112585656A (zh) 2021-03-30
JP2023514746A (ja) 2023-04-07
US20220397406A1 (en) 2022-12-15
CN112585656B (zh) 2022-06-17
JP7462778B2 (ja) 2024-04-05
EP4099293A1 (en) 2022-12-07
CN115188183A (zh) 2022-10-14

Similar Documents

Publication Publication Date Title
WO2021168660A1 (zh) 特殊路况的识别方法、装置、电子设备和存储介质
US11915318B2 (en) Controlling autonomous vehicles to optimize traffic characteristics
US11714413B2 (en) Planning autonomous motion
US20220165100A1 (en) Intervention in operation of a vehicle having autonomous driving capabilities
US11702070B2 (en) Autonomous vehicle operation with explicit occlusion reasoning
US20190243364A1 (en) Autonomous vehicle integrated user alert and environmental labeling
US11307585B2 (en) Introspective competence modeling for AV decision making
US11820387B2 (en) Detecting driving behavior of vehicles
US10730531B1 (en) Machine-learning based vehicle motion control system
US20210191394A1 (en) Systems and methods for presenting curated autonomy-system information of a vehicle
US20210403001A1 (en) Systems and methods for generating lane data using vehicle trajectory sampling
CN114929543A (zh) 预测周围因素的加塞概率
US20210405641A1 (en) Detecting positioning of a sensor system associated with a vehicle
US12084088B2 (en) Pedestrian intent yielding
US20220355824A1 (en) Predicting near-curb driving behavior on autonomous vehicles
US20230280751A1 (en) Virtual barriers for reserved corridors
US20230347931A1 (en) Scenario based monitoring and control of autonomous vehicles
US20240211046A1 (en) Vision-Based Road Feel Enhancement in Vehicles

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: 20922073

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022550856

Country of ref document: JP

Kind code of ref document: A

ENP Entry into the national phase

Ref document number: 2020922073

Country of ref document: EP

Effective date: 20220830

ENP Entry into the national phase

Ref document number: 20227031702

Country of ref document: KR

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE