Map updating and autonomous driving method, device, equipment, medium and program product

Abstract

The present disclosure provides a map updating method and device, an autonomous driving method and device, an electronic device, a program product, and a storage medium, and relates to the field of data processing technology, and in particular to the field of autonomous driving technology. The present disclosure first detects whether the map information of the current crowdsourced map meets the preset trigger conditions, and only triggers the task of crowdsourced map update when the map information meets the preset trigger conditions, thereby overcoming the defect of uneven collection data of vehicle feedback caused by large differences in traffic volume in different areas within a certain period of time. At the same time, the technical solution of the present disclosure is to generate crowdsourced collection tasks in a targeted manner based on the actual situation of the first historical collection data for generating the crowdsourced map, thereby improving the integrity of the collection data fed back by the vehicle. Since the uniformity and integrity of the collection data fed back by the vehicle are improved, the accuracy of the updated crowdsourced map can be effectively improved, which is conducive to improving the safety of autonomous driving.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, and in particular to the field of autonomous driving technology, and discloses a map updating method and device, an autonomous driving method and device, an electronic device, a non-transitory computer-readable storage medium storing computer instructions, and a computer program product. Background Art

[0002] With the rapid development of autonomous driving technology, its application scenarios are becoming more and more extensive. Crowdsourcing maps refer to high-precision maps that meet the timeliness requirements of autonomous driving by updating road information in real time through crowdsourcing data collection. Most of the current crowdsourcing data collection solutions generate multiple crowdsourcing collection tasks offline according to a fixed cycle, distribute the generated multiple crowdsourcing collection tasks to vehicles passing through the feature area, and complete the crowdsourcing data collection by the vehicles receiving the crowdsourcing collection tasks. Summary of the invention

[0003] The present disclosure at least provides a map updating method and device, an automatic driving method and device, an electronic device, a program product, and a storage medium.

[0004] According to one aspect of the present disclosure, a map updating method is provided, comprising:

[0005] When the map information of the current crowdsourcing map meets the preset trigger condition, obtaining the first historical collection data corresponding to the current crowdsourcing map;

[0006] Generate at least one crowdsourcing collection task according to the first historical collection data, and assign each crowdsourcing collection task to a corresponding vehicle;

[0007] The current crowdsourcing map is updated based on the collected data fed back by each vehicle based on the corresponding crowdsourcing collection task.

[0008] According to another aspect of the present disclosure, there is provided an automatic driving method, comprising:

[0009] Obtaining a crowdsourced map updated using the above map updating method;

[0010] The driving route of the autonomous vehicle is determined based on the updated crowdsourced map and the current position of the autonomous vehicle.

[0011] According to another aspect of the present disclosure, there is provided a map updating device, comprising:

[0012] A data acquisition module, used for acquiring first historical collection data corresponding to the current crowdsourcing map when the map information of the current crowdsourcing map meets a preset trigger condition;

[0013] A task generation module, used to generate at least one crowdsourcing collection task according to the first historical collection data, and assign each crowdsourcing collection task to a corresponding vehicle;

[0014] The map update module is used to update the current crowdsourcing map according to the collection data fed back by each vehicle based on the corresponding crowdsourcing collection task.

[0015] According to another aspect of the present disclosure, there is provided an automatic driving device, comprising:

[0016] A map acquisition module, used to acquire a crowdsourced map updated by the above map updating method;

[0017] The route determination module is used to determine the driving route of the autonomous driving vehicle based on the updated crowdsourced map and the current position of the autonomous driving vehicle.

[0018] According to another aspect of the present disclosure, there is provided an electronic device, comprising:

[0019] at least one processor; and

[0020] a memory communicatively connected to the at least one processor; wherein,

[0021] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method in any embodiment of the present disclosure.

[0022] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided. The computer instructions are used to enable a computer to execute the method in any embodiment of the present disclosure.

[0023] According to another aspect of the present disclosure, a computer program product is provided, including a computer program / instruction, which implements the method in any embodiment of the present disclosure when the computer program / instruction is executed by a processor.

