An in-transit management method and device for an autonomous logistics vehicle

Abstract

The present application provides a method and device for in-transit management of autonomous logistics vehicles. The method determines the in-transit abnormal data of the autonomous logistics vehicle through a built-in autonomous driving monitoring module. Based on the in-transit abnormal data and the real-time video stream, the in-transit information is determined and sent to the cloud server to obtain the logistics vehicle control instructions. The real-time video stream comes from the built-in image acquisition device. And based on the in-transit abnormal data, emergency control instructions are generated to control the in-transit driving status of the autonomous logistics vehicle until the logistics vehicle control instructions are executed. The above scheme improves the emergency risk avoidance capability of the autonomous logistics vehicle, enables the autonomous logistics vehicle to intelligently handle emergencies or road emergencies, and improves the user experience of using the autonomous logistics vehicle.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to a management method and device for an automatic driving logistics vehicle. BACKGROUND

[0002] In the past, economic development zones, export processing zones, bonded zones, industrial parks or manufacturing parks and the like require a large number of logistics vehicles and corresponding vehicle drivers to realize logistics transportation within a closed park. With the promotion of the concept of "reducing costs and increasing efficiency, energy saving and environmental protection", the operating costs of the logistics industry in the park are difficult to reduce, and problems such as the difficulty of recruiting drivers for park logistics vehicles have emerged, prompting the park logistics industry to reform.

[0003] With the development of science and technology, park logistics is developing towards automation, intelligence and unmanned. Current automatic driving logistics vehicles can automatically travel within the park according to a planned path. However, the automatic driving logistics vehicle has limitations. In the event of an emergency or a road emergency in the park, the emergency response capability is poor, and intelligent processing of the emergency event cannot be performed, which may increase the severity of the accident. SUMMARY

[0004] The embodiments of the present application provide a management method and device for an automatic driving logistics vehicle, which can improve the emergency response capability of the automatic driving logistics vehicle, enable the automatic driving logistics vehicle to intelligently process an emergency event or a road emergency, and improve the user experience of using the automatic driving logistics vehicle.

[0005] In one aspect, the embodiments of the present application provide a management method for an automatic driving logistics vehicle, which comprises:

[0006] The in-trip abnormal data of the automatic driving logistics vehicle is determined by the built-in automatic driving monitoring module. The in-trip information is determined according to the in-trip abnormal data and the real-time video stream, and the in-trip information is sent to the cloud server to obtain the logistics vehicle control instruction. The real-time video stream comes from the built-in image acquisition device. The emergency control instruction is generated according to the in-trip abnormal data to control the in-trip driving state of the automatic driving logistics vehicle until the logistics vehicle control instruction is executed.

[0007] In one implementation manner of the present application, the real-time video stream is used as the in-trip information, and the in-trip information is sent to the cloud server in real time.

[0008] In one implementation manner of the present application, the real-time video stream and / or vehicle driving information are input into a preset abnormal monitoring model by the automatic driving monitoring module to determine whether the automatic driving logistics vehicle has in-trip abnormal data. The vehicle driving information at least includes sensor operation data. The in-trip abnormal data includes external abnormalities of the logistics vehicle and internal abnormalities of the logistics vehicle.

[0009] In an implementation form of the present application, the in-transit abnormal data is parsed to determine an abnormal code of the in-transit abnormal data. According to the abnormal code and a preset abnormal level correspondence table, an abnormal level corresponding to the abnormal code is determined. According to the abnormal level, a corresponding emergency control instruction is determined. The emergency control instruction at least includes one or more of the following: a turn signal, an alarm signal, a deceleration signal, and a stop signal.

[0010] In an implementation form of the present application, in the case that the emergency control instruction is a stop signal, a stop acceleration corresponding to the stop signal in a stop acceleration correspondence table is determined.

[0011] In an implementation form of the present application, the in-transit abnormal data and the real-time video stream are taken as in-transit information. Alternatively, the abnormal code corresponding to the in-transit abnormal data and the real-time video stream are taken as in-transit information. Alternatively, the real-time video stream is taken as the in-transit information.

