WO2023088270A1 - 地图更新方法及其装置 - Google Patents
地图更新方法及其装置 Download PDFInfo
- Publication number
- WO2023088270A1 WO2023088270A1 PCT/CN2022/132089 CN2022132089W WO2023088270A1 WO 2023088270 A1 WO2023088270 A1 WO 2023088270A1 CN 2022132089 W CN2022132089 W CN 2022132089W WO 2023088270 A1 WO2023088270 A1 WO 2023088270A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- automatic driving
- target
- location point
- road
- map
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 230000004044 response Effects 0.000 claims description 29
- 238000004590 computer program Methods 0.000 claims description 26
- 230000005856 abnormality Effects 0.000 claims description 15
- 238000010586 diagram Methods 0.000 description 14
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000007488 abnormal function Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/23—Updating
- G06F16/2379—Updates performed during online database operations; commit processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
Definitions
- the present disclosure relates to the technical field of intelligent transportation, and in particular to a map updating method, device, electronic equipment and storage medium.
- the first purpose of the present disclosure is to propose a method for updating a map.
- the second purpose of the present disclosure is to propose a map updating device.
- the third object of the present disclosure is to provide an electronic device.
- a fourth object of the present disclosure is to provide a non-transitory computer-readable storage medium.
- a fifth object of the present disclosure is to provide a computer program product.
- a sixth object of the present disclosure is to propose a computer program.
- the first aspect of the present disclosure provides a method for updating a map, including: determining a target vehicle exiting the automatic driving mode on the target road; acquiring driving data of the target vehicle in the non-automatic driving mode; The driving data is clustered to generate at least one cluster; according to the cluster, the automatic driving enabling status of each location point of the target road on the map is updated, and the automatic driving enabling status is used for Indicate whether the location point allows passing vehicles to enter the automatic driving mode.
- the determination of the target vehicle exiting the automatic driving mode on the target road includes: obtaining a candidate vehicle driving on the road network exiting the automatic driving mode; obtaining the driving track of the candidate vehicle; The driving trajectory is matched with the target road to obtain the target vehicle.
- the driving data includes the position of the target vehicle on the target road when the automatic driving mode is exited and the trigger conditions for exiting the automatic driving mode, wherein the driving data Performing clustering to generate at least one cluster includes: comparing the driving data of each of the target vehicles, and acquiring target vehicles at the same location and with the same trigger condition as a cluster.
- the updating the automatic driving enabling information of the target road on the map according to the cluster cluster further includes: acquiring the number of target vehicles in the cluster cluster; The number of the target vehicles determines the automatic driving enabling state of the location point corresponding to the cluster.
- the determining the automatic driving enabling state of the location point corresponding to the cluster according to the number of the target vehicles includes: responding to the number of the target vehicles being greater than the set If the number of the target vehicles is less than the set number, it is determined that the automatic driving enable state of the location point is a non-enabled state; in response to the number of the target vehicle being less than the set number, the road state information of the location point is obtained, and based on the The road state is determined to determine the automatic driving enabling state of the location point.
- the determining the automatic driving enabling state of the location point based on the road state includes: in response to the road state information indicating that the location point has a road abnormality, then determining the The automatic driving enabling state of the location point is a non-enabled state; in response to the road state information indicating that there is no road abnormality at the location point, it is determined that the automatic driving enabling state of the location point is an enabled state.
- the map updating method further includes: identifying consecutive target location points from the determined non-enabled location points, and combining the target location points to obtain at least one location area ; Generate map update information based on the remaining discontinuous location points and the automatic driving enablement status of the at least one location area, and send the map update information to the vehicle.
- the implementation of the first aspect of the present disclosure proposes a map update method, including: in response to the vehicle exiting the automatic driving mode, collecting driving data in the non-automatic driving mode and sending it to the cloud server; receiving the cloud server according to the The map update information generated by the driving data, based on the map update information, updates the automatic driving enabling status of each location point on the target road on the map, and the automatic driving enabling status is used to indicate whether the location point allows The passing vehicle enters the automatic driving mode.
- the driving data includes the position of the target vehicle on the target road when the automatic driving mode is exited and the trigger conditions for exiting the automatic driving mode.
- the implementation mode of the second aspect of the present disclosure proposes a map update device, including: a determination module, configured to determine a target vehicle exiting the automatic driving mode on the target road; an acquisition module, acquiring the driving status of the target vehicle in the non-automatic driving mode Data; a clustering module, clustering the driving data to generate at least one cluster; an update module, updating the automatic driving enabling status of each location point of the target road on the map according to the clustering , the automatic driving enabling state is used to indicate whether the location point allows passing vehicles to enter the automatic driving mode.
- the determination module is further configured to: obtain candidate vehicles driving on the road network and exit the automatic driving mode; obtain the driving trajectory of the candidate vehicle; match the driving trajectory with the target road , to obtain the target vehicle.
- the updating module is further configured to: compare the driving data of each of the target vehicles, and obtain the target vehicles at the same location and with the same trigger conditions as a clustering clusters.
- the update module is further configured to: acquire the number of target vehicles in the cluster; determine the automatic driving enable state.
- the update module is further configured to: in response to the number of the target vehicles being greater than the set number, determine that the automatic driving enablement state of the location point is a non-enabling state; If the number of the target vehicles is less than the set number, the road state information of the location point is obtained, and the automatic driving enabling state of the location point is determined based on the road state.
- the update module is further configured to: determine that the automatic driving enabling state of the location point is disabled in response to the road state information indicating that the location point has a road abnormality State: in response to the road state information indicating that no road abnormality occurs at the location point, then determine that the automatic driving enabling state of the location point is an enabled state.
- the update module is further configured to: identify continuous target position points in position from the determined non-enabled position points, and combine the target position points to obtain at least one position area ; Generate map update information based on the remaining discontinuous location points and the automatic driving enablement status of the at least one location area, and send the map update information to the vehicle.
- the implementation mode of the second aspect of the present disclosure proposes a map update device, including: in response to the vehicle exiting the automatic driving mode, collecting driving data in the non-automatic driving mode and sending it to the cloud server; receiving the cloud server according to the The map update information generated by the driving data, based on the map update information, updates the automatic driving enabling status of each location point on the target road on the map, and the automatic driving enabling status is used to indicate whether the location point allows The passing vehicle enters the automatic driving mode.
- the driving data includes the position of the target vehicle on the target road when the automatic driving mode is exited and the trigger conditions for exiting the automatic driving mode.
- the third aspect of the present disclosure provides an electronic device, including: at least one processor; and a memory connected to the at least one processor in communication; wherein, the memory stores information that can be used by the Instructions executed by at least one processor, the instructions are executed by the at least one processor to implement the map update method according to any embodiment of the first aspect of the present disclosure.
- the implementation of the fourth aspect of the present disclosure proposes a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to implement the information described in any embodiment of the first aspect of the present disclosure.
- the map update method is a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to implement the information described in any embodiment of the first aspect of the present disclosure.
- the implementation mode of the fifth aspect of the present disclosure proposes a computer program product, including a computer program, when the computer program is executed by a processor, it is used to implement the computer program described in any embodiment of the first aspect of the present disclosure.
- the map update method
- the embodiment of the sixth aspect of the present disclosure provides a computer program, the computer program includes computer program code, when the computer program code is run on the computer, the computer executes any of the following aspects of the first aspect of the present disclosure.
- FIG. 1 is a schematic diagram of a map updating method according to an embodiment of the present disclosure
- Fig. 2 is a schematic diagram of another map update method according to an embodiment of the present disclosure.
- Fig. 3 is a schematic diagram of another map update method according to an embodiment of the present disclosure.
- Fig. 4 is a schematic diagram of another map updating method according to an embodiment of the present disclosure.
- Fig. 5 is a schematic diagram of another map updating method according to an embodiment of the present disclosure.
- FIG. 6 is a schematic diagram of a map updating method according to an embodiment of the present disclosure.
- Fig. 7 is a block diagram of a map updating device according to an embodiment of the present disclosure.
- Fig. 8 is a block diagram of another map update device according to an embodiment of the present disclosure.
- Fig. 9 is a block diagram of an electronic device according to an embodiment of the present disclosure.
- FIG. 1 is a schematic diagram of a map updating method proposed by an embodiment of the present disclosure. As shown in FIG. 1 , the map updating method includes the following steps: 101-104.
- ODD Opera Design Domain
- the vehicle to exit the automatic driving mode may include user takeover during automatic driving, abnormal function exit, positioning failure, perception failure, etc.
- the driving data can be uploaded to the server through the positioning system of the vehicle itself.
- the target vehicle can also upload the driving data of the target vehicle in the non-automatic driving mode to the server through a navigation map application (Application, APP).
- a navigation map application Application, APP
- the driving data can be clustered to analyze target vehicles at different locations and with different trigger conditions.
- the driving data of each target vehicle can be compared, and the target vehicles at the same location point and with the same trigger condition can be obtained as a cluster. Therefore, by analyzing and horizontally comparing the target vehicle with the same trigger condition at the same location, it can be judged whether the location is due to the user's own reasons for switching to automatic driving, which greatly increases the credibility of the data.
- the location point can be set in advance, or can be delineated on the map according to certain rules. For example, a location point can be delineated at intervals on the target road, location points can be set at key locations of the target road (such as bridges, forks), etc. There is no limitation here, and specific settings can be made according to actual conditions. Certainly.
- the enabling status of the location point may be updated by analyzing different clusters at different locations.
- the updated map in the server can be sent to the map in the vehicle for updating.
- the cluster may be analyzed by the server to generate configuration information corresponding to the cluster, and the map may be updated through the configuration information.
- the driving data of the cluster can also be manually analyzed to determine whether the location point corresponding to the cluster still meets the conditions for automatic driving, and generate configuration information. Further, after obtaining the configuration information, the cloud can update the map according to the configuration information, and send the updated map to the vehicle end. Thus, dynamic adjustment of ODD is realized.
- the ODD update period of the HD map is not fixed, for example, the update period may be 12 hours, 24 hours, 48 hours, etc. Specifically, it is set according to actual needs, and no limitation is made here.
- the update time the purpose of dynamically updating the ODD can be achieved, the timeliness of the map is enhanced, and the safety of the user's automatic driving is increased at the same time.
- the target vehicle exiting the automatic driving mode on the target road firstly determine the target vehicle exiting the automatic driving mode on the target road, and obtain the driving data of the target vehicle in the non-automatic driving mode, then cluster the driving data to generate at least one cluster, and finally According to the clusters, the automatic driving enablement status of each location point on the target road on the map is updated, and the automatic driving enabling status is used to indicate whether the location point allows passing vehicles to enter the automatic driving mode. Therefore, by classifying the vehicles on the road that exit the automatic driving mode, it is possible to better analyze whether the road still has the conditions for automatic driving, which greatly increases the safety of the user's automatic driving.
- the method includes: 201-203.
- the driving data can be uploaded to the server through the positioning system of the vehicle itself, and it is analyzed according to the driving data whether the vehicle is a candidate vehicle for exiting the automatic driving mode.
- the driving data of the vehicle can also be uploaded to the server through the navigation map APP, and the vehicle can be determined as a candidate vehicle.
- the driving track of the vehicle may be uploaded to the server through the positioning system of the candidate vehicle, so as to obtain the driving track of the candidate vehicle.
- the server may be connected to the road information database and/or the traffic management platform, and obtain the driving trajectories of the candidate vehicles from the information database and/or the traffic management platform.
- the driving track of the candidate vehicle can be uploaded to the server through the navigation map APP installed on the candidate vehicle.
- the driving trajectory of the candidate vehicle can be matched with the shape of the target road. Further, when the driving trajectory of the candidate vehicle and the shape of the target road are the same, it can be considered that the candidate vehicle is driving on the target road , the candidate vehicle is the target vehicle.
- the matching value of the driving trajectory and the shape of the target road can be obtained first, and the matching value is compared with a matching threshold to determine whether the candidate vehicle is the target vehicle.
- the matching threshold can be 0.9.
- the matching value of the driving trajectory and the shape of the target road is greater than or equal to 0.9, the candidate vehicle can be considered as the target vehicle.
- the matching value of the driving trajectory and the shape of the target road is less than 0.9 , then the candidate vehicle can be recognized as not the target vehicle.
- the candidate vehicles first obtain the candidate vehicles driving on the road network and exit the automatic driving mode, then obtain the driving trajectories of the candidate vehicles, and finally match the driving trajectories with the target road to obtain the target vehicles. Therefore, the candidate vehicles are screened through the road trajectory, the processing of subsequent data is reduced, and the processing cost is reduced.
- the automatic driving enabling information of the target road on the map is updated according to the clusters, which can be further explained by referring to FIG. 3 , including the following steps as shown in FIG. 3 : 301-302.
- the clustering process may refer to the steps in the foregoing embodiments.
- statistics may be performed on the cluster to obtain the number of target vehicles in the cluster.
- the automatic driving enabling state of the location point in response to the number of target vehicles being greater than the set number, it is determined that the automatic driving enabling state of the location point is a non-enabled state, and the location point does not have the condition for automatic driving; in response to the target vehicle's If the number is less than the set number, the road state information of the location point is obtained, and based on the road state, the automatic driving enabling state of the location point is determined.
- the set number can be 5.
- the number of target vehicles in the cluster is greater than or equal to 5, it can be considered that the location point corresponding to the cluster does not meet the conditions for automatic driving.
- the number of target vehicles in the cluster When the number of target vehicles is less than 5, continue to perform data analysis on the clusters according to the steps in the above embodiment.
- the number of target vehicles in the cluster is obtained, and then according to the number of target vehicles, the automatic driving enabling status of the location point corresponding to the cluster is determined. In this way, the cost of data processing can be reduced by judging whether the location point meets the conditions for automatic driving based on the number of target vehicles in the cluster.
- the determination of the automatic driving enabling state of the location point based on the road state can also be explained with reference to FIG. 4 , as shown in FIG. 4 , including the following steps: 401-404.
- the server can be connected to the road information database and/or the traffic management platform, obtain the road state information of the location point from the information database and/or the traffic management platform, and determine the automatic driving of the location point based on the road state enable state.
- the road state information of the location point can also be obtained according to the information collection device of the vehicle.
- the information collection device can include a vehicle camera, a vehicle radar, and the like.
- road abnormalities may include various types.
- road abnormalities may include road construction, traffic accidents, and failure of satellite positioning.
- road state information of the location point When the road state information of the location point is judged as road abnormality, it can be considered that the road does not meet the conditions for automatic driving; when the road state information of the location point is judged as non-road abnormality, it can be considered that the automatic driving is switched to non-automatic driving
- the reason is the user's own reasons, and this location has the conditions for automatic driving.
- the user's own reasons may include the user voluntarily switching from automatic driving to non-automatic driving, vehicle failure, etc.
- the number of target vehicles in the cluster is first obtained, and then in response to the number of target vehicles being less than the set number, the road state information of the location point is obtained, and based on the road state, the automatic driving of the location point is determined Enabled state, finally in response to the road state information indicating that there is a road abnormality at the location point, then determine that the automatic driving enablement state of the location point is a non-enabled state, and respond to the road state information indicating that the location point does not have road abnormality, then determine the location point
- the autopilot enabling state of is the enabled state.
