Intelligent driving cooperative collision avoidance system and method based on Internet of Vehicles

Abstract

The invention discloses an intelligent driving cooperative collision avoidance system and method based on the Internet of Vehicles, and belongs to the technical field of automatic driving. Comprising a vehicle-mounted unit, a road side unit and a service platform, the vehicle-mounted unit is used for collecting vehicle state information and surrounding environment information and sending the vehicle state information and the surrounding environment information to the road side unit and the service platform. The road side unit is used for collecting road condition information, performing target detection based on the surrounding environment information and the road condition information, and obtaining obstacle information; and the service platform is used for evaluating a collision risk according to the vehicle state information and the obstacle information, predicting an optimal collision avoidance strategy based on the collision risk, and sending an instruction to the vehicle-mounted unit to perform collision avoidance control. Potential collision risks can be analyzed based on vehicle state information and road condition information which are shared in real time, and the safety of road traffic is improved. The problem that a traditional collision avoidance system mainly depends on perception and decision of a single vehicle and lacks cooperation with other vehicles and road infrastructures is solved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to an intelligent driving collaborative collision avoidance system and method based on an Internet of Vehicles. Background Art

[0002] The statements in this section merely mention background art related to the present invention and do not necessarily constitute prior art.

[0003] With the rapid development of the automobile industry and the increasing perfection of intelligent transportation systems, autonomous driving technology has become an important direction for future transportation development. However, in a complex traffic environment, how to effectively avoid collisions and ensure driving safety is still an important challenge facing autonomous driving technology.

[0004] Traditional collision avoidance systems mainly rely on the perception and decision-making of a single vehicle, lacking coordination with other vehicles and road infrastructure, and have the following problems:

[0005] 1. Limited perception range: Due to the physical limitations of the sensors, the vehicle can only detect obstacles or other vehicles within its direct line of sight. This means that in some cases, such as curves, bad weather conditions, or when there is occlusion, the effectiveness and reliability of the system will be greatly reduced.

[0006] 2. Information islands: Each vehicle is an independent information processing unit and cannot share real-time data with other vehicles or road infrastructure. This leads to incomplete information, making it difficult for the system to make the best collision avoidance decision.

[0007] 3. Delayed response: It takes a certain amount of time from perception to decision-making and then to execution. Especially when driving at high speeds, even a small time difference may lead to an accident. Summary of the invention

[0008] In order to address the deficiencies of the prior art, the present invention provides an intelligent driving collaborative collision avoidance system and method based on the Internet of Vehicles, which analyzes potential collision risks based on real-time shared vehicle status information and road condition information to improve road traffic safety.

[0009] In a first aspect, the present invention provides an intelligent driving collaborative collision avoidance system based on vehicle networking;

[0010] An intelligent driving collaborative collision avoidance system based on vehicle networking, including an on-board unit, a roadside unit and a service platform;

[0011] The on-board unit is used to collect vehicle status information and surrounding environment information and send them to the roadside unit and the service platform; the roadside unit is used to collect road condition information, perform target detection based on the surrounding environment information and road condition information, and obtain obstacle information; the service platform is used to evaluate the collision risk based on the vehicle status information and obstacle information, predict the best collision avoidance strategy based on the collision risk, and send instructions to the on-board unit to perform collision avoidance control.

[0012] In some embodiments, the target detection based on the surrounding environment information and the road condition information and the acquisition of obstacle information are specifically as follows: the environment image and the road traffic image are processed by a trained target detection model to obtain the obstacle detection result; the obstacle detection result in a continuous time is processed by a trained trajectory tracking model to obtain the motion trajectory of the dynamic obstacle.

[0013] In some embodiments, the target detection model is a YOLOv8s model, and the trajectory tracking model is a ReID model.

[0014] In some embodiments, assessing the collision risk based on the vehicle state information and the obstacle information includes:

[0015] Determine the longitudinal risk time based on the longitudinal position, longitudinal speed and length of the vehicle and the longitudinal position and longitudinal speed of the dynamic obstacle;

[0016] Determine the lateral risk time based on the lateral position, lateral speed and vehicle width of the vehicle and the lateral position and lateral speed of the dynamic obstacle;

[0017] The risk index is determined based on the longitudinal risk time and the lateral risk time; if the risk index is greater than the preset risk threshold, it is considered that there is a potential collision risk.