[0012] In an implementation form of the present application, in the case that the execution of the logistics vehicle control instruction is ended, it is determined whether there is in-transit abnormal data. In the case that it is determined that there is no in-transit abnormal data, a release abnormal instruction is generated. The release abnormal instruction is used to release the emergency control instruction. Otherwise, the emergency control instruction is executed.

[0013] On the other hand, the present application also provides an in-transit management method for an automatic driving logistics vehicle, which comprises:

[0014] Obtaining in-transit information from a logistics vehicle end. Based on user feedback operation on the in-transit information, a logistics vehicle control instruction is generated and sent to the logistics vehicle end, so as to manage the automatic driving logistics vehicle in transit through the logistics vehicle control instruction.

[0015] In an implementation form of the present application, the in-transit information is sent to a corresponding display terminal to display the real-time video stream and / or the in-transit abnormal data and / or the abnormal code of the logistics vehicle end.

[0016] On the other hand, the present application also provides an in-transit management device for an automatic driving logistics vehicle, which comprises:

[0017] At least one processor; and a memory connected with the at least one processor in communication. The memory stores instructions executable 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:

[0018] The in-transit abnormal data of the automatic driving logistics vehicle is determined through the built-in automatic driving monitoring module. According to the in-transit abnormal data and the real-time video stream, the in-transit information is determined, and the in-transit information is sent to the cloud server to obtain the logistics vehicle control instruction. The real-time video stream is from the built-in image acquisition device. And according to the in-transit abnormal data, the emergency control instruction is generated to control the in-transit driving state of the automatic driving logistics vehicle until the logistics vehicle control instruction is executed.

[0019] Through the above-mentioned scheme, the in-transit abnormal data of the automatic driving logistics vehicle is determined through the automatic driving monitoring module of the automatic driving logistics vehicle, and then the automatic driving logistics vehicle is controlled in an emergency or remotely. The closed-loop control of the automatic driving logistics vehicle in an emergency is realized. The emergency avoidance ability of the automatic driving logistics vehicle is improved, and the automatic driving logistics vehicle intelligently handles emergencies or road emergencies, improving the user experience of using the automatic driving logistics vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0020] The drawings described herein are used to provide further understanding of the present application, and form a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application, and do not constitute an improper limitation on the present application. In the drawings:

[0021] Figure 1 A flowchart of a method for in-transit management of an automatic driving logistics vehicle in an embodiment of the present application;

[0022] Figure 2 Another flowchart of a method for in-transit management of an automatic driving logistics vehicle in an embodiment of the present application;

[0023] Figure 3 A schematic diagram of an architecture for a method for in-transit management of an automatic driving logistics vehicle in an embodiment of the present application;

[0024] Figure 4 A structural schematic diagram of an in-transit management device for an automatic driving logistics vehicle in an embodiment of the present application. DETAILED DESCRIPTION

[0025] To make the purpose, technical scheme and advantages of the present application clearer, the technical scheme of the present application will be described clearly and completely below in combination with specific embodiments of the present application and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0026] According to incomplete statistics, there are 478 national economic development zones, export processing zones, bonded zones and the like in China, 1170 provincial development zones of various types, more than 22,000 industrial parks, manufacturing parks and the like, and countless university campuses, residential parks and the like. Under the social environment of "reducing costs and increasing efficiency, energy saving and environmental protection", the logistics industry in closed parks is also facing many problems such as high operating costs and difficulties in recruiting drivers. In order to improve the efficiency of loading and unloading, transportation, receiving and warehousing and other logistics work and realize high-quality transformation and upgrading development, automation, intelligentization and unmannedization of logistics parks have gradually become a development trend.

[0027] The emergence of the automatic driving logistics vehicle solves the above problems. However, the automatic driving logistics vehicle is limited by the performance of the perception processor (such as a laser radar, a visual camera) installed therein, and lacks high-performance processing capability for road emergencies, so that the automatic driving logistics vehicle cannot timely make intelligent processing and emergency processing when encountering a sudden event or a road emergency event in the park, such as a manhole cover depression, a tree falling and the like affecting the driving of the automatic driving logistics vehicle.