- Fig. 5 is a schematic diagram of another exemplary implementation of a method for updating a map according to an embodiment of the present disclosure. As shown in Fig. 5 , the method includes: 501-502.
- 501 Identify continuous target position points in position from the determined non-enabled position points, and combine the target position points to obtain at least one position area.
- data processing may be performed on the location points to analyze the positional relationship between the location points.
- the area of the location point can be merged into a continuous location area, which is a non-ODD, and Generate configuration data and update the map.
- the location area where the target location point is located is updated to non-ODD.
- the continuous position points can be merged into continuous non-ODD by analyzing the non-enabled position points.
- Fig. 6 is a schematic diagram of an exemplary implementation of a method for updating a map according to an embodiment of the present disclosure. As shown in Fig. 6 , the method includes: 601-602.
- the vehicle sensor in response to the vehicle exiting the automatic driving mode, can collect the driving data of the car, and send it to the navigation map APP, and then the navigation map APP sends it to the cloud server.
- the driving data can also be uploaded to the server after the vehicle has driven a complete non-ODD road.
- the complete driving data of the vehicle collected by the sensor can be uploaded to the server in order of sampling time. Further, the server can match the existing ODD map with the collected driving data to determine whether the existing ODD road status needs to be updated.
- the automatic driving enablement status is used to indicate whether the location point allows vehicles to pass through Enter autopilot mode.
- the driving data includes the position of the target vehicle on the target road when the automatic driving mode is exited and the trigger conditions for exiting the automatic driving mode.
- the target non-ODD area is convenient Subsequently, the target non-ODD area is restored to the ODD area for manual review to reduce the target area and reduce the restoration cost.
- the driving data in the non-automatic driving mode is collected and sent to the cloud server, and then the map update information generated by the cloud server according to the driving data is received, and the map update information is updated , to update the automatic driving enabling status of each location point on the target road on the map, and the automatic driving enabling status is used to indicate whether the location point allows passing vehicles to enter the automatic driving mode. Therefore, by analyzing the driving data collected in the non-automatic driving mode, the state of the target road is updated to increase the safety of the user's automatic driving.
- the map APP can remind the self-driving vehicle, and the processor of the vehicle can perform corresponding operations. For example, it can downgrade the driving state of the vehicle, prompt to take over, and pull over. wait.
- FIG. 7 is a schematic diagram of a map updating device proposed by an embodiment of the present disclosure. As shown in FIG.
- the determination module 710 is configured to determine the target vehicle exiting the automatic driving mode on the target road.
- the obtaining module 720 is used to obtain driving data of the target vehicle in a non-automatic driving mode.
- Clustering module 730 clustering the driving data to generate at least one cluster.
- the update module 740 updates the automatic driving enabling status of each location point on the target road on the map, and the automatic driving enabling status is used to indicate whether the location point allows passing vehicles to enter the automatic driving mode.
- the determining module 710 is further configured to: obtain candidate vehicles driving on the road network and exit the automatic driving mode; obtain the driving trajectories of the candidate vehicles; match the driving trajectories with the target road to obtain the target vehicle.
- the update module 740 is further configured to: compare the driving data of each target vehicle, and acquire target vehicles at the same location and with the same trigger condition as a cluster.
- the update module 740 is further configured to: obtain the number of target vehicles in the cluster; and determine the automatic driving enabling status of the location point corresponding to the cluster according to the number of target vehicles.
- the update module 740 is further configured to: in response to the number of target vehicles being greater than the set number, determine that the automatic driving enablement state of the location point is a non-enabled state; in response to the number of target vehicles If the number is less than the set number, the road state information of the location point is obtained, and based on the road state, the automatic driving enabling state of the location point is determined.
- the update module 740 is further configured to: determine that the automatic driving enablement state of the location point is a non-enabled state in response to the road state information indicating that the location point has a road anomaly; in response to the road state information If there is no road abnormality at the indicated location point, it is determined that the automatic driving enabling state of the location point is the enabled state.
- the update module 740 is further configured to: identify continuous target position points on the position from the determined non-enabled position points, and combine the target position points to obtain at least one position area;
- the non-contiguous location points on the location and the automatic driving enablement state of at least one location area generate map update information and send the map update information to the vehicle.
- FIG. 8 is a schematic diagram of a map update device 800 proposed in the present disclosure. As shown in FIG. 8 , the device includes: a collection module 810 and a receiving module 820 .
- the collection module 810 is configured to collect driving data in the non-automatic driving mode in response to the vehicle exiting the automatic driving mode, and send the data to the cloud server.
- the receiving module 820 receives the map update information generated by the cloud server according to the driving data, based on the map update information, updates the automatic driving enabling status of each location point on the target road on the map, and the automatic driving enabling status is used to indicate whether the location point is allowed The passing vehicle enters the automatic driving mode.
- the driving data includes the location of the target vehicle on the target road when the automatic driving mode is exited and the trigger conditions for exiting the automatic driving mode.
- an embodiment of the present disclosure also proposes an electronic device 900. As shown in FIG. Instructions executed by the processor, the instructions are executed by at least one processor 901 to implement the map update method according to the embodiment of the first aspect of the present disclosure.
- the embodiments of the present disclosure also provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to implement the map updating method according to the embodiment of the first aspect of the present disclosure.
- the embodiments of the present disclosure further propose a computer program product, including a computer program, and when the computer program is executed by a processor, the map update method according to the embodiment of the first aspect of the present disclosure is implemented.
- the embodiments of the present disclosure further propose a computer program, the computer program includes computer program code, when the computer program code is run on the computer, the computer performs the map update according to the embodiment of the first aspect of the present disclosure method.
- first and second are used for descriptive purposes only, and cannot be interpreted as indicating or implying relative importance or implicitly specifying the quantity of indicated technical features. Thus, a feature defined as “first” and “second” may explicitly or implicitly include one or more of these features.
- “plurality” means two or more, unless otherwise specifically defined.
