WO2024051248A1 - 一种自动驾驶车辆的数据标记方法及标记装置 - Google Patents
一种自动驾驶车辆的数据标记方法及标记装置 Download PDFInfo
- Publication number
- WO2024051248A1 WO2024051248A1 PCT/CN2023/100040 CN2023100040W WO2024051248A1 WO 2024051248 A1 WO2024051248 A1 WO 2024051248A1 CN 2023100040 W CN2023100040 W CN 2023100040W WO 2024051248 A1 WO2024051248 A1 WO 2024051248A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data
- vehicle
- information
- rule
- model
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 230000007613 environmental effect Effects 0.000 claims abstract description 8
- 230000001960 triggered effect Effects 0.000 claims description 42
- 238000002372 labelling Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 16
- 230000000007 visual effect Effects 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 6
- 238000011156 evaluation Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 230000008569 process Effects 0.000 description 6
- 238000012360 testing method Methods 0.000 description 5
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000013480 data collection Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000000644 propagated effect Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME 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
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0841—Registering performance data
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME 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
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0808—Diagnosing performance data
Definitions
- the present application relates to the field of autonomous driving technology, specifically, to a data marking method and marking device for an autonomous vehicle.
- This application requests the priority of the patent application submitted to the State Intellectual Property Office of China on September 9, 2022, with the application number 202211106633.1 and the invention title "A data marking method and marking device for autonomous vehicles”.
- Autonomous driving refers to the collaborative work of visual image processing technology, radar sensing technology, monitoring equipment, global positioning systems and artificial intelligence technology, so that the vehicle's central processor can be fully automatic and safe without any active human intervention. Controlled machine autonomous driving behavior; autonomous driving technology will become the general trend of future automobile development.
- the information data dropped to disk is mainly used for problem recurrence, bug location and troubleshooting in offline environments, and collection of high-precision maps.
- the accumulated data can also be used for simulation.
- test tasks of autonomous vehicles can be divided into many different task types.
- the current testing method uses the same set of fixed data disk storage methods for different test task types. This will collect a large amount of repeated data that has nothing to do with the test task, wasting disk resources and causing disorganized data to bring problems to data analysis. a heavy workload.
- the purpose of this application is to provide a data labeling method and labeling device for autonomous vehicles to solve the technical problems of data duplication, waste of disk resources, and heavy data processing workload in the prior art.
- this application provides a data system for an autonomous driving vehicle.
- the marking method includes: collecting relevant data of the vehicle, the data including vehicle own parameters and environmental parameters; triggering data type judgment, and judging the type of the data, wherein the type includes model trigger data and rule-triggered data; when the data belongs to the model-triggered data or rule-triggered data, the data is marked and recorded.
- determining the type of the data includes: comparing the data with rule configuration information and model configuration information, where the rule configuration information and model configuration information include multiple entries and are pre-stored. In the vehicle; based on the comparison result, the type of the data is determined, where the data has multiple types.
- the comparing the information with the rule configuration information and the model configuration information includes: comparing the information with each item of the rule configuration information and the model configuration information.
- the method before collecting the relevant information of the vehicle, the method further includes: selecting the channel information of the vehicle to verify the data collected by the vehicle.
- the method further includes tagging the data based on recognized voice input information or input information of a UI interface of the autonomous vehicle.
- the method further includes obtaining attribute information of the vehicle, and recording the attribute information in the data collected by the vehicle, where the attribute information includes calibration information, current location information of the vehicle, Weather information.
- the method before determining the type of the data, the method further includes: updating the rule configuration information and the model configuration information.
- this application also provides a data marking device for an autonomous vehicle, including:
- a collection module used to collect relevant data of the vehicle, where the data includes vehicle parameters and environmental parameters; a judgment module, used to judge the type of the data after triggering the data type judgment, where the type includes a model Trigger data and rule-triggered data; a marking module, used to mark and record the data when the data belongs to the model-triggered data or rule-triggered data.
- the present application also provides a storage medium that stores a computer program.
- the computer program is executed by a processor, the steps of the method described in any of the above technical solutions are implemented.
- the present application also provides an electronic device, which at least includes a memory and a processor.
- a computer program is stored on the memory.
- the processor implements any of the above technical solutions when executing the computer program on the memory. steps of the method described in .
- the embodiment of this application marks model-triggered data or rule-triggered data based on the type of vehicle-related data.
- a visual desktop application it supports rule configuration and delivery, model update and delivery, partial and full data customization, and weather information. Markings, road section information markings, voice control and reminders, etc., can realize the automatic collection of specified data under single-person driving.
- Figure 1 is a schematic diagram of the steps of the data labeling method for autonomous vehicles provided by this application;
- Figure 2 is a flow chart of steps for determining the data type provided by this application.
- Figure 3 is a structural block diagram of the data marking device for autonomous vehicles provided by this application.
- Figure 4 is a schematic structural diagram of an electronic device provided by this application.
- the first embodiment of the present application relates to the field of autonomous driving technology, and specifically to a data labeling method for autonomous vehicles.
- Autonomous vehicles here include but are not limited to pure electric vehicles, hybrid vehicles, etc.
- the embodiment of the present application marks model-triggered data or rule-triggered data based on the type of vehicle-related data, thereby realizing automatic collection and marking of designated data during vehicle operation.
- the data labeling method for autonomous vehicles includes the following steps:
- relevant data of the vehicle are collected, where the data includes the vehicle itself parameters and environment parameters.
- the information includes information about the surrounding environment where the vehicle is located, such as information about obstacles around the vehicle, traffic congestion status information, etc.; on the other hand, the related information also includes information about the vehicle itself, such as the The current control software version information of the vehicle, the status and parameter information of the vehicle when collecting data.
