Automatic driving control method based on vehicle-road cloud coordination

Abstract

The invention discloses an automatic driving control method based on vehicle-road cloud cooperation, and the method comprises the steps: transmitting obstacle, weather and local road condition information to a vehicle end and a cloud end through a road end, and giving a local speed curve of the road end; through vehicle-road cloud global information sharing, the vehicle end marks timestamps on data sent by the cloud end and the road end so as to match corresponding sensing results, and a vehicle end speed curve is generated according to the vehicle end sensing results and road end road condition information; the cloud end gives a cloud end global speed curve according to a navigation planning route of the vehicle and a sensing result of a corresponding road end on the planning route in combination with global traffic flow, historical data and high-precision map information; and adjusting weights corresponding to the cloud end, the road end and the vehicle end, and planning a final speed curve, so that the vehicle performs self-vehicle tracking execution according to the final speed curve. The intelligent level of automatic driving of the vehicle can be improved, and the use comfort of a user is improved.

Description

Technical Field

[0001] This invention relates to the technical field of vehicle-road-cloud cooperative control, and more specifically, to an autonomous driving control method based on vehicle-road-cloud cooperation. Background Technology

[0002] Vehicle-Road-Cloud Collaboration (VRCC) is a technological system that integrates multi-dimensional data from vehicles, road infrastructure (roadside equipment), and cloud platforms to achieve real-time information sharing and collaborative decision-making. Through global information sharing and distributed intelligent decision-making, VRCC upgrades the longitudinal control of autonomous vehicles from "single-vehicle intelligence" to "system intelligence," significantly improving safety in complex scenarios (e.g., reducing rear-end collisions by 70%) and traffic efficiency (e.g., increasing road capacity by 30%). However, in existing autonomous driving applications, unreasonable route planning and speed settings can easily occur, resulting in insufficient flexibility and a poor user experience. Therefore, how to utilize VRCC to improve the intelligence level of autonomous driving is of great significance. Summary of the Invention

[0003] This invention provides an autonomous driving control method based on vehicle-road-cloud collaboration, which solves the problem that existing vehicles using vehicle-road-cloud collaboration have unreasonable route planning and driving speed, which easily leads to poor user experience. It can improve the intelligence level of vehicle autonomous driving and increase user comfort.

[0004] To achieve the above objectives, the present invention provides the following technical solution:

[0005] An autonomous driving control method based on vehicle-road-cloud cooperation includes:

[0006] The system transmits information about obstacles, weather, and local road conditions to the vehicle and cloud via the roadside, and provides local speed curves from the roadside.

[0007] Through global information sharing between vehicle, road, and cloud, data sent from the vehicle to the cloud and roadside is timestamped to match the corresponding perception results, and a vehicle speed curve is generated based on the vehicle perception results and roadside road condition information.

[0008] Based on the vehicle's navigation route planning and the perception results of the corresponding road ends on the planned route, combined with global traffic flow, historical data and high-precision map information, the cloud provides a global speed curve.

[0009] Adjust the weights corresponding to the cloud, road, and vehicle ends, plan the final speed curve, and enable the vehicle to perform self-tracking execution according to the final speed curve.

[0010] Preferred options also include:

[0011] The vehicle-to-infrastructure (V2I) network, through which vehicle-road-cloud collaboration is used, transmits vehicle location, driving route, vehicle status information, and perceived surrounding environment to the roadside and cloud.

[0012] Preferably, the matching of the corresponding perception results includes:

[0013] The vehicle-side system matches the perception results from the roadside with its own perception results to obtain the historical trajectory of the currently perceived obstacle. The historical trajectory is used to obtain a more accurate prediction result for longitudinal motion control. When communication is blocked, the data verified in the previous frame is used to make a prediction to predict the position and speed of the obstacle.

[0014] Preferably, adjusting the weights corresponding to the cloud, road, and vehicle terminals includes:

[0015] The weights of cloud, roadside, and vehicle-side terminals are dynamically adjusted based on road conditions and communication status.