[0024] According to the technology disclosed in the present invention, it is first detected whether the map information of the current crowdsourcing map meets the preset trigger conditions, for example, it is detected whether the map information meets the data uniformity trigger conditions. The task of crowdsourcing map update is triggered only when the map information meets the preset trigger conditions, and it is not triggered based on a fixed period. Therefore, the defect of uneven collection data of vehicle feedback caused by the large difference in traffic volume in different areas within a certain period of time is overcome, and the uniformity of the collection data of vehicle feedback is improved. At the same time, the technical solution disclosed in the present invention does not generate crowdsourcing collection tasks according to offline preset strategies, but generates crowdsourcing collection tasks in a targeted manner based on the actual situation of the first historical collection data for generating crowdsourcing maps, which overcomes the defect of incomplete collection data caused by offline generation of crowdsourcing collection tasks and improves the integrity of collection data of vehicle feedback. When the uniformity and integrity of the collection data of vehicle feedback are improved, the accuracy of the updated crowdsourcing map can be effectively improved, which is conducive to improving the accuracy and safety of autonomous driving.

[0025] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0027] Figure 1 is one of the flow charts of the map updating method according to the present disclosure;

[0028] Figure 2 is the second flowchart of the map updating method disclosed in the present invention;

[0029] Figure 3 is a flow chart of an autonomous driving method according to the present disclosure;

[0030] Figure 4 is a schematic diagram of the structure of a map updating device according to the present disclosure;

[0031] Figure 5 is a schematic diagram of the structure of the automatic driving device according to the present disclosure;

[0032] Figure 6 is a schematic structural diagram of an electronic device according to the present disclosure. DETAILED DESCRIPTION

[0033] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0034] With the rapid development of autonomous driving technology, its application scenarios are becoming more and more extensive. Crowdsourcing maps refer to high-precision maps that meet the timeliness requirements of autonomous driving by updating road information in real time through crowdsourcing data collection. Crowdsourcing data collection is very different from traditional data collection. Specifically, traditional data collection is planned. For a region, the collected data is complete, uniform, and has consistent errors; while crowdsourcing data collection is random. For a region, the collected data may be incomplete, uneven, and have random errors.

[0035] Most crowdsourcing data collection solutions are based on a fixed cycle, pre-generating multiple crowdsourcing collection tasks offline by region, distributing the generated multiple crowdsourcing collection tasks to agent OEM vehicles passing through the characteristic area, and the OEM vehicles receiving the crowdsourcing collection tasks complete the crowdsourcing data collection. The data collected by the OEM vehicles include location, sensor perception data, and vehicle chassis data. Finally, the OEM vehicles feed back the collected data to the cloud corresponding to the crowdsourcing map.

[0036] The task of triggering crowdsourcing map updates or crowdsourcing data collection at a fixed period has the defect of uneven data collection feedback from vehicles due to the large difference in traffic volume in different areas within a certain period of time. In addition, crowdsourcing collection tasks are generated according to offline preset strategies. Since the data collected according to the preset strategy is quite different from the data that needs to be updated for the actual crowdsourcing map, and the uncertainty of the actual driving conditions of the vehicle causes the inability to timely feedback the collected data, the financial bureau data feedback from OEM vehicles is prone to incompleteness. In addition, the errors of different vehicles or different vehicles in the same area are random. At present, the collected data of the vehicle connection is not processed according to the randomness of the errors of each vehicle, but is processed using a unified default error information. This also causes inaccurate collected data for updating crowdsourcing maps, resulting in low update accuracy for crowdsourcing maps.

[0037] The quality or accuracy of crowdsourced maps is highly dependent on the quality of the collected data fed back by vehicles. The more complete and uniform the collected data is, and the more precise the error is, the higher the quality of the updated crowdsourced map will be. Therefore, a better crowdsourced data collection mechanism is needed.