- the version information can be retained during data recording, and the collected data can be organized and archived according to the version information.
- the version information can be submitted through the commit information submitted by git. To determine, it can also be marked by the version in the published product description file.
- vehicle external information it can be collected through information collection components such as cameras or sensors connected to the central processor of the vehicle.
- information collection components such as cameras or sensors connected to the central processor of the vehicle.
- current road condition information can be collected through a front camera, where the road condition information includes information about obstacles ahead and traffic lights. Information etc.
- the method further includes, before collecting the relevant information of the vehicle, selecting the channel information of the vehicle to verify the data collected by the vehicle.
- Channel is a channel for transmitting data and manages data communication in CyberRT. Users can publish/subscribe to the same Channel to establish communication and achieve point-to-point communication.
- step S101 After completing the above step S101, in this step, data type determination is triggered, and the type of the data is determined, where the type includes model triggering data and rule triggering data.
- determining the data type specifically includes:
- rule triggering strongly relies on the output of each sensor data, when the rules cannot be effectively implemented, triggering through the trained model Send target data collection instructions, such as detecting special vehicles, special obstacles, special driving routes, etc.
- target data collection instructions such as detecting special vehicles, special obstacles, special driving routes, etc.
- rule configuration information and model configuration information are stored in the vehicle in advance. We can regularly update the rule configuration information and model configuration information stored in the vehicle as needed to ensure the integrity of information collection.
- the type of data is determined based on the result of comparing the collected data with the pre-stored rule configuration information and model configuration information.
- the same parameter will represent different meanings in different scenarios. Therefore, when collecting data, you can select single or multiple trigger rules to combine the information. Compare with each entry of the rule configuration information and model configuration information. When multiple rules are triggered for the same data, the rules triggered by the collected data will be marked, that is, the same data will have multiple rule marks.
- rule configuration data structure is as follows:
- rule logic When the rule switch is turned on, the data of the target Channel is checked in the rule arbitration logic trigger.cc. If the rule conditions are met, the rule is deemed to be triggered. It is necessary to backtrace and continuously record data according to the rule configuration information, and record the rule hit information in info .txt. In order to avoid noise Noise interference, rule logic will be updated and issued in real time according to needs.
- step S102 when the data belongs to the model-triggered data or rule-triggered data, the data is marked.
- the method further includes marking the data based on the recognized voice input information or the input information of the UI interface of the autonomous vehicle.
- the method further includes obtaining attribute information of the vehicle, and recording the attribute information in the data collected by the vehicle, where the attribute information includes calibration information, current location information of the vehicle, Weather information.
- the current vehicle location information can be determined and recorded through the positioning information; the weather information of the current location can be obtained through the positioning information.
- the Baidu map interface can be used to obtain the city name based on the IP to determine the location of the current vehicle area. Weather information and records.
- the data labeling method for autonomous vehicles marks model-triggered data or rule-triggered data based on the type of vehicle-related data, and supports rule configuration and issuance, model update and downloading through a visual desktop application. Transmission, partial and full data customization, weather information marking, road section information marking, voice control and reminders, etc., can realize the automatic collection of specified data under single-person driving.
- the second aspect of this application also provides an autonomous vehicle Vehicle data marking device, which can be integrated on electronic equipment.
- the marking device 200 may include: a collection module 210, a judgment module 220, and a marking module 230, specifically as follows:
- the collection module 210 is used to collect relevant data of the vehicle, where the data includes vehicle parameters and environmental parameters.
- the judgment module 220 is used to judge the type of the data after triggering the data type judgment, where the type includes model-triggered data and rule-triggered data.
- the marking module 230 is configured to mark the data when the data belongs to the model-triggered data or rule-triggered data.
- the data labeling method for autonomous vehicles marks model-triggered data or rule-triggered data based on the type of vehicle-related data, and supports rule configuration and issuance, model update and downloading through a visual desktop application. Transmission, partial and full data customization, weather information marking, road segment information marking, voice control and reminders, etc., can realize the automatic collection of specified data under single-person driving.
- the third embodiment of the present application provides a storage medium.
- the storage medium is a computer-readable medium and stores a computer program.
- the method provided by the embodiment of the present application is implemented, including the following: Steps S101 to S103:
- S101 collect relevant data of the vehicle, where the data includes the vehicle's own parameters and environmental parameters;
- S102 trigger data type determination, and determine the type of data, where the type includes model triggering data and rule triggering data;
- the data labeling method for autonomous vehicles provided according to the embodiments of this application is based on vehicle phase Depending on the type of data, model-triggered data or rule-triggered data is marked.
- model-triggered data or rule-triggered data is marked.
- the visual desktop application it supports rule configuration and delivery, model update and delivery, partial and full data customization, weather information marking, road section information marking, Voice control and reminders, etc., can realize the automatic collection of specified data under single-person driving.
- the fourth embodiment of the present application provides an electronic device.
- the electronic device at least includes a processor 401 and a memory 402.
- a computer program is stored on the memory 402.
- the processor 401 executes the computer program on the memory 402.
- the program implements the method provided by any embodiment of this application. Exemplarily, the method for executing the computer program of the electronic device is as follows:
- S101 collect relevant data of the vehicle, where the data includes the vehicle's own parameters and environmental parameters;
- S102 trigger data type determination, and determine the type of data, where the type includes model triggering data and rule triggering data;
- the above-mentioned collection module 210, judgment module 220, and marking module 230 are all stored in the memory 402 as program units, and the processor 401 executes the above-mentioned program units stored in the memory 402 to implement corresponding functions.