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
Abstract
提出了一种地图的更新方法、装置、电子设备及存储介质,该方法包括:确定目标道路上退出自动驾驶模式的目标车辆;获取目标车辆在非自动驾驶模式下的驾驶数据;对驾驶数据进行聚类,生成至少一个聚类簇;根据聚类簇,对地图上目标道路各位置点的自动驾驶使能状态进行更新,自动驾驶使能状态用于指示位置点是否允许通行车辆进入自动驾驶模式。
Description
相关申请的交叉引用
本申请基于申请号为202111372383.1、申请日为2021年11月18日的中国专利申请提出,并要求该中国专利申请的优先权,该中国专利申请的全部内容在此引入本申请作为参考。
本公开涉及智能交通技术领域,具体涉及一种地图更新方法、装置、电子设备及存储介质。
目前具备自动驾驶功能的车辆通常安装高精地图,高精地图上的运行设计区域(Operational design domain,ODD)可以对车辆自动驾驶过程提供进行辅助。相关技术中,自动驾驶使用的高精地图的ODD为静态的,无论现实世界如何变化,只要地图数据不变,该ODD不变。并且前高精地图的更新是很慢的,这就对用户的自动驾驶操作造成了很大的安全隐患。
发明内容
本公开的第一个目的在于提出一种地图更新方法。
本公开的第二个目的在于提出一种地图更新装置。
本公开的第三个目的在于提出一种电子设备。
本公开的第四个目的在于提出一种非瞬时计算机可读存储介质。
本公开的第五个目的在于提出一种计算机程序产品。
本公开的第六个目的在于提出一种计算机程序。
为达上述目的,本公开第一方面实施方式提出了一种地图更新方法,包括:确定目标道路上退出自动驾驶模式的目标车辆;获取所述目标车辆在非自动驾驶模式下的驾驶数据;对所述驾驶数据进行聚类,生成至少一个聚类簇;根据所述聚类簇,对地图上所述目标道路各位置点的自动驾驶使能状态进行更新,所述自动驾驶使能状态用于指示所述位置点是否允许通行车辆进入自动驾驶模式。
在本公开的一个实施例中,所述确定目标道路上退出自动驾驶模式的目标车辆,包括:获取行驶在路网上退出自动驾驶模式的候选车辆;获取所述候选车辆的驾驶轨迹;将所述驾驶轨迹和目标道路进行匹配,获取所述目标车辆。
在本公开的一个实施例中,所述驾驶数据包括退出自动驾驶模式时所述目标车辆在所述目标道路上的位置点和退出自动驾驶模式的触发条件,其中,所述对所述驾驶数据进行聚类,生成至少一个聚类簇,包括:将每个所述目标车辆的驾驶数据进行比较,获取在同 一个位置点,且所述触发条件相同的目标车辆,作为一个聚类簇。
在本公开的一个实施例中,所述根据所述聚类簇,对地图上所述目标道路的自动驾驶使能信息进行更新,还包括:获取所述聚类簇中目标车辆的数量;根据所述目标车辆的数量,确定所述聚类簇所对应位置点的自动驾驶使能状态。
在本公开的一个实施例中,所述根据所述目标车辆的数量,确定所述聚类簇所对应位置点的所述自动驾驶使能状态,包括:响应于所述目标车辆的数量大于设定数量,则确定所述位置点的自动驾驶使能状态为非使能状态;响应于所述目标车辆的数量小于所述设定数量,则获取所述位置点的道路状态信息,并基于所述道路状态,确定所述位置点的自动驾驶使能状态。
在本公开的一个实施例中,所述基于所述道路状态,确定所述位置点的自动驾驶使能状态,包括:响应于所述道路状态信息指示所述位置点出现道路异常,则确定所述位置点的自动驾驶使能状态为非使能状态;响应于所述道路状态信息指示所述位置点未出现道路异常,则确定所述位置点的自动驾驶使能状态为使能状态。
在本公开的一个实施例中,所述地图更新方法,还包括:从确定出非使能的位置点中识别位置上连续的目标位置点,并将所述目标位置点合并得到至少一个位置区域;基于剩余的位置上未连续的位置点和所述至少一个位置区域的自动驾驶使能状态,生成地图更新信息,并将所述地图更新信息发送给车辆。
本公开第一方面实施方式提出了一种地图更新方法,包括:响应于车辆退出自动驾驶模式,则采集非自动驾驶模式下的驾驶数据,并发送给云服务器;接收所述云服务器根据所述驾驶数据生成的地图更新信息,基于所述地图更新信息,对地图上所述目标道路各位置点的自动驾驶使能状态进行更新,所述自动驾驶使能状态用于指示所述位置点是否允许通行车辆进入自动驾驶模式。
在本公开的一个实施例中,所述地图更新方法,所述驾驶数据包括退出自动驾驶模式时所述目标车辆在所述目标道路上的位置点和退出自动驾驶模式的触发条件。
本公开第二方面实施方式提出了一种地图更新装置,包括:确定模块,用于确定目标道路上退出自动驾驶模式的目标车辆;获取模块,获取所述目标车辆在非自动驾驶模式下的驾驶数据;聚类模块,对所述驾驶数据进行聚类,生成至少一个聚类簇;更新模块,根据所述聚类簇,对地图上所述目标道路各位置点的自动驾驶使能状态进行更新,所述自动驾驶使能状态用于指示所述位置点是否允许通行车辆进入自动驾驶模式。
在本公开的一个实施例中,所述确定模块,还用于:获取行驶在路网上退出自动驾驶模式的候选车辆;获取所述候选车辆的驾驶轨迹;将所述驾驶轨迹和目标道路进行匹配,获取所述目标车辆。
在本公开的一个实施例中,所述更新模块,还用于:将每个所述目标车辆的驾驶数据进行比较,获取在同一个位置点,且所述触发条件相同的目标车辆,作为一个聚类簇。
在本公开的一个实施例中,所述更新模块,还用于:获取所述聚类簇中目标车辆的数量;根据所述目标车辆的数量,确定所述聚类簇所对应位置点的自动驾驶使能状态。
在本公开的一个实施例中,所述更新模块,还用于:响应于所述目标车辆的数量大于设定数量,则确定所述位置点的自动驾驶使能状态为非使能状态;响应于所述目标车辆的数量小于所述设定数量,则获取所述位置点的道路状态信息,并基于所述道路状态,确定所述位置点的自动驾驶使能状态。
在本公开的一个实施例中,所述更新模块,还用于:响应于所述道路状态信息指示所述位置点出现道路异常,则确定所述位置点的自动驾驶使能状态为非使能状态;响应于所述道路状态信息指示所述位置点未出现道路异常,则确定所述位置点的自动驾驶使能状态为使能状态。
在本公开的一个实施例中,所述更新模块,还用于:从确定出非使能的位置点中识别位置上连续的目标位置点,并将所述目标位置点合并得到至少一个位置区域;基于剩余的位置上未连续的位置点和所述至少一个位置区域的自动驾驶使能状态,生成地图更新信息,并将所述地图更新信息发送给车辆。
本公开第二方面实施方式提出了一种地图更新装置,包括:响应于车辆退出自动驾驶模式,则采集非自动驾驶模式下的驾驶数据,并发送给云服务器;接收所述云服务器根据所述驾驶数据生成的地图更新信息,基于所述地图更新信息,对地图上所述目标道路各位置点的自动驾驶使能状态进行更新,所述自动驾驶使能状态用于指示所述位置点是否允许通行车辆进入自动驾驶模式。
在本公开的一个实施例中,所述驾驶数据包括退出自动驾驶模式时所述目标车辆在所述目标道路上的位置点和退出自动驾驶模式的触发条件。
为达上述目的,本公开第三方面实施方式提出了一种电子设备,包括:至少一个处理器;以及与所述至少一个处理器通信连接的存储器;其中,所述存储器存储有可被所述至少一个处理器执行的指令,所述指令被所述至少一个处理器执行,以实现如本公开第一方面任一实施例所述的地图更新方法。
为达上述目的,本公开第四方面实施方式提出了一种存储有计算机指令的非瞬时计算机可读存储介质,其中,所述计算机指令用于实现如本公开第一方面任一实施例所述的地图更新方法。
为达上述目的,本公开第五方面实施方式提出了一种计算机程序产品,包括计算机程序,所述计算机程序在被处理器执行时用于实现如本公开第一方面任一实施例所述的地图更新方法。
为达上述目的,本公开第六方面实施例提出了一种计算机程序,所述计算机程序包括计算机程序代码,当所述计算机程序代码在计算机上运行时,使得计算机执行如本公开第一方面任一实施例所述的地图更新方法。
图1是本公开一个实施方式的一种地图更新方法的示意图;
图2是本公开一个实施方式的另一种地图更新方法的示意图;
图3是本公开一个实施方式的另一种地图更新方法的示意图;
图4是本公开一个实施方式的另一种地图更新方法的示意图;
图5是本公开一个实施方式的另一种地图更新方法的示意图;
图6是本公开一个实施方式的一种地图更新方法的示意图;
图7是本公开一个实施方式的一种地图更新装置的框图;
