Vehicle assisted driving method, system, service platform and vehicle

Abstract

The application discloses a vehicle auxiliary driving method, system, service platform and vehicle, and is applied to an intelligent driving vehicle. The method comprises the following steps: when a first vehicle performs a self-driving task and the first vehicle is in a networking state with at least one second vehicle, the computing power resources of the second vehicle are configured to perform at least part of the driving task of the first vehicle, wherein the driving task of the first vehicle is determined by at least the perception data of the first vehicle and / or the perception data of the second vehicle. According to the method provided by the application, the idle computing power resources of the second vehicle are reasonably allocated to assist in performing at least part of the driving task of the first vehicle, the computing power resource allocation effect of the vehicles in the network is improved, and the vehicle driving performance and intelligent driving cooperation stability of the vehicles in the group are effectively improved.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, specifically to a vehicle-assisted driving method, system, service platform, and vehicle. Background Technology

[0002] With the development of intelligent driving technology for vehicles, collaborative intelligent driving can realize functions such as multi-vehicle platooning, queue maintenance, and collaborative lane changing.

[0003] However, vehicles currently have a large number of sensors and need to process a large amount of data in real time. Increasing computing resources would increase vehicle costs. Therefore, it is necessary to consider how to allocate data processing to avoid affecting vehicle performance due to poor allocation of computing resources. Summary of the Invention

[0004] This application provides a vehicle-assisted driving method, system, service platform, and vehicle, aiming to solve the problems of lag and delay in intelligent driving groups caused by insufficient vehicle computing power in related technologies.

[0005] In a first aspect, this application provides a vehicle-assisted driving method, applied to a first vehicle, comprising: When the first vehicle is performing its own driving task and the first vehicle is in a network state with at least one second vehicle, the computing resources of the second vehicle are configured to perform at least part of the driving task of the first vehicle. The driving task of the first vehicle is determined at least by the perception data of the first vehicle and / or the perception data of the second vehicle; The driving task is determined by at least the perception data of the first vehicle and / or the perception data of the second vehicle, including: When the perception performance of the first vehicle is less than that of the second vehicle, the driving task is determined at least through the perception data of the second vehicle; and / or When the perception performance of the first vehicle is greater than or equal to that of the second vehicle, the driving task is determined at least by the perception data of the first vehicle and the target perception data of the second vehicle for the target area, wherein the target area includes the perception blind spot of the first vehicle.

[0006] In one embodiment of this application, the method includes: When the first vehicle is performing its own driving task, if the computing power resource status of the first vehicle indicates that the first vehicle is in a computing power overload state, at least a portion of the driving task is configured to be performed by the second vehicle, and the at least a portion of the driving task is configured to be performed using the computing power resources of the second vehicle.

[0007] In one embodiment of this application, the computing power resource status includes available computing power resources and / or computing power load, and the computing power resource status of the first vehicle indicates that the first vehicle is in a computing power overload state, including at least one of the following situations: The available computing power resources of the first vehicle do not meet the computing power load required for the driving task of the first vehicle; The computing load of the first vehicle is greater than the preset computing load threshold.

[0008] In one embodiment of this application, the method further includes: When the computing power resource status of the first vehicle indicates that the first vehicle is not in a state of computing power overload, the first vehicle and the second vehicle maintain a network state, and the driving task of the first vehicle is executed by the computing power resources of the first vehicle.

[0009] In one embodiment of this application, the driving task of the first vehicle is further determined in the following manner: Configured to perform the task of the first vehicle as determined by user instructions.

[0010] In one embodiment of this application, the method further includes: When the first vehicle and the second vehicle are in intelligent driving mode, and the distance between the first vehicle and the second vehicle is less than a first distance threshold and / or they are on the same road, near-field communication networking is performed between the first vehicle and the second vehicle through the first communication device of the first vehicle; When the first vehicle and the second vehicle are in intelligent driving mode, and the distance between the first vehicle and the second vehicle is greater than or equal to a first distance threshold and / or they are not on the same road, the first vehicle communicates remotely with the network platform through its second communication device to form a remote communication network with the second vehicle.

[0011] In one embodiment of this application, the method further includes: When the first vehicle and the second vehicle are in a near-field communication network, service resources are allocated to the first vehicle and the second vehicle according to their service needs and / or vehicle types. or, When the first vehicle and the second vehicle are in a remote communication network, if the first vehicle has a service demand, a planned route from the starting position of the first vehicle to the destination position of the service resource is generated based on the cross-road condition information provided by the second vehicle. The service requirements include parking and / or charging requirements, and the service resources include parking spaces and / or charging devices.

[0012] In one embodiment of this application, the step of planning and generating a planned route from the starting position of the first vehicle to the destination position of the service resource using cross-segment road condition information provided by the second vehicle includes: The road condition data of the first vehicle is updated using the cross-road condition information provided by the second vehicle. Based on the updated traffic data, a planned route is generated from the starting position of the first vehicle to the destination position of the service resource.

[0013] In one embodiment of this application, in a driving scenario where the first vehicle and the second vehicle are in a near-field communication network, the method further includes: If there is a first target object that needs to be avoided in the driving scenario, then control the first vehicle and the second vehicle to follow the vehicle in front of the network to avoid the first target object; If there is a second target object requiring emergency braking in the driving scenario, then each vehicle in the network is controlled to perform emergency braking at the corresponding emergency braking level. The emergency braking level of different vehicles is related to the driving order of the vehicles in the network and / or the distance to the preceding vehicle in the network.

[0014] In one embodiment of this application, the second vehicle includes multiple vehicles, and the method further includes: The driving task of the first vehicle is performed by utilizing the computing resources of the target second vehicle in the second vehicle. The target second vehicle is obtained at least by sorting the computing power status of the second vehicle.

[0015] In one embodiment of this application, during the process of configuring the computing resources of the second vehicle to execute at least part of the driving task of the first vehicle, if the computing resource status of the second vehicle indicates that the second vehicle is in a computing overload state, then at least part of the driving task of the first vehicle is configured to be executed by the computing resources of the third vehicle, wherein the third vehicle is in a network state with the first vehicle and the at least one second vehicle.

[0016] Secondly, this application provides a vehicle-assisted driving method, applied to a second vehicle, comprising: Upon receiving a computing power request from a first vehicle that is networked with the second vehicle, the driving task of the first vehicle is executed based on the computing power resources of the second vehicle, wherein the driving task is also executed by the computing power resources of the first vehicle. The driving task of the first vehicle is determined at least by the perception data of the first vehicle and / or the perception data of the second vehicle; The driving task is determined by at least the perception data of the first vehicle and / or the perception data of the second vehicle, including: When the perception performance of the first vehicle is less than that of the second vehicle, the driving task is determined at least through the perception data of the second vehicle; and / or When the perception performance of the first vehicle is greater than or equal to that of the second vehicle, the driving task is determined at least by the perception data of the first vehicle and the target perception data of the second vehicle for the target area, wherein the target area includes the perception blind spot of the first vehicle.

[0017] Thirdly, this application provides a vehicle-assisted driving system configured to be obtained through a communication network of multiple vehicles, wherein any vehicle in the communication network is configured to implement assisted driving of the vehicle through the vehicle-assisted driving method described in any of the preceding claims.

[0018] Fourthly, this application provides a service platform configured to remotely communicate with at least two vehicles to achieve vehicle networking, wherein the service platform is configured to receive vehicle information from at least one vehicle to execute the vehicle assisted driving method as described in any of the preceding claims.

[0019] Fifthly, this application provides a vehicle that performs the vehicle assisted driving method as described in any of the preceding claims.

[0020] The vehicle-assisted driving method provided in this application, when a first vehicle is performing its own driving task and is in a network state with at least one second vehicle, utilizes the computing resources of the second vehicles to perform at least part of the first vehicle's driving task. The driving task of the first vehicle is determined at least by the perception data of the first vehicle and / or the perception data of the second vehicles. By using the method provided in this application, when the first vehicle is performing its own driving task and is in a network state with at least one second vehicle, the idle computing resources of the second vehicles can be reasonably utilized to assist in performing at least part of the first vehicle's driving task, improving the allocation of computing resources among vehicles in the network and effectively enhancing the vehicle driving performance and intelligent driving cooperation stability within the group. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This application provides a schematic flowchart of a vehicle assisted driving method according to an embodiment of the present application. Figure 2 This application provides a schematic flowchart illustrating the steps for forming a vehicle intelligent driving group and allocating computing power in an embodiment of the present application. Figure 3 A flowchart illustrating the steps for coordinated yielding to emergency vehicles provided in this application embodiment; Figure 4 A flowchart illustrating the steps of intelligent driving group collaboration from parking space to parking space, provided in an embodiment of this application; Figure 5 A flowchart illustrating the steps of collaborative intelligent driving under cross-road segment intelligent driving group data sharing provided in this application embodiment; Figure 6 This is a schematic diagram of the architecture of an intelligent driving cooperative system for implementing the vehicle assisted driving method provided in an embodiment of this application; Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] The use of "applies to" or "configured to" in this application implies open and inclusive language, which does not exclude the applicability to or configuration to devices performing additional tasks or steps. Additionally, the use of "based on" implies openness and inclusivity, because processes, steps, calculations, or other actions "based on" one or more of the stated conditions or values ​​may in practice be based on additional conditions or values ​​beyond those stated.

