Multi-vehicle automatic driving scheduling method, device, equipment and medium

Abstract

The invention provides a multi-vehicle automatic driving scheduling method and device, equipment and a medium, relates to the technical field of cloud computing services, is suitable for a vehicle automatic driving scene, and comprises the steps: obtaining a first driving path and a first vehicle control parameter planned in a target area of a first controlled vehicle set, a first vehicle control instruction of each first controlled vehicle is generated and issued; in the automatic driving process of each first controlled vehicle, initial environment flow data uploaded by each road side sensor in the target area is received, so that whether a second controlled vehicle set needing vehicle control scheduling adjustment exists in the first controlled vehicle set or not is recognized; and in response to the identification that the second controlled vehicle set exists, obtaining target obstacle logistics data of each second controlled vehicle based on each initial environment flow data so as to generate a second vehicle control instruction of each second controlled vehicle and issue the second vehicle control instruction.

Description

Technical Field

[0001] The present disclosure relates to the field of cloud computing services, and in particular to a method, device, equipment and medium for scheduling multi-vehicle autonomous driving, which are applicable to the field of autonomous driving technology. Background Art

[0002] With the development of technology, the vehicle's autonomous driving technology has provided more and more convenience for people's work and life. Among the related technologies, the vehicle's autonomous driving requires the configuration of corresponding vehicle-side sensing equipment and vehicle-side computing equipment on the vehicle body, which has a high configuration cost. Summary of the invention

[0003] The present disclosure proposes a multi-vehicle autonomous driving scheduling method, device, equipment and medium.

[0004] According to a first aspect of the present disclosure, a multi-vehicle automatic driving scheduling method is proposed, which is applicable to the vehicle side, including: obtaining a first driving path and a first vehicle control parameter planned by each first controlled vehicle set in a target area to generate and issue a first vehicle control instruction for each first controlled vehicle; during the automatic driving process of each first controlled vehicle, receiving initial environmental flow data uploaded by each roadside sensor in the target area to identify whether there is a second controlled vehicle set in the first controlled vehicle set that requires vehicle control scheduling adjustment; in response to identifying the existence of the second controlled vehicle set, obtaining the target obstacle flow data of each second controlled vehicle based on each initial environmental flow data to generate and issue a second vehicle control instruction for each second controlled vehicle.

[0005] According to the second aspect of the present disclosure, a multi-vehicle automatic driving scheduling method is proposed, which is applicable to the vehicle side, including: receiving a target vehicle control instruction issued from the cloud, and determining the driving speed information and driving direction information of the controlled vehicle based on the driving path information and vehicle control parameter information carried in the target vehicle control instruction, wherein the target vehicle control instruction is obtained based on the method proposed in the first aspect above; and performing automatic driving of the controlled vehicle based on the driving path information, the driving speed information and the driving direction information.

[0006] According to a third aspect of the present disclosure, a multi-vehicle automatic driving scheduling device is proposed, which is suitable for the cloud, including: an acquisition module, used to acquire the first driving path and first vehicle control parameter planned by each first controlled vehicle set in the target area, so as to generate and issue the first vehicle control instruction of each first controlled vehicle; an identification module, used to receive the initial environmental flow data uploaded by each roadside sensor in the target area during the automatic driving process of each first controlled vehicle, so as to identify whether there is a second controlled vehicle set in the first controlled vehicle set that requires vehicle control scheduling adjustment; a generation module, used to obtain the target obstacle flow data of each second controlled vehicle based on each initial environmental flow data in response to identifying the existence of the second controlled vehicle set, so as to generate and issue the second vehicle control instruction of each second controlled vehicle.

[0007] According to the fourth aspect of the present disclosure, a multi-vehicle automatic driving scheduling device is proposed, which is suitable for the vehicle side, including: a receiving module, used to receive the target vehicle control command issued by the cloud, and determine the driving speed information and driving direction information of the controlled vehicle based on the driving path information and vehicle control parameter information carried in the target vehicle control command, wherein the target vehicle control command is obtained based on the device proposed in the third aspect above; an automatic driving module, used to perform automatic driving of the controlled vehicle based on the driving path information, the driving speed information and the driving direction information.

[0008] According to the fifth aspect of the present disclosure, an electronic device is proposed, comprising: 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, and the instructions are executed by the at least one processor so that the at least one processor can execute the multi-vehicle autonomous driving scheduling method proposed in the first aspect and / or the second aspect above.

[0009] According to the sixth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is proposed, wherein the computer instructions are used to enable the computer to execute the multi-vehicle autonomous driving scheduling method proposed in the first aspect and / or the second aspect above.

[0010] According to a seventh aspect of the present disclosure, a computer program product is proposed, comprising a computer program, which, when executed by a processor, implements the multi-vehicle autonomous driving scheduling method proposed in the first aspect and / or the second aspect above.

[0011] 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

[0012] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0013] Figure 1 A schematic diagram of a process flow of a multi-vehicle automatic driving scheduling method according to an embodiment of the present disclosure;

[0014] Figure 2 A schematic diagram of a flow chart of a multi-vehicle automatic driving scheduling method according to another embodiment of the present disclosure;

[0015] Figure 3 A schematic diagram of a flow chart of a multi-vehicle automatic driving scheduling method according to another embodiment of the present disclosure;

[0016] Figure 4 A schematic diagram of a flow chart of a multi-vehicle autonomous driving scheduling method according to another embodiment of the present disclosure;

[0017] Figure 5 This is a schematic diagram of the structure of a multi-vehicle automatic driving dispatching device according to an embodiment of the present disclosure;

[0018] Figure 6 This is a schematic diagram of the structure of a multi-vehicle automatic driving dispatching device according to an embodiment of the present disclosure;

[0019] Figure 7 A schematic block diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0020] 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.

[0021] Data processing is a basic part of system engineering and automatic control. Data is a form of expression of facts, concepts or instructions, which can be processed by manual or automatic devices. After data is interpreted and given a certain meaning, it becomes information. Data processing is the collection, storage, retrieval, processing, transformation and transmission of data. The basic purpose of data processing is to extract and derive valuable and meaningful data for certain specific people from a large amount of data that may be disorganized and difficult to understand.

[0022] Figure 1 FIG. 1 is a flow chart of a multi-vehicle automatic driving scheduling method according to an embodiment of the present disclosure, which is applicable to the cloud. Figure 1 As shown, the method includes:

[0023] S101, obtaining first driving paths and first vehicle control parameters planned by each set of first controlled vehicles in a target area, so as to generate and issue first vehicle control instructions for each first controlled vehicle.

[0024] In the disclosed embodiment, the controlled vehicle that currently needs to be autonomously driven can be marked as the first controlled vehicle, and then a first controlled vehicle set is formed based on the first controlled vehicles, and the area where each first controlled vehicle in the first controlled vehicle set needs to be autonomously driven is determined as the target area.

[0025] It should be noted that the first controlled vehicle proposed in the embodiment of the present disclosure may be a non-sensing vehicle that is not equipped with a vehicle-side sensing device, or a vehicle whose configured sensing device is abnormal or fails, resulting in the inability to rely on the vehicle-side sensing device to achieve autonomous driving. No specific limitation is made here.

[0026] Optionally, there are multiple drivable paths in the target area. In this scenario, a driving path can be screened for each first controlled vehicle from the multiple drivable paths provided in the target area, wherein the tasks to be performed of each first controlled vehicle can be obtained, and driving path planning for automatic driving can be performed for each first controlled vehicle, and the driving path planned for each first controlled vehicle in the target area can be determined as the first driving path of each first controlled vehicle.

[0027] Optionally, each first controlled vehicle has its own driving attribute parameters, wherein the driving attribute parameters may include the speed parameter range and the acceleration parameter per 100 kilometers of each first controlled vehicle. In this scenario, after obtaining the first driving path of each first controlled vehicle, the specific vehicle control driving parameters of each first controlled vehicle on each first driving path can be determined based on the driving attribute parameters of each first controlled vehicle, and the vehicle control driving parameters can be determined as the first vehicle control parameters of each first controlled vehicle.

[0028] Among them, the first vehicle control parameters may include relevant parameters such as the planned driving speed, planned driving acceleration, planned driving time, planned driving direction, and planned driving order of each first controlled vehicle when automatically driving on its respective first driving path.

[0029] Furthermore, based on the vehicle control instruction generation algorithm in the relevant technology, based on the first driving path and the first vehicle control parameter of each first controlled vehicle, a corresponding control instruction is generated as the first vehicle control instruction of each first controlled vehicle, and based on the information interaction link between each first controlled vehicle and the cloud, the issuance of each first vehicle control instruction is realized.

[0030] S102, during the automatic driving process of each first controlled vehicle, receiving initial environmental flow data uploaded by each roadside sensor in the target area to identify whether there is a second controlled vehicle set in the first controlled vehicle set that requires vehicle control scheduling adjustment.

[0031] In the disclosed embodiment, after each first controlled vehicle receives the first vehicle control instruction required by itself, it can start automatic driving in the target area based on the received first vehicle control instruction. During the automatic driving process of each first controlled vehicle, it is necessary to detect and identify whether each first controlled vehicle is in a safe automatic driving state.

[0032] Optionally, sensor equipment for data collection is provided on the roadside of the target area, which can be marked as a roadside sensor in the target area. In this scenario, each roadside sensor will continuously collect data within its coverage area to obtain multiple groups of collected data. It can be seen that the multiple groups of data collected by each roadside sensor are continuous and real-time. In this scenario, for any roadside sensor, the multiple groups of continuous and real-time collected data collected by the roadside sensor can be used to form the stream data collected by the roadside sensor, and the data can be marked as the initial environmental flow data collected by the roadside sensor.

[0033] In this scenario, the cloud can integrate the initial environmental flow data collected and uploaded by each roadside sensor across multiple sensors, and obtain the vehicle condition information and road condition information of each first controlled vehicle during automatic driving through the integrated flow data, so as to identify whether each first controlled vehicle is in a safe automatic driving state.

[0034] Optionally, when it is identified that there are some controlled vehicles in the first controlled vehicle set that are in an unsafe autonomous driving state, it can be determined that the controlled vehicles in the unsafe autonomous driving state need to undergo vehicle control adjustment, and then the part of the vehicles can be determined as the second controlled vehicles in the first controlled vehicle set that need to undergo vehicle control adjustment, and the set consisting of the second controlled vehicles can be determined as the second controlled vehicle set.

[0035] It should be noted that the roadside sensors in the target area may include lidar sensors, image acquisition sensors, and other types of sensors capable of collecting road condition and vehicle condition information, etc., which are not specifically limited here.

[0036] S103, in response to identifying the existence of the second controlled vehicle set, obtaining target obstacle flow data of each second controlled vehicle based on each initial environmental flow data, so as to generate and issue a second vehicle control instruction for each second controlled vehicle.

[0037] In the disclosed embodiment, when it is identified that a second controlled vehicle set exists in a first controlled vehicle set, obstacle flow data of the surrounding environment of each second controlled vehicle can be obtained through the initial environmental flow data uploaded by each roadside sensor, wherein each initial environmental flow data can be integrated according to the flow data integration method in the relevant technology, and based on the integrated environmental flow data, the obstacle flow data of the surrounding environment of each second controlled vehicle can be extracted as the target obstacle flow data of each second controlled vehicle.

[0038] For any second controlled vehicle, the relative position relationship between the second controlled vehicle and the dynamic obstacles and static obstacles in its surrounding environment can be obtained based on the target obstacle flow data of the second controlled vehicle, wherein the dynamic obstacles may include other vehicles driving automatically around the second controlled vehicle, and may also include moving objects set to move on a path in the target area, which are not specifically limited here.

[0039] Optionally, based on the relative position relationship, the driving path and driving parameters of the second controlled vehicle for automatic driving in a safe driving state between each dynamic obstacle and each static obstacle can be determined, and the path can be determined as the current updated driving path of the second controlled vehicle, marked as the second driving path, and the updated vehicle control parameters of the second controlled vehicle can be obtained based on the driving parameters, marked as the second vehicle control parameters.

[0040] Optionally, through a preset vehicle control instruction generation method, based on the second driving path and second vehicle control parameters updated by the second controlled vehicle, a vehicle control instruction required to be updated when the second controlled vehicle performs vehicle control adjustment and scheduling is generated and determined as the second vehicle control instruction.

[0041] Furthermore, the second vehicle control instructions of each second controlled vehicle are sent to the corresponding vehicle terminals, thereby realizing the vehicle control dispatch of each second controlled vehicle.

[0042] The multi-vehicle automatic driving scheduling method proposed in the present disclosure obtains the first driving path and the first vehicle control parameter planned by each first controlled vehicle in the target area to generate and issue a first vehicle control instruction. During the automatic driving process of each first controlled vehicle, the initial environmental flow data uploaded by each roadside sensor is received to identify whether there is a second controlled vehicle set among each first controlled vehicle that needs to be adjusted in vehicle control scheduling. When the existence of the second controlled vehicle set is identified, the target obstacle flow data of each second controlled vehicle is obtained based on the initial environmental flow data uploaded by each roadside sensor, and then the second vehicle control instruction of each second controlled vehicle is generated and issued. In the present disclosure, the cloud plans the driving path and driving parameters for each first controlled vehicle, and generates the first vehicle control instruction to realize the automatic driving of each first controlled vehicle in the target area. There is no need to configure the vehicle-side sensing equipment on the vehicle side, which reduces the configuration cost of the automatic driving vehicle. The initial environmental flow data collected and uploaded by each roadside sensor is integrated across multiple sensors to obtain the target obstacle flow data of each second controlled vehicle. Compared with the related technology of fusing sensor data within a set range through an edge computing unit, the data fusion range of the roadside sensor is expanded, and the calculation steps of the data fusion of each initial environmental flow data are simplified. The second vehicle control instruction of each second controlled vehicle is calculated through the cloud, which improves the calculation efficiency and accuracy of the second vehicle control instruction, thereby improving the timeliness of the vehicle control scheduling adjustment of the controlled vehicle and the safety of automatic driving, thereby improving the safety and stability of the scheduling of multi-vehicle automatic driving, and optimizing the scheduling method of multi-vehicle automatic driving.

[0043] In the above embodiment, regarding the scheduling of multiple vehicles in the target area, the automatic driving can also be combined with Figure 2 Further understanding, Figure 2 FIG. 1 is a flow chart of a multi-vehicle automatic driving scheduling method according to another embodiment of the present disclosure. Figure 2 As shown, the method includes:

[0044] S201, obtaining first driving paths and first vehicle control parameters planned by each set of first controlled vehicles in a target area, so as to generate and issue first vehicle control instructions for each first controlled vehicle.

[0045] Optionally, a regional path map of the target area is obtained, and the starting position and the ending position of each first controlled vehicle in the regional path map are received.

[0046] In the disclosed embodiment, there is a driving path within the target area that can perform autonomous driving, and a map composed of this part of the driving path can be determined as a regional path map within the target area.

[0047] In this scenario, the entire path of each first controlled vehicle can be planned based on the regional path map, so as to obtain the first driving path planned for each first controlled vehicle in the target area.

[0048] As a possible implementation method, based on the mixed integer programming strategy in the relevant technology, the full path planning can be performed on each first controlled vehicle in the regional path map of the target area, so as to obtain the first driving path of each first controlled vehicle.

