Control method for cooperative passage of vehicles

Abstract

The invention relates to the technical field of vehicle-road cloud integration, in particular to a vehicle collaborative passage control method, which comprises the following steps: in response to a collaborative request of a current vehicle, acquiring an initial collaborative target meeting a collaborative request condition; obtaining a corresponding historical time sequence information aggregation representation according to the state information of the initial cooperation target to generate a prediction trajectory and uncertainty; fusing the prediction trajectory, the uncertainty and the network connection trajectory to obtain a final prediction trajectory; and determining potential cooperation targets, calculating rear vehicle influence values of different potential cooperation targets to determine a final cooperation target, and generating a planning track of the final cooperation target and the current vehicle to control passing of the corresponding vehicle. Therefore, the problems that in related technologies, the vehicle-to-vehicle communication cooperation range is limited, so that the applicable scene is single, in addition, global traffic participant information is difficult to obtain only through information transmission between cooperation vehicles, accurate cognition cannot be achieved in the face of complex scenes, and the cooperation behavior efficiency is low are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle-road-cloud integration, and in particular to a control method for vehicle cooperative passing. BACKGROUND

[0002] In related technologies, for the positioning and evaluation scene of neighbor vehicles when the vehicles with communication capabilities are driving, multi-source asynchronous state information can be obtained by using communication and sensing technology, and data fusion can be realized by particle filtering, thereby improving the positioning accuracy. Alternatively, the environment can be classified by information control, and the sensing weight of the sensor can be allocated to selectively fuse data, and after analyzing the reliability and other indicators, the information control result can be further analyzed and fused according to the evaluation feedback.

[0003] However, in related technologies, vehicle-to-vehicle communication is often used, which has limited cooperative range on the one hand, resulting in single applicable scene; on the other hand, it is difficult to obtain global traffic participant information by information transmission between cooperative vehicles, which cannot accurately recognize the scene when facing complex scenes, resulting in low efficiency of cooperative behavior, which needs to be improved. SUMMARY

[0004] The present application provides a control method for vehicle cooperative passing to solve the problems in related technologies that vehicle-to-vehicle communication has limited cooperative range, resulting in single applicable scene, in addition, only relying on information transmission between cooperative vehicles cannot obtain global traffic participant information, cannot accurately recognize the scene when facing complex scenes, and cooperative behavior is inefficient.

[0005] The first aspect of the present application provides a control method for vehicle cooperative passing, comprising the following steps: in response to a cooperative request of a current vehicle, obtaining at least one initial cooperative target meeting the cooperative request condition; obtaining state information of the at least one initial cooperative target, and obtaining historical time sequence information aggregation representation of the corresponding initial cooperative target according to the state information, to generate a predicted trajectory of the at least one initial cooperative target and uncertainty of the predicted trajectory by using the historical time sequence information aggregation representation; fusing the predicted trajectory, the uncertainty of the predicted trajectory and a networked trajectory in the at least one initial cooperative target to obtain a final predicted trajectory of the at least one initial cooperative target; determining at least one potential cooperative target based on the final predicted trajectory and the at least one initial cooperative target, and calculating a rear vehicle influence value corresponding to different potential cooperative targets based on the at least one potential cooperative target, to determine a final cooperative target according to the rear vehicle influence value, and generating a first planning trajectory of the final cooperative target and a second planning trajectory of the current vehicle according to the cooperative request, to control the final cooperative target to pass according to the first planning trajectory and control the current vehicle to pass according to the second planning trajectory, respectively.

[0006] Optionally, in one embodiment of this application, obtaining the historical time-series information aggregation representation corresponding to the initial collaborative target based on the state information includes: identifying the information source of the state information; obtaining the collection time of the state information; and generating the historical time-series information aggregation representation based on the information source, the collection time, and the state information.

[0007] Optionally, in one embodiment of this application, the step of generating the predicted trajectory of the at least one initial cooperative target and the uncertainty of the predicted trajectory using the historical time-series information aggregation representation includes: determining the neighboring historical time-series information aggregation representations of neighboring initial cooperative targets based on the at least one initial cooperative target; calculating a first interactive coding feature and a second interactive coding feature under different information source conditions for the neighboring initial cooperative targets and the corresponding initial cooperative targets based on the neighboring historical time-series information aggregation representation and the historical time-series information aggregation representation; calculating a third interactive coding feature of the at least one initial cooperative target under different information source conditions based on the historical time-series information aggregation representation, the neighboring historical time-series information aggregation representation, the first interactive coding feature, the second interactive coding feature and the third interactive coding feature, and generating the predicted trajectory and the uncertainty of the predicted trajectory using a target Transformer network.

[0008] Optionally, in one embodiment of this application, fusing the predicted trajectory, the uncertainty of the predicted trajectory, and the networked trajectory in the at least one initial collaborative target to obtain the final predicted trajectory of the at least one initial collaborative target includes: determining a first weight of the predicted trajectory and a second weight of the networked trajectory based on the uncertainty of the predicted trajectory; and fusing the first weight, the second weight, the predicted trajectory, and the networked trajectory to obtain the final predicted trajectory.

[0009] Optionally, in one embodiment of this application, the formula for calculating the final predicted trajectory may be, but is not limited to, the following: , in, Indicates the initial collaboration goal The final predicted trajectory; Indicates the initial collaboration goal The predicted trajectory; Navigation information indicating the target of the network connection; Represents the fusion weights for the predicted trajectory; This represents the fusion weight of the connected trajectory.