[0025] In this application, the term "exemplary" is used to mean "serving as an example, illustration, or description." Any embodiment described as "exemplary" in this application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is provided to enable any person skilled in the art to make and use this application. Details are set forth in the following description for purposes of explanation. It should be understood that those skilled in the art will recognize that this application can be made without using these specific details. In other instances, well-known structures and processes are not described in detail to avoid obscuring the description of this application with unnecessary detail. Therefore, this application is not intended to be limited to the embodiments shown, but is consistent with the broadest scope of the principles and features disclosed in this application.

[0026] To clearly understand the vehicle-assisted driving method provided in this application embodiment, the relevant application scenarios of the vehicle-assisted driving method will be specifically described below. Specifically, the vehicle-assisted driving method provided in this application is generally used to realize intelligent driving of vehicles. Intelligent driving refers to automatically making decisions and controlling the behavior of the vehicle during driving, such as braking, acceleration, or steering, based on artificial intelligence or other intelligent methods, under safe driving conditions. In particular, with the development of vehicle intelligent driving technology, "parking space to parking space" end-to-end intelligent driving has become an important development direction, aiming to provide users with a seamless assisted driving experience from any starting parking space to any ending parking space, truly achieving a seamless connection of "use it as soon as you get in the car, and leave as soon as you get out of the car." In this process, in order to further improve the intelligent driving effect of vehicles, related technologies have proposed cooperative intelligent driving, that is, intelligent driving under multi-vehicle cooperation, realizing functions such as multi-vehicle platooning, queue maintenance, and cooperative lane changing.

[0027] However, vehicles currently have a large number of sensors, especially when they are networked, requiring real-time processing of large amounts of data. Increasing computing resources would lead to higher vehicle costs. Therefore, it is necessary to consider how to allocate data processing resources for intelligent driving tasks within the network to avoid affecting vehicle performance and the user's intelligent driving experience due to poor allocation of computing resources.

[0028] To address the aforementioned technical issues, this application provides a vehicle-assisted driving method. The method involves a first vehicle performing its own driving task while the first vehicle is networked with at least one second vehicle. The first vehicle utilizes the computing resources of the second vehicle to perform at least a portion of its driving task, effectively utilizing the idle computing resources of vehicles within the network to assist in the execution of the driving task. This avoids overloading the computing power of a single vehicle, ensures the overall computing efficiency of the intelligent driving collaboration system, and effectively improves the stability of intelligent driving collaboration within the group. For ease of understanding, specific embodiments will be described below.

[0029] Please see Figure 1 , Figure 1 This application provides a schematic flowchart of a vehicle assisted driving method, specifically including step S110: S110, when the first vehicle is performing its own driving task and the first vehicle is in a network state with at least one second vehicle, the computing resources of the second vehicle are configured to perform at least part of the driving task of the first vehicle.

[0030] In one embodiment of this application, the first vehicle can generally be understood as the main vehicle that performs the vehicle assisted driving method, i.e., the vehicle itself, while the second vehicle is generally another vehicle besides the main vehicle.

[0031] Specifically, in one embodiment of this application, the first vehicle performs its own driving task and is in a network state with at least one second vehicle. Typically, the first vehicle, with its intelligent driving (assisted driving) function activated, broadcasts a group request for intelligent driving collaboration, or receives a group request broadcast by a second vehicle. After the group request is approved, the first vehicle joins the corresponding intelligent driving collaboration group. Communication and interaction, including vehicle driving status data and surrounding environment data, are achieved through the communication modules of the first and second vehicles, particularly low-latency communication modules, such as V2X (Vehicle-to-Everything) or 5G-A (5G-Advanced). Of course, in addition to the above methods, the first vehicle can also join an intelligent driving collaboration group containing other specific preset vehicles to obtain more information; this embodiment of the application does not limit this. Specifically, to facilitate understanding of the above content, the following will describe it in conjunction with specific embodiments.

[0032] In one embodiment of this application, the method includes: When the first vehicle and the second vehicle are in intelligent driving mode, and the distance between the first vehicle and the second vehicle is less than a first distance threshold and / or they are on the same road, near-field communication networking is established between the first vehicle and the second vehicle through the first communication device of the first vehicle.

[0033] In one embodiment of this application, when the first vehicle has its intelligent driving function activated, i.e., is in intelligent driving mode, it can further broadcast an intelligent driving collaboration request from the first vehicle as needed, such as detecting whether the user has activated the intelligent driving collaboration command. Specifically, the intelligent driving collaboration request typically includes core information about the first vehicle. For example, in some possible implementations, the intelligent driving collaboration request may typically include sensor configuration (e.g., whether it is equipped with LiDAR), computing power parameters, current location, and destination. Of course, based on actual needs, the intelligent driving collaboration request may also include more information. For example, for new energy vehicles, it may also include remaining battery power and whether it is compatible with flash charging technology, thereby comprehensively providing the basic data required for group formation and subsequent collaboration, ensuring the accuracy of networking and collaboration. Of course, in another possible implementation, the first vehicle may also receive an intelligent driving collaboration request broadcast from the second vehicle and display it on the in-vehicle terminal (such as an in-vehicle host), for example, displaying a prompt message such as "Vehicle with license plate number XX (XXX meters away from you) invites you to join the intelligent driving collaboration group." Based on this, after the intelligent driving collaboration request is verified, if the distance between the first vehicle and the second vehicle is less than a first distance threshold and / or they are on the same road, the first vehicle will be controlled to join the corresponding intelligent driving group on the same road segment. That is, the first vehicle and the second vehicle will form a near-field communication network through the first vehicle's first communication device. Specifically, in one possible implementation, the first distance threshold can be 100 meters, that is, to achieve automatic configuration of intelligent driving collaboration within 100 meters and the formation of intelligent driving groups on the same road segment.

[0034] Alternatively, in another possible implementation, the first vehicle can also be configured to join a cross-road segment intelligent driving group, thereby balancing the convenience of same-road segment collaboration with the flexibility of cross-road segment collaboration. For example, in another possible implementation, the method further includes: When the first vehicle and the second vehicle are in intelligent driving mode, and the distance between the first vehicle and the second vehicle is greater than or equal to a first distance threshold and / or they are not on the same road, the first vehicle communicates remotely with the network platform through its second communication device to form a remote communication network with the second vehicle.

[0035] Specifically, when the first vehicle and the second vehicle are in intelligent driving mode, and the distance between the first vehicle and the second vehicle is greater than or equal to a first distance threshold and / or they are not on the same road, remote communication can be achieved between the first vehicle and the network platform through the second communication device of the first vehicle, with the network platform acting as an intermediary to realize remote communication networking with the second vehicle.

[0036] Specifically, to improve the effectiveness of remote communication networking, the first and second vehicles can be vehicles that meet preset conditions. For example, typically, the first and second vehicles can be vehicles from a company / organization's internal vehicle group. Of course, for the first vehicle, the user can customize the second vehicle that can join the remote communication network according to actual needs, and this application embodiment does not impose such limitations. Based on this, when the first and second vehicles form a cross-road segment intelligent driving collaborative group through remote communication networking, corresponding cross-road segment feature information can also be configured. Typically, cross-road segment feature information can include real-time road conditions (construction, congestion, severe weather, etc.), sensor detection data, parking lot space occupancy / vacancy status, and its own intelligent driving strategy parameters, thereby enabling various configurations for the first vehicle, including route planning. The specific implementation scheme will be described in subsequent related embodiments.

[0037] When the first vehicle is performing its own driving task and is in a network state with at least one second vehicle, the computing resources of the second vehicle are configured to perform at least part of the driving task of the first vehicle. That is, the driving task of the first vehicle is partly performed by itself and partly performed by the second vehicle.

[0038] Furthermore, in some embodiments of this application, these driving tasks can generally be understood as maintaining the intelligent driving collaborative state between the first vehicle and the second vehicle to cope with various data processing tasks required for different intelligent driving scenarios. For example, in one possible implementation, the driving task may include data processing tasks such as environmental analysis and path planning. Of course, based on actual needs, the driving task may also include the calculation of control commands for each vehicle. For example, in one possible implementation, the driving task of the first vehicle is determined by at least one of the following methods: It is determined at least by the perception data of the first vehicle and / or the perception data of the second vehicle.

[0039] The tasks determined by at least the perception data of the first vehicle and / or the perception data of the second vehicle typically include data processing tasks for intelligent driving, such as environmental analysis and path planning. Of course, in addition to the driving tasks mentioned above, driving tasks may include more, and this application embodiment does not impose any limitations on this.