图8是本公开一个实施方式的另一种地图更新装置的框图;
图9是本公开一个实施方式的一种电子设备的框图。
下面详细描述本公开的实施例,所述实施例的示例在附图中示出,其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的,旨在用于解释本公开,而不能理解为对本公开的限制。
图1为本公开实施例提出的一种地图更新方法的示意图,如图1所示,该地图更新方法包括以下步骤:101-104。
101,确定目标道路上退出自动驾驶模式的目标车辆。
具体地,车辆通常只在高精地图的运行设计区域(Operational Design Domain,ODD)才能使用自动驾驶功能进行驾驶。相关技术中,可通过高精地图的ODD,可以使自动驾驶汽车获得超普通车载传感器探测距离的感知能力,拓展多种复杂功能场景ODD。
在本公开实施例中,车辆退出自动驾驶模式的原因可为多种,其中,可包括自动驾驶过程中用户接管、功能异常退出、定位失效、感知失效等。
102,获取目标车辆在非自动驾驶模式下的驾驶数据。
在本公开实施例中,当车辆从自动驾驶状态进入非自动驾驶状态后,可通过车辆自身的定位系统将驾驶数据上传至服务器中。
在一些实施例中,目标车辆还可通过导航地图应用(Application,APP)将目标车辆在非自动驾驶模式下的驾驶数据上传至服务器中。
需要说明的是,在获取目标车辆在非自动驾驶模式下的驾驶数据后,需要对驾驶数据进行脱敏处理,即对驾驶数据中包含用户信息的敏感数据进行变形,以保护用户的私人信息。
103,对驾驶数据进行聚类,生成至少一个聚类簇。
在获取到目标车辆在非自动驾驶模式下的驾驶数据的后,需要对驾驶数据进行分析。在本公开实施例中,可通过对驾驶数据进行聚类,来分析不同位置、不同触发条件的目标车辆。
在本公开实施例中,可将每个目标车辆的驾驶数据进行比较,获取在同一个位置点,且触发条件相同的目标车辆,作为一个聚类簇。由此,可通过对同一位置点同一触发条件的目标车辆进行分析和横向比较,判断该位置点是否为用户自身原因进行自动驾驶的切换,大大增加了数据的可信度。
104,根据聚类簇,对地图上目标道路各位置点的自动驾驶使能状态进行更新,自动驾驶使能状态用于指示位置点是否允许通行车辆进入自动驾驶模式。
需要说明的是,目标道路上的位置点可为多个。该位置点可为提前设定好的,也可以根据一定的规则在地图上进行划定。举例来说,可在目标道路上每隔一段距离划定一个位置点、在目标道路关键位置(例如桥梁、岔路口)等设置位置点等,此处不作任何限定,具体可以根据实际情况进行设定。
在本公开实施例中,在获取到驾驶数据的聚类簇后,可通过对不同位置不同的聚类簇进行分析,以对该位置点的使能状态进行更新。
进一步地,服务器中更新后的地图可下发给车辆中的地图进行更新。
在本公开实施例中,可将通过服务器对聚类簇进行分析,以生成该聚类簇对应的配置信息,并通过配置信息对地图进行更新。
在一些实施例中,还可通过人工对聚类簇的驾驶数据进行分析,以判断该聚类簇对应的位置点是否还具备自动驾驶条件,并生成配置信息。进一步地,云端在获取到配置信息后,可根据配置信息对地图进行更新,并将更新后的地图发送给车端。由此,实现ODD的动态调整。
需要说明的是,高精地图的ODD更新周期并不固定,举例来说,该更新周期可为12小时、24小时、48小时等。具体根据实际需要进行设定,此处不作任何限定。由此,通过设定更新时间,可以实现动态更新ODD的目的,增强了地图的时效性,同时增加了用户自动驾驶的安全性。
在本公开实施例中,首先确定目标道路上退出自动驾驶模式的目标车辆,并获取目标车辆在非自动驾驶模式下的驾驶数据,然后对驾驶数据进行聚类,生成至少一个聚类簇,最后根据聚类簇,对地图上目标道路各位置点的自动驾驶使能状态进行更新,自动驾驶使能状态用于指示位置点是否允许通行车辆进入自动驾驶模式。由此,通过对道路上退出自动驾驶模式的车辆进行分类的方式,可以更好地分析出道路是否还具备自动驾驶的条件,大大增加了用户自动驾驶的安全性。
为了更好的确定目标道路上自动驾驶状态异常的目标车辆,还可通过图2进一步解释,该方法包括:201-203。
201,获取行驶在路网上退出自动驾驶模式的候选车辆。
在本公开实施例中,可通过车辆自身的定位系统,将驾驶数据上传至服务器中,并根据驾驶数据分析该车辆是否为退出自动驾驶模式的候选车辆。
在一些实施例中,在车辆退出自动驾驶模式后,还可通过导航地图APP将车辆的驾驶数据上传至服务器中,并将车辆确定为候选车辆。
202,获取候选车辆的驾驶轨迹。
在本公开实施例中,可以通过候选车辆的定位系统将车辆的驾驶轨迹上传到服务器中,以获取候选车辆的驾驶轨迹。
在一些实施例中,服务器可以与道路信息数据库和/或交通管理平台连接,从信息库和 /或交通管理平台处获取候选车辆的驾驶轨迹。
在一些实施例中,可通过候选车辆安装的导航地图APP将候选车辆的行驶轨迹上传到服务器中。
203,将驾驶轨迹和目标道路进行匹配,获取目标车辆。
在本公开实施例中,可将候选车辆的驾驶轨迹和目标道路的形状进行匹配,进一步地,当候选车辆的驾驶轨迹和目标道路的形状相同时,则可认为该候选车辆在目标道路上行驶,该候选车辆为目标车辆。
需要说明的是,可首先获取驾驶轨迹和目标道路的形状的匹配值,并将匹配值与匹配阈值进行比较,以确定该候选车辆是否为目标车辆。举例来说,该匹配阈值可为0.9,驾驶轨迹和目标道路的形状的匹配值大于或等于0.9时,则可认为该候选车辆为目标车辆,驾驶轨迹和目标道路的形状的匹配值小于0.9时,则可认候选车辆不为目标车辆。
在本公开实施例中,首先获取行驶在路网上退出自动驾驶模式的候选车辆,然后获取候选车辆的驾驶轨迹,最后将驾驶轨迹和目标道路进行匹配,获取目标车辆。由此,通过道路轨迹对候选车辆进行筛选,减少后续数据的处理,降低处理成本。
上述实施例中,根据聚类簇,对地图上目标道路的自动驾驶使能信息进行更新,还可通过图3进一步解释,包括如图3所示的以下步骤:301-302。
301,获取聚类簇中目标车辆的数量。
在本公开实施例中,聚类过程可以参考上述实施例中的步骤。
进一步地,在生成至少一个聚类簇后,可对聚类簇进行统计,以获取聚类簇中目标车辆的数量。
302,根据目标车辆的数量,确定聚类簇所对应位置点的自动驾驶使能状态。
在本公开实施例中,响应于目标车辆的数量大于设定数量,则确定位置点的自动驾驶使能状态为非使能状态,该位置点已不具备自动驾驶的条件;响应于目标车辆的数量小于设定数量,则获取位置点的道路状态信息,并基于道路状态,确定位置点的自动驾驶使能状态。
举例来说,设定数量可为5,当聚类簇中的目标车辆数量大于或等于5时,则可认为该聚类簇对应的位置点已不具备自动驾驶条件,当聚类簇中的目标车辆数小于5时,则按照上述实施例中的步骤,继续对聚类簇进行数据分析。
在本公开实施例中,首先获取聚类簇中目标车辆的数量,然后根据目标车辆的数量,确定聚类簇所对应位置点的自动驾驶使能状态。由此,通过聚类簇中目标车辆的数量,判断该位置点是否具备自动驾驶条件,可以降低数据处理的成本。
上述实施例中,基于道路状态,确定位置点的自动驾驶使能状态,还可通过图4进行解释,如图4所示,包括以下步骤:401-404。
401,获取聚类簇中目标车辆的数量。
具体可参照上述实施例中的步骤,此处不再赘述。
402,响应于目标车辆的数量小于设定数量,则获取位置点的道路状态信息,并基于道 路状态,确定位置点的自动驾驶使能状态。
在本公开实施例中,服务器可以与道路信息数据库和/或交通管理平台连接,从信息库和/或交通管理平台处获取位置点的道路状态信息,并基于道路状态,确定位置点的自动驾驶使能状态。
在一些实施例中,还可根据车辆的信息采集设备获取位置点的道路状态信息,举例来说,该信息采集设备可包括车载摄像头、车载雷达等。
403,响应于道路状态信息指示位置点出现道路异常,则确定位置点的自动驾驶使能状态为非使能状态。
404,响应于道路状态信息指示位置点未出现道路异常,则确定位置点的自动驾驶使能状态为使能状态。
需要说明的是,道路异常可包括多种,举例来说,道路异常可包括道路施工、交通事故、卫星无法定位等。当位置点道路状态信息被判断为道路异常后,可认为该道路已经不具备自动驾驶的条件;当位置点道路状态信息被判断为非道路异常后,则可认为该自动驾驶切换为非自动驾驶的原因为用户自身原因,该位置点具备自动驾驶的条件。