[0038] In view of the above technical defects, the present disclosure at least provides a map update method and device, an automatic driving method and device, an electronic device, a program product and a storage medium. The technology of the present disclosure first detects whether the map information of the current crowdsourced map meets the preset trigger conditions, such as detecting whether the map information meets the data uniformity trigger condition. The task of crowdsourced map update is triggered only when the map information meets the preset trigger conditions, and the task of crowdsourced map update is not triggered based on a fixed period. Therefore, the defect of unevenness of collected data fed back by vehicles caused by the large difference in traffic volume in different areas within a certain period of time is overcome, and the uniformity of collected data fed back by vehicles is improved. At the same time, the technical solution of the present disclosure does not generate crowdsourced collection tasks according to offline preset strategies, but generates crowdsourced collection tasks in a targeted manner based on the actual situation of the first historical collection data of the crowdsourced map generation, which overcomes the defect of incomplete collection data caused by offline generation of crowdsourced collection tasks and improves the integrity of collected data fed back by vehicles. When the uniformity and integrity of collected data fed back by vehicles are improved, the accuracy of the updated crowdsourced map can be effectively improved, which is conducive to improving the accuracy and safety of automatic driving.

[0039] The map updating method disclosed in the present invention is described below through specific embodiments.

[0040] Figure 1 The flowchart of the map updating method of the embodiment of the present disclosure is shown. The execution subject of the embodiment can be a device with computing capabilities. Figure 1 As shown, the map updating method of the embodiment of the present disclosure may include the following steps:

[0041] S110. When the map information of the current crowdsourcing map meets a preset trigger condition, obtain first historical collection data corresponding to the current crowdsourcing map.

[0042] Exemplarily, the map information includes data features of crowdsourced collected data corresponding to the current crowdsourced map, and the crowdsourced collected data is the crowdsourced collected data for generating the current crowdsourced map. The first historical collected data may be data collected in an area corresponding to the crowdsourced map within a period of history. The first historical collected data may include the crowdsourced collected data, and may also include data collected from the area corresponding to the crowdsourced map at an earlier time.

[0043] The preset trigger condition may include at least one of a data uniformity trigger condition, a data confidence trigger condition, and a data integrity trigger condition. The data uniformity trigger condition may include at least one of a time uniformity trigger condition and a position uniformity trigger condition.

[0044] When the time uniformity corresponding to the map information is poor, the time uniformity trigger condition is met; when the location uniformity corresponding to the map information is good, the location uniformity trigger condition is met; when the confidence corresponding to the map information is low, the data confidence trigger condition is met; when the data integrity corresponding to the map information is good, the data integrity trigger condition is met. When the map information meets or meets at least one of the above preset trigger conditions, the task of crowdsourcing map update or the task of crowdsourcing data collection is triggered. At this time, the first historical collection data corresponding to the current crowdsourcing map is obtained and the following steps are performed.

[0045] S120: Generate at least one crowdsourcing collection task according to the first historical collection data, and assign each crowdsourcing collection task to a corresponding vehicle.

[0046] The first historically collected data may be data in an area corresponding to a crowdsourcing map collected within a certain period of history. Here, based on the statistical results of the data collected within a certain period of history, a crowdsourcing collection task that best suits the current situation can be generated, and the collected data can be guaranteed to fully cover the area corresponding to the crowdsourcing map as much as possible.

[0047] For example, the specific method of assigning a vehicle to a crowdsourcing collection task is to: determine the task area of ​​the crowdsourcing collection task; and select vehicles that have passed through the task area in the past or in the future as vehicles that match the crowdsourcing collection task. Among them, selecting vehicles that have passed through the task area in the past as vehicles that match the crowdsourcing collection task can ensure that the vehicle can feedback the collected data in a timely manner, thereby facilitating the improvement of the integrity of the collected data fed back by the vehicle.

[0048] S130: Update the current crowdsourcing map according to the collected data fed back by each vehicle based on the corresponding crowdsourcing collection task.

[0049] Exemplarily, it is possible to determine whether there is a difference between the collected data fed back by the current vehicle and the collected data used to generate the current crowdsourced map, and if there is a difference, update the crowdsourced map based on the collected data fed back by the current vehicle, or update the crowdsourced map based on the difference information between the collected data fed back by the current vehicle and the collected data used to generate the current crowdsourced map.

[0050] In some embodiments, the map information of the current crowdsourced map meets the preset trigger condition, which may be that the data feature of the crowdsourced collected data meets the preset trigger condition. When the data feature meets the preset trigger condition, the crowdsourced map update task is triggered, and the first historical collected data corresponding to the current crowdsourced map is obtained. For example, Figure 2 As shown, a crowdsourcing map observer can be used to extract data features of crowdsourcing collected data and determine whether the above data features meet preset trigger conditions.