- the data labeling method for autonomous vehicles marks model-triggered data or rule-triggered data based on the type of vehicle-related data, and supports rule configuration and issuance, model update and downloading through a visual desktop application. Transmission, partial and full data customization, weather information marking, road segment information marking, voice control and reminders, etc., can realize the automatic collection of specified data under single-person driving.
- the above-mentioned storage medium may be included in the above-mentioned electronic device; it may also exist independently without being assembled into the electronic device.
- the above-mentioned storage medium carries one or more programs.
- the electronic device obtains at least two Internet Protocol addresses; sends at least two Internet Protocol addresses to the node evaluation device.
- a node evaluation request wherein the node evaluation device selects an Internet Protocol address from at least two Internet Protocol addresses and returns it; receives the Internet Protocol address returned by the node evaluation device; wherein the obtained Internet Protocol address indicates the content Edge nodes in the distribution network.
- the storage medium carries one or more programs.
- the electronic device When the one or more programs are executed by the electronic device, the electronic device: receives a node evaluation request including at least two Internet Protocol addresses; receives a node evaluation request from at least two Internet Protocol addresses; Among the protocol addresses, an Internet Protocol address is selected; the selected Internet Protocol address is returned; wherein the received Internet Protocol address indicates an edge node in the content distribution network.
- Computer program code for performing the operations of the present application may be written in one or more programming languages, including, but not limited to, object-oriented programming languages—such as Java, Smalltalk, C++, and Includes conventional procedural programming languages—such as "C” or similar programming languages.
- the program code may execute entirely on the passenger computer, partly on the passenger computer, as a stand-alone software package, partly on the passenger computer and partly on a remote computer or entirely on the remote computer or server.
- the remote computer may be connected to the passenger computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider). Internet connection).
- LAN local area network
- WAN wide area network
- Internet service provider e.g., using an Internet service provider
- the storage medium mentioned above in this application may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two.
- the computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of computer readable storage media may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard drive, random access memory (RAM), read only memory (ROM), removable Programmd read-only memory (EPROM or flash memory), fiber optics, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
- a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device.
- the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, in which computer-readable program code is carried. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above.