进一步地,用户自身原因可包括用户自愿切换自动驾驶为非自动驾驶、车辆故障等。
在本公开实施例中,首先获取聚类簇中目标车辆的数量,然后响应于目标车辆的数量小于设定数量,则获取位置点的道路状态信息,并基于道路状态,确定位置点的自动驾驶使能状态,最后响应于道路状态信息指示位置点出现道路异常,则确定位置点的自动驾驶使能状态为非使能状态,响应于道路状态信息指示位置点未出现道路异常,则确定位置点的自动驾驶使能状态为使能状态。由此,通过对道路状态信息对驾驶数据进行筛选,可以确定位置点是否还具备自动驾驶的条件,增加了地图的安全性和实用性。
图5为本公开实施例一种地图更新方法的另一种示例性实施方式的示意图,如图5所示,该方法包括:501-502。
501,从确定出非使能的位置点中识别位置上连续的目标位置点,并将目标位置点合并得到至少一个位置区域。
在本公开实施例中,在确定不具备自动驾驶条件的位置点后,可对位置点进行数据处理,分析出位置点之间的位置关系。
在一些实施例中,当目标位置点相邻的位置点为不具备驾驶条件的位置点时,可将位置点的区域进行合并成为一个连续的位置区域,该位置区域即为一个非ODD,并生成配置数据,对地图进行更新。
在一些实施例中,当目标位置点相邻的位置点为具备驾驶条件的位置点时,则将此目标位置点位于的位置区域更新为非ODD。
502,基于剩余的位置上未连续的位置点和至少一个位置区域的自动驾驶使能状态,生成地图更新信息,并将地图更新信息发送给车辆。
在本公开实施例中,首先从确定出非使能的位置点中识别位置上连续的目标位置点,并将目标位置点合并得到至少一个位置区域,然后基于剩余的位置上未连续的位置点和至 少一个位置区域的自动驾驶使能状态,生成地图更新信息,并将地图更新信息发送给车辆。由此,可以通过对非使能的位置点进行分析,将连续位置点合并为连续的非ODD。
图6为本公开实施例一种地图更新方法的一种示例性实施方式的示意图,如图6所示,该方法包括:601-602。
601,响应于车辆退出自动驾驶模式,则采集非自动驾驶模式下的驾驶数据,并发送给云服务器。
在本公开实施例中,响应于车辆退出自动驾驶模式,车辆传感器可收集汽车的驾驶数据,并发送给导航地图APP,并由导航地图APP发送给云服务器。
在一些实施例中,还可在车辆驾驶完完整的非ODD道路后,将驾驶数据上传到服务器中。
在一些实施例中,还可在车辆处于非驾驶状态后,将传感器采集的车辆完整的驾驶数据按照采样时间顺序上传到服务器中。进一步地,服务器可根据现有的ODD地图和采集的驾驶数据进行匹配,以确定现有ODD道路状态是否需要进行更新。
602,接收云服务器根据驾驶数据生成的地图更新信息,基于地图更新信息,对地图上目标道路各位置点的自动驾驶使能状态进行更新,自动驾驶使能状态用于指示位置点是否允许通行车辆进入自动驾驶模式。
需要说明的是,驾驶数据包括退出自动驾驶模式时目标车辆在目标道路上的位置点和退出自动驾驶模式的触发条件。
进一步地,在驾驶车辆退出自动驾驶模式后,还需要对驾驶车辆恢复自动驾驶状态的位置点进行采集,我们可以认为该恢复点与退出自动驾驶模式的位置点之间为目标非ODD区域,方便后续将目标非ODD区域恢复为ODD区域进行人工复核,减小目标区域,降低恢复成本。在本公开实施例中,首先响应于车辆退出自动驾驶模式,则采集非自动驾驶模式下的驾驶数据,并发送给云服务器,然后接收云服务器根据驾驶数据生成的地图更新信息,基于地图更新信息,对地图上目标道路各位置点的自动驾驶使能状态进行更新,自动驾驶使能状态用于指示位置点是否允许通行车辆进入自动驾驶模式。由此,通过对采集非自动驾驶模式下的驾驶数据进行分析,对目标道路进行状态的更新,增加用户自动驾驶的安全性。
进一步地,自动驾驶车辆接近非ODD时,地图APP可对自动驾驶车辆进行提醒,并由车辆的处理器进行相应的操作,举例来说,可对车辆的驾驶状态进行降级、提示接管、靠边停车等。
图7为本公开实施例提出的一种地图更新装置的示意图,如图7所示,该地图更新装置700,包括:确定模块710、获取模块720、聚类模块730、更新模块740。
其中,确定模块710,用于确定目标道路上退出自动驾驶模式的目标车辆。
获取模块720,获取目标车辆在非自动驾驶模式下的驾驶数据。
聚类模块730,对驾驶数据进行聚类,生成至少一个聚类簇。
更新模块740,根据聚类簇,对地图上目标道路各位置点的自动驾驶使能状态进行更 新,自动驾驶使能状态用于指示位置点是否允许通行车辆进入自动驾驶模式。
在本公开的一个实施例中,确定模块710,还用于:获取行驶在路网上退出自动驾驶模式的候选车辆;获取候选车辆的驾驶轨迹;将驾驶轨迹和目标道路进行匹配,获取目标车辆。
在本公开的一个实施例中,更新模块740,还用于:将每个目标车辆的驾驶数据进行比较,获取在同一个位置点,且触发条件相同的目标车辆,作为一个聚类簇。
在本公开的一个实施例中,更新模块740,还用于:获取聚类簇中目标车辆的数量;根据目标车辆的数量,确定聚类簇所对应位置点的自动驾驶使能状态。
在本公开的一个实施例中,更新模块740,还用于:响应于目标车辆的数量大于设定数量,则确定位置点的自动驾驶使能状态为非使能状态;响应于目标车辆的数量小于设定数量,则获取位置点的道路状态信息,并基于道路状态,确定位置点的自动驾驶使能状态。
在本公开的一个实施例中,更新模块740,还用于:响应于道路状态信息指示位置点出现道路异常,则确定位置点的自动驾驶使能状态为非使能状态;响应于道路状态信息指示位置点未出现道路异常,则确定位置点的自动驾驶使能状态为使能状态。
在本公开的一个实施例中,更新模块740,还用于:从确定出非使能的位置点中识别位置上连续的目标位置点,并将目标位置点合并得到至少一个位置区域;基于剩余的位置上未连续的位置点和至少一个位置区域的自动驾驶使能状态,生成地图更新信息,并将地图更新信息发送给车辆。
图8为本公开提出的一种地图更新装置800的示意图,如图8所示,该装置包括:采集模块810、接收模块820。
其中,采集模块810,用于响应于车辆退出自动驾驶模式,则采集非自动驾驶模式下的驾驶数据,并发送给云服务器。
接收模块820,接收云服务器根据驾驶数据生成的地图更新信息,基于地图更新信息,对地图上目标道路各位置点的自动驾驶使能状态进行更新,自动驾驶使能状态用于指示位置点是否允许通行车辆进入自动驾驶模式。
在本公开的一个实施例中,驾驶数据包括退出自动驾驶模式时目标车辆在目标道路上的位置点和退出自动驾驶模式的触发条件。
为了实现上述实施例,本公开实施例还提出一种电子设备900,如图9所示,该电子设备900包括:处理器901和处理器通信连接的存储器902,存储器902存储有可被至少一个处理器执行的指令,指令被至少一个处理器901执行,以实现如本公开第一方面实施例的地图更新方法。
为了实现上述实施例,本公开实施例还提出一种存储有计算机指令的非瞬时计算机可读存储介质,其中,计算机指令用于使计算机实现如本公开第一方面实施例的地图更新方法。
为了实现上述实施例,本公开实施例还提出一种计算机程序产品,包括计算机程序,计算机程序在被处理器执行时实现如本公开第一方面实施例的地图更新方法。
为了实现上述实施例,本公开实施例还提出一种计算机程序,该计算机程序包括计算机程序代码,当该计算机程序代码在计算机上运行时,使得计算机执行如本公开第一方面实施例的地图更新方法。
需要说明的是,前述对地图更新方法的实施例的解释说明也适用于该本公开实施例的地图更新装置、非临时性计算机可读存储介质、电子设备、计算机程序产品和计算机程序,此处不再赘述。
在本公开的描述中,需要理解的是,术语“中心”、“纵向”、“横向”、“长度”、“宽度”、“厚度”、“上”、“下”、“前”、“后”、“左”、“右”、“竖直”、“水平”、“顶”、“底”“内”、“外”、“顺时针”、“逆时针”、“轴向”、“径向”、“周向”等指示的方位或位置关系为基于附图所示的方位或位置关系,仅是为了便于描述本公开和简化描述,而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作,因此不能理解为对本公开的限制。