[0049] As another possible implementation method, the full path planning can be performed for each first controlled vehicle based on the starting point information and the end point information of each first controlled vehicle, wherein the starting point and the end point of each first controlled vehicle in the target area can be obtained, and the mapping positions of the starting point and the end point in the regional path map can be obtained, thereby obtaining the starting point position and the end point position of each first controlled vehicle in the regional path map of the target area.

[0050] Optionally, based on the starting point position and the end point position, full path planning is performed for each first controlled vehicle in the regional path map, and the first driving path of each first controlled vehicle is screened out from a path list provided by the regional path map.

[0051] In the disclosed embodiment, there is a set path list in the regional path map. For any first controlled vehicle, based on the starting position and the end position of the first controlled vehicle, a driving path that can start from the starting position and reach the end position can be screened from the path list as the first driving path of the first controlled vehicle in the regional path map.

[0052] Optionally, first path driving parameters planned for each first controlled vehicle on each first driving path are obtained, and first vehicle control parameters planned for each first controlled vehicle are determined based on the first path driving parameters, wherein the first path driving parameters include at least the driving speed, driving acceleration, driving direction, and driving order planned for each first controlled vehicle.

[0053] In the disclosed embodiment, after obtaining the first driving path planned for each first controlled vehicle, it is also necessary to obtain driving parameters such as speed parameters of each first controlled vehicle when automatically driving on its respective first driving path, wherein the relevant driving parameters of each first controlled vehicle when automatically driving on its respective first driving path can be determined as the first path driving parameters of each first controlled vehicle.

[0054] Among them, the first path driving parameters may include relevant driving parameters pre-planned when the first controlled vehicle performs automatic driving on its corresponding first driving path, and may include pre-planned driving speed, driving acceleration, driving direction and driving order, etc., wherein the driving order can be understood as the departure order of each first controlled vehicle when multiple vehicles set off at the same time, and the passing order of each first controlled vehicle when multiple vehicles pass the same intersection at the same time, etc., which is not specifically limited here.

[0055] Optionally, based on the first driving path and the first path driving parameters, a first vehicle control instruction for each first controlled vehicle is generated and issued.

[0056] In the disclosed embodiment, cloud computing services provided in the cloud can be used to perform algorithmic processing on the first driving path and first path driving parameters of each first controlled vehicle based on a vehicle control instruction generation algorithm in related technologies, and then obtain the first vehicle control instruction of each first controlled vehicle according to the result of the algorithmic processing.

[0057] It should be noted that, for any first controlled vehicle, the first vehicle control instruction corresponding to the first controlled vehicle carries unique identification information of the first controlled vehicle, and the identification information can be obtained by combining the vehicle identification number (Vehicle Identification Number, VIN) of the first controlled vehicle and the tracking identification (trackID) of the first controlled vehicle.

[0058] In the disclosed embodiment, there is a corresponding pre-accurate area for the target area for automatic driving of each first controlled vehicle. When each first controlled vehicle enters the pre-preparation area, the identification information of each first controlled vehicle can be collected by a scanning device arranged in the pre-preparation area, and transmitted to each roadside sensor and the cloud in the target area, so as to provide execution conditions for subsequent downstream tasks such as cloud computing and information collection of each first controlled vehicle.

[0059] S202, during the automatic driving process of each first controlled vehicle, receiving initial environmental flow data uploaded by each roadside sensor in the target area to identify whether there is a second controlled vehicle set in the first controlled vehicle set that requires vehicle control scheduling adjustment.

[0060] Optionally, based on the initial environmental flow data uploaded by each roadside sensor, it is identified whether each first controlled vehicle has a driving risk. For any first controlled vehicle, in response to identifying that the first controlled vehicle has a driving risk, the first controlled vehicle is determined to be the second controlled vehicle in the first controlled vehicle set that needs to undergo vehicle control scheduling adjustment, so as to obtain a second controlled vehicle set.

[0061] In the disclosed embodiment, the initial environmental flow data uploaded by each roadside sensor can be fused across multiple sensors through the cloud computing service provided by the cloud. In this scenario, it is possible to identify whether each first controlled vehicle has a driving risk from the fused flow data.

[0062] For any first controlled vehicle, when it is identified through the cloud that the first controlled vehicle is automatically driving on its first driving path based on the current first path driving parameters, there may be risk events such as collision or scratches with dynamic obstacles and static obstacles around it, it can be determined that the first controlled vehicle has a driving risk. In this scenario, the first controlled vehicle can be determined as the second controlled vehicle that requires vehicle control scheduling adjustment.

[0063] Furthermore, based on each second controlled vehicle identified in the first controlled vehicle set, a corresponding second controlled vehicle set is formed.

[0064] S203, during the automatic driving process of each second controlled vehicle, receiving the initial environmental flow data collected by each roadside sensor, and screening out candidate environmental flow data covering the second controlled vehicle from each initial environmental flow data.

[0065] In the disclosed embodiment, each second controlled vehicle is a controlled vehicle that is currently in the process of autonomous driving. In this scenario, corresponding screening can be performed on the initial environmental flow data uploaded by each roadside sensor in the target area to obtain environmental flow data associated with each second controlled vehicle and mark them as candidate environmental flow data for each second controlled vehicle.

[0066] Optionally, for any second controlled vehicle, flow data can be screened from each initial environmental flow data based on the identification information of the second controlled vehicle, and then some flow data carrying the identification information of the second controlled vehicle can be screened out from each initial environmental flow data and determined as candidate environmental flow data of the second controlled vehicle.

[0067] Optionally, for any second controlled vehicle, flow data can be filtered in the image dimension based on the appearance features of the second controlled vehicle from each initial environmental flow data, and then some flow data carrying the identification information of the second controlled vehicle can be filtered out from each initial environmental flow data and determined as candidate environmental flow data for the second controlled vehicle.

[0068] S204, extracting dynamic obstacle flow data and static obstacle flow data of the environment around the second controlled vehicle from the candidate environment flow data to obtain target obstacle flow data of the second controlled vehicle.

[0069] In the disclosed embodiment, after obtaining the candidate environmental flow data of each second controlled vehicle, the cloud computing service provided by the cloud can be used to perform flow data fusion across multiple sensors on each candidate environmental flow data to obtain fused environmental flow data of each second controlled vehicle.

[0070] In this scenario, for any second controlled vehicle, multiple sets of dynamic obstacle data and multiple sets of static obstacle information within a set range around the second controlled vehicle can be obtained from the fused environmental flow data of the second controlled vehicle, thereby obtaining dynamic obstacle flow data and static obstacle flow data within the set range around the second controlled vehicle.

[0071] Furthermore, the dynamic obstacle logistics data and the static obstacle logistics data are integrated to obtain all obstacle logistics data in a set range around the second controlled vehicle, which are marked as target obstacle logistics data of the second controlled vehicle.

[0072] As an example, for any second controlled vehicle, such as Figure 3 As shown, obtain Figure 3 The initial environmental flow data uploaded by the distance sensor 1, the roadside sensor 2, ..., and the roadside sensor N are shown. Figure 3 The input module shown inputs the initial environmental flow data uploaded to the cloud by each roadside sensor into Figure 3 In the probability distribution model shown, candidate environmental flow data covering the second controlled vehicle are screened out from each initial environmental flow data through the probability distribution model, and associated obstacles associated with the second controlled vehicle are obtained from the candidate environmental flow data.

[0073] Further, through Figure 3 The fusion correction module shown performs error correction in the time dimension and the space dimension on each associated obstacle obtained by screening, and uses the associated obstacles after fusion correction and the unassociated obstacles output by the probability distribution model that are not related to the second controlled vehicle as corresponding output results.

[0074] like Figure 3 As shown, Figure 3 The scenario shown also includes a multi-sensor obstacle fusion channel. Figure 3 In the illustrated scenario, the candidate environment flow data carrying associated obstacles in the output results can be fused across multiple sensors through the multi-sensor obstacle fusion channel to obtain the target obstacle flow data of the second controlled vehicle.