- a computer-readable signal medium may also be any storage medium other than a computer-readable storage medium that can be sent, propagated, or transmitted for use by a system, device, or machine executing instructions. software or used in conjunction with it.
- the program code contained on the storage medium can be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.
- each block in the flowchart or block diagram may represent a module, segment, or portion of code that contains one or more logic functions that implement the specified executable instructions.
- the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown one after another may actually execute substantially in parallel, or they may sometimes execute in the reverse order, depending on the functionality involved.
- each block of the block diagram and/or flowchart illustration, and combinations of blocks in the block diagram and/or flowchart illustration can be implemented by special purpose hardware-based systems that perform the specified functions or operations. , or can be implemented using a combination of specialized hardware and computer instructions.
- the units involved in the embodiments of this application can be implemented in software or hardware. Among them, the name of a unit does not constitute a limitation on the unit itself under certain circumstances.
- FPGAs Field Programmable Gate Arrays
- ASICs Application Specific Integrated Circuits
- ASSPs Application Specific Standard Products
- SOCs Systems on Chips
- CPLD Complex Programmable Logical device
- a machine-readable medium may be a tangible medium that may contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.
- the machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium.
- Machine-readable media may include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any suitable combination of the foregoing.
- machine-readable storage media would include one or more wire-based electrical connections, laptop disks, hard drives, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
- RAM random access memory
- ROM read only memory
- EPROM or flash memory erasable programmable read only memory
- CD-ROM portable compact disk read-only memory
- magnetic storage device or any suitable combination of the above.
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
本申请公开了一种自动驾驶车辆的数据标记方法和标记装置,所述标记方法包括:采集所述车辆的相关数据,所述数据包括车辆自身参数和环境参数;判断所述数据的类型,其中所述类型包括模型触发数据和规则触发数据;当所述数据属于所述模型触发数据或规则触发数据时,对所述数据进行标记并记录。本申请基于车辆相关数据的类型,对模型触发数据或规则触发数据进行标记,通过可视化的桌面应用程序,支持规则配置和下发、模型更新及下发、部分及全量数据定制、天气信息标记、路段信息标记、语音控制及提醒等,可在单人驾驶的情况下,实现指定要求的数据的自动采集。
Description
本申请涉及自动驾驶技术领域,具体而言,涉及一种自动驾驶车辆的数据标记方法及标记装置。本申请要求于2022年9月9日提交至中国国家知识产权局、申请号为202211106633.1、发明名称为“一种自动驾驶车辆的数据标记方法及标记装置”的专利申请的优先权。
自动驾驶,是指通过视觉图像处理技术、雷达感知技术、监控设备、全球定位系统及人工智能技术等协同工作,让整车中央处理器可以在没有任何人类主动干预的前提下、全自动并安全控制的机器自主驾驶行为;自动驾驶技术将成为未来汽车发展的大势所趋。
自动驾驶车辆在运行中的车辆状态数据、各种定位装置、雷达、摄像头等传感器采集获得的信息数据均需要及时的记录并存储至磁盘。落盘的信息数据主要用于离线环境的问题复现、bug定位与排查,与高精地图的采集,累积的数据还可用于仿真。
根据自动驾驶车辆的测试任务所针对的场景或所采集数据类型的不同,可以将自动驾驶车辆的测试任务划分多种不同的任务类型。目前的测试方法对于不同的测试任务类型,采用同一套固定的数据落盘存储方法,由此会采集大量的与测试任务无关的重复数据,浪费磁盘资源的同时杂乱无章的数据也给数据分析带来了繁重的工作量。
发明内容
有鉴于此,本申请的目的在于提供一种自动驾驶车辆的数据标记方法及标记装置,以解决现有技术中数据重复、浪费磁盘资源,同时数据处理工作量繁重的技术问题。
为了实现上述目的,第一方面,本申请提供了一种自动驾驶车辆的数
据标记方法,所述标记方法包括:采集所述车辆的相关数据,所述数据包括车辆自身参数和环境参数;触发数据类型判断,并判断所述数据的类型,其中所述类型包括模型触发数据和规则触发数据;当所述数据属于所述模型触发数据或规则触发数据时,对所述数据进行标记并记录。