[0016] If the road conditions are good and the road is mostly straight, then the weight corresponding to the cloud should be set higher than the weight corresponding to the vehicle and road ends.

[0017] If the road conditions are poor or the road is mostly curved, then the weight corresponding to the road end should be set higher than the weight corresponding to the cloud end and the vehicle end.

[0018] If the communication signal at the vehicle's location is poor or the speed curves corresponding to the cloud and roadside locations differ from the set value, then the vehicle's location will take precedence, and the weight corresponding to the vehicle's location will be set higher than the weight corresponding to the cloud and roadside locations.

[0019] Preferably, the process of planning the final velocity curve includes:

[0020] Set basic weights for the cloud, vehicle, and roadside;

[0021] To assess road conditions, the road is described based on factors such as pothole severity, congestion coefficient, straight road ratio, and curvature factor. The road conditions are then quantified, and weights are determined based on the quantified road condition data.

[0022] The communication quality is judged based on signal strength and latency. When the signal strength is less than the threshold or the latency exceeds 200ms, the weight of the corresponding data source is reset to 0.

[0023] Speed ​​curve difference judgment is based on the difference between the cloud speed and the road speed. When the cumulative difference exceeds a certain threshold, the corresponding weight is set to a set value.

[0024] The weights corresponding to the cloud, vehicle, and road terminals are normalized to ensure that the sum of the weights is 1.

[0025] The final velocity curve is generated through weighted fusion.

[0026] Preferably, the step of generating the final velocity curve through weighted fusion includes:

[0027] According to the formula: The final velocity curve is generated by fusion, where, Global speed curve in the cloud. Local speed curve at the end of the road, Vehicle end speed curve, Cloud-based weighting coefficients Roadside weighting coefficient Vehicle-side weighting coefficient.

[0028] Preferably, the step of generating the final velocity curve through weighted fusion further includes:

[0029] Introduce safety constraints to the final velocity curve;

[0030] According to the formula: The final velocity curve is obtained, where v safe For safety constraints, the emergency braking distance is determined in real time by the vehicle.

[0031] Preferred options also include:

[0032] When the roadside detects an obstacle in the vehicle's blind spot or an obstacle with irregular movement that exceeds a set threshold, the roadside system prompts the vehicle to slow down in advance, provides the obstacle type and location information, so that the vehicle can slow down in advance, adjusts the ROI of the sensor, and adjusts the braking to a pre-braking state to improve the braking response speed. If necessary, the roadside system can directly trigger the vehicle's emergency braking system through low-latency communication.

[0033] Preferred options also include:

[0034] Weather sensors are installed at the roadside to detect weather conditions and determine the road surface adhesion of the road section, so as to provide the road surface adhesion coefficient to the vehicle.

[0035] The cloud-based system issues speed limit commands based on the road surface adhesion, enabling the vehicle to automatically adjust its following distance, speed, and braking control parameters.

[0036] Preferred options also include:

[0037] When coordinating traffic flow at traffic light intersections, the roadside provides real-time information on traffic light phases, countdown times, and queuing conditions at the intersection, while the vehicle side calculates the optimal speed to avoid sudden braking or running red lights.

[0038] This invention provides an autonomous driving control method based on vehicle-road-cloud collaboration. It dynamically adjusts the weights of the cloud, roadside, and vehicle-side components based on road conditions and communication status. A final speed curve is planned based on the local speed curve of the roadside component, the global speed curve of the cloud, and the speed curve of the vehicle-side component, enabling the vehicle to perform autonomous tracking and execution according to this final speed curve. This addresses the problems of unreasonable route planning and driving speed in existing vehicle-road-cloud collaboration systems, which can lead to poor user experience. It improves the intelligence level of autonomous driving and increases user comfort. Attached Figure Description

[0039] To more clearly illustrate the specific embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly described below.

[0040] Figure 1 This is a schematic diagram of an autonomous driving control method based on vehicle-road-cloud collaboration provided by the present invention.