[0075] S205 , obtaining updated second driving paths and second vehicle control parameters of each second controlled vehicle based on the target obstacle logistics data, so as to generate and issue second vehicle control instructions for each second controlled vehicle.

[0076] Optionally, for any second controlled vehicle, a target obstacle set around the second controlled vehicle is acquired according to the target obstacle flow data, wherein the target obstacle set includes a static obstacle set and a dynamic obstacle set.

[0077] In the disclosed embodiment, the target obstacle flow data carries dynamic obstacle information and static obstacle information within a set range around each second controlled vehicle, and the dynamic obstacle set and static obstacle set within the set range around each second controlled vehicle can be obtained through the target obstacle flow data.

[0078] Furthermore, based on the dynamic obstacle set and the static obstacle set, a target obstacle set surrounding the second controlled vehicle is formed.

[0079] Among them, the set range around the controlled vehicle can be set to a set range corresponding to a circle with a radius of 30 meters and the controlled vehicle as the center, or a set range of other shapes, which is not specifically limited here.

[0080] Optionally, a relative distance parameter between the second controlled vehicle and each target obstacle is calculated to obtain a safe distance between the second controlled vehicle and each target obstacle.

[0081] In the disclosed embodiment, after the target obstacle set of any second controlled vehicle is obtained, the relative distance parameters between the second controlled vehicle and each target obstacle in the target obstacle set can be obtained through the cloud computing service provided by the cloud.

[0082] Furthermore, based on a safety distance algorithm in the related art, each relative distance parameter is processed by an algorithm, and then the safety distance between the second controlled vehicle and each target obstacle is obtained according to the result of the algorithm processing.

[0083] Optionally, based on the safety distance, a second driving path and a second vehicle control parameter updated by the second controlled vehicle are obtained.

[0084] Among them, for any second controlled vehicle, the first segment path currently traveled by the second controlled vehicle is obtained from the first driving path, and the first driving route of the second controlled vehicle in the first segment path is partially adjusted based on the safety distance to obtain the adjusted second driving route.

[0085] In the disclosed embodiment, the first driving path may be composed of multiple segments, wherein any segment path currently being traveled by the second controlled vehicle may be marked as a segment path of the second controlled vehicle in the first driving path, and the driving route planned by the second controlled vehicle on the segment path may be marked as the first driving route of the second controlled vehicle on the segment path.

[0086] In the disclosed embodiment, the target obstacle set of the second controlled vehicle may include a dynamic obstacle set and a fine-tuning obstacle set that are associated with the second controlled vehicle in the segment path. In this scenario, the first driving route of the second controlled vehicle on the segment path can be partially adjusted based on the safety distance between the second controlled vehicle and each target obstacle, and the adjusted driving route can be determined as the second driving route of the second controlled vehicle on the segment path.

[0087] Among them, the distributed model predictive control algorithm in the related technology and the vehicle obstacle avoidance algorithm in the related technology that can be configured in the cloud can perform local driving route adjustment and optimization on the first driving route of the second controlled vehicle on the segment path, thereby obtaining the adjusted second driving route of the second controlled vehicle on the segment path.

[0088] Optionally, a first segment driving parameter of the second controlled vehicle on the segment path is obtained, and the first segment driving parameter is adjusted based on the safety distance to obtain an updated second segment driving parameter of the second controlled vehicle.

[0089] In the disclosed embodiment, for any second controlled vehicle, the driving parameters of the second controlled vehicle planned to travel on the segment path can be marked as the first segment driving parameters of the second controlled vehicle. In this scenario, the driving parameters of the second controlled vehicle when performing automatic driving based on the second driving route can also be adjusted according to the safety distance and the adjusted second driving route, and the adjusted driving parameters can be determined as the second segment driving parameters of the second controlled vehicle.

[0090] Optionally, based on the second driving route and the second segment driving parameters, the first driving path and the first vehicle control parameters corresponding to the second controlled vehicle are updated to obtain updated second driving path and second vehicle control parameters.

[0091] In the disclosed embodiment, for any second controlled vehicle, the first driving path planned for the second controlled vehicle can be partially updated based on the second driving route, and the updated path is determined as the second driving path of the second controlled vehicle.

[0092] And, based on the second segment driving parameters, the first vehicle control parameters planned for the second controlled vehicle are locally updated to obtain updated second vehicle control parameters.

[0093] Furthermore, based on the cloud computing service provided by the cloud, based on the updated second vehicle control parameters and the second driving path, a corresponding second vehicle control instruction is generated and issued.

[0094] In the disclosed embodiment, when each first controlled vehicle performs automatic driving, there may be a situation where multiple vehicles are crowded in the target area, or there may be a situation where there is a risk of conflict between multiple vehicles, which can be understood in combination with the following contents:

[0095] Optionally, in response to initial environmental flow data uploaded by each roadside sensor, it is identified that there is a multi-vehicle congested sub-area in the target area, and a preset vehicle platoon scheduling strategy is obtained.

[0096] In the disclosed embodiment, for any sub-area within the target area, when the number of controlled vehicles performing autonomous driving in the sub-area is greater than or equal to a preset vehicle number threshold, it can be determined that the sub-area is a multi-vehicle crowded sub-area within the target area.

[0097] Among them, the cloud can identify multi-vehicle crowded sub-areas through the initial environmental flow data collected and uploaded by various roadside sensors.

[0098] In this scenario, the scheduling strategy corresponding to the multi-vehicle crowded sub-area can be obtained, marked as the vehicle formation scheduling strategy, wherein the third controlled vehicles in the multi-vehicle crowded sub-area can be queued based on the vehicle formation scheduling strategy, and the sorting interval of each third controlled vehicle can be obtained, and the third driving path and third vehicle control parameters of each third controlled vehicle can be generated based on the queue sorting and sorting interval to generate the third vehicle control instructions of each third controlled vehicle and issue them.

[0099] In the disclosed embodiment, the vehicle formation scheduling strategy can be understood as the cloud numbering and queuing the controlled vehicles in the multi-vehicle crowded sub-area, thereby scheduling the multiple controlled vehicles into a vehicle queue, thereby achieving safe automatic driving of the controlled vehicles in the multi-vehicle crowded sub-area.

[0100] Optionally, the controlled vehicles in the multi-vehicle crowded sub-area can be marked as third controlled vehicles, wherein each third controlled vehicle can be sorted in queue based on the vehicle formation scheduling strategy, and the vehicle spacing between each third controlled vehicle can be calculated based on the vehicle spacing algorithm in the relevant technology as the sorting interval when each third controlled vehicle is queued.

[0101] In this scenario, the cloud computing service provided by the cloud can be used to calculate the sorting position of each third controlled vehicle in the preset vehicle queue based on the determined queue sorting and the sorting interval of each third controlled vehicle, and based on the sorting position and the current automatic driving position of each third controlled vehicle, the updated driving path of each third controlled vehicle can be calculated and marked as the third driving path of each third controlled vehicle.

[0102] Also, relevant driving parameters such as driving speed and driving direction required for each third controlled vehicle to reach its respective sorting position are obtained, thereby obtaining updated third vehicle control parameters of each third controlled vehicle.

[0103] Furthermore, a new vehicle control instruction is generated based on the third driving path and the third vehicle control parameter that need to be updated, and is issued as the third vehicle control instruction of each third controlled vehicle.

[0104] It should be noted that in the process of calculating the third driving path and the third vehicle control parameters, it is necessary to consider the formation setting and vehicle spacing setting of each third controlled vehicle, and it is also necessary to consider related factors such as the lead vehicle control and the rear vehicle coordination in each third controlled vehicle, which are not specifically limited here.

[0105] Optionally, in response to initial environmental flow data uploaded by each roadside sensor, a conflict risk sub-area in the target area is identified, a set of fourth controlled vehicles in the conflict risk sub-area is obtained, the regional driving order of each fourth controlled vehicle in the conflict risk sub-area is determined, and a fourth driving path and fourth vehicle control parameters of each fourth controlled vehicle are generated based on the regional driving order to generate and issue a fourth vehicle control instruction.

