Vehicle control methods, devices, systems, vehicles and storage media

Abstract

This disclosure provides a vehicle control method, device, system, vehicle, and storage medium. The method includes: generating basic mobility planning data based on vehicle sensor data; sending the basic mobility planning data and sensor data to a server; receiving a risk assessment result or a remote safety command generated based on the risk assessment result from the server, wherein the risk assessment result is generated based on the basic mobility planning data and sensor data; and controlling the vehicle's mobility based on the basic mobility planning data and in conjunction with the remote safety command or risk assessment result, constructing a dual-link collaborative safety redundancy control architecture to achieve linkage and cooperation between the vehicle and the server, thereby effectively improving the vehicle's environmental adaptability and risk identification and early warning accuracy during vehicle movement.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent driving technology, and particularly to a vehicle control method, device, system, vehicle, and storage medium. Background Art

[0002] Currently, in the vehicle movement scenario in the field of artificial intelligence, the movement planning of vehicles mainly relies on a single link of its own. Due to the limited detection range of vehicle-mounted sensing hardware (such as cameras and lidar), and the local computing power being limited by volume and power consumption, the planning accuracy is low, and safety risks such as collisions and path deviations are likely to occur due to misjudgments of complex environments (such as obstacle occlusion and unconventional objects). Summary of the Invention

[0003] The present disclosure provides a vehicle control method, device, system, vehicle, and storage medium, which can achieve dual-link collaborative control between the vehicle and the server, and improve the environmental adaptation ability and the accuracy of risk warning when the vehicle moves.

[0004] In a first aspect embodiment of the present disclosure, a vehicle control method is proposed. This method is applied to a vehicle and includes: generating basic movement planning data based on the sensor data of the vehicle;

[0005] Sending the basic movement planning data and the sensor data to the server; Receiving a risk assessment result sent by the server or a remote safety instruction generated based on the risk assessment result, where the risk assessment result is generated based on the basic movement planning data and the sensor data; Based on the basic movement planning data, and in combination with the remote safety instruction or the risk assessment result, performing movement control on the vehicle.

[0006] On the basis of maintaining the basic safety operation ability, the vehicle of the present disclosure can independently generate basic movement planning data based on its own sensor data by relying on a low-computing-power algorithm; at the same time, the vehicle uploads multi-source sensor data to the server in real time, and the server uses the large model carried to complete high-precision environmental perception and global risk assessment, and sends the corresponding risk assessment result or remote safety instruction to the vehicle. It is realized by combining local autonomous planning at the vehicle end and intelligent decision-making in the server cloud, constructing a dual-link collaborative safety redundancy control architecture, realizing the linkage and cooperation between the vehicle end and the server, and thus effectively improving the environmental adaptation ability and the risk identification and warning accuracy during the vehicle movement process.

[0007] In some embodiments of the present disclosure, performing movement control on the vehicle based on the basic movement planning data, and in combination with the remote safety instruction or the risk assessment result includes: Performing movement control on the vehicle based on the basic movement planning data and in combination with the remote safety instruction; or, Based on the risk assessment results, local safety commands for the vehicle are generated to control the vehicle's movement based on the basic mobility planning data and in combination with the local safety commands.

[0008] This disclosure provides two control paths: server-generated remote security commands to directly control vehicle movement and vehicle-generated local security commands to control vehicle movement. This enriches the implementation methods of vehicle movement control and can cope with various complex environments.

[0009] In some embodiments of this disclosure, generating local safety commands for the vehicle based on risk assessment results includes: Analyze the risk assessment results to identify semantic risk identification results and spatial risk identification results within the risk assessment results; If at least one of the semantic risk identification results and the spatial risk identification results indicates that there is a risk in the basic mobility planning data, then a local security instruction is generated based on at least one of the semantic risk identification results and the spatial risk identification results. When both semantic risk identification results and spatial risk identification results indicate that there is no risk in the basic mobility planning data, local security instructions are generated based on the basic mobility planning data.

[0010] This disclosure enables the generation of local safety commands in vehicles by analyzing risks from both semantic and spatial dimensions, and generating local safety commands in accordance with different scenarios, thus ensuring the refinement and rationality of the generated local safety commands.

[0011] In some embodiments of this disclosure, vehicle movement control based on basic mobility planning data, combined with remote safety commands or risk assessment results, includes: If no remote security command or risk assessment result is received from the server within the preset feedback period, a preset safe movement mode is activated; the preset safe movement mode is generated by the vehicle based on sensor data. In the preset safe movement mode, the vehicle's movement is controlled.

[0012] This disclosure adds a communication timeout fallback mechanism, which allows the vehicle to automatically switch to a preset safe movement mode in the event of disconnection or delay, ensuring reliable vehicle operation.

[0013] A second aspect of this disclosure provides a vehicle control method applied to a server, the method comprising: receiving basic mobility planning data and sensor data sent by a vehicle, wherein the basic mobility planning data is generated by the vehicle based on the sensor data; Based on basic mobility planning data and sensor data, generate risk assessment results, or generate remote security commands based on risk assessment results; Remote safety commands or risk assessment results are sent to the vehicle and used in conjunction with basic mobility planning data to control the vehicle's movement.

[0014] This disclosure uses the server's high-precision perception to identify risks in the basic mobility planning data generated by vehicles, and outputs risk assessment results or remote safety commands to provide global decision support for vehicle mobility collaborative control.

[0015] In some embodiments of this disclosure, generating risk assessment results based on basic mobility planning data and sensor data includes: Based on sensor data, basic mobility planning data, and deep learning models, mobility risk identification is performed to obtain semantic risk identification results and spatial risk identification results. Risk assessment results are generated based on semantic risk identification results and spatial risk identification results.

[0016] This disclosure improves the scenario generalization ability of risk assessment by integrating deep learning models to identify risks from both semantic and spatial dimensions.

[0017] In some embodiments of this disclosure, generating remote security commands based on risk assessment results includes: If at least one of the semantic risk identification results or the spatial risk identification results in the risk assessment results indicates that there is a risk in the basic mobility planning data, a remote security command is generated based on at least one of the semantic risk identification results and the spatial risk identification results. When both semantic risk identification results and spatial risk identification results indicate that there is no risk, remote security instructions are generated based on basic mobility planning data.

[0018] This disclosure generates remote security commands based on dual-dimensional risk identification results for different scenarios, thereby achieving accurate matching between remote security commands and actual scenarios.

[0019] In some embodiments of this disclosure, mobility risk identification is performed based on sensor data, basic mobility planning data, and a deep learning model to obtain semantic risk identification results, including: Based on sensor data, basic mobility planning data, and deep learning models, risk scenarios are identified in the basic mobility planning data to obtain risk scenario labels and / or suggested mobility speeds. Based on risk scenario labels and / or suggested movement speeds, semantic risk annotation is performed on basic mobility planning data to generate semantic risk identification results that include risk scenario labels and / or suggested movement speeds.

[0020] This disclosure enables scene semantic classification and speed-adaptive output, accurately identifies special risk scenarios, and enriches the risk expression capabilities of semantic dimensions.