[0051] Exemplarily, the above data features include at least one of the following: uniformity features of the collection time of the above crowdsourced data; uniformity features of the collection locations of the above crowdsourced data; integrity of the above crowdsourced data for the geographical scope corresponding to the current crowdsourced map; confidence of the above crowdsourced data. Specifically, when the time uniformity corresponding to the map information, that is, the uniformity feature of the above collection time, is poor, the time uniformity trigger condition is met; when the location uniformity corresponding to the map information, that is, the uniformity feature of the above collection location, is poor, the location uniformity trigger condition is met; when the confidence corresponding to the map information is low, the data confidence trigger condition is met; when the data integrity corresponding to the map information, that is, the integrity of the above crowdsourced data for the geographical scope corresponding to the current crowdsourced map, is low, the data integrity trigger condition is met.

[0052] The above embodiment does not trigger the crowdsourcing map update task based on a fixed period, but uses a crowdsourcing map observer to detect whether the crowdsourcing collected data used to generate the current crowdsourcing map is uniform in timeliness and / or geography, whether the crowdsourcing collected data is complete, and whether the confidence of the crowdsourcing collected data meets the preset requirements. When the preset conditions are not met, that is, when the preset trigger conditions are met, the crowdsourcing map update task is triggered, thereby ensuring the integrity, uniformity and accuracy of the collected data fed back by the vehicle.

[0053] In some embodiments, Figure 2 As shown, after a task triggering a crowdsourcing map update is added to a crowdsourcing task pool, the online strategy formulation component obtains the first historical collection data from the data collector according to the tasks in the crowdsourcing task pool, and generates at least one crowdsourcing collection task according to the first historical collection data. The collection data fed back by each vehicle based on the corresponding crowdsourcing collection task is collected and stored by the data collector.

[0054] Exemplarily, the online strategy formulation component may specifically use the following steps to split or generate crowdsourcing collection tasks:

[0055] First, based on the first historical collection data, at least one target area where data collection is required is determined; then, the at least one target area is clustered to obtain at least one cluster center; then, based on the at least one cluster center, at least one data collection route is generated using the principle of shortest path coverage; finally, based on the at least one data collection route, at least one crowdsourcing collection task is generated.

[0056] Exemplarily, the target area for data collection may be an area where the corresponding collected data is incomplete, uneven in timeliness, uneven in geographical area, or where the confidence does not meet the preset conditions. On this basis, the cluster center is determined according to the actual situation of the historically collected data, and at least one data collection route is generated using the principle of shortest path coverage. Then, according to the above data collection route, a crowdsourcing collection task is generated, which can formulate a splitting strategy that best suits the current situation, that is, generate a crowdsourcing collection task that best suits the current situation, which is conducive to improving the integrity, uniformity and accuracy of the collected data of the vehicle based on the feedback of the crowdsourcing collection task.

[0057] In some embodiments, since the error information of each vehicle is random, the collected data used to update the crowdsourced map is not accurate enough. At this time, the collected data fed back by each vehicle can be adjusted using the following steps: first, the data collection error corresponding to each vehicle is determined separately; then, for each vehicle, the collected data fed back by the vehicle is adjusted according to the data collection error and error weight corresponding to the vehicle to obtain the target collected data corresponding to the vehicle.

[0058] After obtaining the target collection data corresponding to each vehicle, the current crowdsourcing map may be updated according to the target collection data corresponding to each vehicle.

[0059] For example, Figure 2 As shown, the data collection error corresponding to a certain vehicle mentioned above can be specifically determined by using the error model corresponding to the vehicle. The error model of each vehicle is determined based on a large amount of historical collected data of the vehicle. Therefore, the data collection error of the vehicle determined by using the error model is targeted and accurate, and at the same time, the error is controllable, which effectively improves the accuracy of the data used to update the crowdsourcing map.