[0041] Figure 2 This is a schematic diagram of an autonomous driving control process based on vehicle-road-cloud collaboration provided by an embodiment of the present invention. Detailed Implementation

[0042] To enable those skilled in the art to better understand the embodiments of the present invention, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings and implementation methods.

[0043] To address the problem of unreasonable route planning and driving speed in current vehicle-road-cloud collaborative systems, which easily leads to poor user experience, this invention provides an autonomous driving control method based on vehicle-road-cloud collaboration. This method solves the problem of unreasonable route planning and driving speed in current vehicle-road-cloud collaborative systems, which easily leads to poor user experience, and can improve the intelligence level of vehicle autonomous driving and increase user comfort.

[0044] like Figure 1 and Figure 2 As shown, an autonomous driving control method based on vehicle-road-cloud cooperation includes:

[0045] S1: Transmits information on obstacles, weather, and local road conditions to the vehicle and cloud via the roadside, and provides local speed curves from the roadside.

[0046] S2: Through global information sharing between vehicle, road and cloud, data sent from the vehicle to the cloud and roadside are timestamped to match the corresponding perception results, and a vehicle speed curve is generated based on the vehicle perception results and roadside road condition information.

[0047] S3: Based on the vehicle's navigation route planning and the perception results of the corresponding road ends on the planned route, combined with global traffic flow, historical data and high-precision map information, the cloud provides a global speed curve.

[0048] S4: Adjust the weights corresponding to the cloud, road, and vehicle ends, plan the final speed curve, and enable the vehicle to perform self-tracking execution according to the final speed curve.

[0049] Specifically, the vehicle-road-cloud collaborative system comprises three modules: vehicle-side (autonomous vehicles), roadside (Roadside Units, RSUs), and cloud. The vehicle-side utilizes onboard sensors (LiDAR, cameras, millimeter-wave radar, etc.) to perceive the surrounding environment in real time, and the autonomous driving domain controller executes local decision-making and control algorithms. The roadside includes roadside sensors and edge computing nodes. Roadside sensors (cameras, radar, weather sensors, etc.) cover a wider range of traffic information. Edge computing nodes provide low-latency local data processing capabilities. The cloud includes a big data platform integrating global traffic flow, historical data, and high-precision maps, as well as AI models or intelligent driving algorithms that distribute dynamic control strategies. By leveraging vehicle-road-cloud collaboration to achieve global information sharing, the vehicle transmits its location, route, status information, and perception results to the roadside and cloud. The roadside transmits perception results, including information on obstacles, weather, and local road conditions, to the vehicle and cloud. The cloud then provides a global speed curve based on the vehicle's navigation route and the perception results from other roadside locations along the planned route, combined with global traffic flow, historical data, and high-precision maps. The roadside provides a local speed curve based on road conditions and obstacle information. The vehicle generates its own speed curve based on its perception results and roadside road condition information, dynamically adjusts coefficients according to road conditions and communication status, and weights and plans the final speed curve, which is then executed by the vehicle itself.

[0050] This method achieves smooth longitudinal control and reduces abrupt acceleration / deceleration by dynamically weighting and adjusting multi-level speed curves (global, local, and vehicle-side) and combining straight / curved road condition weight allocation. Cloud-based global traffic flow and historical data are used to optimize speed planning, reducing dwell time on congested sections and improving traffic efficiency.

[0051] The method also includes: the vehicle transmitting its location, driving route, vehicle status information, and perceived surrounding environment to the roadside and cloud via a vehicle-road-cloud collaborative Internet of Vehicles.

[0052] Furthermore, the matching of the corresponding perception results includes: the vehicle end matching the perception results from the road end with the vehicle's own perception results to obtain the historical trajectory of the currently perceived obstacle, and obtaining a more accurate prediction result through the historical trajectory for longitudinal motion control; when communication is blocked, the data verified in the previous frame is used to make a prediction to predict the position and speed of the obstacle.