[0040] Specifically, in one embodiment of this application, the sensor data complementarity among the aforementioned vehicles can be determined based on the perception performance of each vehicle. For example, in one possible implementation, for high-spec vehicles (with strong perception performance), their environmental perception data can compensate for the detection accuracy shortcomings of low-spec vehicles, while for low-spec vehicles (with relatively weaker perception performance), priority is given to supplementing the perception blind spots of high-spec vehicles, thereby improving the overall perception capability of the group. That is, in one embodiment of this application, when the perception performance of the first vehicle is greater than that of the target vehicle in the at least one second vehicle, the driving task will be determined by the perception data of the first vehicle and the target perception data of the second vehicle regarding the perception blind spot of the first vehicle. That is, the driving task is determined by at least the perception data of the first vehicle and / or the perception data of the second vehicle, including: When the perception performance of the first vehicle is greater than or equal to that of the second vehicle, the driving task is determined at least by the perception data of the first vehicle and the target perception data of the second vehicle for the target area, wherein the target area includes the perception blind spot of the first vehicle.

[0041] Alternatively, in another possible implementation, if the perception performance of the first vehicle is less than or equal to the perception performance of the target vehicle among at least one of the second vehicles, the driving task is determined using the perception data of the second vehicle to ensure the decision-making effectiveness of the intelligent driving task. That is, the driving task is determined by at least the perception data of the first vehicle and / or the perception data of the second vehicle, including: If the perception performance of the first vehicle is less than that of the second vehicle, the driving task is determined at least by the perception data of the second vehicle.

[0042] Furthermore, in some possible implementations, the driving task of the first vehicle can also be determined in the following way: Configured to perform the task of the first vehicle as determined by user instructions; The configuration refers to the tasks to be executed as determined by user commands, which typically include operations on in-vehicle applications installed on the vehicle's infotainment system, such as playing music or opening other applications.

[0043] Specifically, to improve the allocation of computing resources, typically, when the computing resource status of the first vehicle indicates that the first vehicle is in a state of computing overload, at least some driving tasks are assigned to the second vehicle for execution. That is, in one embodiment of this application, the method includes: When the first vehicle is performing its own driving task, if the computing power resource status of the first vehicle indicates that the first vehicle is in a computing power overload state, at least a portion of the driving task is configured to be performed by the second vehicle, and the at least a portion of the driving task is configured to be performed using the computing power resources of the second vehicle.

[0044] The computing power resource status of the first vehicle indicates whether it is in a state of computing power overload, which can usually be determined through various information. For example, in one possible implementation, the computing power resource status includes available computing power resources, that is, the computing power resources remaining after deducting the full amount of computing power resources configured for the vehicle from the computing power resources that have been occupied. In this case, it can be determined whether the available computing power resources can meet the computing power load required for the driving task of the first vehicle. For example, if the available computing power resources are less than the computing power load required for the driving task of the first vehicle, it can be considered that the first vehicle is currently in a state of computing power overload, and at least some of the driving tasks can be assigned to the second vehicle for execution.

[0045] Alternatively, in another embodiment, the computing power resource status may also include computing power load, that is, the percentage of currently occupied computing power resources relative to the total computing power resources. Typically, to meet the redundancy requirements of vehicle computing, the load percentage should be lower than a certain preset computing power load threshold. Therefore, it can be determined whether the vehicle is in a computing power overload state by whether the computing power load of the first vehicle is less than the preset computing power load threshold. For example, in one possible implementation, the computing power load threshold can be 80%. In this case, if the computing power load of the first vehicle exceeds 80%, it can be considered that the first vehicle is in a computing power overload state. Of course, based on actual needs, the computing power load threshold can also be configured to other values, and this application embodiment does not limit this.

[0046] Based on the above, if the computing power resource status of the first vehicle indicates that the first vehicle is not in a computing power overload state, the first vehicle and the second vehicle will continue to maintain a network state, and the driving task of the first vehicle will be configured to be executed by the computing power resources of the first vehicle. During the execution of its own driving task, the first vehicle will continuously monitor its own computing power resource status to determine whether it is in a computing power overload state.

[0047] In one embodiment of this application, where the second vehicle comprises multiple vehicles, configuring at least a portion of the driving task to be executed by the second vehicle can typically be achieved by evaluating the computing resource status of the second vehicle and selecting the second vehicle with the better computing resource status. That is, in one possible implementation, the method includes: The driving task of the first vehicle is performed by utilizing the computing resources of the target second vehicle in the second vehicle. The target second vehicle is obtained at least by sorting the computing power status of the second vehicle.

[0048] For example, the second vehicle with low computing load and high available computing resources should be selected first.

[0049] Furthermore, when the second vehicle is performing the driving task of the first vehicle, if the second vehicle is in a state of computing power overload due to increased workload or other factors, the second vehicle can, with authorization from the first vehicle, be configured to configure at least a portion of the first vehicle's driving task to be executed using the computing power resources of a third vehicle within the network. This could be achieved by forwarding the driving task through the second vehicle, or by the second vehicle notifying the first vehicle, which then forwards the driving task. That is, in one embodiment of this application, the method further includes: During the process of the second vehicle's computing resources being configured to execute at least part of the driving task of the first vehicle, if the computing resource status of the second vehicle indicates that the second vehicle is in a computing overload state, then at least part of the driving task of the first vehicle is configured to be executed by the computing resources of a third vehicle, wherein the third vehicle is in a network state with the first vehicle and the at least one second vehicle.

[0050] It should be noted that the underlying data transmission for configuring driving tasks for the second vehicle, allowing it to perform driving tasks using its computing resources, can rely on the aforementioned near-field communication or remote communication methods. For example, the first and second vehicles can exchange collaborative information, including but not limited to computing load and intelligent driving tasks, to achieve dynamic allocation of computing resources. Specifically, this will be explained below with reference to embodiments.

[0051] In one embodiment of this application, when the first vehicle is performing its own driving task and the first vehicle is in a network state with at least one second vehicle, the cooperation information of at least one second vehicle is determined; based on the computing power load state of the first vehicle and the cooperation information, the driving task configured to be processed by the first vehicle is determined.

[0052] Specifically, based on the computing power load status and collaboration information of the first vehicle, the driving tasks configured for processing by the first vehicle are determined, including: Based on the computing power load status of each vehicle and the driving task of each vehicle, the driving tasks that each vehicle needs to handle are determined.

[0053] For example, for vehicles that are in a state of computing overload or are about to be in a state of computing overload, the number of driving tasks or computing power requirements that they need to handle can usually be reduced. For vehicles that are not in a state of computing overload, such as vehicles with lower computing power load, more driving tasks can usually be configured for them, such as cooperating with other vehicles to complete the processing of driving tasks.

[0054] Furthermore, in one possible implementation, the collaborative information may include collaborative computing load, which is used to characterize the computing load status of the second vehicle.

[0055] At this time, based on the computing power load status of the first vehicle and the collaborative information, a driving task configured to be processed by the first vehicle is determined, including: Based on the computing power load status of the first vehicle and the collaborative computing power load of the at least one second vehicle, the target intelligent driving task configured to be processed by the first vehicle is determined.

[0056] Specifically, in one embodiment of this application, based on the collaborative computing power load received by the first vehicle from the second vehicle, the first vehicle will compare its own computing power load status with the collaborative computing power load to select and calculate a driving task that matches its own computing power load. In particular, the target intelligent driving task typically includes data processing tasks related to the intelligent driving control of the first vehicle, such as calculating the control commands of the first vehicle, like driving direction and / or speed; that is, the first vehicle's computing power prioritizes the calculation of its intelligent driving control parameters. Furthermore, if the computing power load of the first vehicle is higher than that of the second vehicle, less important intelligent driving tasks, such as environmental analysis, are prioritized for calculation by the second vehicle; if the computing power load of the first vehicle is lower than that of the second vehicle, the intelligent driving data processing tasks requiring collaborative calculation provided by the second vehicle are processed.

[0057] In addition, in another possible implementation, the collaborative information may also include collaborative intelligent driving tasks, that is, various data processing tasks provided by the second vehicle that require collaborative calculation to maintain the intelligent driving collaborative state in order to cope with various intelligent driving scenarios. For example, it may typically include control commands of the second vehicle, such as the calculation of driving direction and / or speed. Of course, it may also include other related data processing tasks, which will not be elaborated in this application embodiment.

[0058] Of course, the collaborative information provided above is only an example of collaborative computing load and collaborative intelligent driving tasks, aiming to combine the computing load of the first vehicle to more appropriately determine the target intelligent driving task that needs to be processed by the first vehicle. Naturally, collaborative information can also include other information designed to achieve more effective processing of intelligent driving tasks.

[0059] For example, in one embodiment of this application, the collaborative information may also include collaborative perception data. Specifically, this collaborative perception data can be obtained through sensors deployed on the second vehicle, thereby enabling collaborative perception data between different vehicle models, such as the fusion of various driving environment point clouds or driving environment images, to obtain more accurate driving environment information, thereby assisting the vehicle's intelligent driving system in making decisions.

[0060] For a clearer understanding of the above, please refer to [link / reference]. Figure 2 Specifically, including: Step 201: Vehicles with intelligent driving capabilities activate intelligent driving and low-latency communication to broadcast their core information (sensors, computing power, location, etc.).