[0028] To solve the above technical problems, the embodiments of the present application provide an in-transit management method and device for an automatic driving logistics vehicle to improve the emergency avoidance capability of the automatic driving logistics vehicle, so that the automatic driving logistics vehicle intelligently processes a sudden event or a road emergency event and improves the user experience of using the automatic driving logistics vehicle.

[0029] The various embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0030] The embodiments of the present application provide an in-transit management method for an automatic driving logistics vehicle. When the logistics vehicle end is taken as an execution subject, as shown in Figure 1 the method can include steps S101-S103:

[0031] S101, the logistics vehicle end determines in-transit abnormal data of the automatic driving logistics vehicle through an automatic driving monitoring module built therein.

[0032] In the embodiments of the present application, the logistics vehicle end corresponds to a processor arranged in the automatic driving logistics vehicle and can acquire self-running data of the automatic driving logistics vehicle and related data of a perception acquisition device arranged in the automatic driving logistics vehicle, such as an image acquisition device, a temperature acquisition device and the like. The image acquisition device includes a laser radar and a visual sensor arranged on the automatic driving logistics vehicle.

[0033] The laser radar can collect point cloud data in the park where the autonomous logistics vehicle is located in advance, and establish a high-precision point cloud map of the park through a simultaneous localization and mapping (SLAM) technology. Then, the park vector map established based on the high-precision point cloud map is used as a navigation map of the autonomous logistics vehicle. Through the selection of the start point and the end point of the navigation map, the autonomous logistics vehicle can be automatically driven between the global path planned between the start point and the end point.

[0034] The visual sensor can collect video data of the position where the autonomous logistics vehicle is located in real time.

[0035] In the embodiments of the present application, the logistics vehicle end can use the real-time video stream as in-transit information, and send the in-transit information to the cloud server in real time.

[0036] The user can watch the real-time video stream on the cloud server end, and can flexibly control the autonomous logistics vehicle according to the watched real-time video stream at any time when the user needs or wants to control the autonomous logistics vehicle.

[0037] In the embodiments of the present application, the logistics vehicle end determines the in-transit abnormal data of the autonomous logistics vehicle through the built-in autonomous driving monitoring module, and specifically includes:

[0038] Through the autonomous driving monitoring module, the logistics vehicle end inputs the real-time video stream and / or vehicle driving information into a preset abnormal monitoring model to determine whether the autonomous logistics vehicle has in-transit abnormal data. The vehicle driving information at least includes sensor operation data. The in-transit abnormal data includes external abnormality of the logistics vehicle and internal abnormality of the logistics vehicle.

[0039] For example, the logistics vehicle end can input the perception information such as clustered obstacles, the intention analysis information such as obstacle predicted trajectory jump, posture, the path planning related information such as inability to plan a safe driving path, and waiting for too long, the control related information such as too poor environment of the driving path (steep slope, road surface concave-convex), and other hardware information such as hardware voltage data and sensor related data, etc. into the abnormal monitoring model to determine whether the autonomous logistics vehicle has in-transit abnormal data.

[0040] The real-time video stream can include video data around the autonomous logistics vehicle when driving, and can also include video data inside the vehicle. For example, in a certain frame of video in the real-time video stream, there is an obstacle such as a garbage can in front of the autonomous logistics vehicle, which is not in the navigation map. The abnormal monitoring model will identify the video frame corresponding to the obstacle in the real-time video stream, and determine that there is an obstacle, and then judge that the obstacle is in-transit abnormal data.

[0041] The abnormality monitoring model provided in the application can include pre-training of a plurality of neural network models, and the training sample set is an image, vehicle related data and the like that can appear in the park and affect the normal driving of the autonomous driving logistics vehicle, which is preset by the user or obtained from the network, such as: a tree leaning on the road, a soil pile, again, such as an image of a fire in the autonomous driving logistics vehicle, a damaged visual sensor, sensor running data, vehicle control related data, such as vehicle driving state related data when the vehicle runs on a bumpy road.