[0010] Optionally, in an embodiment of the present application, the formula for calculating the rear vehicle impact value can be, but is not limited to: , wherein, represents the potential cooperative target quantitative impact value on the rear vehicle; represents the potential cooperative target the relative position of the rear target and the first target; represents the potential cooperative target the relative speed of the rear target and the first target; represents the potential cooperative target the final position after performing the cooperative trajectory; represents the potential cooperative target the final speed after performing the cooperative trajectory; represents the potential cooperative target the number of targets existing within a certain range in the rear; represents the impact calculation function. Optionally, in an embodiment of the present application, the formula for calculating the historical time sequence information aggregation representation can be, but is not limited to:

[0011] , wherein, represents the historical time sequence information aggregation representation of the initial cooperative target from the information source ; represents the state information of the initial cooperative target collected by the information source at the moment ; represents the length of the historical information sequence stored in the edge cloud; represents the Transformer network. Optionally, in an embodiment of the present application, wherein the expression of the first interaction encoding feature can be, but is not limited to:

[0012] , the expression of the second interaction encoding feature can be, but is not limited to: , the expression of the third interaction encoding feature can be, but is not limited to: , , wherein, ​represents an interactive coding feature, wherein represents a first interactive coding feature; represents a second interactive coding feature; represents a third interactive coding feature; and represents a different information source; and represents a different initial collaboration goal; represents state information of an initial collaboration goal gathered by an information source at a time instant ; represents state information of an initial collaboration goal gathered by an information source at a time instant ; represents state information of an initial collaboration goal gathered by an information source at a time instant ; represents state information of an initial collaboration goal gathered by an information source at a time instant ; represents a historical temporal information aggregated representation of an initial collaboration goal from an information source ; represents a historical temporal information aggregated representation of an initial collaboration goal from an information source ; represents a historical temporal information aggregated representation of an initial collaboration goal from an information source ; represents a historical temporal information aggregated representation of an initial collaboration goal from an information source ; represents a multi-layer perceptron.

[0013] The second aspect embodiment of the application provides a control device for vehicle cooperative passing, comprising: an acquisition module configured to acquire at least one initial cooperative target meeting a cooperative request condition in response to a cooperative request of a current vehicle; a generation module configured to acquire state information of the at least one initial cooperative target, and obtain historical time sequence information aggregation representation of a corresponding initial cooperative target according to the state information, so as to generate a predicted trajectory of the at least one initial cooperative target and uncertainty of the predicted trajectory by using the historical time sequence information aggregation representation; a fusion module configured to fuse the predicted trajectory, the uncertainty of the predicted trajectory and a networked trajectory in the at least one initial cooperative target, to obtain a final predicted trajectory of the at least one initial cooperative target; and a control module configured to determine at least one potential cooperative target based on the final predicted trajectory and the at least one initial cooperative target, calculate a rear vehicle influence value corresponding to different potential cooperative targets based on the at least one potential cooperative target, determine a final cooperative target according to the rear vehicle influence value, and generate a first planning trajectory of the final cooperative target and a second planning trajectory of the current vehicle according to the cooperative request, so as to control the final cooperative target to pass according to the first planning trajectory and control the current vehicle to pass according to the second planning trajectory.

[0014] Optionally, in an embodiment of the application, the generation module comprises: an identification unit configured to identify an information source of the state information; an acquisition unit configured to acquire a collection time of the state information; and a first generation unit configured to generate the historical time sequence information aggregation representation based on the information source, the collection time and the state information.

[0015] Optionally, in an embodiment of the application, the generation module comprises: a first determination unit configured to determine a neighboring historical time sequence information aggregation representation of a neighboring initial cooperative target of different initial cooperative targets based on the at least one initial cooperative target; a first calculation unit configured to calculate a first interaction encoding feature of the neighboring initial cooperative target and a corresponding initial cooperative target under a same information source condition and a second interaction encoding feature under a different information source condition based on the neighboring historical time sequence information aggregation representation and the historical time sequence information aggregation representation; a second calculation unit configured to calculate a third interaction encoding feature of the at least one initial cooperative target under a different information source condition based on the historical time sequence information aggregation representation; and a second generation unit configured to generate the predicted trajectory and the uncertainty of the predicted trajectory by using a target Transformer network based on the historical time sequence information aggregation representation, the neighboring historical time sequence information aggregation representation, the first interaction encoding feature, the second interaction encoding feature and the third interaction encoding feature.

[0016] Optionally, in one embodiment of this application, the fusion module includes: a second determining unit, configured to determine a first weight of the predicted trajectory and a second weight of the connected trajectory based on the uncertainty of the predicted trajectory; and a third generating unit, configured to fuse the first weight, the second weight, the predicted trajectory, and the connected trajectory to obtain the final predicted trajectory.

[0017] Optionally, in one embodiment of this application, the formula for calculating the final predicted trajectory may be, but is not limited to, the following: , in, Indicates the initial collaboration goal The final predicted trajectory; Indicates the initial collaboration goal The predicted trajectory; Navigation information indicating the target of the network connection; Represents the fusion weights for the predicted trajectory; This represents the fusion weight of the connected trajectory.

[0018] Optionally, in one embodiment of this application, the formula for calculating the impact value of the following vehicle may be, but is not limited to, the following: , in, Indicate potential collaborative goals The quantitative impact on following vehicles; Indicate potential collaborative goals rear The first goal and the first The relative positions of the targets; Indicate potential collaborative goals rear The first goal and the first The relative speed of the targets; Indicate potential collaborative goals The final position after executing the collaborative trajectory; Indicate potential collaborative goals The final velocity after executing the collaborative trajectory; Indicate potential collaborative goals The number of targets existing within a certain range behind; This indicates the function that affects the calculation.

[0019] Optionally, in one embodiment of this application, the calculation formula for the aggregation and representation of historical time-series information may be, but is not limited to, the following: , in, Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates information source exist Initial collaborative goal for real-time data collection Status information; This indicates the length of the historical information sequence stored at the edge cloud. This represents the Transformer network.

[0020] Optionally, in one embodiment of this application, the expression of the first interactive coding feature may be, but is not limited to,: , The expression for the second interactive coding feature may be, but is not limited to, as follows: , The expression for the third interactive coding feature may be, but is not limited to, as follows: , in, Represents the interactive coding feature, where, Indicates the first interactive coding feature; This represents the second interactive coding feature; Indicates the third interactive coding feature; and Indicates different sources of information; and Indicate different initial collaboration goals; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; This represents a multilayer perceptron.

[0021] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle cooperative passage control method as described in the above embodiments.

[0022] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described vehicle cooperative passage control method.

[0023] A fifth aspect of this application provides a computer program product, including a computer program that, when executed, implements the above-described vehicle cooperative passage control method.