[0061] Specifically, in this embodiment, a vehicle with parking space-to-parking space intelligent driving capability will broadcast its core information to the surrounding area in real time after activating its intelligent driving system and low-latency communication module (such as V2X or 5G-A). This information includes sensor configuration (whether it is equipped with LiDAR), computing power parameters, current location, destination, remaining battery power, and whether it is compatible with flash charging technology. This provides comprehensive basic data required for group formation and subsequent collaboration, ensuring the accuracy of networking and collaboration.

[0062] Step 202: The system detects the distance between vehicles. If the distance is ≤100 meters, the system automatically forms a group for the same road segment. If the distance is >100 meters and the vehicle belongs to a preset group, the vehicle is added to a cross-road segment group.

[0063] Specifically, in this embodiment, the system detects the communication signals and distances of surrounding vehicles in real time and establishes flexible networking rules. When the distance between vehicles is ≤100 meters, communication pairing can be completed automatically and a smart driving group for the same road segment can be formed. When the distance between vehicles is >100 meters, but belongs to a preset group (such as an internal vehicle group of a company or organization), it can automatically join the corresponding cross-road segment smart driving group, taking into account both the convenience of collaboration within the same road segment and the flexibility of collaboration across road segments.

[0064] Step 203: After the group is formed, computing power is dynamically allocated according to the computing power load of each vehicle. Vehicles with high load are assisted in computing by other vehicles.

[0065] Specifically, in one embodiment of this application, after the formation of a road segment intelligent driving group or a cross-road segment intelligent driving group, each vehicle automatically uploads its own computing power parameters and current computing power load status. The system can quickly detect and analyze the load of each vehicle and execute dynamic computing power allocation tasks. If a vehicle faces complex road conditions such as narrow garages or dense traffic flow and needs to perform a large amount of high-intensity calculations such as environmental analysis and path planning, other vehicles automatically mobilize some of their processor computing power to assist it in completing the calculations, while the vehicle itself switches to a low computing power mode, maintaining only basic perception and following functions, thereby achieving efficient utilization of computing power.

[0066] Step 204: Computing power initialization is complete. The group enters collaborative standby mode and shares basic information.

[0067] Specifically, in one embodiment of this application, after the computing power allocation initialization is completed, the group officially enters the collaborative standby state. Each vehicle synchronously shares its own location, sensor status, remaining power and other basic information, opens up the data transmission channel, and ensures that subsequent processes such as sensor complementarity, route planning and collaborative power replenishment can proceed smoothly, thus preparing for full-process collaboration.

[0068] Based on the aforementioned solution, when the first vehicle is in a state of intelligent driving cooperation with at least one second vehicle, the intelligent driving system of the first vehicle will continue to operate and, in conjunction with the driving scenario, realize various cooperative intelligent driving functions, including cooperative yielding, cooperative avoidance, cooperative braking, cooperative parking, and cooperative positioning. Specifically, to facilitate understanding of the above, the following will describe each function in conjunction with an embodiment. In one embodiment of this application, when the first vehicle and the second vehicle are in a driving scenario of near-field communication networking, the method further includes: If there is a first target object that needs to be avoided in the driving scenario, then control the first vehicle and the second vehicle to follow the vehicle in front of the network to avoid the first target object; If there is a second target object requiring emergency braking in the driving scenario, then each vehicle in the network is controlled to perform emergency braking at the corresponding emergency braking level. The emergency braking level of different vehicles is related to the driving order of the vehicles in the network and / or the distance to the preceding vehicle in the network.

[0069] For example, in one possible implementation, for the first target object that needs to be avoided in a driving scenario, such as a special vehicle (fire truck, ambulance), the first vehicle and the second vehicle will be controlled to maintain a synchronized attitude with the vehicle in front of the network to avoid the object. Alternatively, for obstacles in the driving scenario, including but not limited to road rocks, road signs, etc., a coordinated driving queue will be maintained, and the first vehicle and the second vehicle will be controlled to follow the vehicle in front of the network to avoid the obstacle object. By maintaining synchronization through queuing, redundant execution of computing power is avoided, and the waste of computing power resources is reduced.

[0070] Furthermore, in other embodiments, when there is a second target object requiring emergency braking in the driving scenario, such as when a vehicle needs to brake suddenly due to a traffic accident, traffic lights, or traffic congestion to avoid a collision, in order to ensure driving safety, each vehicle in the network will be controlled to perform emergency braking at the corresponding emergency braking level. The emergency braking level of different vehicles is related to the driving order of the vehicles in the network and / or the distance to the vehicle in front in the network. By adopting a strategy of using differentiated control for each vehicle in a collaborative overall manner, the driving safety of intelligent driving collaboration can be effectively improved.

[0071] Specifically, to facilitate understanding of the above content, the following will provide detailed explanations of cooperative yielding, cooperative avoidance, and cooperative braking.

[0072] Specifically, in one embodiment of this application, the vehicle's intelligent driving system can be configured to achieve cooperative yielding to emergency vehicles. For details, please refer to... Figure 3 , Figure 3 The flowchart illustrating the steps for coordinated yielding to emergency vehicles provided in this application embodiment specifically includes: Step 301: Emergency vehicle signals or yield requests are detected in the same road segment group.

[0073] Specifically, in one embodiment of this application, during the driving or collaborative standby process, the intelligent driving group on the same road segment detects the surrounding traffic environment in real time through its own sensor system, and at the same time receives signals sent by surrounding vehicles and traffic facilities through the communication module to accurately detect whether emergency vehicles such as ambulances, police cars, and ambulances are passing by, or whether it receives emergency yielding requests initiated by other vehicles, ensuring that no emergency scenario is missed.

[0074] Step 302: The system analyzes the emergency vehicle information and issues a coordinated yielding instruction to the group.

[0075] Specifically, in one embodiment of this application, when an emergency vehicle signal or emergency yielding request is detected, the system quickly analyzes the emergency vehicle's driving direction, speed, and distance from the group, accurately determines the location, width, and time requirement for opening the emergency passage, and immediately issues a unified coordinated yielding instruction to all vehicles in the group, specifying the yielding direction, yielding speed, and final stopping position for each vehicle.

[0076] Step 303: All vehicles coordinate to give way and open an emergency lane.

[0077] Specifically, in one embodiment of this application, after receiving the coordinated yielding instruction, each vehicle automatically adjusts its driving speed and vehicle position based on its current location, the distribution of surrounding obstacles, and its driving status, and coordinates to orderly avoid obstacles on both sides of the road, quickly opening up a dedicated emergency lane that meets the requirements for emergency passage, ensuring that emergency vehicles can pass smoothly and quickly, and avoiding the impact on emergency efficiency due to improper yielding by individuals.

[0078] Step 304: Monitor emergency vehicles in real time and dynamically adjust yielding strategies.

[0079] Specifically, in one embodiment of this application, the driving status of emergency vehicles is monitored in real time, including driving routes and speed changes, and the group yielding strategy is dynamically adjusted; if the driving route of the emergency vehicles changes, the yielding instruction is updated immediately to notify each vehicle to adjust its yielding position, so as to avoid traffic chaos caused by the lag in the yielding strategy and ensure the safety of emergency passage.

[0080] Step 305: After the emergency vehicles have passed, the group regroups and resumes the original procedure.

[0081] Specifically, in one embodiment of this application, after the emergency vehicles have completely passed through the road section where the group is located, the system detects the current road traffic status in real time. After confirming that there are no safety hazards and no other emergency needs, it issues a rallying order to all vehicles in the group, notifying each vehicle to prepare to resume its original driving status.

[0082] Step 306: When route adjustments are needed, update the planned route synchronously.

[0083] Specifically, in one embodiment of this application, each vehicle automatically adjusts its position and speed according to the assembly command, quickly assembles and restores its original driving formation, and continues to execute the previous intelligent driving process from parking space to parking space; if the original driving route is changed during the emergency yielding process, the system updates the planned route synchronously to ensure that the intelligent driving process proceeds normally and does not affect the overall traffic efficiency.

[0084] In another possible implementation, the vehicle's intelligent driving system can be configured to collaboratively avoid obstacles based on forward warning information. Specifically, for ease of understanding, the following will explain the specific steps involved.

[0085] ① The high-end vehicle detected a warning obstacle at a certain distance ahead. In one embodiment of this application, a high-configuration vehicle, such as a vehicle equipped with lidar, can detect obstacles at a preset distance ahead, such as 80 meters, including falling rocks, road construction signs, or other obstacles that affect the vehicle's driving and require emergency avoidance.

[0086] ② Higher-spec vehicles will synchronize sensing data to lower-spec vehicles in real time. In one embodiment of this application, after detecting an obstacle, the high-configuration vehicle will simultaneously transmit the perception data of the detected obstacle, such as its location (distance), size, and shape, to the low-configuration vehicle, so that the low-configuration vehicle can make an avoidance decision in advance.

[0087] ③ The group comprehensively analyzes the distance between each vehicle and the obstacle to calculate the optimal avoidance path. In one embodiment of this application, each vehicle in the intelligent driving group will plan and calculate the optimal avoidance path in advance based on the distance between its own vehicle and the obstacle.