[0021] In some embodiments of this disclosure, spatial risk identification results are obtained by performing motion risk identification based on sensor data, basic motion planning data, and deep learning models, including: Based on sensor data and deep learning models, safe passage areas are determined. Based on basic mobility planning data and safe passage areas, path risk identification is performed on the basic mobility planning data to obtain spatial risk identification results.

[0022] This disclosure constructs a safe passage zone using a deep learning model, verifies the rationality of the path from the perspective of spatial accessibility, and achieves accurate risk identification in the spatial dimension.

[0023] A third aspect of this disclosure provides a vehicle control device applied to a vehicle, the device comprising: The first generation unit is used to generate basic mobility planning data based on vehicle sensor data; The first transmitting unit is used to send basic mobility planning data and sensor data to the server; The first receiving unit is used to receive risk assessment results or remote security instructions generated based on risk assessment results sent by the server. The risk assessment results are generated based on basic mobility planning data and sensor data. The control unit is used to control the movement of the vehicle based on basic mobility planning data and in conjunction with remote safety commands or risk assessment results.

[0024] In some embodiments of this disclosure, the control unit is further configured to: Based on basic mobility planning data, and combined with remote safety commands, vehicle movement is controlled; or, Based on the risk assessment results, local safety commands for the vehicle are generated to control the vehicle's movement based on the basic mobility planning data and in combination with the local safety commands.

[0025] In some embodiments of this disclosure, the control unit is further configured to: Analyze the risk assessment results to identify semantic risk identification results and spatial risk identification results within the risk assessment results; If at least one of the semantic risk identification results and the spatial risk identification results indicates that there is a risk in the basic mobility planning data, then a local security instruction is generated based on at least one of the semantic risk identification results and the spatial risk identification results. When both semantic risk identification results and spatial risk identification results indicate that there is no risk in the basic mobility planning data, local security instructions are generated based on the basic mobility planning data.

[0026] A fourth aspect of this disclosure provides a vehicle control device applied to a server, the device comprising: The second receiving unit is used to receive basic mobility planning data and sensor data sent by the vehicle. The second generation unit is used to generate risk assessment results based on basic mobility planning data and sensor data, or to generate remote security instructions based on risk assessment results. The second sending unit is used to send remote safety commands or risk assessment results to the vehicle. The remote safety commands or risk assessment results are used to control the movement of the vehicle in conjunction with basic mobility planning data.

[0027] In some embodiments of this disclosure, the second generating unit is further configured to: Based on sensor data, basic mobility planning data, and deep learning models, mobility risk identification is performed to obtain semantic risk identification results and spatial risk identification results. Risk assessment results are generated based on semantic risk identification results and spatial risk identification results.

[0028] In some embodiments of this disclosure, the second generating unit is further configured to: If at least one of the semantic risk identification results or the spatial risk identification results in the risk assessment results indicates that there is a risk in the basic mobility planning data, a remote security command is generated based on at least one of the semantic risk identification results and the spatial risk identification results. When both semantic risk identification results and spatial risk identification results indicate that there is no risk, remote security instructions are generated based on basic mobility planning data.

[0029] In some embodiments of this disclosure, the second generating unit is further configured to: Based on sensor data, basic mobility planning data, and deep learning models, risk scenarios are identified in the basic mobility planning data to obtain risk scenario labels and / or suggested mobility speeds. Based on risk scenario labels and / or suggested movement speeds, semantic risk annotation is performed on basic mobility planning data to generate semantic risk identification results that include risk scenario labels and / or suggested movement speeds.

[0030] A fifth aspect of this disclosure provides a vehicle control system, including...

[0031] Vehicles and servers; The vehicle is used to perform the methods described in the first aspect of the present disclosure; The server is used to perform the methods described in the second aspect of this disclosure.

[0032] A sixth aspect of this disclosure provides a non-transitory computer-readable storage medium having computer instructions stored thereon for causing a computer to perform the methods described in the first or second aspect of this disclosure.

[0033] A seventh aspect of this disclosure provides a vehicle for performing the methods described in the first aspect of this disclosure, or including a vehicle control device as described in the third aspect of this disclosure.

[0034] An eighth aspect of this disclosure provides a computer program product that, when run on a computer, causes the computer to perform a method as described in any one of the first or second aspect embodiments of this disclosure.

[0035] In summary, the vehicle control method proposed in this disclosure can generate basic mobility planning data based on vehicle sensor data; send the basic mobility planning data and sensor data to a server; receive risk assessment results or remote safety commands generated based on the risk assessment results from the server; and perform vehicle mobility control based on the basic mobility planning data and in conjunction with the remote safety commands or risk assessment results, thereby constructing a dual-link collaborative safety redundancy control architecture to achieve linkage and cooperation between the vehicle and the server, and effectively improve the vehicle's environmental adaptability and risk identification and early warning accuracy during vehicle movement.

[0036] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0037] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure, and are not intended to unduly limit this disclosure.

[0038] Figure 1 A flowchart illustrating a vehicle control method provided in this embodiment of the present disclosure. Figure 1 ; Figure 2 A flowchart illustrating a vehicle control method provided in this embodiment of the present disclosure. Figure 2 ; Figure 3 A flowchart illustrating a vehicle control method provided in this embodiment of the present disclosure. Figure 3 ; Figure 4 A flowchart illustrating a vehicle control method provided in this embodiment of the present disclosure. Figure 4 ; Figure 5A schematic diagram of the structure of a vehicle control device provided in this embodiment of the present disclosure. Figure 1 ; Figure 6 A schematic diagram of the structure of a vehicle control device provided in this embodiment of the present disclosure. Figure 2 ; Figure 7 This is a schematic diagram of the structure of a vehicle control system provided in an embodiment of the present disclosure; Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure. Detailed Implementation

[0039] Embodiments of this disclosure are described in detail below. Examples of these embodiments are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this disclosure, and should not be construed as limiting this disclosure.

[0040] It should be noted that the acquisition, storage, use, and processing of data in this disclosed technical solution comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0041] It should also be noted that all data processed in this disclosure is data that has been explicitly authorized by the user or relevant party, and has been de-identified or anonymized before collection and use, and does not contain any personally identifiable information or user privacy content; all data is used only for vehicle control purposes, ensuring that data security and user privacy rights are fully protected while achieving technical effects.

[0042] In intelligent driving scenarios, current vehicle motion planning largely relies on a single link, which has significant limitations. On the one hand, the detection range of vehicle-side perception hardware (such as cameras and LiDAR) is limited; on the other hand, the vehicle's local computing power is constrained by size and power consumption, resulting in insufficient planning accuracy. This makes vehicles prone to misjudgment in complex environments (such as obstacle occlusion or unconventional object scenarios), leading to safety risks such as collisions and path deviations.

[0043] Taking specific scenarios as an example, current indoor (including underground parking) vehicle movement planning schemes are mainly divided into four categories, each with obvious shortcomings: 1) Radio frequency ranging solution: It requires the deployment of a large number of base stations or beacons, and the debugging and maintenance costs are high; at the same time, it is affected by the multipath effect, resulting in poor positioning accuracy and failing to meet the needs of accurate vehicle finding.

[0044] 2) UWB or millimeter-wave TOF solutions: High hardware costs and low terminal penetration rate, also relying on field deployment; and the metal structure of underground parking garages can easily cause signal attenuation, affecting the positioning effect.

[0045] 3) Vehicle-based visual positioning and mapping scheme: The sensor accuracy and computing performance of vehicles are relatively weak, resulting in low mapping accuracy; in addition, manual data collection is required, which further increases labor costs.

[0046] 4) Parking assistance map solution: Although a visual point cloud map with centimeter-level accuracy can be established by using cameras and LiDAR to meet the parking assistance needs, this type of map is only applicable to parking assistance scenarios and cannot be directly reused in other mobile scenarios.

[0047] It is evident that existing indoor vehicle mobility planning solutions generally suffer from high costs and poor accuracy, and cannot effectively reuse existing parking assistance visual point cloud map resources, making it difficult to balance economy, accuracy, and resource utilization.

[0048] Therefore, to address the aforementioned issues, this disclosure proposes a vehicle control method that establishes a dual-link collaborative mechanism between the vehicle and the server by introducing a server link. Leveraging the server's stronger computing power and more comprehensive environmental perception capabilities, this method achieves high-precision environmental perception and accurate risk assessment, thereby enhancing the vehicle's environmental adaptability and the accuracy of risk warnings during movement.

[0049] The specific details of this method are as follows.

[0050] Figure 1 A flowchart illustrating a vehicle control method provided in this embodiment of the present disclosure. Figure 1 .like Figure 1 As shown, this method is applied to a vehicle and may include the following steps.

[0051] Step 101: Generate basic mobility planning data based on the vehicle's sensor data.

[0052] In some embodiments, the vehicles disclosed herein can utilize their own perception capabilities and basic low-computing-power algorithms to generate basic mobility planning data that meets minimum safe operation requirements.

[0053] Specifically, vehicles can collect surrounding environmental data (such as obstacle locations, road boundaries, and their current position) through their onboard sensors (e.g., cameras, lidar, IMU inertial measurement units). This data is then processed by local algorithms (e.g., path planning and obstacle avoidance algorithms) to ultimately generate a path plan that meets basic mobility requirements—this is the basic mobility planning data. Basic mobility planning data can include the planned path (the specific travel trajectory from the current location to the target location), the planned speed (the speed plan corresponding to the planned trajectory, such as traveling at 5 m / s for one section and decelerating to 2 m / s for another), and the planned steering angle.

[0054] Among these features, when generating basic mobility planning data, vehicles can also perform local risk assessments on the basic mobility planning data to ensure that the basic mobility planning data meets the driving conditions on the vehicle side.

[0055] The vehicles mentioned in this disclosure can be any type of vehicle with mobility attributes (such as passenger cars, commercial vehicles, special-purpose vehicles, etc.), and are not limited in the embodiments of this disclosure.

[0056] Vehicle sensor data is multi-source fusion sensor data collected by the vehicle through various onboard sensors, including environmental and self-state data. Examples include environmental perception data (i.e., scene images captured by cameras, visual depth images, point cloud data scanned by LiDAR, millimeter-wave radar detection data, etc.) and position and attitude data (i.e., acceleration and angular velocity data collected by IMU, GPS / BeiDou positioning data, etc.).

[0057] Optionally, for vehicle-moving scenarios, the vehicle-side primarily focuses on basic safety operations, executing only low-computing-power algorithms to ensure the vehicle possesses basic driving capabilities and minimum safety guarantees. The vehicle can run basic functional modules locally, including perception (identifying nearby obstacles), localization (determining the current location), decision-making (generating basic driving logic), planning (outputting the initial driving path), and control (performing basic operations such as steering and acceleration), ensuring that it can maintain a minimum level of driving capability even without cloud support. Simultaneously, it collects real-time sensor data such as image frames and LiDAR point clouds, and generates basic movement planning data locally based on this sensor data.

[0058] Step 102: Send the basic mobility planning data and sensor data to the server.

[0059] In some embodiments, this disclosure introduces a server to perform more refined global risk verification by sending basic mobility planning data and sensor data to the server, thereby compensating for the limitations of vehicle-side computing power and perception.

[0060] A server is a computing node with high computing power, large-capacity storage, and global data access capabilities. This disclosure, by introducing the cloud-based high computing power of the server, performs in-depth analysis of perceived information based on complex algorithms such as deep learning, effectively improving the precision of risk identification and the accuracy of early warning, and achieving enhanced all-domain perception of the vehicle's driving environment.

[0061] Optionally, for vehicle-moving scenarios, the vehicle-side can use a data transmission network to upload the collected multi-source sensor data (such as real-time images, environmental point clouds, and its own positioning information) and locally generated basic mobility planning data to the cloud (i.e., the server) at high speed, ensuring the real-time performance and integrity of data transmission and providing data support for high-precision processing in the cloud.

[0062] For example, the vehicles and servers in this disclosure have been pre-associated. The association between the vehicles and servers can be pre-established in the following manner: 1) Vehicle initiates pairing: The vehicle sends a pairing request to the server. After receiving the pairing request, the server returns pairing confirmation information to the vehicle. Both parties complete two-way identity verification and confirmation, and establish the association between the vehicle and the server. 2) Server initiates pairing: The server sends a pairing request to the vehicle. After receiving the pairing request, the vehicle returns pairing confirmation information to the server. Both parties complete two-way identity verification and confirmation, and establish the association between the vehicle and the server.

[0063] 3) Pre-set binding in the background: The vehicle device identifier and server identifier are pre-entered in the server's management backend to complete the static binding configuration. After the vehicle goes online, it will automatically establish an association with the server. 4) Key-based identity authentication and binding: The vehicle and the server verify each other's identities based on a preset encryption key and a unique device identifier. Once the identity verification is successful, an association is automatically established. 5) Automatic local area network discovery: Vehicles and servers in the same communication local area network can detect each other through the device broadcast discovery mechanism. After a successful handshake negotiation, they can automatically establish an association.

[0064] Step 103: Receive the risk assessment results or remote security instructions generated based on the risk assessment results sent by the server.

[0065] In this disclosure, the risk assessment results are generated based on basic mobility planning data and sensor data.

[0066] In some embodiments, remote safety commands are generated by the server based on risk assessment results generated using a high-precision perception, risk identification, and security fusion strategy. These remote safety commands are used to control vehicle movement in conjunction with basic mobility planning data. Remote safety commands include, but are not limited to: deceleration commands, detour commands, braking commands, speed limit commands, path correction commands, maintaining current speed, and obstacle avoidance commands.

[0067] The risk assessment results are obtained by the server after identifying risks in the basic mobility planning data. They characterize whether security risks exist in the basic mobility planning data, the level of risk, and the location of the risk. Risk assessment results include, but are not limited to: presence or absence of risk, risk level, risk type, risk area, and risk confidence level.

[0068] In some embodiments, after the vehicle sends sensor data and basic mobility planning data to the server, the server can use complex algorithms (such as deep learning models) to perform reasoning analysis on the sensor data and basic mobility planning data to obtain remote safety instructions or risk assessment results, and then send the remote safety instructions or risk assessment results to the vehicle.