[0042] In S102, the logistics vehicle end determines the in-transit information according to the in-transit abnormal data and the real-time video stream, and sends the in-transit information to the cloud server to obtain the logistics vehicle control instruction.

[0043] The logistics vehicle end determines the in-transit information according to the in-transit abnormal data and the real-time video stream, and sends the in-transit information to the cloud server to obtain the logistics vehicle control instruction.

[0044] The logistics vehicle end can take the in-transit abnormal data and the real-time video stream as the in-transit information. Alternatively, the logistics vehicle end takes the abnormality code corresponding to the in-transit abnormal data and the real-time video stream as the in-transit information. Alternatively, the real-time video stream is taken as the in-transit information. The abnormality code is obtained by analyzing the in-transit abnormal data, and specific reference is made to step S103.

[0045] The above scheme can make the autonomous driving logistics vehicle flexibly send the in-transit information after the subsequent in-transit abnormality occurs.

[0046] In S103, the logistics vehicle end generates an emergency control instruction according to the in-transit abnormal data to control the in-transit driving state of the autonomous driving logistics vehicle until the logistics vehicle control instruction is executed.

[0047] In the embodiments of the application, the logistics vehicle end generates an emergency control instruction according to the in-transit abnormal data, which specifically includes:

[0048] Firstly, the logistics vehicle end analyzes the in-transit abnormal data to determine the abnormality code of the in-transit abnormal data.

[0049] The logistics vehicle end can determine the abnormality code corresponding to the in-transit abnormal data by analyzing the in-transit abnormal data. For example, if the in-transit abnormal data is a leaning tree in front of the road, the abnormality code corresponds to 001; if the in-transit abnormal data is a speed bump in the road, the abnormality code corresponds to 002. Here, the in-transit abnormal data only exists exemplarily, and the abnormality code also exists exemplarily. The specific content and the corresponding relationship of the two are set according to actual use, and the application does not make specific limitations on this.

[0050] Then, the logistics vehicle end determines the abnormality level corresponding to the abnormality code according to the abnormality code and the preset abnormality level table.

[0051] The abnormality level correspondence table can be stored in the logistics vehicle terminal or in a storage medium connected to the logistics vehicle terminal, such as a hard disk. The storage location of the abnormality registration correspondence table is set according to actual needs. The abnormality level correspondence table is a correspondence table of abnormality codes and abnormality levels, for example: 001-high level, 002-medium level, 003-low level, and the like. Different abnormality levels can correspond to different vehicle control modes, for example, the control mode of the high level is: emergency braking, the control mode of the medium level is: deceleration and parking, and the control mode of the low level is: deceleration. The correspondence between the specific abnormality registration and the corresponding control mode can be set during actual use, and the present application does not make specific limitations thereto.

[0052] Then, the logistics vehicle terminal determines the corresponding emergency control instruction according to the abnormality level. The emergency control instruction at least includes one or more of the following: generating a turning signal, generating an alarm signal, generating a deceleration signal, and generating a parking signal.

[0053] In the embodiment of the present application, the generation of the turning signal can make the automatic driving logistics vehicle avoid the obstacle generating the in-transit abnormality data and turn. The generation of the alarm signal can be that the automatic driving logistics vehicle issues a warning such as "please avoid", or the automatic driving logistics vehicle issues a long-sounding alarm sound signal.

[0054] The generation of the deceleration signal can make the automatic driving logistics vehicle decelerate according to the deceleration signal.

[0055] In addition, in the case where the emergency control instruction is a parking signal, the parking acceleration corresponding to the parking signal in the parking acceleration correspondence table is determined.

[0056] The parking acceleration correspondence table refers to different accelerations for vehicle deceleration when parking. For example, when the automatic driving logistics vehicle is decelerated, the goods on the logistics vehicle are relatively heavy, and the logistics vehicle terminal can use a parking signal with an acceleration a; when the situation of the automatic driving logistics vehicle is urgent and needs to be parked urgently, the logistics vehicle terminal can use a parking signal with an acceleration b, where the acceleration a is less than the acceleration b.