[0024] This application embodiment can respond to the current vehicle's cooperation request and obtain an initial cooperation target that meets the cooperation request conditions. Then, based on the state information of the initial cooperation target, it generates a corresponding historical time-series information aggregation representation to generate a predicted trajectory and uncertainty corresponding to the initial cooperation target. Finally, it uses the connected trajectory to determine the final predicted trajectory to obtain potential cooperation targets, and determines the final cooperation target based on the impact value of following vehicles. This yields the final cooperation target and the planned trajectory of the current vehicle, thereby controlling the corresponding vehicle passage. It effectively utilizes the advantages of the vehicle-road-cloud integrated system, integrates information from different sources to achieve interactive trajectory prediction, establishes behavior prediction for numerous traffic participants in complex environments, and fully considers road traffic efficiency over a wide area, assessing the impact of cooperation behavior on vehicles in subsequent road segments. This allows for the selection of more efficient cooperation vehicles and the planning of more efficient cooperation trajectories. Therefore, it solves the problems in related technologies, such as the limited scope of vehicle-to-vehicle communication cooperation leading to a single applicable scenario, the difficulty in obtaining global traffic participant information through information transmission between cooperation vehicles alone, the inability to accurately recognize complex scenarios, and the low efficiency of cooperation behavior.

[0025] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0026] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a schematic diagram of the structure of a cooperative vehicle access strategy enforcement system according to an embodiment of this application; Figure 2 This is a flowchart of a vehicle cooperative passage control method provided according to an embodiment of this application; Figure 3 This is a schematic diagram of a cooperative vehicle traffic situation provided according to an embodiment of this application; Figure 4 A flowchart illustrating the working principle of a vehicle cooperative passage control method according to an embodiment of this application; Figure 5 This is a block diagram of a vehicle cooperative passage control device provided according to an embodiment of this application; Figure 6 This is a structural schematic diagram of a vehicle provided according to an embodiment of this application. Detailed Implementation

[0027] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0028] Before explaining the control method for cooperative vehicle passage provided in the embodiments of this application, the cooperative vehicle passage strategy execution system involved in the embodiments of this application will be introduced first.

[0029] Specifically, Figure 1 This is a schematic diagram of the structure of a cooperative vehicle access strategy enforcement system according to an embodiment of this application.

[0030] like Figure 1 As shown, the cooperative vehicle traffic strategy execution system includes a roadside unit 101, an on-board unit 102, an edge cloud data transfer subsystem 103, an edge cloud real-time decision-making subsystem 104, an edge cloud fusion perception subsystem 105, and an edge cloud system control subsystem 106.

[0031] When a vehicle is about to reach a bottleneck section and cannot pass through alone due to complex road conditions, it sends a collaboration request to the edge cloud through the onboard unit.

[0032] The edge cloud receives a collaboration request and sends the multi-source perception information uploaded by the roadside unit 101 and the vehicle-mounted unit 102 to the edge cloud fusion perception subsystem 105 via the edge cloud data transfer subsystem 103. The edge cloud fusion perception subsystem 105 performs interactive trajectory prediction by fusing multi-source information and then sends the predicted trajectory back to the edge cloud data transfer subsystem 103. The edge cloud data transfer subsystem 103 then sends the predicted trajectory to the edge cloud real-time decision-making subsystem 104. The edge cloud real-time decision-making subsystem 104 corrects the predicted trajectory, judges the impact of potential collaborative vehicles, and selects the final collaborative vehicle by sequentially issuing collaboration requests. Then, the edge cloud system control subsystem 106 plans trajectories for the final collaborative vehicle and the vehicle based on the final collaborative vehicle, and issues them to the relevant vehicles for execution via the edge cloud data transfer subsystem 103.

[0033] The following describes a vehicle cooperative passage control method according to embodiments of this application with reference to the accompanying drawings. Addressing the limitations of vehicle-to-vehicle communication cooperation mentioned in the background art, which leads to a single applicable scenario, and the difficulty in obtaining global traffic participant information solely through information transmission between cooperative vehicles, resulting in inaccurate understanding of complex scenarios and low efficiency in cooperative behavior, this application provides a vehicle cooperative passage control method. In this method, in response to a current vehicle's cooperation request, an initial cooperation target satisfying the cooperation request conditions is obtained. Then, based on the state information of the initial cooperation target, a corresponding historical time-series information aggregation representation is generated to generate a predicted trajectory and uncertainty corresponding to the initial cooperation target. The final predicted trajectory is then determined using the connected trajectory to obtain potential cooperation targets. Finally, the final cooperation target is determined based on the impact value of following vehicles, thereby obtaining the final cooperation target and the planned trajectory of the current vehicle, and controlling the corresponding vehicle passage. This method effectively utilizes the advantages of a vehicle-road-cloud integrated system, integrates information from different sources to achieve interactive trajectory prediction, establishes behavior prediction for numerous traffic participants in complex environments, and fully considers road traffic efficiency over a wide area, assessing the impact of cooperative behavior on vehicles in subsequent road segments. This allows for the selection of more efficient cooperative vehicles and the planning of more efficient cooperative trajectories. This solves the problems in related technologies, such as the limited scope of vehicle-to-vehicle communication collaboration, which leads to a single applicable scenario. In addition, relying solely on information transmission between collaborative vehicles makes it difficult to obtain information on all traffic participants, resulting in an inability to accurately recognize complex scenarios and low efficiency of collaborative behavior.

[0034] Specifically, Figure 2 This is a flowchart of a vehicle cooperative passage control method provided according to an embodiment of this application.

[0035] like Figure 2 As shown, the control method for cooperative vehicle passage includes the following steps: In step S201, in response to the current vehicle's cooperation request, at least one initial cooperation target that meets the cooperation request conditions is obtained.

[0036] In some embodiments, when a vehicle is facing a bottleneck and has difficulty passing through a road segment, the present application sends a cooperation request to the edge cloud. After receiving the cooperation request, the edge cloud, based on the roadside sensor perception results uploaded by the current vehicle, the intelligent connected vehicle sensor perception results, the connected vehicle status information, etc., obtains an initial cooperation target that meets the conditions of the cooperation request by fusing multi-source information for collaborative prediction and considering the interaction effect, and predicts the future trajectory and uncertainty of the initial cooperation target (different traffic participants, such as vehicles, pedestrians, etc., this application does not make specific restrictions), thereby achieving high-precision prediction of the future trajectory and uncertainty of the initial cooperation target.