[0088] ④ The vehicle in front makes an emergency turn to avoid the obstacle. In one embodiment of this application, the vehicle in front can perform an emergency turn under safe driving constraints to avoid an obstacle.

[0089] ⑤ Coordinated braking (staged deceleration) with the following vehicle to avoid rear-end collisions. In one embodiment of this application, the following vehicle will further consider the safe distance from the preceding vehicle and implement coordinated braking, such as graded deceleration, to avoid rear-end collisions between vehicles.

[0090] ⑥ Dangerous areas are marked and uploaded to the sharing platform, allowing subsequent vehicles to automatically avoid them. In one embodiment of this application, after passing through an obstacle section, the dangerous area containing the obstacle is marked and uploaded to a sharing platform to achieve cross-section information sharing and remind other vehicles that need to pass through the section to automatically avoid it.

[0091] In another possible implementation, the vehicle's intelligent driving system can be configured to perform coordinated braking in response to sudden abnormal information. Specifically, for ease of understanding, the following will explain the specific steps involved.

[0092] ① The lead vehicle detected an accident ahead (camera + millimeter-wave radar fusion). In one embodiment of this application, the vehicle at the forefront of the intelligent driving group can use its own perception modules, such as image acquisition devices and millimeter-wave radar, to monitor whether there are any sudden abnormal accidents that require emergency braking ahead, such as rear-end collisions.

[0093] ② Accident perception data is broadcast to all vehicles in the group, and each vehicle updates its environmental model synchronously. In one embodiment of this application, accident perception data can be broadcast to all vehicles in the group, and the vehicles can synchronously update the current driving environment model as needed, such as selecting the driving environment model of the accident section to assist in intelligent driving decision-making.

[0094] ③ High-computing-power vehicles within the group participate in the calculation of the cooperative braking strategy. Specifically, in the embodiments of this application, in the case of an accident, vehicles with high computing power (i.e., low computing power load) within the group need to participate in the calculation of the cooperative braking strategy, such as calculating the braking acceleration of each vehicle in the group, in order to ensure the driving safety of the vehicles and avoid rear-end collisions.

[0095] ④ Each vehicle performs graded braking according to the gradient. In one embodiment of this application, each vehicle in the intelligent driving group performs graded braking according to the driving formation gradient. For example, the lead vehicle uses an acceleration braking of -6m / s², and the subsequent vehicles decrease in speed according to the formation gradient.

[0096] ⑤ Monitor braking performance in real time and adjust immediately if any abnormalities are found. In one embodiment of this application, during the coordinated braking process, the braking effect of each vehicle is monitored in real time, and if any abnormality is found, the braking decision of the vehicle is immediately adjusted.

[0097] ⑥ After safely parking, all vehicles should turn on the hazard warning lights to ensure that no vehicle brakes suddenly and a rear-end collision occurs. In one embodiment of this application, after a safe stop, all vehicles in the intelligent driving group coordinate to turn on their warning lights to alert following vehicles and prevent rear-end collisions caused by all braking vehicles having to stop suddenly.

[0098] In another possible implementation, the vehicle's intelligent driving system can be configured to collaboratively plan the service needs of the vehicle, including parking or charging needs. Of course, it is also feasible to plan to meet other needs of vehicle operation, such as refueling. This application embodiment does not limit this. In this case, the corresponding service resources usually include parking spaces and / or charging devices.

[0099] In one embodiment of this application, the method includes: When the first vehicle and the second vehicle are in a near-field communication network, service resources are allocated to the first vehicle and the second vehicle according to their service needs and / or vehicle types. or, When the first vehicle and the second vehicle are in a remote communication network, if the first vehicle has a service demand, a planned route from the starting position of the first vehicle to the destination position of the service resource is generated based on the cross-road condition information provided by the second vehicle.

[0100] That is, when the first vehicle and the second vehicle are in a near-field communication network, the service needs and / or vehicle types of both vehicles will be considered to achieve coordinated allocation of service resources in a specific scenario, thereby enabling vehicle parking. When the first vehicle and the second vehicle are in a long-range communication network, if the first vehicle has service needs, a planned route from the starting position of the first vehicle to the destination location of the service resource can be planned using cross-segment road condition information provided by the second vehicle. For example, in one implementation, planning a route from the starting position of the first vehicle to the destination location of the service resource using cross-segment road condition information provided by the second vehicle includes: The road condition data of the first vehicle is updated using the cross-road condition information provided by the second vehicle. Based on the updated traffic data, a planned route is generated from the starting position of the first vehicle to the destination position of the service resource.

[0101] Specifically, the traffic information provided by the second vehicle across road segments is used to update the traffic data of the first vehicle. For example, if the road segment where the second vehicle is located is congested, the first vehicle's traffic data will promptly indicate the congested segment, thereby avoiding entering that segment when planning the route and causing traffic congestion. In other words, based on the updated traffic data, a planned route from the starting position of the first vehicle to the destination position of the service resource is generated.

[0102] Specifically, to facilitate understanding of the above content, the following will be explained in conjunction with specific embodiments.

[0103] In one embodiment of this application, taking the implementation of collaborative parking and parking space allocation in a specific scenario as an example, the specific steps include:

[0104] ① The group obtains real-time parking information for the destination.

[0105] In one embodiment of this application, the intelligent driving group can obtain parking information at the destination location, such as a parking lot, charging station, or fast charging station, through information shared by intelligent driving groups across road segments or other means. This information includes the number of available parking spaces, the location of available spaces, and whether charging is supported. For ease of description, a parking lot will be used as an example in subsequent embodiments of this application.

[0106] ② Vehicles with low battery levels will be given priority for parking at the nearest charging station, while other vehicles will be assigned to convenient parking spaces.

[0107] In one embodiment of this application, charging station parking spaces can be allocated to low-battery vehicles that need charging within the intelligent driving group, such as allocating the nearest charging station parking space according to the battery level. For other regular vehicles that do not need charging, convenient parking spaces are allocated according to distance.

[0108] ③ The allocation results for each vehicle are synchronized to the intelligent driving system.

[0109] In one embodiment of this application, the parking space allocation results for each vehicle will be provided to the intelligent driving system of each vehicle, so as to facilitate the intelligent driving system of each vehicle to make path planning and control decisions for allocating parking spaces.

[0110] ④ Vehicles with low battery levels should enter the parking area first, followed by other vehicles in sequence. In one embodiment of this application, vehicles with low battery levels are given priority to enter the location and park, while the remaining vehicles are parked in sequence.

[0111] ⑤ After parking is completed, the parking space occupancy status will be automatically updated to the sharing platform. In one embodiment of this application, after each vehicle has parked, the parking space occupancy status is automatically updated to the sharing platform to update the real-time parking space information.

[0112] ⑥ The group remains in communication standby, awaiting user requests for coordinated departure. In one embodiment of this application, after each vehicle has parked, the vehicles in the group remain in a communication standby state, waiting for user requests, and then collaboratively drive out of the parking lot according to the received call command.

[0113] In another possible implementation, the vehicle's intelligent driving system can be configured to achieve cooperative positioning in weak localization environments, such as accurate positioning in driving environments with weak localization data, like tunnels. Specifically, this includes the following steps: ① High-precision positioning calibration was completed before the group entered the tunnel. In one embodiment of this application, when weak positioning data is detected ahead, such as in a tunnel driving scenario, high-precision positioning calibration is performed before vehicles in the group enter the tunnel, such as through GPS (Global Positioning System) and RTK (Real-time kinematic).

[0114] ②After GPS is interrupted, each vehicle starts inertial navigation calculation + sensor perception fusion. After entering the tunnel, that is, after the positioning data signal is interrupted, each vehicle will acquire its own inertial data through the IMU (Inertial Measurement Unit) to estimate the vehicle's current position based on inertial navigation. At the same time, each vehicle will perceive and fuse driving environment information through sensors.

[0115] ③ High-end vehicles offer LiDAR point cloud matching to improve positioning accuracy. In one embodiment of this application, the high-end vehicle will provide a LiDAR point cloud of the surrounding driving environment for matching, thereby further improving the accuracy of the vehicle's positioning data.

[0116] ④ All vehicles will share location results, and group fusion optimization will be implemented. In one embodiment of this application, each vehicle in the group will optimize the location results by voting or other means based on the location results shared by each vehicle.

[0117] ⑤ When changing lanes in a tunnel, the vehicle in front provides information on the road conditions ahead, and the vehicle behind provides information on what is behind. In one embodiment of this application, in a tunnel driving scenario, if it is necessary to change lanes in the tunnel, the leading vehicle in the group will provide the road conditions ahead, and the following vehicle will provide the information of vehicles approaching from behind, thereby completing the lane change in the tunnel under the premise of driving safety.

[0118] ⑥ GPS recovery was detected as the vehicle approached the exit, and positioning resynchronization was quickly completed.

[0119] In one embodiment of this application, when approaching the tunnel exit, that is, when GPS positioning data is detected to be restored, the resynchronization of positioning information is quickly completed based on the restored GPS positioning data.