[0060] In some embodiments, the data collection error corresponding to a vehicle may be determined using the following steps:

[0061] First, the second historical collected data of the vehicle is obtained; then, the sensor error and / or positioning error of the vehicle is determined based on the second historical collected data; finally, the data collection error corresponding to the vehicle is determined based on the sensor error and / or positioning error of the vehicle.

[0062] The second historical collected data may be data collected by the vehicle within a period of time in history. The positioning error may include a lateral positioning error, a longitudinal positioning error, an angle error, etc. When determining the sensor error and / or positioning error of the vehicle, the second historical collected data of the vehicle, the high-precision map data, and the data collected by vehicles associated with the vehicle within a period of time in history may be specifically combined. The vehicles associated with the vehicle may include vehicles in the same area as the vehicle.

[0063] Exemplarily, the error model includes the sensor error and / or positioning error, and the data collection error corresponding to the vehicle can be determined according to the error model.

[0064] By using the data collected from the vehicle over a period of time in history, the error information for the vehicle, ie, the above-mentioned data collection error, can be determined more accurately.

[0065] The automatic driving method disclosed in the present invention is described below through specific embodiments.

[0066] Figure 3 The flowchart of the autonomous driving method of the embodiment of the present disclosure is shown. The execution subject of the embodiment can be a device with computing capabilities on the autonomous driving vehicle, or a device with computing capabilities remotely connected to the autonomous driving vehicle. Figure 3 As shown, the automatic driving method of the embodiment of the present disclosure may include the following steps:

[0067] S310: Obtain a crowdsourced map updated by the map updating method of the above embodiment.

[0068] S320: Determine a driving route of the autonomous driving vehicle based on the updated crowdsourced map and the current position of the autonomous driving vehicle.

[0069] The above embodiments can be used to accurately update the crowdsourced map, so that the crowdsourced map can be used to determine the driving route, which can improve the safety and accuracy of autonomous driving.

[0070] Based on the same inventive concept, a map updating device corresponding to a map updating method is also provided in an embodiment of the present disclosure. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to the above-mentioned map updating method in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0071] like Figure 4 FIG. 1 is a schematic diagram of the structure of a map updating device provided by an embodiment of the present disclosure, including:

[0072] The data acquisition module 410 is used to acquire the first historical collection data corresponding to the current crowd-sourced map when the map information of the current crowd-sourced map meets the preset trigger condition.

[0073] The task generation module 420 is used to generate at least one crowdsourcing collection task according to the first historical collection data, and respectively assign each crowdsourcing collection task to a corresponding vehicle.

[0074] The map updating module 430 is used to update the current crowdsourcing map according to the collection data fed back by each vehicle based on the corresponding crowdsourcing collection task.

[0075] In some embodiments, the map information includes data features of crowdsourced collected data corresponding to the current crowdsourced map.

[0076] When the map information of the current crowdsourced map meets the preset trigger condition, the data acquisition module 410 acquires the first historical collection data corresponding to the current crowdsourced map, and is used to:

[0077] Extract data features of crowdsourced data;

[0078] When the data feature meets the preset trigger condition, the first historical collection data corresponding to the current crowdsourcing map is obtained.

[0079] In some embodiments, the data feature includes at least one of the following:

[0080] The uniformity characteristics of the collection time of crowdsourced data; the uniformity characteristics of the collection location of crowdsourced data; the integrity of the crowdsourced data for the geographical scope corresponding to the current crowdsourced map; and the confidence level of the crowdsourced data.

[0081] In some embodiments, when the task generation module 420 generates at least one crowdsourcing collection task according to the first historical collection data, it is used to:

[0082] Determining at least one target area where data collection is required based on the first historical collection data;

[0083] Performing clustering processing on at least one target area to obtain at least one cluster center;

[0084] generating at least one data collection route according to at least one cluster center;

[0085] At least one crowdsourcing data collection task is generated according to at least one data collection route.

[0086] In some embodiments, when updating the current crowdsourced map according to the collected data fed back by each vehicle based on the corresponding crowdsourced collection task, the map update module 430 is used to:

[0087] Determine the data collection error corresponding to each vehicle respectively;

[0088] For each vehicle, the collected data fed back by the vehicle is adjusted according to the data collection error and error weight corresponding to the vehicle to obtain the target collected data corresponding to the vehicle;

[0089] According to the target collection data corresponding to each vehicle, the current crowdsourcing map is updated.