[0037] In step S202, state information of at least one initial collaborative target is obtained, and historical time series information aggregation representation of the corresponding initial collaborative target is obtained based on the state information, so as to generate the predicted trajectory and uncertainty of the predicted trajectory of at least one initial collaborative target using the historical time series information aggregation representation.

[0038] It is understood that, in the embodiments of this application, the status information may include, but is not limited to, the perception results of roadside sensors, the perception results of intelligent connected vehicle sensors, and the status information of connected vehicles, etc., and this application does not impose specific limitations.

[0039] In some embodiments, this application can obtain the state information of the initial collaborative target, obtain the corresponding historical time series information aggregation representation, and use the historical time series information aggregation representation to generate the predicted trajectory and its uncertainty of each initial collaborative target.

[0040] Optionally, in one embodiment of this application, obtaining a historical time-series information aggregation representation of the corresponding initial collaborative target based on the state information includes: identifying the information source of the state information; obtaining the collection time of the state information; and generating a historical time-series information aggregation representation based on the information source, collection time, and state information. The calculation formula for the historical time-series information aggregation representation may be, but is not limited to, the following: , in, Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates information source exist Initial collaborative goal for real-time data collection Status information; This indicates the length of the historical information sequence stored at the edge cloud. This represents the Transformer network.

[0041] In some embodiments, the present application can first identify the information source of the status information and the corresponding collection time, and then perform time series information aggregation to obtain the motion trend representation of different traffic participants and obtain the corresponding historical time series information aggregation representation.

[0042] For example, embodiments of this application are shown in Figure 3 In the illustrated scenario, the edge cloud can aggregate state information from different sources with stored historical state information to obtain a temporal representation of the movement trends of each traffic participant, thus generating a historical temporal information aggregation representation. As a node in the interaction graph construction, the calculation formula for the aggregation and representation of historical time-series information can be, but is not limited to, the following: , in, Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates information source exist Initial collaborative goal for real-time data collection Status information; This indicates the length of the historical information sequence stored at the edge cloud. This represents the Transformer network.

[0043] It should be noted that the source of the information is... This application does not impose specific restrictions, but may include, but is not limited to, roadside sensors, intelligent connected vehicle sensors, etc.

[0044] Furthermore, in order to avoid spatiotemporal information leakage caused by the interaction of information in the early and later stages of the aggregation process, this embodiment adds an additional temporal mask to the information at each moment, the expression of which may be, but is not limited to: , in, and This represents the time of each of the two state information involved in the interaction, if If the current state information is earlier than the state information to be interacted with, then a mask is added to block the interaction.

[0045] Optionally, in one embodiment of this application, generating a predicted trajectory and the uncertainty of the predicted trajectory using historical time-series information aggregation representation includes: determining the neighboring historical time-series information aggregation representations of neighboring initial collaborative targets based on at least one initial collaborative target; calculating a first interactive coding feature and a second interactive coding feature under different information source conditions for neighboring initial collaborative targets and their corresponding initial collaborative targets based on the neighboring historical time-series information aggregation representations and historical time-series information aggregation representations; calculating a third interactive coding feature of at least one initial collaborative target under different information source conditions based on the historical time-series information aggregation representations; and generating a predicted trajectory and the uncertainty of the predicted trajectory using a target Transformer network based on the historical time-series information aggregation representations, neighboring historical time-series information aggregation representations, the first interactive coding feature, the second interactive coding feature, and the third interactive coding feature. The expression for the first interactive coding feature may be, but is not limited to, as follows: , The expression for the second interactive coding feature can be, but is not limited to, as follows: , The expression for the third interactive coding feature can be, but is not limited to, as follows: , in, Represents the interactive coding feature, where, Indicates the first interactive coding feature; This represents the second interactive coding feature; Indicates the third interactive coding feature; and Indicates different sources of information; and Indicate different initial collaboration goals; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; This represents a multilayer perceptron.

[0046] As one possible implementation, embodiments of this application can first determine the aggregated representation of neighboring historical time-series information of different initial collaborative targets, and then combine the aggregated historical time-series information representation to calculate a first interactive coding feature of neighboring initial collaborative targets and corresponding initial collaborative targets under the same information source condition and a second interactive coding feature under different information source conditions. The expression for the first interactive coding feature can be, but is not limited to, as follows: , The expression for the second interactive coding feature can be, but is not limited to, as follows: , in, Indicates the first interactive coding feature; This represents the second interactive coding feature; and Indicates different sources of information; and Indicate different initial collaboration goals; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; This represents a multilayer perceptron, used to encode relative state information.

[0047] Furthermore, embodiments of this application can aggregate representations based on historical time-series information to calculate the third interaction coding features of the initial collaborative target under different information source conditions, wherein the expression of the third interaction coding feature can be, but is not limited to, as follows: , in, Indicates the third interactive coding feature; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation.

[0048] Furthermore, in this embodiment, historical time-series information aggregation representation, neighboring historical time-series information aggregation representation, first interactive coding feature, second interactive coding feature and third interactive coding feature can be input into the target Transformer network, and multi-source information fusion and global interaction can be performed in sequence to update the node representation. By decoding the updated node representation, the corresponding predicted trajectory and uncertainty can be generated, thereby realizing the prediction of the future trajectory of each initial cooperative target.

[0049] For example, embodiments of this application can aggregate time-series information at the edge cloud and then represent the aggregated historical time-series information of different traffic participants from various information sources. Treating each node as a node, edge connections are established using the relative state information of neighboring traffic participants at the current moment to represent the interaction effects, generating a first interaction coding feature and a second interaction coding feature, the expression of which can be, but is not limited to: , , Aggregated representation of historical time-series information of the same traffic participant collected from different information sources Edge connections are established for multi-source information fusion to generate a third interactive coding feature, the expression of which may be, but is not limited to: , Furthermore, in this embodiment, the aggregated representations of the aforementioned nodes and various edge connections can be input into the target Transformer network for the same traffic participant collected from different information sources. Based on the extracted graph nodes and edge connection The target Transformer network is used to fuse multi-source information and update the node representation obtained by fusing multi-source information. Its expression can be, but is not limited to, as: , Furthermore, in this embodiment, based on the node representations and edge connections that fuse multi-source information, the target Transformer network is further utilized for global interaction to obtain node representations that fuse interactive information. Its expression can be, but is not limited to, as: , Finally, the embodiments of this application will represent the nodes that integrate interactive information. The inputs are decoded in a multilayer perceptron to generate the predicted trajectories and uncertainties for each traffic participant. The expression for this can be, but is not limited to, the following: , in, Indicates traffic participants The predicted trajectory; This indicates the uncertainty of the predicted trajectory; This refers to a multilayer perceptron, used to decode predicted trajectories and uncertainties.