[0120] The solution provided in this application embodiment enables intelligent driving collaboration in multiple scenarios, particularly from parking space to parking space, under the cooperative intelligent driving state of a first vehicle and a second vehicle. For a clearer understanding of the above, please refer to... Figure 4 , Figure 4 A flowchart illustrating the steps of intelligent driving group collaboration from parking space to parking space, as provided in this application embodiment, specifically includes: Step 401: The sensor system of the same road segment is activated to collect surrounding environmental data in real time. In the embodiments of this application, when vehicles in the same road segment intelligent driving group enter the cooperative operation state, each vehicle activates the corresponding sensor system according to its own sensor configuration. Among them, high-end vehicles (equipped with high-precision sensors such as LiDAR) activate all high-precision sensors, while low-end vehicles activate basic sensors. All vehicles collect surrounding environmental data in real time (including obstacles, lane lines, traffic lights, parking space outlines, etc.) to provide data support for subsequent perception coordination and route planning.

[0121] Step 402: High- and low-configuration vehicles within the group share sensor data bidirectionally to complete environmental perception fusion. In the embodiments of this application, a two-way complementary mechanism of high- and low-configuration vehicle sensors is activated to maximize the perception capability within the group. The high-configuration vehicle synchronizes the long-distance, high-precision environmental data collected by the LiDAR to the low-configuration vehicle in real time, effectively making up for the shortcomings of the low-configuration vehicle's insufficient detection accuracy. At the same time, the low-configuration vehicle accurately collects the perception blind spot data such as the side and rear of the high-configuration vehicle and low obstacles through its own basic sensors, and synchronizes it back to the high-configuration vehicle, improving the overall perception dimension of the group and enhancing the comprehensiveness of environmental detection.

[0122] Step 403: Integrate vehicle information and real-time traffic conditions to plan the entire route from parking space to parking space. In the embodiments of this application, the system integrates core information such as the starting parking space, destination parking space, remaining battery power, and flash charging technology compatibility status of all vehicles, and combines it with external environmental data such as real-time traffic conditions and traffic light durations to plan the entire process route from parking space to parking space in a coordinated manner. The route covers all stages of automatic parking out, driving, recharging (if there are vehicles that need recharging), and automatic parking in, ensuring the optimality and completeness of the route.

[0123] Step 404: For vehicles compatible with flash charging that require recharging, prioritize recharging and plan recharging routes. In the embodiments of this application, for vehicles in the group that are compatible with flash charging technology, the system prioritizes charging based on the remaining battery level of each vehicle. It prioritizes planning the optimal route through the flash charging station for vehicles with low battery levels that need emergency charging. At the same time, it reasonably arranges the charging order and charging time of each vehicle to ensure that the charging process is synchronized with the overall driving rhythm of the group and avoids the group from becoming disconnected due to charging a single vehicle.

[0124] Step 405: Allocate parking spaces at the destination, prioritizing parking spaces near fast-charging stations for vehicles requiring refueling. In the embodiments of this application, the system intelligently allocates available parking spaces at the destination by combining factors such as the vehicle body size and user driving preferences, with a focus on optimizing the allocation of parking spaces for vehicles that need to recharge. It prioritizes allocating the nearest available parking spaces in the flash charging station to vehicles that need to recharge, thereby achieving a seamless connection between "recharging and parking" and improving the convenience of recharging and parking.

[0125] Step 406: The group collaboratively executes automatic parking to avoid collisions. In the embodiments of this application, each vehicle in the intelligent driving group will cooperate to perform automatic parking operations according to the planned full-process route. Each vehicle accurately judges the distance and position of surrounding obstacles based on bidirectional complementary data from sensors, and smoothly and orderly parks out of its own starting space, avoiding collisions between vehicles and ensuring a safe and efficient parking process.

[0126] Step 407: Dynamically adjust formation and speed during operation to maintain distributed computing power collaboration. In the embodiments of this application, during the driving process, the system dynamically adjusts the group formation and driving speed according to real-time road conditions and traffic light switching to achieve coordinated passage through traffic lights, ensuring that the group can efficiently pass through the intersection within the green light window, while continuously maintaining the distributed computing power collaborative mode to ensure computing efficiency under complex road conditions and avoid intelligent driving lag and delay.

[0127] Step 408: Vehicles requiring charging should proceed with flash charging in sequence, while other vehicles wait in line. In the embodiments of this application, vehicles that need to be recharged can enter the flash charging station in sequence according to the planned order. Taking advantage of the convenient features of flash charging technology, such as "plug and charge and contactless payment", they can quickly and efficiently recharge. During the recharge period, other vehicles can wait together in a safe area around the flash charging station, maintain communication connection, avoid the group from becoming disconnected, and ensure that they can quickly regroup after recharging.

[0128] Step 409: After recharging, the group assembles and coordinates to automatically dock. In the embodiments of this application, after the charging is completed, the vehicle that needs to be charged will quickly leave the flash charging station, regroup with other vehicles in the group, and continue to the destination along the planned route. After arriving at the destination, each vehicle will work together to perform automatic parking operation. By combining complementary data from sensors, the parking angle and speed will be precisely adjusted to smoothly park in the assigned destination parking space.

[0129] Step 410: After parking is completed, the group updates the parking space information to the sharing platform. In one embodiment of this application, after all vehicles have completed automatic parking, the occupancy status of their own parking spaces is automatically synchronized to the group sharing platform, and the parking space information is updated in real time. This provides accurate reference for other smart groups going to the same destination, such as smart groups that cross road segments. At the same time, the group can choose to automatically disband or remain in standby state according to user needs, waiting for subsequent coordination instructions.

[0130] Building upon the foregoing, and considering the shortcomings of related technologies such as delayed updates and lack of targeted sharing of road condition or parking space data, as well as the lack of coordination in intelligent driving strategies, one embodiment of this application further provides a group sharing platform. This platform enables real-time synchronization of road condition and parking space data across different road segments, while also supporting collaborative optimization of intelligent driving strategies to ensure a consistent intelligent driving experience within the group. For details, please refer to [link to relevant documentation]. Figure 5 , Figure 5 This application provides a flowchart of collaborative intelligent driving under cross-road segment intelligent driving group data sharing as an embodiment of the present application. Specifically, it includes the following steps: Step 501: Vehicles in different road sections upload core data to the sharing platform in real time. In one embodiment of this application, low-latency communication connections are continuously maintained for intelligent driving group vehicles on different road segments to ensure the real-time performance and stability of data transmission. In addition, each vehicle uploads its own core data to the group sharing platform in real time, including real-time road conditions (construction, congestion, severe weather, etc.), sensor detection data, parking space occupancy / vacancy status, and its own intelligent driving strategy parameters, providing data support for cross-road segment collaboration.

[0131] Step 502: The sharing platform organizes data and updates road condition and parking space maps. In one embodiment of this application, the group sharing platform will filter, organize and integrate all uploaded data, remove invalid data and correct biased data, and update the regional road condition map and parking space map in real time to ensure map freshness and accuracy, providing accurate data support for subsequent cross-segment route planning and parking space scheduling, and avoiding the impact of data lag on the collaborative effect.

[0132] Step 503: When planning a route, the vehicle calls upon cross-segment data to avoid undesirable road sections. In one embodiment of this application, when the vehicle initiates intelligent driving route planning from parking space to parking space, it can automatically call cross-segment road condition data from the group sharing platform. The system combines this data to accurately identify undesirable road segments such as construction, congestion, and severe weather, avoids such road segments, plans the optimal driving route, reduces travel time, and improves cross-segment intelligent driving efficiency.

[0133] Step 504: Vehicles heading to the parking lot obtain available parking spaces through the platform and make adjustments. In one embodiment of this application, for vehicles heading to a designated parking lot, the latest parking space information of the parking lot can be quickly obtained through a group sharing platform, including the location, size, and distance from the entrance of the available parking spaces. Based on this information, the system automatically assists the vehicle in being dispatched to a suitable available parking space, avoiding parking lot congestion caused by blindly searching for parking spaces and improving parking efficiency.

[0134] Step 505: After optimizing the intelligent driving strategy, the vehicle synchronizes the parameters to the sharing platform. In one embodiment of this application, a vehicle on a certain road segment optimizes its intelligent driving strategy parameters (such as following distance, lane change sensitivity, parking accuracy, etc.) based on the road conditions of its own road segment (such as highways or congested urban areas), and immediately synchronizes the optimized strategy parameters to the group sharing platform to realize the sharing of strategy experience.

[0135] Step 506: Other vehicles refer to the optimized parameters and adjust their own intelligent driving strategies. In one embodiment of this application, other vehicles on different road segments receive optimization strategy parameters pushed by the sharing platform in real time. Combined with the road conditions of their own road segments, they automatically adjust their own intelligent driving strategy parameters to achieve coordinated and unified intelligent driving strategies within the group. This ensures that the intelligent driving experience and operation logic of vehicles in the same group remain consistent across different road segments, thereby improving the user experience.

[0136] Step 507: When the vehicle status changes, update the information to the sharing platform simultaneously. In one embodiment of this application, if a vehicle leaves the current road segment, changes its destination, or leaves the intelligent driving group due to user needs, it immediately sends a status update information to the group sharing platform; the sharing platform quickly receives and updates the group data, adjusts the network structure and coordination strategy, ensures the accuracy and timeliness of cross-road segment coordination, and avoids interference from invalid data.