[0053] This method relies on local vehicle-side perception and historical data prediction to ensure control continuity when communication is interrupted (e.g., using the previous frame's data to predict obstacle trajectories). Multi-source data fusion (vehicle-side, road-side, and cloud-side) and timestamp matching mechanisms improve perception redundancy and decision-making accuracy.

[0054] Furthermore, the adjustment of the weights corresponding to the cloud, road, and vehicle terminals includes:

[0055] The weights of cloud, roadside, and vehicle-side terminals are dynamically adjusted based on road conditions and communication status.

[0056] If the road conditions are good and the road is mostly straight, then the weight corresponding to the cloud should be set higher than the weight corresponding to the vehicle and road ends.

[0057] If the road conditions are poor or the road is mostly curved, then the weight corresponding to the road end should be set higher than the weight corresponding to the cloud end and the vehicle end.

[0058] If the communication signal at the vehicle's location is poor or the speed curves corresponding to the cloud and roadside locations differ from the set value, then the vehicle's location will take precedence, and the weight corresponding to the vehicle's location will be set higher than the weight corresponding to the cloud and roadside locations.

[0059] In practical applications, when road conditions are good and there are many straight roads, the cloud-based system has a higher weight; when road conditions are poor or there are many curves, the road-side system has a higher weight. When the signal is poor or there is a large difference between the speed curves of the cloud-based system and the road-side system, the vehicle-side system takes the lead.

[0060] Furthermore, the planning of the final velocity curve includes:

[0061] Set basic weights for the cloud, vehicle, and roadside;

[0062] To assess road conditions, the road is described based on factors such as pothole severity, congestion coefficient, straight road ratio, and curvature factor. The road conditions are then quantified, and weights are determined based on the quantified road condition data.

[0063] The communication quality is judged based on signal strength and latency. When the signal strength is less than the threshold or the latency exceeds 200ms, the weight of the corresponding data source is reset to 0.

[0064] Speed ​​curve difference judgment is based on the difference between the cloud speed and the road speed. When the cumulative difference exceeds a certain threshold, the corresponding weight is set to a set value.

[0065] The weights corresponding to the cloud, vehicle, and road terminals are normalized to ensure that the sum of the weights is 1.

[0066] The final velocity curve is generated through weighted fusion.

[0067] Furthermore, the generation of the final velocity curve through weighted fusion includes:

[0068] According to the formula: The final velocity curve is generated by fusion, where, Global speed curve in the cloud. Local speed curve at the end of the road, Vehicle end speed curve, Cloud-based weighting coefficients Roadside weighting coefficient Vehicle-side weighting coefficient. This weighting coefficient is dynamically adjusted, ranging from 0 to 1.

[0069] Furthermore, the step of generating the final velocity curve through weighted fusion also includes:

[0070] Introduce safety constraints to the final velocity curve;

[0071] According to the formula: The final velocity curve is obtained, where v safe For safety constraints, the emergency braking distance is determined in real time by the vehicle.

[0072] In one embodiment, the calculation process for the final velocity curve is as follows:

[0073] ① Set the base weights, for example: ω c =0.4, ω r =0.3, ω v =0.3;

[0074] ② Make road condition judgments, describe the road based on the degree of potholes, congestion coefficient (number of obstacles per unit length), straight road ratio (percentage of straight road length in a unit planned route), and curvature factor (reciprocal of curve radius), quantify the road condition, and influence the weight based on the road condition data;

[0075] ③ Perform communication quality judgment based on signal strength and latency. When the signal strength is less than the threshold or the latency exceeds 200ms, the weight of the corresponding data source is reset to 0.

[0076] ③ Speed ​​curve difference judgment: Calculate the difference between the cloud speed and the road speed. If the cumulative difference exceeds a certain threshold, then set the weight as ω. c =0.1, ω r =0.1, ω v =0.8;

[0077] ④ Finally, normalize the weights to ensure that the sum of the weights is 1;

[0078] ⑤ The final velocity curve is generated through weighted fusion.