在一些实施方式中,所述判断所述数据的类型包括:将所述数据与规则配置信息和模型配置信息进行比较,其中,所述规则配置信息和模型配置信息包括多个条目,被预先存储在所述车辆中;基于比较结果,判断所述数据的类型,其中所述数据有多种类型。
在一些实施方式中,所述将所述信息与规则配置信息和模型配置信息进行比较包括:将所述信息与规则配置信息和模型配置信息的各条目均进行比较。
在一些实施方式中,在采集所述车辆的相关信息之前,所述方法还包括:选中所述车辆的信道信息以对所述车辆采集的数据进行验证。
在一些实施方式中,所述方法还包括基于识别到的语音输入信息或所述自动驾驶车辆的UI界面的输入信息对所述数据进行标记。
在一些实施方式中,所述方法还包括获取所述车辆的属性信息,并将所述属性信息记录在所述车辆采集的数据中,其中所述属性信息包括标定信息、车辆的当前位置信息、天气信息。
在一些实施方式中,在判断所述数据的类型之前,所述方法还包括:对规则配置信息和模型配置信息进行更新。
第二方面,本申请还提供了一种自动驾驶车辆的数据标记装置,包括:
采集模块,用于采集所述车辆的相关数据,其中,所述数据包括车辆自身参数和环境参数;判断模块,用于触发数据类型判断后,判断所述数据的类型,其中所述类型包括模型触发数据和规则触发数据;标记模块,用于当所述数据属于所述模型触发数据或规则触发数据时,对所述数据进行标记并记录。
第三方面,本申请还提供一种存储介质,存储有计算机程序,所述计算机程序被处理器执行时实现上述任一项技术方案中所述方法的步骤。
第四方面,本申请还提供一种电子设备,至少包括存储器、处理器,所述存储器上存储有计算机程序,所述处理器在执行所述存储器上的计算机程序时实现上述任一项技术方案中所述方法的步骤。
本申请实施例基于车辆相关数据的类型,对模型触发数据或规则触发数据进行标记,通过可视化的桌面应用程序,支持规则配置和下发、模型更新及下发、部分及全量数据定制、天气信息标记、路段信息标记、语音控制及提醒等,可在单人驾驶的情况下,实现指定要求的数据的自动采集。
为使本申请的上述目的、特征和优点能更明显易懂,下文特举较佳实施例,并配合所附附图,作详细说明如下。
为了更清楚地说明本申请实施例或现有技术中的技术方案,下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本申请中记载的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其他的附图。
图1是本申请所提供的自动驾驶车辆的数据标记方法的步骤示意图;
图2是本申请所提供的判断所述数据类型的步骤流程图;
图3是本申请所提供的自动驾驶车辆的数据标记装置的结构框图;
图4是本申请所提供的电子设备的结构示意图。
下面,结合附图对本申请的具体实施例进行详细的描述,但不作为本申请的限定。
应理解的是,可以对此处公开的实施例做出各种修改。因此,上述说明书不应该视为限制,而仅是作为实施例的范例。本领域的技术人员将想到在本申请的范围和精神内的其他修改。
包含在说明书中并构成说明书的一部分的附图示出了本申请的实施例,并且与上面给出的对本申请的大致描述以及下面给出的对实施例的详细描述一起用于解释本申请的原理。
通过下面参照附图对给定为非限制性实例的实施例的优选形式的描述,本申请的这些和其它特性将会变得显而易见。
还应当理解,尽管已经参照一些具体实例对本申请进行了描述,但本
领域技术人员能够确定地实现本申请的很多其它等效形式,它们具有如权利要求所述的特征并因此都位于借此所限定的保护范围内。
当结合附图时,鉴于以下详细说明,本申请的上述和其他方面、特征和优势将变得更为显而易见。
此后参照附图描述本申请的具体实施例;然而,应当理解,所公开的实施例仅仅是本申请的实例,其可采用多种方式实施。熟知和/或重复的功能和结构并未详细描述以避免不必要或多余的细节使得本申请模糊不清。因此,本文所公开的具体的结构性和功能性细节并非意在限定,而是仅仅作为权利要求的基础和代表性基础用于教导本领域技术人员以实质上任意合适的详细结构多样地使用本申请。
需要说明的是,本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换,以便这里描述的本申请的实施例能够以除了在这里图示或描述的那些以外的顺序实施。此外,术语“包括”和“具有”以及他们的任何变形,意图在于覆盖不排他的包含,例如,包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元,而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
本说明书可使用词组“在一种实施例中”、“在另一个实施例中”、“在又一实施例中”或“在其他实施例中”,其均可指代根据本申请的相同或不同实施例中的一个或多个。
下面结合附图和具体实施例对本申请作进一步的说明。
实施例1
本申请的第一实施例涉及自动驾驶技术领域,具体地涉及一种自动驾驶车辆的数据标记方法。这里的自动驾驶车辆包括但不限于纯电动车、混合动力车辆等。
本申请实施例基于车辆相关数据的类型,对模型触发数据或规则触发数据进行标记,实现了车辆运行过程中对指定数据的自动采集和标记。
如图1所示,所述自动驾驶车辆的数据标记方法包括以下步骤:
S101,采集所述车辆的相关数据。
在本步骤中,采集所述车辆的相关数据,其中所述数据包括车辆自身
参数和环境参数。
具体地,所述车辆在运行过程中,采集与所述车辆的运行相关的信息。一方面,所述信息包括所述车辆所处的周边环境信息,例如所述车辆周边的障碍物信息、交通拥堵状态信息等;另一方面,所述相关信息还包括车辆自身信息,例如所述车辆当前的控制软件版本信息,所述车辆采集数据时的状态及参数信息。
同时,功能测试中的数据记录和软件版本是息息相关的,因此,可以在数据记录时保留版本信息,并按版本信息对采集的数据进行整理归档,其中,版本信息既可通过git提交的commit信息来确定,也可通过发布的product说明文件中的version进行标记。
对于车辆外部信息,可以通过与所述车辆的中央处理器连接的摄像头或传感器等信息采集部件采集,例如可以通过前部摄像头采集当前的路况信息,其中所述路况信息包括前方障碍物信息以及红绿灯信息等。
在一些实施方式中,所述方法还包括在采集所述车辆的相关信息之前,选中所述车辆的信道信息以对所述车辆采集的数据进行验证。
以百度Apollo系统为例,Channel是传输数据的通道,管理CyberRT中的数据通信。用户可以发布/订阅同一个Channel建立通信,实现点对点通信。
S102,触发数据类型判断,并判断所述数据的类型。
在完成上述步骤S101后,在本步骤中,触发数据类型判断,并判断所述数据的类型,其中所述类型包括模型触发数据和规则触发数据。
具体地,触发数据类型判断,其中数据类型判断可以由规则触发器和模型触发器实现,触发数据类型判断后,能够对所采集的数据的类型进行判断。图2示出了本申请所提供的判断所述数据类型的步骤流程图,如图所示,判断所述数据的类型具体包括:
S201,将所述数据与规则配置信息和模型配置信息进行比较,其中,所述规则配置信息和模型配置信息包括多个条目,被预先存储在所述车辆中。
具体地,对于不同的场景具有不同的规则判断逻辑,因此,在数据采集的过程中,对应具有不同的规则配置信息。由于规则触发强依赖各传感器数据的输出,因此,在规则无法有效实施时,通过已经训练过的模型触
发目标数据采集指令,例如检测到特殊车辆、特殊障碍物、特殊行驶路线等。通过触发模型采集特定的数据,还可以反哺模型的训练和完善,改进后的模型对当前模型进行更新,形成完整的学习过程。
通常,这些规则配置信息和模型配置信息被预先储存在所述车辆中。我们可以根据需要,定期对储存在所述车辆中的规则配置信息和模型配置信息进行更新,以确保信息采集的完整性。
S202,基于比较结果,判断所述数据的类型,其中所述数据有多种类型。