此外,术语“第一”、“第二”仅用于描述目的,而不能理解为指示或暗示相对重要性或者隐含指明所指示的技术特征的数量。由此,限定有“第一”、“第二”的特征可以明示或者隐含地包括一个或者更多个该特征。在本公开的描述中,“多个”的含义是两个或两个以上,除非另有明确具体的限定。
在本说明书的描述中,参考术语“一个实施例”、“一些实施例”、“示例”、“具体示例”、或“一些示例”等的描述意指结合该实施例或示例描述的具体特征、结构、材料或者特点包含于本公开的至少一个实施例或示例中。在本说明书中,对上述术语的示意性表述不必须针对的是相同的实施例或示例。而且,描述的具体特征、结构、材料或者特点可以在任一个或多个实施例或示例中以合适的方式结合。此外,在不相互矛盾的情况下,本领域的技术人员可以将本说明书中描述的不同实施例或示例以及不同实施例或示例的特征进行结合和组合。
尽管上面已经示出和描述了本公开的实施例,可以理解的是,上述实施例是示例性的,不能理解为对本公开的限制,本领域的普通技术人员在本公开的范围内可以对上述实施例进行变化、修改、替换和变型。
本公开所有实施例均可以单独被执行,也可以与其他实施例相结合被执行,均视为本公开要求的保护范围。
Claims (15)
- 一种地图的更新方法,包括:确定目标道路上退出自动驾驶模式的目标车辆;获取所述目标车辆在非自动驾驶模式下的驾驶数据;对所述驾驶数据进行聚类,生成至少一个聚类簇;根据所述聚类簇,对地图上所述目标道路各位置点的自动驾驶使能状态进行更新,所述自动驾驶使能状态用于指示所述位置点是否允许通行车辆进入自动驾驶模式。
- 根据权利要求1所述的方法,其中,所述确定目标道路上退出自动驾驶模式的目标车辆,包括:获取行驶在路网上退出自动驾驶模式的候选车辆;获取所述候选车辆的驾驶轨迹;将所述驾驶轨迹和目标道路进行匹配,确定所述目标车辆。
- 根据权利要求1或2所述的方法,其中,所述驾驶数据包括退出自动驾驶模式时所述目标车辆在所述目标道路上的位置点和退出自动驾驶模式的触发条件,其中,所述对所述驾驶数据进行聚类,生成至少一个聚类簇,包括:将每个所述目标车辆的驾驶数据进行比较,获取在同一个位置点,且所述触发条件相同的目标车辆,作为一个聚类簇。
- 根据权利要求1-3中任一项所述的方法,其中,所述根据所述聚类簇,对地图上所述目标道路的自动驾驶使能信息进行更新,还包括:获取所述聚类簇中目标车辆的数量;根据所述目标车辆的数量,确定所述聚类簇所对应位置点的自动驾驶使能状态。
- 根据权利要求4所述的方法,其中,所述根据所述目标车辆的数量,确定所述聚类簇所对应位置点的所述自动驾驶使能状态,包括:响应于所述目标车辆的数量大于设定数量,则确定所述位置点的自动驾驶使能状态为非使能状态;响应于所述目标车辆的数量小于所述设定数量,则获取所述位置点的道路状态信息,并基于所述道路状态,确定所述位置点的自动驾驶使能状态。
- 根据权利要求5所述的方法,其中,所述基于所述道路状态,确定所述位置点的自动驾驶使能状态,包括:响应于所述道路状态信息指示所述位置点出现道路异常,则确定所述位置点的自动驾 驶使能状态为非使能状态;响应于所述道路状态信息指示所述位置点未出现道路异常,则确定所述位置点的自动驾驶使能状态为使能状态。
- 根据权利要求6所述的方法,其中,所述方法还包括:从确定出非使能的位置点中识别位置上连续的目标位置点,并将所述目标位置点合并得到至少一个位置区域;基于剩余的位置上未连续的位置点和所述至少一个位置区域的自动驾驶使能状态,生成地图更新信息,并将所述地图更新信息发送给车辆。
- 一种地图的更新方法,包括:响应于车辆退出自动驾驶模式,则采集非自动驾驶模式下的驾驶数据,并发送给云服务器;接收所述云服务器根据所述驾驶数据生成的地图更新信息,基于所述地图更新信息,对地图上所述目标道路各位置点的自动驾驶使能状态进行更新,所述自动驾驶使能状态用于指示所述位置点是否允许通行车辆进入自动驾驶模式。
- 根据权利要求8所述的方法,其中,所述驾驶数据包括退出自动驾驶模式时所述目标车辆在所述目标道路上的位置点和退出自动驾驶模式的触发条件。
- 一种地图的更新装置,包括:确定模块,用于确定目标道路上退出自动驾驶模式的目标车辆;获取模块,获取所述目标车辆在非自动驾驶模式下的驾驶数据;聚类模块,对所述驾驶数据进行聚类,生成至少一个聚类簇;更新模块,根据所述聚类簇,对地图上所述目标道路各位置点的自动驾驶使能状态进行更新,所述自动驾驶使能状态用于指示所述位置点是否允许通行车辆进入自动驾驶模式。
- 一种地图的更新装置,包括:采集模块,用于响应于车辆退出自动驾驶模式,则采集非自动驾驶模式下的驾驶数据,并发送给云服务器;接收模块,用于接收所述云服务器根据所述驾驶数据生成的地图更新信息,基于所述地图更新信息,对地图上所述目标道路各位置点的自动驾驶使能状态进行更新,所述自动驾驶使能状态用于指示所述位置点是否允许通行车辆进入自动驾驶模式。
- 一种电子设备,包括存储器、处理器;其中,所述处理器通过读取所述存储器中存储的可执行程序代码来运行与所述可执行程序代码对应的程序,以用于实现如权利要求 1-9中任一项所述的方法。
- 一种计算机可读存储介质,其上存储有计算机程序,其中,该程序被处理器执行时实现如权利要求1-9中任一项所述的方法。
- 一种计算机程序产品,包括计算机程序,所述计算机程序在被处理器执行时实现根据权利要求1-9中任一项所述的方法。
- 一种计算机程序,所述计算机程序包括计算机程序代码,当所述计算机程序代码在计算机上运行时,使得计算机执行根据权利要求1-9中任一项所述的方法。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP22894803.0A EP4435623A1 (en) | 2021-11-18 | 2022-11-15 | Map update method and apparatus thereof |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111372383.1 | 2021-11-18 | ||
CN202111372383.1A CN115438051A (zh) | 2021-11-18 | 2021-11-18 | 地图更新方法及其装置 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2023088270A1 true WO2023088270A1 (zh) | 2023-05-25 |
Family
ID=84271522
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2022/132089 WO2023088270A1 (zh) | 2021-11-18 | 2022-11-15 | 地图更新方法及其装置 |
Country Status (3)
Country | Link |
---|---|
EP (1) | EP4435623A1 (zh) |
CN (1) | CN115438051A (zh) |
WO (1) | WO2023088270A1 (zh) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116340307A (zh) * | 2023-06-01 | 2023-06-27 | 北京易控智驾科技有限公司 | 坡道图层生成方法和装置、高精度地图及电子设备 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017146934A (ja) * | 2016-02-19 | 2017-08-24 | 住友電気工業株式会社 | 情報処理装置、データ抽出方法、プログラム更新方法、記憶媒体及びコンピュータプログラム |
CN109781122A (zh) * | 2019-01-31 | 2019-05-21 | 北京经纬恒润科技有限公司 | 高精度地图更新方法及装置 |
CN111105614A (zh) * | 2019-12-06 | 2020-05-05 | 惠州市德赛西威汽车电子股份有限公司 | 一种基于道路社交圈的交通状况预测方法 |