[0057] Furthermore, the parking acceleration correspondence table can determine the parking acceleration according to the in-transit abnormality data or the abnormality code of the in-transit abnormality data. For example, the in-transit abnormality data is a road surface depression, the parking acceleration is a according to the query of the parking acceleration correspondence table, the abnormality code is 001, the parking acceleration is b according to the query of the parking acceleration correspondence table, and the like.

[0058] The logistics vehicle end can send an emergency control instruction to the chassis controller of the vehicle, so that the automatic driving logistics vehicle performs an alarm or stops with different acceleration or performs deceleration driving with different acceleration or turns in a certain direction at a speed, and the like. Since the logistics vehicle end and the cloud server communicate through a network, even in the case of smooth communication network, the cloud server transmits logistics vehicle control instructions to control the automatic driving logistics vehicle, which has a delay of hundreds of milliseconds. Therefore, the emergency control instruction of the logistics vehicle end avoids emergency braking when the logistics vehicle control instruction cannot control the automatic driving logistics vehicle in time.

[0059] In the embodiment of the application, the logistics vehicle end generates an emergency control instruction according to the in-transit abnormal data to control the in-transit driving state of the automatic driving logistics vehicle, and the method further comprises:

[0060] When the logistics vehicle end ends the execution of the logistics vehicle control instruction, it determines whether there is in-transit abnormal data. In the case where it is determined that there is no in-transit abnormal data, an abnormality release instruction is generated. The abnormality release instruction is used to release the emergency control instruction. Otherwise, the emergency control instruction is executed.

[0061] That is, after the cloud server ends remote control or remote driving through the logistics vehicle control instruction, the logistics vehicle end does not immediately release the emergency control instruction executed after encountering in-transit abnormal data, but needs to determine whether the in-transit abnormal data still exists, and release the executed emergency control instruction after the in-transit abnormal data no longer exists. If the in-transit abnormal data still exists, the logistics vehicle end will continue to execute the emergency control instruction.

[0062] For example, when the logistics vehicle end executes an emergency control instruction to stop with an acceleration a, it receives a logistics vehicle control instruction from the cloud server, and the logistics vehicle end will immediately execute the logistics vehicle control instruction to enter remote driving or remote control. If the cloud server and the logistics vehicle end are disconnected or the cloud server actively ends the logistics vehicle control instruction, the logistics vehicle end will determine whether there is in-transit abnormal data in the real-time video stream of the automatic driving logistics vehicle when the logistics vehicle control instruction ends. If there is in-transit abnormal data, the logistics vehicle end will determine the emergency control instruction corresponding to the in-transit abnormal data and execute it. If there is no in-transit abnormal data, the logistics vehicle end will no longer execute the emergency control instruction, that is, the remote control or remote driving is released from the in-transit abnormal data.

[0063] The priority of the logistics vehicle control instruction from the cloud server is higher than that of the emergency control instruction of the logistics vehicle end. When there is an unexecuted logistics vehicle control instruction, the logistics vehicle end will preferentially execute the logistics vehicle control instruction. And after the execution of the logistics vehicle control instruction, it will also be judged whether to continue the emergency control instruction, so as to realize the closed-loop control of the automatic driving logistics vehicle, improve the emergency avoidance capability of the automatic driving logistics vehicle, make the automatic driving logistics vehicle intelligently handle emergencies or road emergencies, and improve the user experience of using the automatic driving logistics vehicle.

[0064] In the embodiment of the present application, on the cloud server side, a method for in-transit management of an automatic driving logistics vehicle includes the following steps:

[0065] S201, the cloud server acquires in-transit information from the logistics vehicle end.

[0066] The in-transit information can be as described in step S103 above, and will not be repeated here.