[0090] In some embodiments, when determining the data collection error corresponding to each vehicle, the map updating module 430 is used to:

[0091] For each vehicle, obtaining second historical collected data of the vehicle;

[0092] Determining a sensor error and / or a positioning error of the vehicle based on the second historical collected data;

[0093] A data collection error corresponding to the vehicle is determined based on a sensor error and / or a positioning error of the vehicle.

[0094] Based on the same inventive concept, an automatic driving device corresponding to an automatic driving method is also provided in an embodiment of the present disclosure. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to the above-mentioned automatic driving method in the embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0095] like Figure 5 FIG. 1 is a schematic diagram of the structure of the automatic driving device provided by the embodiment of the present disclosure, including:

[0096] The map acquisition module 510 is used to acquire the crowdsourced map updated by the map updating method of the above embodiment.

[0097] The route determination module 520 is used to determine the driving route of the autonomous driving vehicle based on the updated crowdsourced map and the current position of the autonomous driving vehicle.

[0098] In the technical solution disclosed herein, the acquisition, storage and application of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0099] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0100] Figure 6 A schematic block diagram of an example electronic device 600 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0101] like Figure 6As shown, the device 600 includes a computing unit 610, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 620 or a computer program loaded from a storage unit 680 into a random access memory (RAM) 630. In the RAM 630, various programs and data required for the operation of the device 600 can also be stored. The computing unit 610, the ROM 620, and the RAM 630 are connected to each other via a bus 640. An input / output (I / O) interface 650 is also connected to the bus 640.

[0102] A number of components in the device 600 are connected to the I / O interface 650, including: an input unit 660, such as a keyboard, a mouse, etc.; an output unit 670, such as various types of displays, speakers, etc.; a storage unit 680, such as a disk, an optical disk, etc.; and a communication unit 690, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 690 allows the device 600 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0103] The computing unit 610 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 610 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 610 performs the various methods and processes described above, such as map updates or autonomous driving methods. For example, in some embodiments, the map update or autonomous driving method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 680. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 600 via the ROM 620 and / or the communication unit 690. When the computer program is loaded into the RAM 630 and executed by the computing unit 610, one or more steps of the map update or autonomous driving method described above may be performed. Alternatively, in other embodiments, the computing unit 610 may be configured to perform a map update or autonomous driving method in any other appropriate manner (e.g., by means of firmware).

[0104] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0105] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0106] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0107] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0108] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0109] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0110] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0111] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A map updating method, comprising: When the map information of the current crowdsourced map meets a preset trigger condition, obtaining first historical collection data corresponding to the current crowdsourced map, wherein the preset trigger condition includes at least one of a data uniformity trigger condition, a data confidence trigger condition, and a data integrity trigger condition; Determine at least one target area where data collection is required based on the first historical collection data, wherein the target area is an area where the corresponding historical collection data is incomplete, uneven in timeliness, uneven in collection area, or whose confidence does not meet preset conditions; Performing clustering processing on the at least one target area to obtain at least one cluster center; generating at least one data collection route according to the at least one cluster center; generating at least one crowdsourcing collection task according to the at least one data collection route; Allocate each of the crowdsourcing collection tasks to a corresponding vehicle respectively; The current crowdsourcing map is updated according to the collection data fed back by each vehicle based on the corresponding crowdsourcing collection task.

2. The method according to claim 1, wherein: The map information includes data features of crowdsourced collected data corresponding to the current crowdsourced map; When the map information of the current crowdsourced map meets the preset trigger condition, obtaining the first historical collection data corresponding to the current crowdsourced map includes: Extracting data features of the crowdsourced data; When the data feature meets the preset trigger condition, the first historical collection data corresponding to the current crowdsourcing map is obtained.

3. The method according to claim 2, wherein: The data characteristics include at least one of the following: The uniformity characteristics of the collection time of the crowd-sourced data; the uniformity characteristics of the collection location of the crowd-sourced data; the integrity of the crowd-sourced data with respect to the geographical scope corresponding to the current crowd-sourced map; and the confidence level of the crowd-sourced data.