CN111161587A (zh) * | 2020-01-03 | 2020-05-15 | 北京汽车集团有限公司 | 车辆的控制方法 |
CN113359698A (zh) * | 2021-05-06 | 2021-09-07 | 前海七剑科技(深圳)有限公司 | 车辆导航方法、装置、计算机设备和存储介质 |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR102103941B1 (ko) * | 2018-11-14 | 2020-04-23 | 주식회사 모빌테크 | 포인트 클라우드 맵 기반의 자율주행차량용 도로 및 차선데이터 실시간 업데이트 방법 |
US11934204B2 (en) * | 2019-05-20 | 2024-03-19 | Hyundai Mobis Co., Ltd. | Autonomous driving apparatus and method |
CN113147793A (zh) * | 2021-05-12 | 2021-07-23 | 银隆新能源股份有限公司 | 电子地图的更新方法及装置、自动驾驶车辆 |
-
2021
- 2021-11-18 CN CN202111372383.1A patent/CN115438051A/zh active Pending
-
2022
- 2022-11-15 WO PCT/CN2022/132089 patent/WO2023088270A1/zh active Application Filing
- 2022-11-15 EP EP22894803.0A patent/EP4435623A1/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2017146934A (ja) * | 2016-02-19 | 2017-08-24 | 住友電気工業株式会社 | 情報処理装置、データ抽出方法、プログラム更新方法、記憶媒体及びコンピュータプログラム |
CN109781122A (zh) * | 2019-01-31 | 2019-05-21 | 北京经纬恒润科技有限公司 | 高精度地图更新方法及装置 |
CN111105614A (zh) * | 2019-12-06 | 2020-05-05 | 惠州市德赛西威汽车电子股份有限公司 | 一种基于道路社交圈的交通状况预测方法 |
CN111161587A (zh) * | 2020-01-03 | 2020-05-15 | 北京汽车集团有限公司 | 车辆的控制方法 |
CN113359698A (zh) * | 2021-05-06 | 2021-09-07 | 前海七剑科技(深圳)有限公司 | 车辆导航方法、装置、计算机设备和存储介质 |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116340307A (zh) * | 2023-06-01 | 2023-06-27 | 北京易控智驾科技有限公司 | 坡道图层生成方法和装置、高精度地图及电子设备 |
CN116340307B (zh) * | 2023-06-01 | 2023-08-08 | 北京易控智驾科技有限公司 | 坡道图层生成方法和装置、高精度地图及电子设备 |
Also Published As
Publication number | Publication date |
---|---|
CN115438051A (zh) | 2022-12-06 |
EP4435623A1 (en) | 2024-09-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11941976B2 (en) | System and method for sharing data collected from the street sensors | |
JP6424761B2 (ja) | 運転支援システム及びセンタ | |
US11361556B2 (en) | Deterioration diagnosis device, deterioration diagnosis system, deterioration diagnosis method, and storage medium for storing program | |
JP4582192B2 (ja) | 車両故障解析システム、車両故障解析装置、車両故障解析方法 | |
KR20200014931A (ko) | 차량용 정보 기억 방법, 차량의 주행 제어 방법, 및 차량용 정보 기억 장치 | |
US11657707B2 (en) | System for calculating an error probability of vehicle sensor data | |
US7831348B2 (en) | Failure detection device, failure detection system and failure detection method | |
JP2012166620A (ja) | 車両情報取得システム及び車両情報取得方法 | |
DE102014216954A1 (de) | System und Verfahren für das Bereitstellen von Wetterinformation | |
WO2023088270A1 (zh) | 地图更新方法及其装置 | |
WO2012090144A2 (en) | Real-time drive assistance system and method | |
JP7380616B2 (ja) | 自動運転制御装置、自動運転制御方法、及び自動運転制御プログラム | |
US20190385444A1 (en) | Vehicle control system, data processing apparatus, and vehicle control method | |
CN109360417B (zh) | 一种基于区块链的危险驾驶行为辨识与推送方法及系统 | |
CN110466450B (zh) | 汽车安全检测系统 | |
US12027042B2 (en) | Road information providing system and road information providing method | |
CN109410598B (zh) | 一种基于计算机视觉的交通路口拥堵检测方法 | |
JP2024045531A (ja) | 情報処理装置、サーバ装置、情報処理方法、及びプログラム | |
CN112598908B (zh) | 驾驶员闯红灯识别方法、装置、电子设备及存储介质 | |
KR101644109B1 (ko) | 어라운드뷰 영상을 이용한 운전면허 코스 시험의 자동채점 시스템 및 방법 | |
JP7363621B2 (ja) | 情報処理装置、情報処理方法、及び、プログラム | |
US20220351553A1 (en) | Indexing sensor data about the physical world | |
US12024100B2 (en) | Device-level fault detection | |
WO2016072082A1 (ja) | 運転支援システム及びセンタ | |
KR102577751B1 (ko) | 스마트 버스 안전관리 시스템 |
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: 22894803 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2022894803 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref document number: 2022894803 Country of ref document: EP Effective date: 20240618 |