[0069] In some embodiments, the server may first identify the risk identification results (e.g., semantic risk identification results and spatial risk identification results) of the basic mobility planning data through deep learning models, sensor data, and basic mobility planning data, and then package the risk identification results as risk assessment results and send them to the vehicle.

[0070] In one embodiment, the server can first identify the risk identification results (such as semantic risk identification results and spatial risk identification results) of the basic mobility planning data through deep learning models, sensor data and basic mobility planning data, and then generate remote safety instructions based on the safety fusion strategy and risk identification results, and send the remote safety instructions to the vehicle.

[0071] Optionally, with further improvements in deep learning models, they can also incorporate security fusion strategies. That is, the server can use deep learning models, sensor data, and basic mobility planning data to identify the risk identification results of the basic mobility planning data, and directly generate remote security commands based on the risk identification results, and then send the remote security commands to the vehicle.

[0072] For example, any method for generating remote security commands can be selected based on actual needs, and there are no restrictions here. The security fusion strategy refers to the security determination rule that generates a corresponding security command if any risk identification result in the risk assessment indicates the existence of a risk.

[0073] Step 104: Based on the basic mobility planning data and combined with remote safety commands or risk assessment results, control the movement of the vehicle.

[0074] In some embodiments, the vehicle may receive a risk assessment result returned by the server after completing the risk identification of the basic mobility planning data, and control the vehicle's movement based on the risk assessment result.

[0075] Specifically, after the server completes the risk identification of the basic mobility planning data, it directly packages the generated risk identification results into risk assessment results (i.e., semantic risk identification results and spatial risk identification results) and sends them to the vehicles.

[0076] At this time, the vehicle analyzes the received risk assessment result, conducts a risk assessment on its own according to the safety integration strategy, and generates a local safety instruction to control the movement of the vehicle based on the basic movement planning data and the local safety instruction.

[0077] Among them, the local safety instructions include, but are not limited to: speed reduction instructions and avoidance instructions in the driving scenario, parking control instructions in the parking scenario, obstacle avoidance instructions in the reverse scenario, etc. After generating the local safety instruction, the present disclosure collaborates with the basic movement planning data to complete vehicle control; for example, if the local safety instruction is a speed reduction instruction, first determine the current reference driving speed corresponding to the basic movement planning data, and then jointly complete the movement control of the vehicle based on the reference driving speed and in cooperation with the speed reduction instruction.

[0078] In some embodiments, the vehicle can receive remote safety instructions generated by the server and control the movement of the vehicle according to the remote safety instructions and the basic movement planning data.

[0079] Among them, the remote safety instructions include, but are not limited to: speed reduction instructions and avoidance instructions in the driving scenario, parking control instructions in the parking scenario, obstacle avoidance instructions in the reverse scenario, etc. After generating the remote safety instruction, the present disclosure collaborates with the basic movement planning data to complete vehicle control; for example, if the local safety instruction is an avoidance instruction, first determine the basic driving path and planned driving posture (such as vehicle body orientation, turning angle, lateral offset position) corresponding to the basic movement planning data, and then jointly complete the movement control of the vehicle based on the reference driving path and planned driving posture and in cooperation with the avoidance instruction.

[0080] In summary, the above embodiments of the present disclosure can generate basic movement planning data based on the sensor data of the vehicle; send the basic movement planning data and sensor data to the server; receive the risk assessment result sent by the server or the remote safety instruction generated based on the risk assessment result, and the risk assessment result is generated based on the basic movement planning data and sensor data; based on the basic movement planning data, and in combination with the remote safety instruction or risk assessment result, perform movement control on the vehicle, realize the construction of a dual-link collaborative safety redundancy control architecture through the combination of vehicle-side local autonomous planning and server cloud intelligent decision-making, realize the linkage cooperation between the vehicle side and the server, and thus effectively improve the environmental adaptation ability and risk identification and warning accuracy during vehicle movement.

[0081] Figure 2 Schematic flow of a vehicle control method provided by an embodiment of the present disclosure Figure 2 . As Figure 2 shown, based on Figure 1 the embodiments shown, the method includes the following steps.

[0082] Step 201: If no remote security command or risk assessment result is received from the server within the preset feedback period, a preset safe movement mode is activated to control the movement of the vehicle under the preset safe movement mode.

[0083] In this disclosure, the preset safe movement mode is generated by the vehicle based on sensor data and basic movement planning data.

[0084] In some embodiments, the preset feedback time period is preset according to the vehicle's application scenario, communication environment and server processing efficiency, for example, 1-3 seconds. The specific duration can be dynamically adjusted and is not limited in this embodiment.

[0085] In this disclosure, if no remote safety command or risk assessment result is received within the preset feedback period, the vehicle will default to triggering a preset safe movement mode.

[0086] In this disclosure, the preset safe movement mode is a pre-configured safety plan for abnormal scenarios stored locally in the vehicle via an algorithm, or an abnormal scenario safety control strategy generated based on the vehicle's own sensor data and basic movement planning data. Its core objective is to ensure vehicle safety in the lowest-risk mode when the server link is interrupted (e.g., due to significant network latency or failure to return remote safety instructions or risk assessment results in a timely manner). The specific actions of this strategy may include, but are not limited to: dynamically reducing the movement speed, for example, lowering the speed value in the original basic movement planning data to below 50% (the specific percentage can be adapted according to the vehicle type, such as reducing passenger cars to below 10 km / h and special-purpose vehicles to below 0.5 m / s), reducing the risk of sudden collisions; in complex environments (e.g., densely populated areas, narrow passages) or when there is still no server feedback after the speed has dropped to the threshold, triggering a stop operation and prompting the driver to take over, thus avoiding risks.

[0087] Specifically, in cases where a preset safe movement mode is generated based on the vehicle's own sensor data and basic movement planning data, if the vehicle does not receive a remote safety command or risk assessment result from the server within a preset feedback period, the vehicle will generate the preset safe movement mode based on environmental data collected in real time by its own sensors and combined with the basic movement planning data. Since the vehicle only runs basic low-computing-power algorithms locally to maintain minimum safe operating capabilities, the sensor data used in this case is only the sensor data required for the operation of the vehicle's basic functional modules.

[0088] For example, a vehicle can use sensor data to identify the distribution of obstacles, road boundaries, and passable space around the vehicle. Combined with the original driving path, planned speed, and driving posture in the basic mobility planning data, it can determine the safe stopping area or low-speed avoidance path for the current vehicle. Then, it can generate control logic adapted to the scenario, such as controlling the vehicle to drive at a low speed of no more than 5 km / h along the adjusted planned path, and continuously monitoring the surrounding environment in real time through sensors. If an obstacle is detected ahead, it can avoid the obstacle or stop the vehicle in time, and prompt the driver to take over, based on the basic mobility planning data.

[0089] It should be noted that the execution of the preset safe movement mode is not permanent. Its termination conditions include two scenarios: First, the vehicle receives a remote control command or risk assessment result resent by the server. At this time, the vehicle will switch to moving according to the remote control command or risk assessment result. Second, it receives a manual intervention command, that is, the driver takes over to ensure that the vehicle is always in a controllable and safe state.