[0067] S202, the cloud server sends the in-transit information to the corresponding display terminal to display the real-time video stream and / or in-transit abnormal data and / or abnormal code of the logistics vehicle end.

[0068] In the embodiment of the present application, the in-transit information can include in-transit abnormal data, abnormal code and real-time video stream. The display terminal connected by the cloud server can display at least one of the real-time video stream, in-transit abnormal data and abnormal code.

[0069] S203, the cloud server generates a logistics vehicle control instruction based on the feedback operation of the user on the in-transit information, and sends the logistics vehicle control instruction to the logistics vehicle end to manage the in-transit logistics vehicle through the logistics vehicle control instruction.

[0070] The user can remotely drive the automatic driving logistics vehicle after viewing the in-transit information, thereby generating a logistics vehicle control instruction corresponding to remote driving and sending the instruction to the current logistics vehicle end.

[0071] For example, when the automatic driving logistics vehicle encounters an abnormality and starts to execute an emergency braking operation, the user views the abnormality through the display terminal. The user can send a logistics vehicle control instruction for remote driving. The logistics vehicle end will start to execute the logistics vehicle control instruction corresponding to remote driving, and will no longer execute the emergency control instruction corresponding to emergency braking until the execution of the logistics vehicle control instruction is completed. In the case where the in-transit abnormal data no longer exists and the logistics vehicle control instruction is executed, the automatic driving logistics vehicle resumes automatic driving.

[0072] In the embodiment of the present application, the architecture diagram of the in-transit management method of the automatic driving logistics vehicle is as shown in Figure 3 specifically includes:

[0073] The automatic driving monitoring module 301 can monitor the automatic driving logistics vehicle in real time, and in the present application, can be used to determine the in-transit abnormal data of the automatic driving logistics vehicle.

[0074] The interaction data uploading module 302 can upload the real-time video stream and the in-transit abnormal data to the cloud server.

[0075] The emergency control braking module 303 can execute the emergency control instruction to perform emergency braking on the automatic driving logistics vehicle.

[0076] The joint arbitration module 304 can arbitrate all control commands, such as the priority of the logistics vehicle control instruction and the emergency control instruction.

[0077] and the automatic driving logistics vehicle 305, the cloud server 306 and the user 307.

[0078] Figure 4 A structural schematic diagram of an in-transit management device for an automatic driving logistics vehicle provided by an embodiment of the present application, the device comprising:

[0079] at least one processor; and a memory communicatively connected with the at least one processor. The memory stores instructions executable 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:

[0080] receive a real-time video stream from an image acquisition device. Determine whether the real-time video stream has in-transit abnormal data. In the case where it is determined that the real-time video stream has in-transit abnormal data, determine in-transit information according to the in-transit abnormal data and the real-time video stream, send the in-transit information to a cloud server to obtain a logistics vehicle control instruction, and generate an emergency control instruction according to the in-transit abnormal data to control the in-transit driving state of the automatic driving logistics vehicle until the logistics vehicle control instruction is executed.

[0081] Each of the embodiments in the present application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the difference from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the part of the method embodiment.

[0082] The device and method provided by the embodiments of the present application are one-to-one correspondence, so the device also has the similar beneficial technical effects as the method. Since the beneficial technical effects of the method have been described in detail above, the beneficial technical effects of the device will not be repeated here.

[0083] It should also be noted that the terms "comprising," "including," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can also include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises a... " does not, without more constraints, exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0084] The above description is merely illustrative of the application, and not restrictive. Various modifications and changes can become apparent to those skilled in the art. Incorporating any modification, equivalent substitution, improvement, etc. within the spirit and principle of the application, shall be included in the scope of the claims of the application.