[0079] The method also includes: when the roadside detects an obstacle in the vehicle's blind spot or an obstacle with irregular movement that exceeds a set threshold, the roadside prompts the vehicle to slow down in advance, provides the obstacle type and location information, so that the vehicle slows down in advance, adjusts the ROI of the sensor, and adjusts the braking to a pre-braking state to improve the braking response speed. If necessary, the roadside can directly trigger the vehicle's emergency braking system through low-latency communication.

[0080] Specifically, when the roadside detects a blind spot on the vehicle side, such as an obstacle on an upcoming curve or a number of irregularly moving obstacles, such as pedestrians or animals, it adjusts the sensor's ROI (Region of Interest) and adjusts the braking to a pre-braking state to improve braking response speed. If necessary, the roadside can directly trigger the vehicle's emergency braking system via low-latency communication (5G / V2X).

[0081] This method improves safety by detecting blind spots and triggering emergency braking, combined with vehicle-side historical trajectory prediction, reducing the risk of collisions caused by obstructed vision or sudden obstacles. Weather sensors and road surface adhesion detection dynamically adjust vehicle speed and braking parameters, reducing the probability of skidding accidents in rainy or snowy weather.

[0082] The method also includes:

[0083] Weather sensors are installed at the roadside to detect weather conditions and determine the road surface adhesion of the road section, so as to provide the road surface adhesion coefficient to the vehicle.

[0084] The cloud-based system issues speed limit commands based on the road surface adhesion, enabling the vehicle to automatically adjust its following distance, speed, and braking control parameters.

[0085] The method also includes: when coordinating traffic flow at traffic light intersections, the roadside provides real-time traffic light phases, countdown times, and intersection queuing information, while the vehicle side calculates the optimal passing speed to avoid sudden braking or running red lights.

[0086] At the same time, processing local data through roadside edge computing nodes reduces the cloud computing load and can reduce communication latency.

[0087] As can be seen, this invention provides an autonomous driving control method based on vehicle-road-cloud collaboration. It dynamically adjusts the weights of the cloud, road, and vehicle terminals based on road conditions and communication status, and plans a final speed curve based on the local speed curve of the road terminal, the global speed curve of the cloud, and the speed curve of the vehicle terminal. This allows the vehicle to perform autonomous tracking and execution according to the final speed curve. This addresses the problem of unreasonable route planning and driving speed in existing vehicle-road-cloud collaboration systems, which can easily lead to a poor user experience. It improves the intelligence level of autonomous driving and increases user comfort.

[0088] The structure, features, and effects of the present invention have been described in detail above with reference to the embodiments shown in the figures. The above description is only a preferred embodiment of the present invention, but the present invention is not limited to the scope of implementation shown in the figures. Any changes made in accordance with the concept of the present invention, or equivalent embodiments modified to have equivalent changes, shall be within the protection scope of the present invention as long as they do not exceed the spirit covered by the specification and figures.

Claims

1. An autonomous driving control method based on vehicle-road-cloud cooperation, characterized in that, include: The system transmits information about obstacles, weather, and local road conditions to the vehicle and cloud via the roadside, and provides local speed curves from the roadside. Through global information sharing between vehicle, road, and cloud, data sent from the vehicle to the cloud and roadside is timestamped to match the corresponding perception results, and a vehicle speed curve is generated based on the vehicle perception results and roadside road condition information. Based on the vehicle's navigation route planning and the perception results of the corresponding road ends on the planned route, combined with global traffic flow, historical data and high-precision map information, the cloud provides a global speed curve. Adjust the weights corresponding to the cloud, road, and vehicle ends, plan the final speed curve, and enable the vehicle to perform self-tracking execution according to the final speed curve.

2. The autonomous driving control method based on vehicle-road-cloud cooperation according to claim 1, characterized in that, Also includes: The vehicle-to-infrastructure (V2I) network, through which vehicle-road-cloud collaboration is used, transmits vehicle location, driving route, vehicle status information, and perceived surrounding environment to the roadside and cloud.