[0106] In the disclosed embodiment, the conflict risk sub-area can be understood as, when the number of controlled vehicles that need to pass through the same intersection or crossroad is greater than the set vehicle number threshold, it can be determined that the sub-area corresponding to the intersection or crossroad is the conflict risk sub-area within the target area.

[0107] In this scenario, the cloud can identify the conflict risk sub-area in the target area through each initial environmental flow data. Optionally, the controlled vehicles in the conflict risk sub-area can be marked as fourth controlled vehicles, thereby obtaining a fourth controlled vehicle set consisting of each fourth controlled vehicle.

[0108] Optionally, for conflict intersections or crossroads in the conflict risk sub-area, the passing order of each fourth controlled vehicle in the sub-area can be set through the cloud as the regional driving order of each fourth controlled vehicle, and then a new fourth driving path and fourth driving parameters of each fourth controlled vehicle are generated based on the regional driving order, and then a new vehicle control instruction of each fourth controlled vehicle is generated as the fourth vehicle control instruction and issued through the cloud computing service in the cloud.

[0109] The multi-vehicle automatic driving scheduling method proposed in the present disclosure realizes the automatic driving of each first controlled vehicle in the target area through the cloud, without the need to configure the vehicle-side sensing equipment on the vehicle side, thereby reducing the configuration cost of the automatic driving vehicle, and integrating the initial environmental flow data collected and uploaded by each roadside sensor across multiple sensors, so as to obtain the target obstacle flow data of each second controlled vehicle. Compared with the related technology of fusing sensor data within a set range through an edge computing unit, the data fusion range of the roadside sensor is expanded, and the calculation steps of the data fusion of each initial environmental flow data are simplified. The second vehicle control instructions of each second controlled vehicle are calculated through the cloud, thereby improving the calculation efficiency and accuracy of the second vehicle control instructions, improving the timeliness of the vehicle control scheduling adjustment of multiple vehicles and the safety of automatic driving, and performing separate scheduling processing on different risk sub-areas through the cloud, thereby improving the safety and stability of the scheduling of multi-vehicle automatic driving, and optimizing the scheduling method of multi-vehicle automatic driving.

[0110] The present disclosure also proposes a multi-vehicle automatic driving scheduling method applicable to the vehicle side, which can be combined with Figure 4 understand, Figure 4 FIG. 1 is a flow chart of a multi-vehicle automatic driving scheduling method according to another embodiment of the present disclosure. Figure 4 As shown, the method includes:

[0111] S401, receiving a target vehicle control instruction sent from the cloud, and determining the driving speed information and driving direction information of the controlled vehicle based on the driving path information and vehicle control parameter information carried in the target vehicle control instruction.

[0112] Among them, the target vehicle control command is based on the above Figures 1 to 3 The method proposed in the embodiment is obtained.

[0113] In the disclosed embodiment, the vehicle control instructions sent from the cloud and received by the vehicle side can be marked as target vehicle control instructions. In this scenario, the controlled vehicle can parse the received target vehicle control instructions to obtain relevant information about the driving path required for autonomous driving and relevant information about vehicle control.

[0114] The relevant information of the driving route may be marked as driving route information, and the relevant information of the vehicle control may be marked as vehicle control parameter information.

[0115] Furthermore, based on the vehicle control parameter information, the speed information and the driving direction that the controlled vehicle needs to reach when performing automatic driving are obtained, which are marked as the driving speed information and driving direction information of the controlled vehicle respectively.

[0116] S402, performing automatic driving of the controlled vehicle based on the driving path information, the driving speed information and the driving direction information.

[0117] In the disclosed embodiment, the controlled vehicle is equipped with an automatic driving system. In this scenario, the automatic driving system configured on the vehicle can realize automatic driving of the controlled vehicle on the driving path corresponding to the driving path information based on the driving speed and acceleration carried in the driving speed information and the driving direction carried in the driving direction information.

[0118] It should be noted that during the automatic driving process of the controlled vehicle, cloud control anomalies may occur. Optionally, in response to the inability to receive the target vehicle control command sent from the cloud, a preset fallback vehicle control strategy is obtained.

[0119] In the disclosed embodiment, when the controlled vehicle is unable to receive the target vehicle control command sent from the cloud, it can be determined that the cloud is currently unable to perform normal autonomous driving scheduling control on the controlled vehicle. In this scenario, the controlled vehicle can be taken over for autonomous driving control through a preset fallback vehicle control strategy.

[0120] Optionally, in response to the controlled vehicle being unable to normally parse the received target vehicle control instruction, a preset fallback vehicle control strategy is obtained.

[0121] In the disclosed embodiment, when the controlled vehicle is unable to parse the received target vehicle control command or the parsed information is unreadable garbled code, it can be determined that the cloud is currently unable to perform normal autonomous driving scheduling control on the controlled vehicle. In this scenario, it is necessary to use a backup vehicle control strategy to take over the autonomous driving control of the controlled vehicle.

[0122] It should be noted that when the controlled vehicle encounters at least one of the two situations mentioned above, namely, being unable to receive the target vehicle control instructions issued by the cloud, and being unable to normally parse the received target vehicle control instructions, it can be determined that there is an abnormality in the cloud's automatic driving scheduling control of the controlled vehicle.

[0123] Optionally, a vehicle-side communication module embedded in the controlled vehicle is started based on the backup vehicle control strategy, and an emergency vehicle control request is sent to the emergency cockpit based on the vehicle-side communication module. The emergency cockpit takes over the automatic driving control of the controlled vehicle based on the emergency vehicle control request.

[0124] In the disclosed embodiment, the controlled vehicle is configured with an embedded vehicle-side communication module, wherein the vehicle-side communication module may be a 5G communication module, wherein the 5G communication module is the bottom layer of the vehicle-side communication module, and the network communication protocol (MQTT over Secure Sockets, MQTTS) in the QuickUDP Internet Connection (QUIC) is an upper-layer communication protocol, wherein MQTT can operate in 5G environment, 4G environment, and wireless communication environments such as V2X, thereby realizing information interaction between the controlled vehicle and the emergency cockpit.

[0125] In this scenario, the controlled vehicle can establish a scheduling relationship with the emergency cockpit that takes over the scheduling through the vehicle-side communication module.

[0126] Optionally, the controlled vehicle can obtain the current abnormal vehicle control information and generate a corresponding emergency vehicle control request, which is then sent to the emergency cockpit through the vehicle-side communication module. After receiving the emergency vehicle control request, the staff in the emergency cockpit can begin to take over the automatic driving control of the controlled vehicle, thereby realizing the automatic driving of the controlled vehicle candidate.

[0127] The multi-vehicle autonomous driving scheduling method proposed in the present invention realizes the autonomous driving of the controlled vehicles based on the target vehicle control instructions issued from the cloud. There is no need to configure the vehicle-side sensing equipment on the vehicle side, which reduces the configuration cost of the autonomous driving vehicles. The controlled vehicles with abnormal cloud scheduling are taken over and controlled through the emergency cockpit, which improves the safety of the autonomous driving of the controlled vehicles and optimizes the multi-vehicle autonomous driving scheduling method.

[0128] An embodiment of the present disclosure further proposes a multi-vehicle autonomous driving scheduling device suitable for the cloud. Since the multi-vehicle autonomous driving scheduling device suitable for the cloud proposed in the embodiment of the present disclosure corresponds to the multi-vehicle autonomous driving scheduling methods suitable for the cloud proposed in the above-mentioned embodiments, the implementation methods of the above-mentioned multi-vehicle autonomous driving scheduling methods suitable for the cloud are also applicable to the multi-vehicle autonomous driving scheduling device suitable for the cloud proposed in the embodiment of the present disclosure, and will not be described in detail in the following embodiments.