[0090] Optionally, for vehicle movement scenarios, this disclosure can monitor the transmission network status in real time. If the network delay exceeds a preset threshold (e.g., delay > 500ms) or the network is interrupted (i.e., the vehicle does not receive remote safety instructions or risk assessment results within a preset feedback period), the vehicle will immediately reduce its speed and switch to a preset safe movement mode (relying only on the local low-computing-power module to maintain safe driving) until the network is restored or a manual intervention instruction is received.

[0091] In summary, the above embodiments of this disclosure can ensure the safe operation of vehicles when the link is abnormal by using a fault-tolerant scheme that triggers a preset safe movement mode after a timeout, thereby improving the environmental adaptability and the accuracy of risk warnings when vehicles are moving.

[0092] Figure 3 A flowchart illustrating a vehicle control method provided in this embodiment of the present disclosure. Figure 3 .like Figure 3 As shown, this method is applied to a server and may include the following steps.

[0093] Step 301: Receive basic mobility planning data and sensor data sent by the vehicle.

[0094] In this disclosure, the basic mobility planning data is generated by the vehicle based on sensor data.

[0095] In some embodiments, the server may receive data via a preset communication protocol.

[0096] During the data reception process, the server can also perform data validity verification: verifying data integrity by determining whether basic motion planning data (such as path coordinates and speed information) and sensor data (such as images, point clouds, and positioning data) are missing, thus avoiding subsequent detection errors due to incomplete data; and verifying data timeliness by determining whether the interval between the data generation time and the reception time exceeds a preset threshold (such as 500ms). If the timeout occurs, it is determined as "data invalid," and an instruction to re-upload the data is sent to the vehicle, ensuring that the server conducts detection based on the latest environmental and planning information.

[0097] In addition, if multiple vehicles upload data at the same time, the server can also classify and store the data by vehicle unique identifier (such as vehicle ID) to avoid data confusion between different vehicles and provide a basis for subsequent targeted risk identification.

[0098] Step 302: Based on basic mobility planning data and sensor data, generate risk assessment results or remote security instructions, wherein the remote security instructions are generated based on the risk assessment results.

[0099] In some embodiments, remote safety commands are generated by the server based on risk assessment results generated using a high-precision perception, risk identification, and security fusion strategy. These remote safety commands are used to control vehicle movement in conjunction with basic mobility planning data. Remote safety commands include, but are not limited to: deceleration commands, detour commands, braking commands, speed limit commands, path correction commands, maintaining current speed, and obstacle avoidance commands.

[0100] The risk assessment results are obtained by the server after identifying risks in the basic mobility planning data. They characterize whether security risks exist in the basic mobility planning data, the level of risk, and the location of the risk. Risk assessment results include, but are not limited to: presence or absence of risk, risk level, risk type, risk area, and risk confidence level.

[0101] In some embodiments, after the vehicle sends sensor data and basic mobility planning data to the server, the server can use complex algorithms (such as deep learning models) to perform reasoning analysis on the sensor data and basic mobility planning data to obtain remote safety instructions or risk assessment results.

[0102] In one alternative embodiment, the server can first identify the risk identification results (e.g., semantic risk identification results and spatial risk identification results) of the basic mobility planning data through deep learning models, sensor data, and basic mobility planning data, and then generate remote security instructions based on the security fusion strategy and the risk identification results.

[0103] In some alternative embodiments, the server may first identify the risk identification results (e.g., semantic risk identification results and spatial risk identification results) of the basic mobility planning data through deep learning models, sensor data, and basic mobility planning data, and then package the risk identification results as risk assessment results.

[0104] In some optional embodiments, as the deep learning model is further improved, the deep learning model can also incorporate security fusion strategies. The server can use the deep learning model, sensor data, and basic mobility planning data to identify the risk identification results of the basic mobility planning data, and directly generate remote security commands based on the risk identification results.

[0105] For example, when generating remote security commands, the server can either generate them directly from a deep learning model, or it can first generate risk assessment results from a deep learning model, and then generate remote security commands based on the security fusion strategy and the risk assessment results. The server can choose either method to generate remote security commands according to actual needs, and there are no restrictions here.

[0106] Step 303: Send remote security instructions or risk assessment results to the vehicle.

[0107] In this disclosure, remote security commands or risk assessment results are used in conjunction with basic mobility planning data to control vehicle mobility.

[0108] In some embodiments, after generating remote security instructions or risk assessment results, the server can feed back the remote security instructions or risk assessment results to the vehicle.

[0109] In some embodiments, the server may add a checksum to the remote security command or risk assessment result (such as security control command parameters or risk identification result details) before sending it. After receiving the remote security command or risk assessment result, the vehicle can verify whether the remote security command or risk assessment result has been damaged in transmission through the checksum. If the verification fails, the vehicle will send a retransmission request to the server, and the server will resend it within a preset number of times (such as 3 times) to avoid the delay caused by multiple retransmissions affecting vehicle control.

[0110] In some embodiments, after the server sends a remote security instruction or risk assessment result, it may also wait for the vehicle to return a confirmation instruction. If no confirmation instruction is received within a preset confirmation time (e.g., 500ms), the server will determine that the current remote security instruction or risk assessment result has failed to be sent. At this time, it can automatically switch to a backup communication link (e.g., switch from cellular network to local area network) to retry until the vehicle is confirmed to have successfully received the instruction.

[0111] In summary, the embodiments disclosed above can receive basic mobility planning data and sensor data sent by a vehicle, whereby the basic mobility planning data is generated by the vehicle based on the sensor data; based on the basic mobility planning data and sensor data, a risk assessment result or remote safety command is generated, wherein the remote safety command is generated based on the risk assessment result; the remote safety command or risk assessment result is sent to the vehicle, and the remote safety command or risk assessment result is used to control the vehicle's movement in conjunction with the basic mobility planning data. This achieves dual-link collaborative control between the vehicle and the server, leveraging the server's stronger computing power and more global environmental perception capabilities to improve the vehicle's environmental adaptability and the accuracy of risk warnings during movement.

[0112] Figure 4 A flowchart illustrating a vehicle control method provided in this embodiment of the present disclosure. Figure 4 .like Figure 4 As shown, based on Figure 3 The illustrated embodiment shows that the method includes the following steps.

[0113] Step 401: Based on sensor data, basic mobility planning data, and deep learning models, mobility risk identification is performed to obtain semantic risk identification results and spatial risk identification results.

[0114] In some embodiments, when the server performs risk identification on basic mobility planning data, it can achieve parallel processing through dual links, namely a semantic understanding link and a spatial verification link, to further improve the integrity and environmental adaptability of the basic mobility planning data.

[0115] In some embodiments, for semantic understanding links, this disclosure can identify potential risk scenarios from environmental description and planning data, that is, transform perceived data into understandable semantic information for risk assessment.

[0116] In some embodiments, this disclosure can convert environmental data (such as a dynamic obstacle 5 meters away or a construction area ahead) and basic movement planning data (such as a plan to travel straight for 20 meters at a speed of 10 m / s) from sensor data into structured natural language text to achieve machine-understandable semantic expression. Then, the natural language text is input into a preset language model (such as a risk identification model trained on a scene). The deep learning model outputs two key pieces of information through semantic analysis: risk scene labels (such as dynamic obstacle avoidance risk or construction area intrusion risk) and a suggested movement speed adapted to the current scene (such as a suggestion to decelerate to 3 m / s). Finally, based on the risk scene labels (including risk type and location) and the suggested movement speed, a semantic risk identification result is generated to determine whether there is a risk in the basic movement plan from a semantic logic level.