在完成上述步骤S201后,在本步骤中,基于采集到的数据与预先存储的规则配置信息和模型配置信息进行比较的结果,判断数据的类型。
具体的,由于车辆在同一时刻会有多种不同的状态,同一个参数在不同的场景下会表征不同的含义,因此,采集数据时可单选也可多选触发器规则,将所述信息与规则配置信息和模型配置信息的各条目均进行比较,当同一数据发生多个规则触发时,对所采集的数据触发的规则均进行标记,即同一个数据会有多个规则标记。
在实际应用的过程中,所述规则配置通过文本方式存储,无需重新编译的前提下即可实现规则的动态更新和生效。通常,规则配置数据结构如下:
规则开关开启时,对目标Channel的数据在规则仲裁逻辑trigger.cc中进行检查,满足规则条件则视为规则触发,需要按规则配置信息进行回溯及持续记录数据,并将规则命中信息记录于info.txt中。为了避免噪
声干扰,规则逻辑会根据需求可实时更新和下发。
S103,当所述数据属于所述模型触发数据或规则触发数据时,对所述数据进行标记并记录。
在完成上述步骤S102后,在本步骤中,当所述数据属于所述模型触发数据或规则触发数据时,对所述数据进行标记。
具体地,在将所述车辆采集的数据与所述规则配置信息和模型配置信息进行比较后,当所述数据属于规则配置信息或模型配置信息中的任一项时,均对其进行标记和记录。
进一步地,所述方法还包括基于识别到的语音输入信息或所述自动驾驶车辆的UI界面的输入信息对所述数据进行标记。
具体地,在数据采集过程中,如遇到特殊情况或在某个时间点需要做标记,可手动点击UI界面标签实时进行数据标记,此时记录的数据将会增加此标签。对于配置了语音识别设备的车辆,可以通过语音进行控制,在任意时刻增加已有或自定义的标签,便于后续数据筛选、分析和训练。
同时,对于某些特定场景,规则和模型均未触发的情况下,可通过此方式触发数据记录,线下对数据进行分析,能有效达到功能改进和模型优化的目标。
在一些实施例中,所述方法还包括获取所述车辆的属性信息,并将所述属性信息记录在所述车辆采集的数据中,其中所述属性信息包括标定信息、车辆的当前位置信息、天气信息。
例如,在车辆运行中,可以通过定位信息,确定当前车辆所在位置信息并记录;通过定位信息获取当前位置的天气信息,例如可以使用百度地图接口,根据ip获取城市名,确定当前车辆所在区域的天气信息并记录。
根据本申请实施例提供的自动驾驶车辆的数据标记方法基于车辆相关数据的类型,对模型触发数据或规则触发数据进行标记,通过可视化的桌面应用程序,支持规则配置和下发、模型更新及下发、部分及全量数据定制、天气信息标记、路段信息标记、语音控制及提醒等,可在单人驾驶的情况下,实现指定要求的数据的自动采集。
实施例2
为了更好地实施以上方法,本申请的第二方面还提供一种自动驾驶车
辆的数据标记装置,该标记装置可以集成在电子设备上。
例如,如图3所示,所述标记装置200可以包括:采集模块210,判断模块220,标记模块230,具体如下:
(1)采集模块210,所述采集模块210用于采集所述车辆的相关数据,其中,所述数据包括车辆自身参数和环境参数。
(2)判断模块220,用于触发数据类型判断后,判断所述数据的类型,其中所述类型包括模型触发数据和规则触发数据。
(3)标记模块230,所述标记模块230用于当所述数据属于所述模型触发数据或规则触发数据时,对所述数据进行标记。
根据本申请实施例提供的自动驾驶车辆的数据标记方法基于车辆相关数据的类型,对模型触发数据或规则触发数据进行标记,通过可视化的桌面应用程序,支持规则配置和下发、模型更新及下发、部分及全量数据定制、天气信息标记、路段信息标记、语音控制及提醒等,可在单人驾驶的情况下,实现指定要求的数据的自动采集。
实施例3
本领域普通技术人员可以理解,上述实施例的各种方法中的全部或部分步骤可以通过指令来完成,或通过指令控制相关的硬件来完成,该指令可以存储于一计算机可读存储介质中,并由处理器进行加载和执行。
为此,本申请的第三实施例提供了一种存储介质,该存储介质为计算机可读介质,存储有计算机程序,该计算机程序被处理器执行时实现本申请实施例提供的方法,包括如下步骤S101至S103:
S101,采集所述车辆的相关数据,所述数据包括车辆自身参数和环境参数;
S102,触发数据类型判断,并判断所述数据的类型,其中所述类型包括模型触发数据和规则触发数据;
S103,当所述数据属于所述模型触发数据或规则触发数据时,对所述数据进行标记。
进一步地,该计算机程序被处理器执行时实现本申请上述任一项实施例提供的其他方法。
根据本申请实施例提供的自动驾驶车辆的数据标记方法基于车辆相
关数据的类型,对模型触发数据或规则触发数据进行标记,通过可视化的桌面应用程序,支持规则配置和下发、模型更新及下发、部分及全量数据定制、天气信息标记、路段信息标记、语音控制及提醒等,可在单人驾驶的情况下,实现指定要求的数据的自动采集。
实施例4
本申请的第四实施例提供了一种电子设备,如图4所示,该电子设备至少包括处理器401和存储器402,存储器402上存储有计算机程序,处理器401在执行存储器402上的计算机程序时实现本申请任意实施例提供的方法。示例性的,电子设备计算机程序执行的方法如下:
S101,采集所述车辆的相关数据,所述数据包括车辆自身参数和环境参数;
S102,触发数据类型判断,并判断所述数据的类型,其中所述类型包括模型触发数据和规则触发数据;
S103,当所述数据属于所述模型触发数据或规则触发数据时,对所述数据进行标记。
具体实现时,上述采集模块210,判断模块220,标记模块230均作为程序单元存储在存储器402中,由处理器401执行存储在存储器402中的上述程序单元来实现相应的功能。
根据本申请实施例提供的自动驾驶车辆的数据标记方法基于车辆相关数据的类型,对模型触发数据或规则触发数据进行标记,通过可视化的桌面应用程序,支持规则配置和下发、模型更新及下发、部分及全量数据定制、天气信息标记、路段信息标记、语音控制及提醒等,可在单人驾驶的情况下,实现指定要求的数据的自动采集。
上述存储介质可以是上述电子设备中所包含的;也可以是单独存在,而未装配入该电子设备中。
上述存储介质承载有一个或者多个程序,当上述一个或者多个程序被该电子设备执行时,使得该电子设备:获取至少两个网际协议地址;向节点评价设备发送包括至少两个网际协议地址的节点评价请求,其中,节点评价设备从至少两个网际协议地址中,选取网际协议地址并返回;接收节点评价设备返回的网际协议地址;其中,所获取的网际协议地址指示内容
分发网络中的边缘节点。
或者,上述存储介质承载有一个或者多个程序,当上述一个或者多个程序被该电子设备执行时,使得该电子设备:接收包括至少两个网际协议地址的节点评价请求;从至少两个网际协议地址中,选取网际协议地址;返回选取出的网际协议地址;其中,接收到的网际协议地址指示内容分发网络中的边缘节点。
可以以一种或多种程序设计语言或其组合来编写用于执行本申请的操作的计算机程序代码,上述程序设计语言包括但不限于面向对象的程序设计语言—诸如Java、Smalltalk、C++,还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在乘客计算机上执行、部分地在乘客计算机上执行、作为一个独立的软件包执行、部分在乘客计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中,远程计算机可以通过任意种类的网络——包括局域网(LAN)或广域网(WAN)—连接到乘客计算机,或者,可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