4. The method according to any one of claims 1 to 3, wherein: The updating of the current crowdsourcing map according to the collected data fed back by each vehicle based on the corresponding crowdsourcing collection task includes: Determine the data collection error corresponding to each vehicle respectively; For each vehicle, according to the data collection error and error weight corresponding to the vehicle, the collected data fed back by the vehicle is adjusted to obtain the target collected data corresponding to the vehicle; The current crowdsourcing map is updated according to the target collection data corresponding to each vehicle.

5. The method according to claim 4, wherein: The step of respectively determining the data collection error corresponding to each vehicle includes: For each vehicle, obtaining second historical collected data of the vehicle; determining a sensor error and / or a positioning error of the vehicle according to the second historical collected data; A data collection error corresponding to the vehicle is determined based on a sensor error and / or a positioning error of the vehicle.

6. An automatic driving method, comprising: Obtaining a crowdsourced map updated by the method described in any one of claims 1 to 5; The driving route of the autonomous driving vehicle is determined based on the updated crowdsourced map and the current position of the autonomous driving vehicle.

7. A map updating device, comprising: A data acquisition module, configured to acquire first historically collected data corresponding to the current crowdsourced map when the map information of the current crowdsourced map meets a preset trigger condition, wherein the preset trigger condition includes at least one of a data uniformity trigger condition, a data confidence trigger condition, and a data integrity trigger condition; A task generation module is used to determine at least one target area where data collection is required based on the first historical collection data; perform clustering processing on the at least one target area to obtain at least one cluster center; generate at least one data collection route based on the at least one cluster center; generate at least one crowdsourcing collection task based on the at least one data collection route, and assign each of the crowdsourcing collection tasks to a corresponding vehicle, wherein the target area is an area where the corresponding historical collection data is incomplete, uneven in timeliness, uneven in collection area, or whose confidence does not meet preset conditions; The map updating module is used to update the current crowdsourcing map according to the collection data fed back by each vehicle based on the corresponding crowdsourcing collection task.

8. The device according to claim 7, wherein: The map information includes data features of crowdsourced collected data corresponding to the current crowdsourced map; When the map information of the current crowdsourced map meets the preset trigger condition, the data acquisition module acquires the first historical collection data corresponding to the current crowdsourced map, and is used to: Extracting data features of the crowdsourced data; When the data feature meets the preset trigger condition, the first historical collection data corresponding to the current crowdsourcing map is obtained.

9. The device according to claim 8, wherein: The data characteristics include at least one of the following: The uniformity characteristics of the collection time of the crowd-sourced data; the uniformity characteristics of the collection location of the crowd-sourced data; the integrity of the crowd-sourced data with respect to the geographical scope corresponding to the current crowd-sourced map; and the confidence level of the crowd-sourced data.

10. The device according to any one of claims 7 to 9, wherein: When updating the current crowdsourcing map according to the collected data fed back by each vehicle based on the corresponding crowdsourcing collection task, the map updating module is used to: Determine the data collection error corresponding to each vehicle respectively; For each vehicle, according to the data collection error and error weight corresponding to the vehicle, the collected data fed back by the vehicle is adjusted to obtain the target collected data corresponding to the vehicle; The current crowdsourcing map is updated according to the target collection data corresponding to each vehicle.

11. The device according to claim 10, wherein: When determining the data collection error corresponding to each vehicle respectively, the map updating module is used to: For each vehicle, obtaining second historical collected data of the vehicle; determining a sensor error and / or a positioning error of the vehicle according to the second historical collected data; A data collection error corresponding to the vehicle is determined based on a sensor error and / or a positioning error of the vehicle.

12. An automatic driving device, comprising: A map acquisition module, used to acquire a crowdsourced map updated by the method described in any one of claims 1 to 5; A route determination module is used to determine the driving route of the autonomous driving vehicle based on the updated crowdsourced map and the current position of the autonomous driving vehicle.

13. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to make a computer execute the method according to any one of claims 1 to 6.

15. A computer program product comprising a computer program / instructions, wherein: When the computer program / instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images