[0129] Figure 5 Schematic diagram of the structure of a multi-vehicle automatic driving dispatching device according to an embodiment of the present disclosure, which is applicable to the cloud, such as Figure 5 As shown, a multi-vehicle automatic driving dispatching device 500 includes an acquisition module 51, an identification module 52 and a generation module 53, wherein:

[0130] An acquisition module 51 is used to acquire the first driving paths and first vehicle control parameters planned by each of the first controlled vehicle sets in the target area, so as to generate and issue the first vehicle control instructions for each of the first controlled vehicles;

[0131] The identification module 52 is used to receive the initial environmental flow data uploaded by each roadside sensor in the target area during the automatic driving process of each first controlled vehicle, so as to identify whether there is a second controlled vehicle set in the first controlled vehicle set that needs vehicle control scheduling adjustment;

[0132] The generating module 53 is used for obtaining the target obstacle flow data of each second controlled vehicle based on each initial environmental flow data in response to identifying the existence of the second controlled vehicle set, so as to generate and issue the second vehicle control instruction of each second controlled vehicle.

[0133] In the disclosed embodiment, the generation module 53 is also used to: during the automatic driving process of each second controlled vehicle, receive the initial environmental flow data collected by each roadside sensor, and screen out candidate environmental flow data covering the second controlled vehicle from each initial environmental flow data; extract the dynamic obstacle flow data and static obstacle flow data of the surrounding environment of the second controlled vehicle from the candidate environmental flow data to obtain the target obstacle flow data of the second controlled vehicle; obtain the updated second driving path and second vehicle control parameters of each second controlled vehicle based on the target obstacle flow data to generate and issue the second vehicle control instructions of each second controlled vehicle.

[0134] In the disclosed embodiment, the generation module 53 is further used to: for any second controlled vehicle, obtain a target obstacle set around the second controlled vehicle according to the target obstacle flow data, wherein the target obstacle set includes a static obstacle set and a dynamic obstacle set; calculate the relative distance parameters between the second controlled vehicle and each target obstacle to obtain a safe distance between the second controlled vehicle and each target obstacle; and obtain an updated second driving path and a second vehicle control parameter of the second controlled vehicle according to the safe distance.

[0135] In the disclosed embodiment, the generation module 53 is also used to: for any second controlled vehicle, obtain the segment path currently traveled by the second controlled vehicle from the first driving path, and locally adjust the first driving route of the second controlled vehicle in the segment path based on the safety distance to obtain the adjusted second driving route; obtain the first segment driving parameters of the second controlled vehicle on the segment path, and adjust the first segment driving parameters based on the safety distance to obtain the updated second segment driving parameters of the second controlled vehicle; based on the second driving route and the second segment driving parameters, update the first driving path and the first vehicle control parameters corresponding to the second controlled vehicle to obtain the updated second driving path and the second vehicle control parameters.

[0136] In the disclosed embodiment, the acquisition module 51 is further used to: acquire a regional path map of the target area, and receive the starting position and the end position of each first controlled vehicle in the regional path map; based on the starting position and the end position, perform full path planning for each first controlled vehicle in the regional path map, and screen out the first driving path of each first controlled vehicle from the path list provided by the regional path map; acquire the first path driving parameters planned on each first driving path of each first controlled vehicle, and determine the first vehicle control parameters planned on each first controlled vehicle based on the first path driving parameters, wherein the first path driving parameters at least include the planned driving speed, driving acceleration, driving direction, and driving order of each first controlled vehicle; based on the first driving path and the first path driving parameters, generate and issue the first vehicle control instructions for each first controlled vehicle.

[0137] In the disclosed embodiment, the identification module 52 is also used to: identify whether each first controlled vehicle has a driving risk based on the initial environmental flow data uploaded by each roadside sensor; for any first controlled vehicle, in response to identifying that the first controlled vehicle has a driving risk, determine that the first controlled vehicle is the second controlled vehicle in the first controlled vehicle set that needs to undergo vehicle control scheduling adjustment, so as to obtain a second controlled vehicle set.

[0138] In the disclosed embodiment, the device also includes a scheduling module, which is used to: in response to the initial environmental flow data uploaded by each roadside sensor, identify the existence of a multi-vehicle crowded sub-area in the target area, and obtain a preset vehicle formation scheduling strategy; queue each third controlled vehicle in the multi-vehicle crowded sub-area based on the vehicle formation scheduling strategy, and obtain the sorting interval of each third controlled vehicle; based on the queue sorting and sorting interval, generate a third driving path and third vehicle control parameters of each third controlled vehicle, so as to generate and issue a third vehicle control instruction for each third controlled vehicle.

[0139] In the disclosed embodiment, the scheduling module is also used to: in response to the initial environmental flow data uploaded by each roadside sensor, identify the existence of a conflict risk sub-area in the target area, and obtain a set of fourth controlled vehicles in the conflict risk sub-area; determine the regional driving order of each fourth controlled vehicle in the conflict risk sub-area, and generate a fourth driving path and fourth vehicle control parameters of each fourth controlled vehicle based on the regional driving order, so as to generate and issue a fourth vehicle control instruction.

[0140] The multi-vehicle automatic driving scheduling device proposed in the present disclosure obtains the first driving path and the first vehicle control parameter planned by each first controlled vehicle in the target area to generate and issue a first vehicle control instruction. During the automatic driving process of each first controlled vehicle, the initial environmental flow data uploaded by each roadside sensor is received to identify whether there is a second controlled vehicle set among each first controlled vehicle that needs to be adjusted in vehicle control scheduling. When the existence of the second controlled vehicle set is identified, the target obstacle flow data of each second controlled vehicle is obtained based on the initial environmental flow data uploaded by each roadside sensor, and then the second vehicle control instruction of each second controlled vehicle is generated and issued. In the present disclosure, the cloud plans the driving path and driving parameters for each first controlled vehicle, and generates the first vehicle control instruction to realize the automatic driving of each first controlled vehicle in the target area. There is no need to configure the vehicle-side sensing equipment on the vehicle side, which reduces the configuration cost of the automatic driving vehicle. The initial environmental flow data collected and uploaded by each roadside sensor is integrated across multiple sensors to obtain the target obstacle flow data of each second controlled vehicle. Compared with the related technology of fusing sensor data within a set range through an edge computing unit, the data fusion range of the roadside sensor is expanded, and the calculation steps of the data fusion of each initial environmental flow data are simplified. The second vehicle control instruction of each second controlled vehicle is calculated through the cloud, which improves the calculation efficiency and accuracy of the second vehicle control instruction, thereby improving the timeliness of the vehicle control scheduling adjustment of the controlled vehicle and the safety of automatic driving, thereby improving the safety and stability of the scheduling of multi-vehicle automatic driving, and optimizing the scheduling method of multi-vehicle automatic driving.

[0141] An embodiment of the present disclosure further proposes a multi-vehicle automatic driving scheduling device applicable to the vehicle side. Since the multi-vehicle automatic driving scheduling device applicable to the vehicle side proposed in the embodiment of the present disclosure corresponds to the multi-vehicle automatic driving scheduling method applicable to the vehicle side proposed in the above-mentioned embodiments, the implementation method of the above-mentioned multi-vehicle automatic driving scheduling method applicable to the vehicle side is also applicable to the multi-vehicle automatic driving scheduling device applicable to the vehicle side proposed in the embodiment of the present disclosure, and will not be described in detail in the following embodiments.