需要说明的是,本申请上述的存储介质可以是计算机可读信号介质或者计算机可读存储介质或者是上述两者的任意组合。计算机可读存储介质例如可以是——但不限于——电、磁、光、电磁、红外线、或半导体的系统、装置或器件,或者任意以上的组合。计算机可读存储介质的更具体的例子可以包括但不限于:具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机访问存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本申请中,计算机可读存储介质可以是任何包含或存储程序的有形介质,该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。而在本申请中,计算机可读信号介质可以包括在基带中或者作为载波一部分传播的数据信号,其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式,包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读信号介质还可以是计算机可读存储介质以外的任何存储介质,该计算机可读信号介质可以发送、传播或者传输用于由指令执行系统、装置或者器
件使用或者与其结合使用的程序。存储介质上包含的程序代码可以用任何适当的介质传输,包括但不限于:电线、光缆、RF(射频)等等,或者上述的任意合适的组合。
附图中的流程图和框图,图示了按照本申请各种实施例的系统、方法和计算机程序产品的可能实现的体系架构、功能和操作。在这点上,流程图或框图中的每个方框可以代表一个模块、程序段、或代码的一部分,该模块、程序段、或代码的一部分包含一个或多个用于实现规定的逻辑功能的可执行指令。也应当注意,在有些作为替换的实现中,方框中所标注的功能也可以以不同于附图中所标注的顺序发生。例如,两个接连地表示的方框实际上可以基本并行地执行,它们有时也可以按相反的顺序执行,这依所涉及的功能而定。也要注意的是,框图和/或流程图中的每个方框、以及框图和/或流程图中的方框的组合,可以用执行规定的功能或操作的专用的基于硬件的系统来实现,或者可以用专用硬件与计算机指令的组合来实现。
描述于本申请实施例中所涉及到的单元可以通过软件的方式实现,也可以通过硬件的方式来实现。其中,单元的名称在某种情况下并不构成对该单元本身的限定。
本文中以上描述的功能可以至少部分地由一个或多个硬件逻辑部件来执行。例如,非限制性地,可以使用的示范类型的硬件逻辑部件包括:现场可编程门阵列(FPGA)、专用集成电路(ASIC)、专用标准产品(ASSP)、片上系统(SOC)、复杂可编程逻辑设备(CPLD)等等。
在本申请的上下文中,机器可读介质可以是有形的介质,其可以包含或存储以供指令执行系统、装置或设备使用或与指令执行系统、装置或设备结合地使用的程序。机器可读介质可以是机器可读信号介质或机器可读储存介质。机器可读介质可以包括但不限于电子的、磁性的、光学的、电磁的、红外的、或半导体系统、装置或设备,或者上述内容的任何合适组合。机器可读存储介质的更具体示例会包括基于一个或多个线的电气连接、便携式计算机盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦除可编程只读存储器(EPROM或快闪存储器)、光纤、便捷式紧凑盘只读存储器(CD-ROM)、光学储存设备、磁储存设备、或上述内容的任何合适组合。
以上描述仅为本申请的较佳实施例以及对所运用技术原理的说明。本领域技术人员应当理解,本申请中所涉及的公开范围,并不限于上述技术特征的特定组合而成的技术方案,同时也应涵盖在不脱离上述公开构思的情况下,由上述技术特征或其等同特征进行任意组合而形成的其它技术方案。例如上述特征与本申请中公开的(但不限于)具有类似功能的技术特征进行互相替换而形成的技术方案。
此外,虽然采用特定次序描绘了各操作,但是这不应当理解为要求这些操作以所示出的特定次序或以顺序次序执行来执行。在一定环境下,多任务和并行处理可能是有利的。同样地,虽然在上面论述中包含了若干具体实现细节,但是这些不应当被解释为对本申请的范围的限制。在单独的实施例的上下文中描述的某些特征还可以组合地实现在单个实施例中。相反地,在单个实施例的上下文中描述的各种特征也可以单独地或以任何合适的子组合的方式实现在多个实施例中。
尽管已经采用特定于结构特征和/或方法逻辑动作的语言描述了本主题,但是应当理解所附权利要求书中所限定的主题未必局限于上面描述的特定特征或动作。相反,上面所描述的特定特征和动作仅仅是实现权利要求书的示例形式。
以上对本申请多个实施例进行了详细说明,但本申请不限于这些具体的实施例,本领域技术人员在本申请构思的基础上,能够做出多种变型和修改实施例,这些变型和修改都应落入本申请所要求保护的范围。
Claims (10)
- 一种自动驾驶车辆的数据标记方法,其特征在于,包括:采集所述车辆的相关数据,所述数据包括车辆自身参数和环境参数;触发数据类型判断,并判断所述数据的类型,其中所述类型包括模型触发数据和规则触发数据;当所述数据属于所述模型触发数据或规则触发数据时,对所述数据进行标记并记录。
- 根据权利要求1所述的数据标记方法,其特征在于,所述判断所述数据的类型包括:将所述数据与规则配置信息和模型配置信息进行比较,其中,所述规则配置信息和模型配置信息包括多个条目,被预先存储在所述车辆中;基于比较结果,判断所述数据的类型,其中所述数据有多种类型。
- 根据权利要求2所述的数据标记方法,其特征在于,所述将所述信息与规则配置信息和模型配置信息进行比较包括:将所述信息与规则配置信息和模型配置信息的各条目均进行比较。
- 根据权利要求1所述的数据标记方法,其特征在于,在采集所述车辆的相关信息之前,所述方法还包括:选中所述车辆的信道信息以对所述车辆采集的数据进行验证。
- 根据权利要求1所述的数据标记方法,其特征在于,所述方法还包括基于识别到的语音输入信息或所述自动驾驶车辆的UI界面的输入信息对所述数据进行标记。
- 根据权利要求1所述的数据标记方法,其特征在于,所述方法还包括获取所述车辆的属性信息,并将所述属性信息记录在所述车辆采集的数据中,其中所述属性信息包括标定信息、车辆的当前位置信息、天气信息。
- 根据权利要求1所述的数据标记方法,其特征在于,在判断所述数据的类型之前,所述方法还包括:对规则配置信息和模型配置信息进行更新。
- 一种自动驾驶车辆的数据标记装置,其特征在于,包括:采集模块,用于采集所述车辆的相关数据,其中,所述数据包括车辆自身参数和环境参数;判断模块,用于触发数据类型判断后,判断所述数据的类型,其中所述类型包括模型触发数据和规则触发数据;标记模块,用于当所述数据属于所述模型触发数据或规则触发数据时,对所述数据进行标记并记录。
- 一种存储介质,存储有计算机程序,其特征在于,所述计算机程序被处理器执行时实现权利要求1至7中任一项所述的自动驾驶车辆的数据标记方法的步骤。
- 一种电子设备,至少包括存储器、处理器,所述存储器上存储有计算机程序,其特征在于,所述处理器在执行所述存储器上的计算机程序时实现权利要求1至7中任一项所述的自动驾驶车辆的数据标记方法的步骤。
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211106633.1A CN116311586A (zh) | 2022-09-09 | 2022-09-09 | 一种自动驾驶车辆的数据标记方法及标记装置 |
CN202211106633.1 | 2022-09-09 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2024051248A1 true WO2024051248A1 (zh) | 2024-03-14 |
Family
ID=86778516
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2023/100040 WO2024051248A1 (zh) | 2022-09-09 | 2023-06-13 | 一种自动驾驶车辆的数据标记方法及标记装置 |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN116311586A (zh) |