[0137] Step 508: After parking is completed, the vehicle's parking space status is synchronized to the sharing platform. In one embodiment of this application, after the vehicle completes the intelligent driving process from parking space to parking space, the information such as the vacancy / occupancy status and parking time of the destination parking space is automatically synchronized to the group sharing platform, and the parking space map is continuously updated. This provides accurate reference for the planning of parking spaces for group vehicles going to the parking lot in the future, ensuring the timeliness and accuracy of parking space information and improving the utilization rate of parking spaces.

[0138] In addition, this application also provides a vehicle-assisted driving method, applied to a second vehicle, comprising: Upon receiving a computing power request from a first vehicle that is networked with the second vehicle, the driving task of the first vehicle is executed based on the computing power resources of the second vehicle, wherein the driving task is also executed by the computing power resources of the first vehicle.

[0139] For example, in one possible implementation, when the first vehicle is in a state of computing power overload, at least part of the driving task of the first vehicle can be executed based on the computing power resources of the second vehicle. For the implementation scheme of computing power overload, driving task, and configuration of executing driving task through the computing power resources of the second vehicle, please refer to the foregoing description of the first vehicle. This application will not repeat the description.

[0140] The vehicle-assisted driving method provided in this application, when a first vehicle is performing its own driving task and is in a network state with at least one second vehicle, utilizes the computing power resources of the second vehicle to perform at least part of the first vehicle's driving task. By using the method provided in this application, when the first vehicle is performing its own driving task and is in a network state with at least one second vehicle, the idle computing power resources of the second vehicle can be reasonably utilized to assist in performing at least part of the first vehicle's driving task, improving the allocation of computing power resources among vehicles in the network, and effectively improving the driving performance and intelligent driving collaboration stability of vehicles within the group.

[0141] To clearly understand the completion process of the vehicle assisted driving method provided in the embodiments of this application, please refer to... Figure 6 , Figure 6 This is a schematic diagram of the architecture of the intelligent driving cooperative system for implementing the vehicle assisted driving method provided in the embodiments of this application. For details, please refer to [link / reference]. Figure 6 The intelligent driving cooperative system includes: The perception layer module 610 serves as the data acquisition foundation for the intelligent driving collaborative system. It encompasses the sensor systems (LiDAR, HD camera, millimeter-wave radar, ultrasonic radar) and low-latency communication modules (V2X / 5G-A) of all intelligent driving vehicles. Its core function is to collect real-time data on the vehicle's own status and the surrounding environment, while simultaneously enabling low-latency data transmission between vehicles and between vehicles and the group sharing platform, providing accurate and real-time data support for all subsequent modules.

[0142] The networking and computing power collaboration module 620 is responsible for the automatic formation of intelligent driving groups (flexible networking within the same road segment / across road segments) and the dynamic allocation of distributed computing power. Its core functions are to detect the distance between vehicles and networking conditions, complete the group formation, and dynamically allocate computing tasks according to the computing power load of each vehicle to avoid overloading the computing power of a single vehicle and ensure the overall computing efficiency of the system. It is the basic support module for the collaborative operation of the entire intelligent driving collaborative system.

[0143] The same-road-segment collaborative control module 630 integrates data collected by the perception layer and group information from the networking module. Its core functions include bidirectional complementarity of high and low configuration vehicle sensors, full-process route planning from parking space to parking space, fast charging collaborative power replenishment, and emergency yielding collaborative control. It realizes full-process collaboration of same-road-segment groups from parking out, driving, power replenishment to parking in, while responding to emergency scenarios and ensuring the safety and convenience of intelligent driving on the same-road-segment.

[0144] The Cross-Road Segment Collaborative Empowerment Module 640, relying on the group sharing platform, has core functions including real-time sharing of cross-road segment road conditions and parking space data, collaborative optimization of intelligent driving strategies, and dynamic updates of vehicle status. It enables mutual empowerment between different road segment groups, expands the application scenarios of intelligent driving teams, improves cross-road segment intelligent driving efficiency and user experience, and continuously updates parking space and road condition maps to provide data support for the entire intelligent driving process.

[0145] The decision and control layer module 650, as the top-level decision-making core of the system, connects the perception layer, the networking and computing power collaboration module, the same-segment collaborative control module, and the cross-segment collaborative empowerment module. Its core function is to receive data uploaded by each module, perform comprehensive analysis and decision-making, and issue collaborative control commands (such as networking commands, computing power allocation commands, route planning commands, emergency yielding commands, etc.). At the same time, it monitors the system's operating status in real time to ensure that each module operates in a coordinated and orderly manner, realizes closed-loop control of the entire system, and ensures the smooth progress of intelligent driving from parking space to parking space.

[0146] In addition to the foregoing, this application also provides a controller, specifically, the controller may be an in-vehicle controller, which can be used to execute the method described in any of the above-mentioned methods to achieve assisted driving of the vehicle.

[0147] Specifically, the controller may be located in an electronic device; for example, please refer to [link to relevant documentation]. Figure 7 , Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: A processor is used to execute the vehicle-assisted driving method provided in any of the above embodiments. The processor can be various general-purpose or special-purpose processing components with processing and computing capabilities, including but not limited to a central processing unit (CPU), a graphics processing unit (GPU), a dedicated artificial intelligence computing chip, a digital signal processor, etc. A memory, communicatively connected to at least one processor, stores a computer program executable by at least one processor, enabling the at least one processor to execute a vehicle-assisted driving method as described in any of the above embodiments. The memory may be a read-only memory (ROM) for storing the computer program; or the computer program may be loaded from a storage unit into random access memory (RAM). The RAM may also store various programs and data required for the operation of a vehicle-assisted driving method.

[0148] I / O interfaces (input units and output units), input units include keyboards, mice, etc., output units include displays, speakers, etc., communication units include network cards, modems, wireless transceivers, processors, and memory.

[0149] The processor controls the overall operation of the electronic device to complete all or part of the steps in the aforementioned vehicle-assisted driving method. The memory stores various types of data to support the operation of the electronic device. This data may include, for example, instructions for any application or method operating on the electronic device, as well as application-related data such as contact data, sent and received messages, images, audio, and video. The memory can be implemented using any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0150] In an exemplary embodiment, the electronic device may be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), or other electronic components to perform the vehicle-assisted driving method described above.

[0151] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the vehicle assisted driving method provided in any of the above embodiments.

[0152] This application also provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it enables the computer program product to implement the vehicle assisted driving method provided in any of the above embodiments.

[0153] This application also provides a vehicle assisted driving system, which is configured to be obtained through a network of multiple vehicles, wherein any vehicle in the communication network is configured to implement assisted driving of the vehicle through the vehicle assisted driving method described in any of the above embodiments.

[0154] This application also provides a service platform configured to remotely communicate with at least two vehicles to achieve vehicle networking. The service platform is configured to receive vehicle information from at least one vehicle to execute the vehicle assisted driving method as described in any of the above embodiments.

[0155] This application also provides a vehicle that includes a controller as described above, or includes a vehicle driver assistance system as described above, or performs a vehicle driver assistance method as described in any of the above claims.

[0156] In one embodiment, the vehicle can be configured for fully or partially autonomous driving. For example, the vehicle can control itself while in autonomous driving mode, and can determine the current state of the vehicle and its surrounding environment through human intervention, determine the possible behaviors of at least one other vehicle in the surrounding environment, and determine the confidence level corresponding to the probability of that other vehicle performing a possible behavior, and control the vehicle based on the determined information. When the vehicle is in autonomous driving mode, it can operate without human interaction.

[0157] The vehicle may also include various subsystems, such as a driving system, sensor system, control system, one or more peripheral devices, as well as power supply, computer system, and user interface. Optionally, the vehicle may include more or fewer subsystems, and each subsystem may include multiple components, such as multiple ECUs (electronic control units, i.e., vehicle computers) per subsystem.

[0158] In addition, each subsystem and component of the vehicle can be interconnected via wired or wireless means.

[0159] A mobility system may include components that provide powered motion to a vehicle. In one embodiment, a mobility system may include an engine, an energy source, a transmission, and wheels / tires. The engine may be an internal combustion engine, an electric motor, an air-compressed engine, or a combination of other types of engines, such as a hybrid engine consisting of a gasoline engine and an electric motor, or a hybrid engine consisting of an internal combustion engine and an air-compressed engine. The engine converts energy into mechanical energy.

[0160] Examples of energy sources include gasoline, diesel, other petroleum-based fuels, propane, other compressed gas-based fuels, ethanol, solar panels, batteries, and other sources of electricity. Energy sources can also power other systems in the vehicle.

[0161] A transmission system can transmit mechanical power from an engine to the wheels. The transmission system may include a gearbox, a differential, and a drive shaft. In one embodiment, the transmission system may also include other components, such as a clutch. The drive shaft may include one or more axles that can be coupled to one or more wheels.