[0117] Among them, the deep learning model disclosed herein is a vision-language model. The vision-language model can identify special scenes in images (such as construction areas, blind spots, transparent objects, water reflections, and other scenes that are easily misjudged by the vehicle), and output the corresponding risk scene labels (such as "construction area - high risk") and the recommended movement speed adapted to the scene.

[0118] In some embodiments, for spatial verification links, this disclosure can identify path risks from 3D environment reconstruction and path matching. That is, this disclosure can determine safe passage areas based on sensor data and deep learning models; and identify path risks based on basic mobility planning data and safe passage areas to obtain spatial risk identification results.

[0119] In some embodiments, determining the safe passage area specifically includes: constructing a three-dimensional environmental mesh containing environmental details based on sensor data (such as lidar point clouds and depth images) and a deep learning model; dividing the empty areas without physical obstructions according to the object occupancy status of each spatial unit in the three-dimensional environmental mesh (such as being occupied by walls / obstacles or being vacant); performing connectivity analysis on the empty areas (such as determining whether each area can reach each other) and combining them to obtain at least one independent connected area; filtering candidate passage areas from at least one connected area based on the vehicle's three-dimensional dimensions (such as length / width / height) contained in the sensor data; and performing three-dimensional expansion processing on the candidate passage areas using a preset safety distance (such as maintaining a 0.5-meter redundancy with obstacles) to obtain an expanded safe and feasible passage.

[0120] Specifically, path risk identification in the spatial verification link includes: calculating the overlap between the planned path in the basic mobility planning data and the safe passage area (e.g., the proportion of the path length falling within the safe area to the total length); if the overlap is less than a preset threshold (e.g., 80%), the planned path is determined to have a risk, and the risky locations deviating from the safe area are marked on the path (e.g., a sequence of coordinate points); if the overlap is greater than or equal to the preset threshold, the planned path is determined to have no risk.

[0121] If the planned path has risks, the planned path in the basic mobility planning data is adjusted based on the marked risk locations (such as replanning to bypass the risk area) to obtain updated mobility planning data. Then, based on information such as whether there are risks, the risk locations in the updated mobility planning data, and the updated mobility planning path (if any), spatial risk identification results are generated to verify the safety of the basic mobility planning from a spatial physical level.

[0122] Step 402: Based on the semantic risk identification results and spatial risk identification results, generate risk assessment results.

[0123] In some embodiments, this disclosure uses the identification results of two links to form the final risk assessment result, thereby achieving cross-validation of semantic risk and spatial risk.

[0124] In some embodiments, the server can integrate the semantic risk identification results and spatial risk identification results into a risk assessment result and send it to the vehicle, which then generates local safety instructions. Alternatively, remote safety instructions can be generated based on the generated risk assessment result (i.e., a risk assessment result that includes both semantic and spatial risk identification results).

[0125] For situations where the server generates remote safety instructions based on risk assessment results: If at least one of the semantic risk identification results or spatial risk identification results in the risk assessment results indicates the existence of risk, remote safety instructions are generated based on the risk information in at least one of the semantic risk identification results or spatial risk identification results (i.e., the risk identification result indicating the existence of risk). For example, risk information such as the calculated safe passage area and risk label are compared with the basic planned route uploaded by the vehicle. If a path conflict is found (such as the planned route deviating from the safe passage) or potential hazards (such as the route passing through a high-risk area), remote safety instructions such as slowing down to 20km / h, detouring, or emergency braking are generated. Alternatively, if neither the semantic risk identification result nor the spatial risk identification result indicates no risk, remote safety instructions are generated based on the basic mobility planning data, and a no-risk prompt is generated at the same time to make the vehicle execute the original plan.

[0126] For scenarios where the server integrates semantic risk identification results and spatial risk identification results into a risk assessment result and sends it to the vehicle, and the vehicle then generates local safety instructions: the server directly packages the semantic risk identification results (semantic risk information) and spatial risk identification results (spatial risk information) into a risk assessment result and sends it to the vehicle, which then autonomously makes decisions to generate local safety instructions.

[0127] In summary, the above embodiments of this disclosure can cover both scenario risks at the textual description level (such as semantic misjudgment in unconventional environments) and path feasibility issues at the physical space level (such as whether there will be collisions with obstacles) through dual-dimensional verification of semantic understanding and spatial verification. Ultimately, this achieves comprehensive risk identification for movement planning and provides a reliable basis for subsequent safety control.

[0128] Figure 5 A schematic diagram of the structure of a vehicle control device 500 provided in this embodiment of the present disclosure. Figure 1 The device is configured in a vehicle and includes: The first generation unit 510 is used to generate basic mobility planning data based on vehicle sensor data. The first transmitting unit 520 is used to transmit basic mobility planning data and sensor data to the server; The first receiving unit 530 is used to receive risk assessment results or remote security instructions generated based on risk assessment results sent by the server. The risk assessment results are generated based on basic mobility planning data and sensor data. Control unit 540 is used to control the movement of the vehicle based on basic mobility planning data and in conjunction with remote safety commands or risk assessment results.

[0129] In some embodiments of this disclosure, the control unit 540 is further configured to: Based on basic mobility planning data, and combined with remote safety commands, vehicle movement is controlled; or, Based on the risk assessment results, local safety commands for the vehicle are generated to control the vehicle's movement based on the basic mobility planning data and in combination with the local safety commands.

[0130] In some embodiments of this disclosure, the control unit 540 is further configured to: Analyze the risk assessment results to identify semantic risk identification results and spatial risk identification results within the risk assessment results; If at least one of the semantic risk identification results and the spatial risk identification results indicates that there is a risk in the basic mobility planning data, then a local security instruction is generated based on at least one of the semantic risk identification results and the spatial risk identification results; or, When both semantic risk identification results and spatial risk identification results indicate that there is no risk in the basic mobility planning data, local security instructions are generated based on the basic mobility planning data.

[0131] In some embodiments of this disclosure, the control unit 540 is further configured to: If no remote security command or risk assessment result is received from the server within the preset feedback period, a preset safe movement mode is activated; the preset safe movement mode is generated by the vehicle based on sensor data and basic movement planning data. In the preset safe movement mode, the vehicle's movement is controlled.

[0132] Figure 6 A schematic diagram of the structure of a vehicle control device 600 provided in this embodiment of the present disclosure. Figure 2 The device is configured on a server and includes: The second receiving unit 610 is used to receive basic mobility planning data and sensor data sent by the vehicle; The second generation unit 620 is used to generate risk assessment results or remote security instructions based on basic mobility planning data and sensor data, wherein the remote security instructions are generated based on the risk assessment results. The second sending unit 630 is used to send remote safety commands or risk assessment results to the vehicle. The remote safety commands or risk assessment results are used to control the movement of the vehicle in conjunction with basic mobility planning data.