Claims

1. A method for managing an autonomous logistics vehicle in transit, characterized in that: The method comprises: Through the built-in autonomous driving monitoring module, abnormal data of autonomous logistics vehicles in transit can be determined; Determine in-transit information based on the in-transit abnormal data and the real-time video stream, and send the in-transit information to the cloud server to obtain logistics vehicle control instructions; wherein the real-time video stream comes from a corresponding image acquisition device; and Generate an emergency control instruction based on the in-transit abnormal data to control the in-transit driving state of the autonomous logistics vehicle until the logistics vehicle control instruction is executed; The step of generating an emergency control instruction according to the abnormal data in transit specifically includes: parsing the in-transit abnormal data to determine an abnormality code of the in-transit abnormal data; Determine the abnormality level corresponding to the abnormality code according to the abnormality code and the preset abnormality level comparison table; the abnormality level comparison table is a corresponding relationship table between abnormality codes and abnormality levels; different abnormality levels correspond to different vehicle control modes; Determine the corresponding emergency control instruction according to the abnormality level; wherein the emergency control instruction includes at least one or more of the following: generating a turn signal, generating an alarm signal, generating a deceleration signal, and generating a stop signal; Among them, the generating of emergency control instructions according to the in-transit abnormal data to control the in-transit driving state of the autonomous driving logistics vehicle until the logistics vehicle control instructions are executed also includes: When the execution of the logistics vehicle control instruction is completed, determining whether the in-transit abnormal data exists; If it does not exist, generate a release exception instruction; wherein the release exception instruction is used to release the emergency control instruction; Otherwise, execute the emergency control instruction.

2. The method according to claim 1, characterized in that The method further comprises: The real-time video stream is used as in-transit information, and the in-transit information is sent to the cloud server in real time.

3. The method according to claim 1, characterized in that The built-in autonomous driving monitoring module is used to determine abnormal in-transit data of autonomous logistics vehicles, including: Through the autonomous driving monitoring module, the real-time video stream and / or vehicle driving information is input into a preset abnormality monitoring model to determine whether the autonomous driving logistics vehicle has any in-transit abnormal data; wherein, the vehicle driving information includes at least: sensor operation data; the in-transit abnormal data includes: external abnormalities of the logistics vehicle and internal abnormalities of the logistics vehicle.

4. The method according to claim 1, characterized in that In the case where the emergency control instruction is to generate a parking signal, a parking acceleration corresponding to the generated parking signal is determined in a parking acceleration comparison table.

5. The method according to claim 1, characterized in that: Determining the in-transit information based on the in-transit abnormal data and the real-time video stream specifically includes: Using the in-transit abnormal data and the real-time video stream as the in-transit information; or Using the abnormal code corresponding to the abnormal data in transit and the real-time video stream as the in-transit information; or The real-time video stream is used as the in-transit information.

6. An in-transit management device for an autonomous logistics vehicle, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: Through the built-in autonomous driving monitoring module, abnormal data of autonomous logistics vehicles in transit can be determined; Determine in-transit information based on the in-transit abnormal data and the real-time video stream, and send the in-transit information to the cloud server to obtain logistics vehicle control instructions; wherein the real-time video stream comes from a corresponding image acquisition device; and Generate an emergency control instruction based on the in-transit abnormal data to control the in-transit driving state of the autonomous logistics vehicle until the logistics vehicle control instruction is executed; The step of generating an emergency control instruction according to the abnormal data in transit specifically includes: parsing the in-transit abnormal data to determine an abnormality code of the in-transit abnormal data; Determine the abnormality level corresponding to the abnormality code according to the abnormality code and the preset abnormality level comparison table; the abnormality level comparison table is a corresponding relationship table between abnormality codes and abnormality levels; different abnormality levels correspond to different vehicle control modes; Determine the corresponding emergency control instruction according to the abnormality level; wherein the emergency control instruction includes at least one or more of the following: generating a turn signal, generating an alarm signal, generating a deceleration signal, and generating a stop signal; Among them, the generating of emergency control instructions according to the in-transit abnormal data to control the in-transit driving state of the autonomous driving logistics vehicle until the logistics vehicle control instructions are executed also includes: When the execution of the logistics vehicle control instruction is completed, determining whether the in-transit abnormal data exists; If it does not exist, generate a release exception instruction; wherein the release exception instruction is used to release the emergency control instruction; Otherwise, execute the emergency control instruction.

Images