3. The autonomous driving control method based on vehicle-road-cloud cooperation according to claim 2, characterized in that, The matching of the corresponding perception results includes: The vehicle-side system matches the perception results from the roadside with its own perception results to obtain the historical trajectory of the currently perceived obstacle. The historical trajectory is used to obtain a more accurate prediction result for longitudinal motion control. When communication is blocked, the data verified in the previous frame is used to make a prediction to predict the position and speed of the obstacle.

4. The autonomous driving control method based on vehicle-road-cloud cooperation according to claim 3, characterized in that, The adjustment of the weights corresponding to the cloud, road, and vehicle terminals includes: The weights of cloud, roadside, and vehicle-side terminals are dynamically adjusted based on road conditions and communication status. If the road conditions are good and the road is mostly straight, then the weight corresponding to the cloud should be set higher than the weight corresponding to the vehicle and road ends. If the road conditions are poor or the road is mostly curved, then the weight corresponding to the road end should be set higher than the weight corresponding to the cloud end and the vehicle end. If the communication signal at the vehicle's location is poor or the speed curves corresponding to the cloud and roadside locations differ from the set value, then the vehicle's location will take precedence, and the weight corresponding to the vehicle's location will be set higher than the weight corresponding to the cloud and roadside locations.

5. The autonomous driving control method based on vehicle-road-cloud cooperation according to claim 4, characterized in that, The final velocity curve is planned, including: Set basic weights for the cloud, vehicle, and roadside; To assess road conditions, the road is described based on factors such as pothole severity, congestion coefficient, straight road ratio, and curvature factor. The road conditions are then quantified, and weights are determined based on the quantified road condition data. The communication quality is judged based on signal strength and latency. When the signal strength is less than the threshold or the latency exceeds 200ms, the weight of the corresponding data source is reset to 0. Speed ​​curve difference judgment is based on the difference between the cloud speed and the road speed. When the cumulative difference exceeds a certain threshold, the corresponding weight is set to a set value. The weights corresponding to the cloud, vehicle, and road terminals are normalized to ensure that the sum of the weights is 1. The final velocity curve is generated through weighted fusion.

6. The autonomous driving control method based on vehicle-road-cloud cooperation according to claim 5, characterized in that, The process of generating the final velocity curve through weighted fusion includes: According to the formula: The final velocity curve is generated by fusion, where, Global speed curve in the cloud. Local speed curve at the end of the road, Vehicle end speed curve, Cloud-based weighting coefficients Roadside weighting coefficient Vehicle-side weighting coefficient.

7. The autonomous driving control method based on vehicle-road-cloud cooperation according to claim 6, characterized in that, The process of generating the final velocity curve through weighted fusion also includes: Introduce safety constraints to the final velocity curve; According to the formula: The final velocity curve is obtained, where v safe For safety constraints, the emergency braking distance is determined in real time by the vehicle.

8. The autonomous driving control method based on vehicle-road-cloud cooperation according to claim 7, characterized in that, Also includes: When the roadside detects an obstacle in the vehicle's blind spot or an obstacle with irregular movement that exceeds a set threshold, the roadside system prompts the vehicle to slow down in advance, provides the obstacle type and location information, so that the vehicle can slow down in advance, adjusts the ROI of the sensor, and adjusts the braking to a pre-braking state to improve the braking response speed. If necessary, the roadside system can directly trigger the vehicle's emergency braking system through low-latency communication.

9. The autonomous driving control method based on vehicle-road-cloud cooperation according to claim 8, characterized in that, Also includes: Weather sensors are installed at the roadside to detect weather conditions and determine the road surface adhesion of the road section, so as to provide the road surface adhesion coefficient to the vehicle. The cloud-based system issues speed limit commands based on the road surface adhesion, enabling the vehicle to automatically adjust its following distance, speed, and braking control parameters.

10. The autonomous driving control method based on vehicle-road-cloud cooperation according to claim 9, characterized in that, Also includes: When coordinating traffic flow at traffic light intersections, the roadside provides real-time information on traffic light phases, countdown times, and queuing conditions at the intersection, while the vehicle side calculates the optimal speed to avoid sudden braking or running red lights.

Images