[0050] In step S203, the predicted trajectory, the uncertainty of the predicted trajectory, and the networked trajectory in at least one initial cooperative target are fused to obtain the final predicted trajectory of at least one initial cooperative target.

[0051] It is understood that the connected trajectory in this application embodiment can be understood as navigation information uploaded by connected vehicles, and can be specifically set by those skilled in the art according to actual conditions; this application does not impose specific limitations. Connected vehicles are automobiles that use advanced communication technologies to achieve information exchange and interaction between the vehicle and its external environment. They can connect and interact with other vehicles, network centers, intelligent transportation systems, residences, offices, and public infrastructure, achieving information exchange between the in-vehicle network and the external network, comprehensively solving the problem of information exchange between people, vehicles, and the external environment.

[0052] In actual implementation, the embodiments of this application can use the uncertainty of the networked trajectory and the predicted trajectory to correct the predicted trajectory and obtain the final predicted trajectory.

[0053] Optionally, in one embodiment of this application, fusing the predicted trajectory, the uncertainty of the predicted trajectory, and the networked trajectory in at least one initial collaborative target to obtain the final predicted trajectory of at least one initial collaborative target includes: determining a first weight of the predicted trajectory and a second weight of the networked trajectory based on the uncertainty of the predicted trajectory; fusing the first weight, the second weight, the predicted trajectory, and the networked trajectory to obtain the final predicted trajectory. The calculation formula for the final predicted trajectory may be, but is not limited to, the following: , in, Indicates the initial collaboration goal The final predicted trajectory; Indicates the initial collaboration goal The predicted trajectory; Navigation information indicating the target of the network connection; Represents the fusion weights for the predicted trajectory; This represents the fusion weight of the connected trajectory.

[0054] In some embodiments, the present application can determine the first weight of the predicted trajectory and the second weight of the network trajectory based on the uncertainty of the predicted trajectory, thereby obtaining the final predicted trajectory. The formula for calculating the final predicted trajectory may be, but is not limited to, the following: , in, Indicates the initial collaboration goal The final predicted trajectory; Indicates the initial collaboration goal The predicted trajectory; Navigation information indicating the target of the network, if traffic participants For non-connected vehicles, set the value to 0; The fusion weights represent the predicted trajectories and are dynamically adjusted based on the confidence level of the uncertainty of the predicted trajectories. The fusion weights of the network trajectory are dynamically adjusted based on communication latency and communication quality.

[0055] In step S204, based on the final predicted trajectory and at least one initial cooperative target, at least one potential cooperative target is determined. Based on this potential cooperative target, the following vehicle impact value corresponding to different potential cooperative targets is calculated. The final cooperative target is then determined according to the following vehicle impact value. A first planned trajectory for the final cooperative target and a second planned trajectory for the current vehicle are generated according to the cooperative request. The first planned trajectory controls the passage of the final cooperative target, and the second planned trajectory controls the passage of the current vehicle, respectively. The formula for calculating the following vehicle impact value may be, but is not limited to, the following: , in, Indicate potential collaborative goals The quantitative impact on following vehicles; Indicate potential collaborative goals rear The first goal and the first The relative positions of the targets; Indicate potential collaborative goals rear The first goal and the first The relative speed of the targets; Indicate potential collaborative goals The final position after executing the collaborative trajectory; Indicate potential collaborative goals The final velocity after executing the collaborative trajectory; Indicate potential collaborative goals The number of targets existing within a certain range behind; This indicates the function that affects the calculation.

[0056] In some embodiments, this application can determine vehicles that may conflict with the current vehicle based on the final predicted trajectory and the initial cooperation target, exclude non-connected vehicles, and designate the remaining vehicles as potential cooperation targets. It then calculates the potential impact value of each potential cooperation target's cooperative behavior on vehicles behind, and issues cooperation requests sequentially based on these impact values ​​until a consent response is received, thus determining the final cooperation target. The formula for calculating the impact value can be, but is not limited to, the following: , in, Indicate potential collaborative goals The quantitative impact on following vehicles; Indicate potential collaborative goals rear The first goal and the first The relative positions of the targets; Indicate potential collaborative goals rear The first goal and the first The relative speed of the targets; Indicate potential collaborative goals The final position after executing the collaborative trajectory; Indicate potential collaborative goals The final velocity after executing the collaborative trajectory; Indicate potential collaborative goals The number of targets existing within a certain range behind; This represents the influence calculation function, used to calculate the impact of a potential collaborative target performing a collaborative action on the subsequent target. The impact of each objective.

[0057] For example, in this application embodiment, based on the final predicted trajectory, connected vehicles that may conflict with the current vehicle can be identified as potential cooperative vehicles. For each potential cooperative vehicle, a simple planning method using a uniform acceleration model is used to determine its position and speed after completing the cooperative behavior. The expression can be, but is not limited to, as follows: , in, Indicates the initial position of potential collaborating vehicles; Indicates the initial speed of the potential cooperative vehicles; The minimum acceleration required to complete the collaborative task.

[0058] Furthermore, in this embodiment of the application, after obtaining the position and speed of each potential cooperating vehicle after cooperative deceleration, the potential impact value of its cooperative deceleration behavior on following vehicles is calculated sequentially. The calculation formula may be, but is not limited to, the following: , Therefore, this application embodiment is based on the following vehicle impact value of each potential cooperative vehicle. The system issues collaboration request commands in ascending order and waits for confirmation until one of the potential collaborating vehicles returns a signal agreeing to collaborate, confirming it as the final collaborating vehicle, and then proceeds with the subsequent collaboration trajectory planning.