[0133] In some embodiments of this disclosure, the second generation unit 620 is further configured to: Based on sensor data, basic mobility planning data, and deep learning models, mobility risk identification is performed to obtain semantic risk identification results and spatial risk identification results. Risk assessment results are generated based on semantic risk identification results and spatial risk identification results.

[0134] In some embodiments of this disclosure, the second generation unit 620 is further configured to: If at least one of the semantic risk identification results or the spatial risk identification results in the risk assessment indicates that there is a risk in the basic mobility planning data, a remote security command is generated based on at least one of the semantic risk identification results and the spatial risk identification results; or, When both semantic risk identification results and spatial risk identification results indicate that there is no risk, remote security instructions are generated based on basic mobility planning data.

[0135] In some embodiments of this disclosure, the second generation unit 620 is further configured to: Based on sensor data, basic mobility planning data, and deep learning models, risk scenarios are identified in the basic mobility planning data to obtain risk scenario labels and / or suggested mobility speeds. Based on risk scenario labels and / or suggested movement speeds, semantic risk annotation is performed on basic mobility planning data to generate semantic risk identification results that include risk scenario labels and / or suggested movement speeds.

[0136] In some embodiments of this disclosure, the second generation unit 620 is further configured to: Based on sensor data and deep learning models, safe passage areas are determined. Based on basic mobility planning data and safe passage areas, path risk identification is performed on the basic mobility planning data to obtain spatial risk identification results.

[0137] Figure 7 This is a schematic diagram of the structure of a vehicle control system 700 provided in an embodiment of this disclosure. Figure 7 As shown, the system includes: Vehicle 710 and server 720; Vehicle 710 is used to generate basic mobility planning data based on sensor data and send the basic mobility planning data and sensor data to the server; and to perform mobility control on the vehicle based on the basic mobility planning data and in conjunction with remote safety commands or risk assessment results.

[0138] Server 720 is used to generate risk assessment results or remote safety commands based on basic mobility planning data and sensor data, wherein the remote safety commands are generated based on the risk assessment results; and to send remote control commands or risk assessment results to the vehicle.

[0139] For example, the specific implementation process of vehicle 710 in this disclosure can be referred to the above. Figures 1 to 2 In the embodiment shown, server 720 can refer to the above description. Figures 3 to 4 The embodiments shown will not be described in detail here.

[0140] The methods and systems provided in the embodiments of this disclosure have been described above. To implement the functions of the methods provided in the embodiments of this disclosure, the electronic device may include hardware structures and software modules, implementing the above functions in the form of hardware structures, software modules, or a combination of hardware structures and software modules. One of the above functions may be executed in the form of hardware structures, software modules, or a combination of hardware structures and software modules.

[0141] Figure 8 This is a block diagram illustrating an electronic device 800 for implementing the above-described method according to an exemplary embodiment. For example, the electronic device 800 may be a vehicle, or a terminal or control component configured on a vehicle, etc.

[0142] Reference Figure 8 The electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input / output (I / O) interface 812, a sensor component 814, and a communication component 816.

[0143] Processing component 802 typically controls the overall operation of electronic device 800, such as operations associated with display, telephone calls, data communication, camera operation, and recording operations. Processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the methods described above. Furthermore, processing component 802 may include one or more modules to facilitate interaction between processing component 802 and other components. For example, processing component 802 may include a multimedia module to facilitate interaction between multimedia component 808 and processing component 802.

[0144] Memory 804 is configured to store various types of data to support the operation of electronic device 800. Examples of such data include instructions for any application or method operating on electronic device 800, contact data, phonebook data, messages, pictures, videos, etc. Memory 804 can be implemented by 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.

[0145] Power supply component 806 provides power to various components of electronic device 800. Power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to electronic device 800.

[0146] Multimedia component 808 includes a screen that provides an output interface between electronic device 800 and a user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touchscreen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensors may sense not only the boundaries of touch or swipe actions but also the duration and pressure associated with the touch or swipe operation. In some embodiments, multimedia component 808 includes a front-facing camera and / or a rear-facing camera.

[0147] Audio component 810 is configured to output and / or input audio signals. For example, audio component 810 includes a microphone (MIC) configured to receive external audio signals when electronic device 800 is in an operating mode, such as call mode, recording mode, and voice recognition mode. The received audio signals may be further stored in memory 804 or transmitted via communication component 816. In some embodiments, audio component 810 also includes a speaker for outputting audio signals.

[0148] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include, but are not limited to, home buttons, volume buttons, power buttons, and lock buttons.

[0149] Sensor assembly 814 includes one or more sensors for providing state assessments of various aspects of electronic device 800. For example, sensor assembly 814 can detect the on / off state of electronic device 800, the relative positioning of components such as the display and keypad of electronic device 800, changes in position of electronic device 800 or a component of electronic device 800, the presence or absence of user contact with electronic device 800, orientation or acceleration / deceleration of electronic device 800, and temperature changes of electronic device 800. Sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 814 may also include an accelerometer, gyroscope, magnetometer, pressure sensor, or temperature sensor.

[0150] Communication component 816 is configured to facilitate wired or wireless communication between electronic device 800 and other devices. Electronic device 800 can access a wireless network based on communication standards. In one exemplary embodiment, communication component 816 receives broadcast signals or broadcast-related information from an external broadcast management system via a broadcast channel.

[0151] In an exemplary embodiment, the electronic device 800 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), controllers, microcontrollers, microprocessors, or other electronic components to perform the methods described above.

[0152] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, which can be executed by a processor 820 of an electronic device 800 to perform the above-described method. For example, the non-transitory computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0153] Embodiments of this disclosure also provide a non-transitory computer-readable storage medium having computer instructions stored thereon for causing a computer to perform the methods described in the above embodiments of this disclosure.

[0154] Embodiments of this disclosure also propose a vehicle for performing the functions described above. Figure 1 , Figure 2The vehicle described in the illustrated embodiments includes a vehicle control device as described in the above embodiments of this disclosure, or a vehicle control system as described in the above embodiments of this disclosure, or electronic equipment as described in the above embodiments of this disclosure.

[0155] Embodiments of this disclosure also provide a computer program product, including a computer program that is executed by a processor using the methods described in the above embodiments of this disclosure.

[0156] It should be noted that the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this disclosure described herein can be implemented in orders other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of systems and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0157] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in at least one embodiment or example.

[0158] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing a particular logical function or process, and the scope of the preferred embodiments of the invention includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as will be understood by those skilled in the art to which embodiments of the invention pertain.

[0159] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processing module, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having at least one wire (vehicle control method), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic device, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0160] It should be understood that various parts of the embodiments of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0161] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0162] Furthermore, the functional units in the various embodiments of the present invention can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc.

[0163] Although embodiments of the present invention have been shown and described above, these embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A vehicle control method, characterized in that, The method is applied to a vehicle, and the method includes: Based on the sensor data of the vehicle, basic mobility planning data is generated; The basic mobility planning data and the sensor data are sent to the server; Receive risk assessment results or remote security commands generated based on the risk assessment results sent by the server, wherein the risk assessment results are generated based on the basic mobility planning data and the sensor data; Based on the basic mobility planning data, and in conjunction with the remote security command or the risk assessment results, the vehicle is controlled for mobility.