[0018] In some embodiments, determining the longitudinal risk time based on the longitudinal position, longitudinal speed and vehicle length of the vehicle and the longitudinal position and longitudinal speed of the dynamic obstacle is specifically: calculating the longitudinal collision time and longitudinal vehicle-to-vehicle time between the vehicle and the dynamic obstacle; determining the lateral risk time based on the longitudinal collision time and longitudinal vehicle-to-vehicle time.

[0019] In some embodiments, the optimal collision avoidance strategy based on collision risk prediction is specifically: using a behavior prediction model to process real-time traffic data to obtain behavior prediction results of dynamic obstacles; based on the behavior prediction results, screening in a preset collision avoidance strategy library to determine the optimal collision avoidance strategy.

[0020] In some embodiments, the behavior prediction model is an improved BiLSTM network, including an input layer, a BiLSTM layer, an Attention layer, and an output layer.

[0021] In some embodiments, the behavior prediction results are screened in a preset collision avoidance strategy library to determine the best collision avoidance strategy by calculating the Pearson correlation coefficient between the behavior prediction results and the collision avoidance strategies, and determining the best collision avoidance strategy based on the size of the Pearson correlation coefficient.

[0022] In some embodiments, the on-board unit includes a first sensor module, a first communication module and a control module, the roadside unit includes a second sensor module, a second communication module and a data processing module, and the service platform is deployed on an edge computing device supported by a 5G network.

[0023] In a second aspect, the present invention provides a method for intelligent driving collaborative collision avoidance based on vehicle networking;

[0024] A method for intelligent driving collaborative collision avoidance based on vehicle networking, based on the above-mentioned intelligent driving collaborative collision avoidance system based on vehicle networking, comprises:

[0025] The onboard unit collects vehicle status information and surrounding environment information and sends it to the roadside unit and service platform;

[0026] The roadside unit collects road condition information, performs target detection based on the surrounding environment information and road condition information, and obtains obstacle information;

[0027] The service platform evaluates the collision risk based on vehicle status information and obstacle information, predicts the best collision avoidance strategy based on the collision risk, and sends instructions to the on-board unit for collision avoidance control.

[0028] Compared with the prior art, the present invention has the following beneficial effects:

[0029] 1. The technical solution provided by the present invention realizes real-time and comprehensive monitoring of road conditions and vehicle driving conditions through real-time communication and data sharing between vehicles, roadsides and service platforms, thereby expanding the vehicle's perception range, providing comprehensive data support for collision avoidance decisions, and improving the effectiveness and reliability of autonomous driving.

[0030] 2. The technical solution provided by the present invention realizes the pre-assessment of potential collision risks and collaborative collision avoidance, thereby improving the safety of road traffic; after assessing the potential collision risk, the service platform will communicate with other vehicles or traffic infrastructure to share information in order to provide early warning to other vehicles.

[0031] 3. The technical solution provided by the present invention ensures that information can be transmitted to all relevant parties in real time through 5G communication, thereby reducing the delay in data transmission. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0033] Figure 1 A schematic diagram of a system framework provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0034] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0035] It should be noted that the terms used herein are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "include" and "have" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0037] Embodiment 1

[0038] The autonomous driving of existing vehicles relies on the perception and decision-making of a single vehicle and lacks coordination with other vehicles and road infrastructure; therefore, the present invention provides an intelligent driving collaborative collision avoidance system based on the Internet of Vehicles, which analyzes potential collision risks based on real-time shared vehicle status information and road condition information to improve road traffic safety.

[0039] Next, combine Figure 1 , a smart driving collaborative collision avoidance system based on the Internet of Vehicles disclosed in this embodiment is described in detail. The smart driving collaborative collision avoidance system based on the Internet of Vehicles includes a vehicle-mounted unit, a roadside unit and a service platform. The vehicle-mounted unit includes a first sensor module, a first communication module and a control module, which are deployed on the vehicle participating in the collaborative collision avoidance and connected to the service platform; the roadside unit includes a second sensor module, a second communication module and a data processing module, which are deployed on the road where collaborative collision avoidance is required; the service platform is deployed on an edge computing device supported by a 5G network, which can quickly analyze the data from the vehicle-mounted unit and the roadside unit, reduce the time for data transmission to the service platform, and reduce latency.