[0059] In some embodiments, this application can plan collaborative trajectories for the final collaborating vehicle and the current vehicle based on a collaboration request. The main content of this embodiment is as follows: First, in the embodiments of this application, the longitudinal and lateral trajectories of the two vehicles in the cooperation process can be described using fifth-order polynomials, and their expressions can be, but are not limited to, as follows: , , in, and These represent the longitudinal and transverse positions of the collaborative trajectory, respectively. Indicates the time required for the collaborative process.

[0060] Next, in order to minimize the impact of cooperative behavior on traffic flow, this embodiment of the application sets that at the end of the cooperative behavior, the speeds of the two cooperative vehicles are the same as those of the vehicles ahead on the road. Therefore, only the cooperative time needs to be given. Displacement during collaboration , This will confirm the collaborative trajectory. Therefore, we select... As optimization variables, construct the optimization problem to find the optimal cooperative trajectory.

[0061] Furthermore, in order to improve the smoothness of vehicle trajectory during the collaborative process and minimize speed fluctuations, the objective function designed in this application embodiment may be, but is not limited to, the following: , in, and This represents the longitudinal and lateral accelerations of the vehicle during the execution of the cooperative trajectory.

[0062] Furthermore, to further ensure the safety of the collaborative process, collision avoidance constraints are set, and a multi-circle collision model is adopted. The two participating vehicles and surrounding vehicles are represented as multiple fully covered collision circles. The potential for a collision on the collaborative trajectory is checked by calculating the distance between the collision circles. The calculation process can be, but is not limited to, as follows: , in, and These represent the two vehicles participating in the collaboration. The vertical and horizontal positions of the centers of the colliding circles; and They represent the surrounding vehicles. The vertical and horizontal positions of the center of the collision circle; and These represent the collision circle radii of the vehicles participating in the collaboration and the surrounding vehicles, respectively. An additional security threshold is set.

[0063] Finally, by solving the above-mentioned constraint optimization problem, the first planned trajectory of the final cooperative target and the second planned trajectory of the current vehicle can be obtained in this embodiment of the application. The passage of the final cooperative target is controlled according to the first planned trajectory and the passage of the current vehicle is controlled according to the second planned trajectory.

[0064] The following is a flowchart illustrating the working principle of the vehicle cooperative passage control method proposed in this application, with reference to a specific embodiment.

[0065] in, Figure 4 This is a flowchart illustrating the working principle of a vehicle cooperative passage control method provided according to an embodiment of this application.

[0066] Step S401: The current vehicle is facing a bottleneck section and cannot pass through. It sends a collaboration request to the edge cloud.

[0067] Step S402: The edge cloud performs interactive trajectory prediction by fusing multi-source information.

[0068] In this embodiment, the edge cloud can aggregate state information from different information sources with stored historical state information to obtain a temporal information representation of the movement trends of each traffic participant, thus obtaining a historical temporal information aggregation representation. , as nodes in the interaction graph construction.

[0069] Furthermore, embodiments of this application can aggregate time-series information at the edge cloud and then represent the aggregated historical time-series information of different traffic participants from various information sources. Treating each traffic participant as a node, edge connections are established using the relative state information of neighboring traffic participants at the current moment to represent interactive effects. Historical time-series information of the same traffic participant collected from different information sources is aggregated and represented. Edge connections are established for multi-source information fusion. Then, using the target Transformer network, multi-source information fusion and global interaction are performed sequentially to update node representations. By decoding the updated node representations, the corresponding predicted trajectories and uncertainties are generated.

[0070] Step S403: The edge cloud corrects the predicted trajectory based on the network trajectory to obtain the final predicted trajectory.

[0071] Step S404: The edge cloud identifies potential collaborative vehicles through the final predicted trajectory.

[0072] In this embodiment of the application, the connected vehicles that may conflict with the current vehicle can be identified based on the final predicted trajectory, and these vehicles can be regarded as potential cooperative vehicles.

[0073] Step S405: Edge computing impact value of vehicles to determine the final collaborative vehicles.

[0074] In this embodiment, the potential impact value of each cooperating vehicle's cooperative behavior on vehicles behind is calculated, and cooperation requests are issued sequentially based on the impact value until a consent response is received to determine the final cooperating vehicle.

[0075] Step S406: Generate the planned trajectories of the final cooperating vehicle and the current vehicle.

[0076] In this embodiment, the first planned trajectory of the final cooperating vehicle and the second planned trajectory of the current vehicle can be obtained by solving a constraint optimization problem, and the passage of the final cooperating vehicle can be controlled according to the first planned trajectory and the passage of the current vehicle can be controlled according to the second planned trajectory.

[0077] The vehicle cooperative passage control method proposed in this application can respond to the current vehicle's cooperative request and obtain an initial cooperative target that meets the cooperative request conditions. Then, based on the state information of the initial cooperative target, it generates a corresponding historical time-series information aggregation representation to generate a predicted trajectory and uncertainty corresponding to the initial cooperative target. Finally, it uses the network trajectory to determine the final predicted trajectory to obtain potential cooperative targets, and determines the final cooperative target based on the impact value of following vehicles. This yields the final cooperative target and the planned trajectory of the current vehicle, thereby controlling the corresponding vehicle passage. It effectively utilizes the advantages of the vehicle-road-cloud integrated system, integrates information from different sources to achieve interactive trajectory prediction, establishes behavior prediction for numerous traffic participants in complex environments, and fully considers road traffic efficiency over a wide area, assessing the impact of cooperative behavior on vehicles in subsequent road segments. This allows for the selection of more efficient cooperative vehicles and the planning of more efficient cooperative trajectories. Therefore, it solves the problems in related technologies, such as the limited scope of vehicle-to-vehicle communication cooperation leading to a single applicable scenario, the difficulty in obtaining global traffic participant information through information transmission between cooperative vehicles alone, the inability to accurately recognize complex scenarios, and the low efficiency of cooperative behavior.

[0078] Next, the control device for cooperative vehicle passage according to an embodiment of this application is described with reference to the accompanying drawings.