[0142] Figure 6 Schematic diagram of the structure of a multi-vehicle automatic driving dispatching device according to an embodiment of the present disclosure, which is applicable to a vehicle side, such as Figure 6 As shown, a multi-vehicle automatic driving dispatching device 600 includes a receiving module 61 and an automatic driving module 62, wherein:

[0143] The receiving module 61 is used to receive the target vehicle control command sent from the cloud, and determine the driving speed information and driving direction information of the controlled vehicle based on the driving path information and vehicle control parameter information carried in the target vehicle control command, wherein the target vehicle control command is based on the above Figure 5 The device proposed in the embodiment is obtained;

[0144] The automatic driving module 62 is used to automatically drive the controlled vehicle based on the driving path information, driving speed information and driving direction information.

[0145] In the disclosed embodiment, the device also includes an emergency module, which is used to: obtain a preset fallback vehicle control strategy in response to an inability to receive a target vehicle control instruction sent from the cloud, and / or an inability to normally parse the received target vehicle control instruction; start a vehicle-side communication module embedded in the controlled vehicle based on the fallback vehicle control strategy, and send an emergency vehicle control request to the emergency cockpit based on the vehicle-side communication module, and the emergency cockpit takes over the automatic driving control of the controlled vehicle based on the emergency vehicle control request.

[0146] The multi-vehicle automatic driving scheduling device proposed in the present invention realizes the automatic driving of the controlled vehicles based on the target vehicle control instructions issued from the cloud. There is no need to configure the vehicle-side sensing equipment on the vehicle side, which reduces the configuration cost of the automatic driving vehicles. The controlled vehicles with abnormal cloud scheduling are taken over and controlled through the emergency cockpit, which improves the safety of the automatic driving of the controlled vehicles and optimizes the multi-vehicle automatic driving scheduling method.

[0147] According to an embodiment of the present disclosure, the present disclosure also proposes an electronic device, a readable storage medium, and a computer program product.

[0148] Figure 7 A schematic block diagram of an example electronic device 700 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.

[0149] like Figure 7 As shown, the device 700 includes a computing unit 701, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 702 or a computer program loaded from a storage unit 709 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the device 700 can also be stored. The computing unit 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0150] A number of components in the device 700 are connected to the I / O interface 705, including: an input unit 706, such as a keyboard, a mouse, etc.; an output unit 706, such as various types of displays, speakers, etc.; a storage unit 709, such as a disk, an optical disk, etc.; and a communication unit 709, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 709 allows the device 700 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0151] The computing unit 701 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 701 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 701 performs the various methods and processes described above, such as a multi-vehicle autonomous driving scheduling method. For example, in some embodiments, the multi-vehicle autonomous driving scheduling method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 709. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 700 via the ROM 702 and / or the communication unit 709. When the computer program is loaded into the RAM 703 and executed by the computing unit 701, one or more steps of the multi-vehicle autonomous driving scheduling method described above may be performed. Alternatively, in other embodiments, the computing unit 701 may be configured to perform the multi-vehicle autonomous driving scheduling method in any other appropriate manner (e.g., by means of firmware).

[0152] 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.

[0153] 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 presented 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, implements the functions / operations specified in the flow chart and / or block diagram. 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.

[0154] 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.

[0155] To propose interactions with a user account, the systems and techniques described herein may 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 account; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user account can propose input to the computer. Other types of devices may also be used to propose interactions with the user account; for example, feedback proposed to the user account may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user account may be received in any form (including acoustic input, voice input, or tactile input).

[0156] 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 account computer with a graphical user account interface or a web browser through which a user account 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.

[0157] 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.

[0158] 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.

[0159] 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 multi-vehicle autonomous driving scheduling method, wherein: Applicable to the cloud, the method includes: Acquire the first driving paths and first vehicle control parameters planned by the first controlled vehicle set in the target area, so as to generate and issue the first vehicle control instructions for each first controlled vehicle; During the automatic driving process of each first controlled vehicle, receiving the initial environmental flow data uploaded by each roadside sensor in the target area to identify whether there is a second controlled vehicle set in the first controlled vehicle set that needs vehicle control scheduling adjustment; In response to identifying the existence of the second controlled vehicle set, target obstacle flow data of each second controlled vehicle is obtained based on each initial environmental flow data, so as to generate and issue a second vehicle control instruction for each second controlled vehicle.

2. The method according to claim 1, wherein: In response to identifying the existence of the second controlled vehicle set, obtaining target obstacle flow data of each second controlled vehicle based on each initial environmental flow data to generate and issue a second vehicle control instruction for each second controlled vehicle includes: During the automatic driving of each second controlled vehicle, receiving initial environmental flow data collected by each roadside sensor, and screening out candidate environmental flow data covering the second controlled vehicle from each initial environmental flow data; Extracting dynamic obstacle flow data and static obstacle flow data of the surrounding environment of the second controlled vehicle from the candidate environment flow data to obtain the target obstacle flow data of the second controlled vehicle; Based on the target obstacle logistics data, the updated second driving path and the second vehicle control parameters of each second controlled vehicle are obtained to generate and issue the second vehicle control instructions of each second controlled vehicle.

3. The method according to claim 2, wherein: The obtaining of the updated second driving path and second vehicle control parameters of each second controlled vehicle based on the target obstacle logistics data includes: For any second controlled vehicle, obtaining a target obstacle set around the second controlled vehicle according to the target obstacle flow data, wherein the target obstacle set includes a static obstacle set and a dynamic obstacle set; Calculating a relative distance parameter between the second controlled vehicle and each target obstacle to obtain a safe distance between the second controlled vehicle and each target obstacle; According to the safety distance, a second driving path and a second vehicle control parameter updated by the second controlled vehicle are obtained.

4. The method according to claim 3, wherein: The acquiring, according to the safety distance, a second driving path and a second vehicle control parameter updated by the second controlled vehicle comprises: For any second controlled vehicle, a segment path currently traveled by the second controlled vehicle is obtained from the first driving path, and a first driving route of the second controlled vehicle in the segment path is partially adjusted based on the safety distance to obtain an adjusted second driving route; Acquire a first segment driving parameter of the second controlled vehicle on the segment path, and adjust the first segment driving parameter based on the safety distance to obtain an updated second segment driving parameter of the second controlled vehicle; Based on the second driving route and the second segment driving parameters, the first driving path and the first vehicle control parameters corresponding to the second controlled vehicle are updated to obtain the updated second driving path and the second vehicle control parameters.

5. The method according to claim 1, wherein: The step of obtaining the first driving paths and first vehicle control parameters planned by the first controlled vehicle set in the target area to generate and issue the first vehicle control instructions for each first controlled vehicle includes: Acquire a regional path map of the target area, and receive a starting position and an end position of each first controlled vehicle in the regional path map; Based on the starting position and the end position, respectively perform full path planning for each first controlled vehicle in the regional path map, and select a first driving path for each first controlled vehicle from a path list provided by the regional path map; Acquire the first path driving parameters planned by each first controlled vehicle on each first driving path, and determine the first vehicle control parameters planned by each first controlled vehicle based on the first path driving parameters, wherein the first path driving parameters at least include the driving speed, driving acceleration, driving direction, and driving order planned by each first controlled vehicle; Based on the first driving path and the first path driving parameters, a first vehicle control instruction for each first controlled vehicle is generated and issued.

6. The method according to claim 1, wherein: The method of receiving the initial environmental flow data uploaded by each roadside sensor in the target area during the automatic driving process of each first controlled vehicle to identify whether there is a second controlled vehicle set in the first controlled vehicle set that requires vehicle control scheduling adjustment includes: Based on the initial environmental flow data uploaded by each roadside sensor, identifying whether each first controlled vehicle has a driving risk; For any first controlled vehicle, in response to identifying that the first controlled vehicle has the driving risk, the first controlled vehicle is determined to be a second controlled vehicle in the first controlled vehicle set that requires vehicle control scheduling adjustment to obtain the second controlled vehicle set.