[0162] A sensor system may include several sensors that sense information about the vehicle's surrounding environment. For example, a sensor system may include a positioning system (which could be GPS, BeiDou, or another positioning system), an inertial measurement unit (IMU), radar, a laser rangefinder, and cameras. The sensor system may also include sensors from the vehicle's internal systems being monitored (e.g., an in-vehicle air quality monitor, fuel gauge, oil temperature gauge, etc.). Data from one or more of these sensors can be used to detect objects and their corresponding characteristics (position, shape, orientation, speed, etc.). This detection and identification is a critical function for the safe operation of autonomous vehicles.

[0163] A positioning system can be used to estimate a vehicle's geographical location. An IMU is used to sense changes in the vehicle's position and orientation based on inertial acceleration. In one embodiment, the IMU can be a combination of an accelerometer and a gyroscope.

[0164] Radar can use radio signals to sense objects in the vehicle's surrounding environment. In some embodiments, in addition to sensing objects, radar can also be used to sense the speed and / or direction of travel of objects.

[0165] A laser rangefinder can use lasers to sense objects in the environment in which a vehicle is located. In some embodiments, a laser rangefinder may include one or more laser sources, a laser scanner, and one or more processing modules, as well as other system components.

[0166] The camera can be used to capture multiple images of the vehicle's surroundings. The camera can be a still camera or a video camera.

[0167] A control system is used to control the operation of a vehicle and its components. A control system may include various components, including a steering system, throttle, braking unit, computer vision system, route control system, and obstacle avoidance system.

[0168] The steering system is operable to adjust the vehicle's direction of travel. For example, in one embodiment, it may be a steering wheel system.

[0169] The throttle is used to control the engine's operating speed and, consequently, the vehicle's speed.

[0170] The braking unit is used to control the deceleration of the vehicle. The braking unit uses friction to slow down the rotational speed of the wheels.

[0171] In other embodiments, the braking unit can convert the kinetic energy of the wheels into electrical current. The braking unit may also take other forms to slow down the wheel rotation speed, thereby controlling the vehicle speed.

[0172] Computer vision systems can be operated to process and analyze images captured by cameras to identify objects and / or features in the environment surrounding a vehicle. These objects and / or features may include traffic signals, road boundaries, and obstacles. Computer vision systems may use object recognition algorithms, structure from motion (SFM) algorithms, video tracking, and other computer vision techniques. In some embodiments, computer vision systems may be used to map the environment, track objects, estimate object velocities, and so on.

[0173] A route control system is used to determine the driving route of a vehicle. In some embodiments, the route control system may combine data from GPS and one or more predetermined maps to determine the driving route for the vehicle.

[0174] Obstacle avoidance systems are used to identify, assess, and avoid or otherwise traverse potential obstacles in the environment in which a vehicle is located.

[0175] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0176] The embodiments, implementation methods, and related technical features of this application can be combined and substituted for each other without conflict.

[0177] The above are merely preferred embodiments of this application and are not intended to limit this application in any way. Any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of this application without departing from the scope of the technical solution of this application shall still fall within the scope of the technical solution of this application.

Claims

1. A vehicle assisted driving method, characterized in that, Applied to the first vehicle, including: When the first vehicle is performing its own driving task and the first vehicle is in a network state with at least one second vehicle, the computing resources of the second vehicle are configured to perform at least part of the driving task of the first vehicle. The driving task of the first vehicle is determined at least by the perception data of the first vehicle and / or the perception data of the second vehicle; The driving task is determined by at least the perception data of the first vehicle and / or the perception data of the second vehicle, including: When the perception performance of the first vehicle is less than that of the second vehicle, the driving task is determined at least through the perception data of the second vehicle; and / or When the perception performance of the first vehicle is greater than or equal to that of the second vehicle, the driving task is determined at least by the perception data of the first vehicle and the target perception data of the second vehicle for the target area, wherein the target area includes the perception blind spot of the first vehicle.

2. The method according to claim 1, characterized in that, The method includes: When the first vehicle is performing its own driving task, if the computing power resource status of the first vehicle indicates that the first vehicle is in a computing power overload state, at least a portion of the driving task is configured to be performed by the second vehicle, and the at least a portion of the driving task is configured to be performed using the computing power resources of the second vehicle.

3. The method according to claim 2, characterized in that, The computing power resource status includes available computing power resources and / or computing power load. The computing power resource status of the first vehicle indicates that the first vehicle is in a computing power overload state, including at least one of the following situations: The available computing power resources of the first vehicle do not meet the computing power load required for the driving task of the first vehicle; The computing load of the first vehicle is greater than the preset computing load threshold.

4. The method according to claim 2, characterized in that, The method further includes: When the computing power resource status of the first vehicle indicates that the first vehicle is not in a state of computing power overload, the first vehicle and the second vehicle maintain a network state, and the driving task of the first vehicle is executed by the computing power resources of the first vehicle.

5. The method according to claim 1, characterized in that, The driving task of the first vehicle is also determined in the following manner: Configured to perform the task of the first vehicle as determined by user instructions.

6. The method according to claim 1, characterized in that, The method further includes: When the first vehicle and the second vehicle are in intelligent driving mode, and the distance between the first vehicle and the second vehicle is less than a first distance threshold and / or they are on the same road, near-field communication networking is performed between the first vehicle and the second vehicle through the first communication device of the first vehicle; When the first vehicle and the second vehicle are in intelligent driving mode, and the distance between the first vehicle and the second vehicle is greater than or equal to a first distance threshold and / or they are not on the same road, the first vehicle communicates remotely with the network platform through its second communication device to form a remote communication network with the second vehicle.

7. The method according to claim 1, characterized in that, The method further includes: When the first vehicle and the second vehicle are in a near-field communication network, service resources are allocated to the first vehicle and the second vehicle according to their service needs and / or vehicle types. or, When the first vehicle and the second vehicle are in a remote communication network, if the first vehicle has a service demand, a planned route from the starting position of the first vehicle to the destination position of the service resource is generated by using the cross-road condition information provided by the second vehicle. The service requirements include parking and / or charging requirements, and the service resources include parking spaces and / or charging devices.

8. The method according to claim 7, characterized in that, The step of planning and generating a route from the starting position of the first vehicle to the destination position of the service resource using cross-segment road condition information provided by the second vehicle includes: The road condition data of the first vehicle is updated using the cross-road condition information provided by the second vehicle. Based on the updated traffic data, a planned route is generated from the starting position of the first vehicle to the destination position of the service resource.

9. The method according to claim 1, characterized in that, In a driving scenario where the first vehicle and the second vehicle are in a near-field communication network, the method further includes: If there is a first target object that needs to be avoided in the driving scenario, then control the first vehicle and the second vehicle to follow the vehicle in front of the network to avoid the first target object; If there is a second target object requiring emergency braking in the driving scenario, then each vehicle in the network is controlled to perform emergency braking at the corresponding emergency braking level. The emergency braking level of different vehicles is related to the driving order of the vehicles in the network and / or the distance to the preceding vehicle in the network.

10. The method according to claim 1, characterized in that, The second vehicle includes multiple vehicles, and the method further includes: The driving task of the first vehicle is performed by utilizing the computing resources of the target second vehicle in the second vehicle. The target second vehicle is obtained at least by sorting the computing power status of the second vehicle.

11. The method according to any one of claims 1 to 10, characterized in that, During the process of the second vehicle's computing resources being configured to execute at least part of the driving task of the first vehicle, if the computing resource status of the second vehicle indicates that the second vehicle is in a computing overload state, then at least part of the driving task of the first vehicle is configured to be executed by the computing resources of a third vehicle, wherein the third vehicle is in a network state with the first vehicle and the at least one second vehicle.

12. A vehicle assisted driving method, characterized in that, Applied to the second vehicle, including: Upon receiving a computing power request from a first vehicle that is networked with the second vehicle, the driving task of the first vehicle is executed based on the computing power resources of the second vehicle, wherein the driving task is also executed by the computing power resources of the first vehicle. The driving task of the first vehicle is determined at least by the perception data of the first vehicle and / or the perception data of the second vehicle; The driving task is determined by at least the perception data of the first vehicle and / or the perception data of the second vehicle, including: When the perception performance of the first vehicle is less than that of the second vehicle, the driving task is determined at least through the perception data of the second vehicle; and / or When the perception performance of the first vehicle is greater than or equal to that of the second vehicle, the driving task is determined at least by the perception data of the first vehicle and the target perception data of the second vehicle for the target area, wherein the target area includes the perception blind spot of the first vehicle.

13. A vehicle driver assistance system, characterized in that, The vehicle assisted driving system is configured to be obtained through a network of multiple vehicles, wherein any vehicle in the communication network is configured to implement assisted driving of the vehicle through any one of claims 1 to 11, or through the vehicle assisted driving method as described in claim 12.

14. A service platform, characterized in that, The service platform is configured to remotely communicate with at least two vehicles to achieve vehicle networking, wherein the service platform is configured to receive vehicle information from at least one vehicle to perform any one of claims 1 to 11, or to perform the vehicle assisted driving method as described in claim 12.

15. A vehicle, characterized in that, The vehicle performs any one of claims 1 to 11, or performs the vehicle assisted driving method as described in claim 12.

Images