[0079] Figure 5 This is a block diagram of a vehicle cooperative passage control device provided according to an embodiment of this application.

[0080] like Figure 5 As shown, the control device 10 for vehicle cooperative passage includes: an acquisition module 100, a generation module 200, a fusion module 300, and a control module 400.

[0081] The acquisition module 100 is used to acquire at least one initial cooperation target that meets the cooperation request conditions in response to the current vehicle's cooperation request.

[0082] The generation module 200 is used to obtain the state information of at least one initial collaborative target and obtain the historical time series information aggregation representation of the corresponding initial collaborative target based on the state information, so as to generate the predicted trajectory and the uncertainty of the predicted trajectory of at least one initial collaborative target using the historical time series information aggregation representation.

[0083] The fusion module 300 is used to fuse the predicted trajectory, the uncertainty of the predicted trajectory, and the networked trajectory in at least one initial collaborative target to obtain the final predicted trajectory of at least one initial collaborative target.

[0084] The control module 400 is used to determine at least one potential cooperative target based on the final predicted trajectory and at least one initial cooperative target, and to calculate the following vehicle impact value corresponding to different potential cooperative targets based on the at least one potential cooperative target, so as to determine the final cooperative target according to the following vehicle impact value, and to generate a first planned trajectory of the final cooperative target and a second planned trajectory of the current vehicle according to the cooperative request, so as to control the passage of the final cooperative target according to the first planned trajectory and control the passage of the current vehicle according to the second planned trajectory.

[0085] Optionally, in one embodiment of this application, the generation module 200 includes: an identification unit, an acquisition unit, and a first generation unit.

[0086] The identification unit is used to identify the source of the status information.

[0087] The acquisition unit is used to acquire the collection time of status information.

[0088] The first generation unit is used to generate a historical time-series information aggregation representation based on the information source, collection time, and status information.

[0089] Optionally, in one embodiment of this application, the generation module 200 includes: a first determining unit, a first calculating unit, a second calculating unit, and a second generating unit.

[0090] The first determining unit is used to determine the aggregated representation of the neighboring historical time series information of different initial collaboration targets based on at least one initial collaboration target.

[0091] The first computing unit is used to calculate, based on the aggregated representation of neighboring historical time-series information and the aggregated representation of historical time-series information, the first interactive coding feature of neighboring initial cooperative targets and corresponding initial cooperative targets under the same information source condition and the second interactive coding feature under different information source conditions.

[0092] The second computing unit is used to calculate the third interactive coding features of at least one initial collaborative target under different information source conditions based on the aggregated representation of historical time-series information.

[0093] The second generation unit is used to generate a predicted trajectory and the uncertainty of the predicted trajectory using the target Transformer network based on historical time series information aggregation representation, neighboring historical time series information aggregation representation, first interactive coding feature, second interactive coding feature and third interactive coding feature.

[0094] Optionally, in one embodiment of this application, the fusion module 300 includes: a second determining unit and a third generating unit.

[0095] The second determining unit is used to determine the first weight of the predicted trajectory and the second weight of the network trajectory based on the uncertainty of the predicted trajectory.

[0096] The third generation unit is used to fuse the first weight, the second weight, the predicted trajectory, and the network trajectory to obtain the final predicted trajectory.

[0097] Optionally, in one embodiment of this application, the formula for calculating the final predicted trajectory may be, but is not limited to, the following: , in, Indicates the initial collaboration goal The final predicted trajectory; Indicates the initial collaboration goal The predicted trajectory; Navigation information indicating the target of the network connection; Represents the fusion weights for the predicted trajectory; This represents the fusion weight of the connected trajectory.

[0098] Optionally, in one embodiment of this application, the formula for calculating the impact value of the following vehicle may be, but is not limited to, the following: , in, Indicate potential collaborative goals The quantitative impact on following vehicles; Indicate potential collaborative goals rear The first goal and the first The relative positions of the targets; Indicate potential collaborative goals rear The first goal and the first The relative speed of the targets; Indicate potential collaborative goals The final position after executing the collaborative trajectory; Indicate potential collaborative goals The final velocity after executing the collaborative trajectory; Indicate potential collaborative goals The number of targets existing within a certain range behind; This indicates the function that affects the calculation.

[0099] Optionally, in one embodiment of this application, the calculation formula for the aggregation and representation of historical time-series information may be, but is not limited to, the following: , in, Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates information source exist Initial collaborative goal for real-time data collection Status information; This indicates the length of the historical information sequence stored at the edge cloud. This represents the Transformer network.

[0100] Optionally, in one embodiment of this application, the expression of the first interactive coding feature may be, but is not limited to,: , The expression for the second interactive coding feature can be, but is not limited to, as follows: , The expression for the third interactive coding feature can be, but is not limited to, as follows: , in, Represents the interactive coding feature, where, Indicates the first interactive coding feature; This represents the second interactive coding feature; Indicates the third interactive coding feature; and Indicates different sources of information; and Indicate different initial collaboration goals; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; This represents a multilayer perceptron.

[0101] It should be noted that the foregoing explanation of the control method embodiment for cooperative vehicle passage also applies to the control device for cooperative vehicle passage in this embodiment, and will not be repeated here.

[0102] The vehicle cooperative passage control device proposed in this application can respond to the current vehicle's cooperative request and obtain an initial cooperative target that meets the cooperative request conditions. Then, based on the state information of the initial cooperative target, it generates a corresponding historical time-series information aggregation representation to generate a predicted trajectory and uncertainty corresponding to the initial cooperative target. Finally, it uses the network trajectory to determine the final predicted trajectory to obtain potential cooperative targets, and determines the final cooperative target based on the impact value of following vehicles. This yields the final cooperative target and the planned trajectory of the current vehicle, thereby controlling the corresponding vehicle passage. It effectively utilizes the advantages of the vehicle-road-cloud integrated system, integrates information from different sources to achieve interactive trajectory prediction, establishes behavior prediction for numerous traffic participants in complex environments, and fully considers road traffic efficiency over a wide area, assessing the impact of cooperative behavior on vehicles in subsequent road segments. This allows for the selection of more efficient cooperative vehicles and the planning of more efficient cooperative trajectories. Therefore, it solves the problems in related technologies, such as the limited scope of vehicle-to-vehicle communication cooperation leading to a single applicable scenario, the difficulty in obtaining global traffic participant information through information transmission between cooperative vehicles alone, the inability to accurately recognize complex scenarios, and the low efficiency of cooperative behavior.