7. The method according to claim 1, wherein: The method further comprises: In response to the initial environmental flow data uploaded by each roadside sensor, identifying the presence of a multi-vehicle congested sub-area in the target area, and obtaining a preset vehicle formation scheduling strategy; Based on the vehicle formation scheduling strategy, the third controlled vehicles in the multi-vehicle congested sub-area are queued and the sorting interval of each third controlled vehicle is obtained; Based on the queue sorting and the sorting interval, a third driving path and a third vehicle control parameter of each third controlled vehicle are generated to generate and issue a third vehicle control instruction of each third controlled vehicle.

8. The method according to claim 1, wherein: The method further comprises: In response to initial environmental flow data uploaded by each roadside sensor, identifying that a conflict risk sub-area exists in the target area, and acquiring a fourth controlled vehicle set in the conflict risk sub-area; Determine the regional driving order of each fourth controlled vehicle in the conflict risk sub-area, and generate a fourth driving path and a fourth vehicle control parameter of each fourth controlled vehicle based on the regional driving order to generate and issue a fourth vehicle control instruction.

9. A method for dispatching multiple vehicles for autonomous driving, wherein: Applicable to the vehicle side, the method comprises: Receiving a target vehicle control command issued by the cloud, and determining the driving speed information and driving direction information of the controlled vehicle based on the driving path information and vehicle control parameter information carried in the target vehicle control command, wherein the target vehicle control command is obtained based on the method described in any one of claims 1 to 8 above; Automatic driving of the controlled vehicle is performed based on the driving path information, the driving speed information and the driving direction information.

10. The method according to claim 9, wherein: The method further comprises: In response to failure to receive the target vehicle control command sent by the cloud, and / or failure to normally parse the received target vehicle control command, obtaining a preset fallback vehicle control strategy; Based on the backup vehicle control strategy, the vehicle-side communication module embedded in the controlled vehicle is started, and based on the vehicle-side communication module, an emergency vehicle control request is sent to the emergency cockpit, and the emergency cockpit takes over the automatic driving control of the controlled vehicle based on the emergency vehicle control request.

11. A multi-vehicle automatic driving dispatching device, wherein: Applicable to the cloud, the device comprises: An acquisition module, used for acquiring the first driving paths and first vehicle control parameters planned by the first controlled vehicle set in the target area, so as to generate and issue the first vehicle control instructions for each first controlled vehicle; An identification module is used to receive the initial environmental flow data uploaded by each roadside sensor in the target area during the automatic driving process of each first controlled vehicle, so as to identify whether there is a second controlled vehicle set in the first controlled vehicle set that needs vehicle control scheduling adjustment; A generation module is used to obtain target obstacle flow data of each second controlled vehicle based on each initial environmental flow data in response to identifying the existence of the second controlled vehicle set, so as to generate and issue a second vehicle control instruction for each second controlled vehicle.

12. The device according to claim 11, wherein The generating module is further used for: During the automatic driving of each second controlled vehicle, receiving initial environmental flow data collected by each roadside sensor, and screening out candidate environmental flow data covering the second controlled vehicle from each initial environmental flow data; Extracting dynamic obstacle flow data and static obstacle flow data of the surrounding environment of the second controlled vehicle from the candidate environment flow data to obtain the target obstacle flow data of the second controlled vehicle; Based on the target obstacle logistics data, the updated second driving path and the second vehicle control parameters of each second controlled vehicle are obtained to generate and issue the second vehicle control instructions of each second controlled vehicle.

13. The device according to claim 12, wherein: The generating module is further used for: For any second controlled vehicle, obtaining a target obstacle set around the second controlled vehicle according to the target obstacle flow data, wherein the target obstacle set includes a static obstacle set and a dynamic obstacle set; Calculating a relative distance parameter between the second controlled vehicle and each target obstacle to obtain a safe distance between the second controlled vehicle and each target obstacle; According to the safety distance, a second driving path and a second vehicle control parameter updated by the second controlled vehicle are obtained.

14. The device according to claim 13, wherein: The generating module is further used for: For any second controlled vehicle, a segment path currently traveled by the second controlled vehicle is obtained from the first driving path, and a first driving route of the second controlled vehicle in the segment path is partially adjusted based on the safety distance to obtain an adjusted second driving route; Acquire a first segment driving parameter of the second controlled vehicle on the segment path, and adjust the first segment driving parameter based on the safety distance to obtain an updated second segment driving parameter of the second controlled vehicle; Based on the second driving route and the second segment driving parameters, the first driving path and the first vehicle control parameters corresponding to the second controlled vehicle are updated to obtain the updated second driving path and the second vehicle control parameters.

15. The device according to claim 11, wherein The acquisition module is further used for: Acquire a regional path map of the target area, and receive a starting position and an end position of each first controlled vehicle in the regional path map; Based on the starting position and the end position, respectively perform full path planning for each first controlled vehicle in the regional path map, and select a first driving path for each first controlled vehicle from a path list provided by the regional path map; Acquire the first path driving parameters planned by each first controlled vehicle on each first driving path, and determine the first vehicle control parameters planned by each first controlled vehicle based on the first path driving parameters, wherein the first path driving parameters at least include the driving speed, driving acceleration, driving direction, and driving order planned by each first controlled vehicle; Based on the first driving path and the first path driving parameters, a first vehicle control instruction for each first controlled vehicle is generated and issued.

16. The device according to claim 11, wherein The identification module is further used for: Based on the initial environmental flow data uploaded by each roadside sensor, identifying whether each first controlled vehicle has a driving risk; For any first controlled vehicle, in response to identifying that the first controlled vehicle has the driving risk, the first controlled vehicle is determined to be a second controlled vehicle in the first controlled vehicle set that requires vehicle control scheduling adjustment to obtain the second controlled vehicle set.

17. The device according to claim 11, wherein: The device also includes a scheduling module, which is used to: In response to the initial environmental flow data uploaded by each roadside sensor, identifying the presence of a multi-vehicle congested sub-area in the target area, and obtaining a preset vehicle formation scheduling strategy; Based on the vehicle formation scheduling strategy, the third controlled vehicles in the multi-vehicle congested sub-area are queued and the sorting interval of each third controlled vehicle is obtained; Based on the queue sorting and the sorting interval, a third driving path and a third vehicle control parameter of each third controlled vehicle are generated to generate and issue a third vehicle control instruction of each third controlled vehicle.

18. The device according to claim 11, wherein The scheduling module is also used for: In response to initial environmental flow data uploaded by each roadside sensor, identifying that a conflict risk sub-area exists in the target area, and acquiring a fourth controlled vehicle set in the conflict risk sub-area; Determine the regional driving order of each fourth controlled vehicle in the conflict risk sub-area, and generate a fourth driving path and a fourth vehicle control parameter of each fourth controlled vehicle based on the regional driving order to generate and issue a fourth vehicle control instruction.

19. A multi-vehicle automatic driving dispatching device, wherein: Applicable to the vehicle end, the device comprises: A receiving module, used to receive a target vehicle control instruction sent from the cloud, and determine the driving speed information and driving direction information of the controlled vehicle based on the driving path information and vehicle control parameter information carried in the target vehicle control instruction, wherein the target vehicle control instruction is obtained based on the device described in any one of claims 11 to 18; An automatic driving module is used to perform automatic driving of the controlled vehicle based on the driving path information, the driving speed information and the driving direction information.

20. The device according to claim 19, wherein The device also includes an emergency module, which is used to: In response to failure to receive the target vehicle control command sent by the cloud, and / or failure to normally parse the received target vehicle control command, obtaining a preset fallback vehicle control strategy; Based on the backup vehicle control strategy, the vehicle-side communication module embedded in the controlled vehicle is started, and based on the vehicle-side communication module, an emergency vehicle control request is sent to the emergency cockpit, and the emergency cockpit takes over the automatic driving control of the controlled vehicle based on the emergency vehicle control request.

21. 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 of any one of claims 1-8 and / or 9-10.

22. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-8 and / or 9-10.

23. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1-8 and / or 9-10.

Images