WO (1) | WO2024051248A1 (zh) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111178454A (zh) * | 2020-01-03 | 2020-05-19 | 北京汽车集团有限公司 | 自动驾驶数据的标注方法、云端控制平台及存储介质 |
US20200294329A1 (en) * | 2019-03-11 | 2020-09-17 | Denso Ten Limited | Data collecting device, data collecting system, data collecting method, and on-vehicle device |
CN112740725A (zh) * | 2020-03-31 | 2021-04-30 | 华为技术有限公司 | 驾驶数据采集方法及装置 |
CN112905849A (zh) * | 2021-02-18 | 2021-06-04 | 中国第一汽车股份有限公司 | 一种车辆数据处理的方法及装置 |
CN114987494A (zh) * | 2022-05-30 | 2022-09-02 | 阿波罗智联(北京)科技有限公司 | 驾驶场景处理方法、装置及电子设备 |
-
2022
- 2022-09-09 CN CN202211106633.1A patent/CN116311586A/zh active Pending
-
2023
- 2023-06-13 WO PCT/CN2023/100040 patent/WO2024051248A1/zh unknown
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20200294329A1 (en) * | 2019-03-11 | 2020-09-17 | Denso Ten Limited | Data collecting device, data collecting system, data collecting method, and on-vehicle device |
CN111178454A (zh) * | 2020-01-03 | 2020-05-19 | 北京汽车集团有限公司 | 自动驾驶数据的标注方法、云端控制平台及存储介质 |
CN112740725A (zh) * | 2020-03-31 | 2021-04-30 | 华为技术有限公司 | 驾驶数据采集方法及装置 |
CN112905849A (zh) * | 2021-02-18 | 2021-06-04 | 中国第一汽车股份有限公司 | 一种车辆数据处理的方法及装置 |
CN114987494A (zh) * | 2022-05-30 | 2022-09-02 | 阿波罗智联(北京)科技有限公司 | 驾驶场景处理方法、装置及电子设备 |
Also Published As
Publication number | Publication date |
---|---|
CN116311586A (zh) | 2023-06-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11400952B2 (en) | Method and apparatus for automated driving | |
US11875551B2 (en) | Collecting and processing data from vehicles | |
CN110378483A (zh) | 部署在模拟平台上的用于训练机器学习模型的系统和方法 | |
CN110517533A (zh) | 一种自主泊车方法及系统 | |
JP2020021471A (ja) | 自動運転車(adv)のサブシステムによるパトロールカーのパトロール | |
CN111243297A (zh) | 交通灯相位控制方法、系统、设备及介质 | |
US11462060B2 (en) | Data collection automation system | |
US20220026220A1 (en) | Map updates based on data captured by an autonomous vehicle | |
US10999719B1 (en) | Peer-to-peer autonomous vehicle communication | |
EP3761138B1 (en) | Method for unmanned vehicle cruising, unmanned vehicle and storage medium | |
CN107745711B (zh) | 一种在自动驾驶模式下确定路线的方法和装置 | |
EP3174000B1 (en) | Information presentation device, method, and program | |
CN112905849A (zh) | 一种车辆数据处理的方法及装置 | |
US20230391357A1 (en) | Methods and apparatus for natural language based scenario discovery to train a machine learning model for a driving system | |
US11874118B2 (en) | Crowdsourcing map maintenance | |
WO2023129224A1 (en) | Systems and methods for updating maps and evaluating map accuracy based on collected image data | |
WO2023137864A1 (zh) | 基于自动驾驶的感知决策模型升级方法、系统及电子装置 | |
US11993287B2 (en) | Fleet-level AV simulation system and method | |
WO2024051248A1 (zh) | 一种自动驾驶车辆的数据标记方法及标记装置 | |
US20240028601A1 (en) | Methods and apparatus for natural language-based safety case discovery to train a machine learning model for a driving system | |
CN115061386B (zh) | 智能驾驶的自动化仿真测试系统及相关设备 | |
JP2021511999A (ja) | 自動運転車両の3ポイントターンの最適プランナー切り替え方法 | |
US20230222332A1 (en) | Advanced Neural Network Training System | |
US12024100B2 (en) | Device-level fault detection | |
US11429097B2 (en) | Programmatic application of router flags for vehicle limitations |
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: 23861951 Country of ref document: EP Kind code of ref document: A1 |