[0103] Figure 6 This is a schematic diagram of the structure of a vehicle according to an embodiment of this application. The vehicle may include: The memory 601, the processor 602, and the computer program stored on the memory 601 and capable of running on the processor 602.

[0104] When the processor 602 executes the program, it implements the vehicle cooperative passage control method provided in the above embodiments.

[0105] Furthermore, the vehicle also includes: Communication interface 603 is used for communication between memory 601 and processor 602.

[0106] The memory 601 is used to store computer programs that can run on the processor 602.

[0107] The memory 601 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0108] If the memory 601, processor 602, and communication interface 603 are implemented independently, then the communication interface 603, memory 601, and processor 602 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 6 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0109] Optionally, in a specific implementation, if the memory 601, processor 602, and communication interface 603 are integrated on a single chip, then the memory 601, processor 602, and communication interface 603 can communicate with each other through an internal interface.

[0110] The processor 602 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0111] This application also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described vehicle cooperative passage control method.

[0112] This application also provides a computer program product, including a computer program that, when executed, implements the above-described vehicle cooperative passage control method.

[0113] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0114] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0115] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0116] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). In addition, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically by optically scanning paper or other media, then editing, interpreting or otherwise processing them as necessary, and then storing them in computer memory.

[0117] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0118] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0119] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0120] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A control method for cooperative vehicle passage, characterized in that, Includes the following steps: In response to the current vehicle's cooperation request, obtain at least one initial cooperation target that meets the conditions of the cooperation request; The state information of the at least one initial collaborative target is obtained, and the historical time series information aggregation representation of the corresponding initial collaborative target is obtained based on the state information, so as to generate the predicted trajectory of the at least one initial collaborative target and the uncertainty of the predicted trajectory using the historical time series information aggregation representation; By integrating the predicted trajectory, the uncertainty of the predicted trajectory, and the networked trajectory in the at least one initial cooperative target, the final predicted trajectory of the at least one initial cooperative target is obtained; Based on the final predicted trajectory and the at least one initial cooperative target, at least one potential cooperative target is determined, and based on the at least one potential cooperative target, the following vehicle impact value corresponding to different potential cooperative targets is calculated, so as to determine the final cooperative target according to the following vehicle impact value, and generate a first planned trajectory of the final cooperative target and a second planned trajectory of the current vehicle according to the cooperative request, so as to control the passage of the final cooperative target according to the first planned trajectory and control the passage of the current vehicle according to the second planned trajectory.

2. The method according to claim 1, characterized in that, The step of obtaining the historical time-series information aggregation representation of the corresponding initial cooperative target based on the state information includes: Identify the source of the status information; The acquisition time of the status information; Based on the information source, the collection time, and the status information, the historical time-series information aggregation representation is generated.

3. The method according to claim 1, characterized in that, The aggregation and characterization of the historical time-series information to generate the predicted trajectory of the at least one initial cooperative target and the uncertainty of the predicted trajectory include: Based on the at least one initial cooperation goal, determine the aggregated representation of the neighboring historical time series information of different initial cooperation goals; Based on the aggregated representation of the neighboring historical time series information and the aggregated representation of the historical time series information, calculate the first interactive coding feature of the neighboring initial cooperative target and the corresponding initial cooperative target under the same information source condition and the second interactive coding feature under different information source conditions; Based on the historical time-series information aggregation representation, the third interaction coding features of the at least one initial collaborative target under different information source conditions are calculated; Based on the historical time series information aggregation representation, the neighboring historical time series information aggregation representation, the first interactive coding feature, the second interactive coding feature, and the third interactive coding feature, the target Transformer network is used to generate the predicted trajectory and the uncertainty of the predicted trajectory.

4. The method according to claim 1, characterized in that, The process of fusing the predicted trajectory, the uncertainty of the predicted trajectory, and the networked trajectory in the at least one initial cooperative target to obtain the final predicted trajectory of the at least one initial cooperative target includes: Based on the uncertainty of the predicted trajectory, a first weight of the predicted trajectory and a second weight of the networked trajectory are determined; The final predicted trajectory is obtained by fusing the first weight, the second weight, the predicted trajectory, and the network trajectory.

5. The method according to claim 1, characterized in that, The calculation formula for the aggregation and representation of historical time-series information is as follows: ， in, Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates information source exist Initial collaborative goal for real-time data collection Status information; This indicates the length of the historical information sequence stored at the edge cloud. This represents the Transformer network.

6. The method according to claim 3, characterized in that, in, The expression for the first interactive coding feature is: ， The expression for the second interactive coding feature is: ， The expression for the third interactive coding feature is: ， in, Represents the interactive coding feature, where, Indicates the first interactive coding feature; This represents the second interactive coding feature; Indicates the third interactive coding feature; and Indicates different sources of information; and Indicate different initial collaboration goals; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates information source exist Initial collaborative goal for real-time data collection Status information; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; Indicates source of information Initial collaboration goals Historical time-series information aggregation representation; This represents a multilayer perceptron.

7. The method according to claim 1, characterized in that, The formula for calculating the final predicted trajectory is: ， in, Indicates the initial collaboration goal The final predicted trajectory; Indicates the initial collaboration goal The predicted trajectory; Navigation information indicating the target of the network connection; Represents the fusion weights for the predicted trajectory; This represents the fusion weight of the connected trajectory.

8. The method according to claim 1, characterized in that, The formula for calculating the impact value of the following vehicle is: ， in, Indicate potential collaborative goals The quantitative impact on following vehicles; Indicate potential collaborative goals rear The first goal and the first The relative positions of the targets; Indicate potential collaborative goals rear The first goal and the first The relative speed of the targets; Indicate potential collaborative goals The final position after executing the collaborative trajectory; Indicate potential collaborative goals The final velocity after executing the collaborative trajectory; Indicate potential collaborative goals The number of targets existing within a certain range behind; This indicates the function that affects the calculation.

Images