2. The method according to claim 1, characterized in that, The process of controlling the vehicle's movement based on the basic mobility planning data and in conjunction with the remote security command or the risk assessment result includes: Based on the aforementioned basic mobility planning data, and in conjunction with the remote safety commands, the vehicle's mobility is controlled; or, Based on the risk assessment results, local safety commands for the vehicle are generated to control the vehicle's movement based on the basic mobility planning data and in conjunction with the local safety commands.

3. The method according to claim 2, characterized in that, The process of generating local safety commands for the vehicle based on the risk assessment results includes: Analyze the risk assessment results to determine the semantic risk identification results and spatial risk identification results in the risk assessment results; If at least one of the semantic risk identification results and the spatial risk identification results indicates that the basic mobility planning data poses a risk, then the local security instruction is generated based on at least one of the semantic risk identification results and the spatial risk identification results; or, If both the semantic risk identification result and the spatial risk identification result indicate that there is no risk in the basic mobility planning data, the local security instruction is generated based on the basic mobility planning data.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: If no remote security command or risk assessment result is received from the server within a preset feedback period, a preset safe movement mode is activated; wherein, the preset safe movement mode is generated by the vehicle based on the sensor data and the basic movement planning data; In the preset safe movement mode, the vehicle is moved and controlled.

5. A vehicle control method, characterized in that, The method is applied to a server, and the method includes: The system receives basic mobility planning data and sensor data sent by the vehicle, wherein the basic mobility planning data is generated by the vehicle based on the sensor data. Based on the basic mobility planning data and the sensor data, a risk assessment result or a remote security command is generated; wherein, the remote security command is generated based on the risk assessment result. The remote safety command or the risk assessment result is sent to the vehicle, and the remote safety command or the risk assessment result is used to control the movement of the vehicle in conjunction with the basic mobility planning data.

6. The method according to claim 5, characterized in that, The risk assessment results generated based on the basic mobility planning data and the sensor data include: Based on the sensor data, the basic mobility planning data, and the deep learning model, mobility risk identification is performed to obtain semantic risk identification results and spatial risk identification results. The risk assessment result is generated based on the semantic risk identification result and the spatial risk identification result.

7. The method according to claim 5, characterized in that, The remote security command is generated based on the risk assessment results and includes: If at least one of the semantic risk identification results or the spatial risk identification results in the risk assessment results indicates that the basic mobility planning data poses a risk, the remote security command is generated based on at least one of the semantic risk identification results and the spatial risk identification results; or, If both the semantic risk identification result and the spatial risk identification result indicate that there is no risk, the remote security instruction is generated based on the basic mobility planning data.

8. The method according to claim 6, characterized in that, Based on the sensor data, the basic mobility planning data, and the deep learning model, mobility risk identification is performed, and the semantic risk identification results include: Based on the sensor data, the basic mobility planning data, and the deep learning model, risk scenarios are identified in the basic mobility planning data to obtain risk scenario labels and / or suggested mobility speeds from the basic mobility planning data. Based on the risk scenario labels and / or the suggested movement speed, semantic risk labeling is performed on the basic movement planning data to generate a semantic risk identification result containing the risk scenario labels and / or the suggested movement speed.

9. The method according to claim 6, characterized in that, Based on the sensor data, the basic mobility planning data, and the deep learning model, mobility risk identification is performed, and the spatial risk identification results include: Based on the sensor data and the deep learning model, a safe passage area is determined; Based on the basic mobility planning data and the safe passage area, path risk identification is performed on the basic mobility planning data to obtain the spatial risk identification result.

10. A vehicle control device, characterized in that, The device is applied to a vehicle, and the device includes: The first generation unit is used to generate basic mobility planning data based on the sensor data of the vehicle. The first sending unit is used to send the basic mobility planning data and the sensor data to the server; The first receiving unit is configured to receive a risk assessment result or a remote security instruction generated based on the risk assessment result sent by the server, wherein the risk assessment result is generated based on the basic mobility planning data and the sensor data. The control unit is used to control the movement of the vehicle based on the basic mobility planning data and in conjunction with the remote safety command or the risk assessment result.

11. The apparatus according to claim 10, characterized in that, The control unit is also used for: Based on the aforementioned basic mobility planning data, and in conjunction with the remote safety commands, the vehicle's mobility is controlled; or, Based on the risk assessment results, local safety commands for the vehicle are generated to control the vehicle's movement based on the basic mobility planning data and in conjunction with the local safety commands.

12. The apparatus according to claim 11, characterized in that, The control unit is also used for: Analyze the risk assessment results to determine the semantic risk identification results and spatial risk identification results in the risk assessment results; If at least one of the semantic risk identification results and the spatial risk identification results indicates that the basic mobility planning data is at risk, then the local security instruction is generated based on at least one of the semantic risk identification results and the spatial risk identification results. or, If both the semantic risk identification result and the spatial risk identification result indicate that there is no risk in the basic mobility planning data, the local security instruction is generated based on the basic mobility planning data.

13. A vehicle control device, characterized in that, The device is used in a server, and the device includes: The second receiving unit is used to receive basic mobility planning data and sensor data sent by the vehicle. The second generation unit is used to generate a risk assessment result or a remote security instruction based on the basic mobility planning data and the sensor data; wherein the remote security instruction is generated based on the risk assessment result. The second sending unit is used to send the remote security command or the risk assessment result to the vehicle, wherein the remote security command or the risk assessment result is used to perform motion control on the vehicle in conjunction with the basic mobility planning data.

14. The apparatus according to claim 13, characterized in that, The second generating unit is further configured to: Based on the sensor data, the basic mobility planning data, and the deep learning model, mobility risk identification is performed to obtain semantic risk identification results and spatial risk identification results. The risk assessment result is generated based on the semantic risk identification result and the spatial risk identification result.

15. The apparatus according to claim 14, characterized in that, The second generating unit is further configured to: If at least one of the semantic risk identification result and the spatial risk identification result in the risk assessment result indicates that there is a risk in the basic mobility planning data, the remote security instruction is generated based on at least one of the semantic risk identification result and the spatial risk identification result. or, If both the semantic risk identification result and the spatial risk identification result indicate that there is no risk, the remote security instruction is generated based on the basic mobility planning data.

16. The apparatus according to claim 14, characterized in that, The second generating unit is further configured to: Based on the sensor data, the basic mobility planning data, and the deep learning model, risk scenarios are identified in the basic mobility planning data to obtain risk scenario labels and / or suggested mobility speeds from the basic mobility planning data. Based on the risk scenario labels and / or the suggested movement speed, semantic risk labeling is performed on the basic movement planning data to generate a semantic risk identification result containing the risk scenario labels and / or the suggested movement speed.

17. A vehicle control system, characterized in that, The system includes: Vehicles and servers; The vehicle is used to perform the steps of the method according to any one of claims 1-4; The server is used to perform the steps of the method according to any one of claims 5-9.

18. A non-transitory computer-readable storage medium, characterized in that, It stores computer instructions that cause the computer to perform the method according to any one of claims 1-9.

19. A vehicle, characterized in that, The vehicle is used to perform the method as described in any one of claims 1-4, or includes the vehicle control device as described in claims 10-12.

20. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-9.

Images