[0040] The first sensor module is used to collect vehicle status information and surrounding environment information. The vehicle status information includes the vehicle's own speed, position, acceleration, driving direction, etc. The surrounding environment information is the environment image; the first communication module is used to communicate with other vehicle-mounted units and roadside units in real time, using vehicle-to-everything (V2X) technology; the control module is used to receive information from the communication module and control the vehicle to perform collision avoidance operations according to the collision avoidance instructions generated by the collaborative collision avoidance algorithm. The first sensor module includes vehicle-mounted GPS, inertial measurement unit, wheel speed sensor, steering angle sensor, camera, etc.

[0041] The second sensor module is used to collect road condition information and traffic signal information, such as road slipperiness, traffic congestion, traffic light status, road traffic images, etc. The second communication module is used to send the collected information to the vehicle-mounted unit; the data processing module is used to receive information from the vehicle-mounted unit and conduct a comprehensive analysis in combination with local information to provide support for collaborative collision avoidance. Specifically, target detection is performed on environmental images and road traffic images to detect surrounding obstacles, and the detected obstacles are continuously tracked to obtain their motion trajectory and speed change information. The second sensor module includes a temperature sensor, a humidity sensor, a temperature sensor, and a camera.

[0042] The service platform is used to receive and process information from the on-board unit and the roadside unit, analyze potential collision risks, and send collision avoidance instructions to relevant vehicles; the service platform needs to have strong data processing capabilities and intelligent decision-making capabilities to support the operation of the collaborative collision avoidance algorithm.

[0043] Specifically, the collision risk assessment model processes the vehicle's own speed, acceleration, driving direction, and the location, speed, acceleration, and other information of obstacles to calculate the potential collision risk between the vehicle and the obstacle. After assessing the potential collision risk, it communicates with other on-board units or roadside units to share information. The big data model predicts the behavior of other vehicles and pedestrians and the best collision avoidance strategy by analyzing a large amount of real-time traffic data, including vehicle location, speed, direction, environment, etc.

[0044] As an implementation method, target detection is performed on the environment image, the road condition image, and the traffic signal image to detect surrounding obstacles, and the detected obstacles are continuously tracked to obtain their motion trajectory and speed change information. Specifically:

[0045] S101. Input the environment image and the road traffic image into the trained YOLOv8s model for processing to obtain an obstacle detection result, where the obstacle detection result is an image of the obstacle selected and the coordinate information of the obstacle.

[0046] The YOLO series of models are well-known for their efficient real-time detection capabilities and high accuracy, and are very suitable for application scenarios such as autonomous driving that require quick decision-making. Therefore, in this embodiment, the existing YOLOv8s model is directly applied for obstacle detection. Before use, environmental images and road traffic images under various environmental conditions are collected and the location and category of obstacles are marked, and a training set is constructed. The YOLOv8s model is trained by the training set until the effect is good. Here, there are four types of obstacles detected, including cars, bicycles, pedestrians, and roadblocks.

[0047] S102. Track the image sequence of the obstacle selected in the continuous time by the trained ReID model, and output the motion trajectory of the dynamic obstacle; according to the motion trajectory of the dynamic obstacle, the position, speed and acceleration of the dynamic obstacle can be calculated.

[0048] As an implementation method, the specific process of calculating the potential collision risk between the vehicle and the dynamic obstacle by processing the vehicle's own speed, driving direction, and the position and speed of the dynamic obstacle through the collision risk assessment model is as follows:

[0049] S201. Calculate the longitudinal collision time and longitudinal inter-vehicle time of the vehicle and the dynamic obstacle based on the longitudinal position, longitudinal speed and vehicle length of the vehicle and the longitudinal position and longitudinal speed of the dynamic obstacle; determine the longitudinal risk time based on the longitudinal collision time and longitudinal inter-vehicle time. The longitudinal collision time is expressed as:

[0050]

[0051] The longitudinal workshop time is expressed as:

[0052]

[0053] The longitudinal risk time is expressed as:

[0054]

[0055] In the formula, y i represents the longitudinal position of the ith dynamic obstacle, y0 represents the longitudinal position of the vehicle, l represents the vehicle length, v y0 represents the longitudinal speed of the vehicle, v yi represents the longitudinal velocity of the ith dynamic obstacle, ξ a , b Indicates the threshold value.

[0056] TTC indicates the time required before a vehicle collides with a dynamic obstacle. The smaller the value, the greater the risk of collision. THW indicates the time required for a vehicle to travel to the relative distance of a dynamic obstacle. The smaller the value, the greater the risk of collision. When the relative distance between the vehicle and the dynamic obstacle is short and the relative speed is low, if the dynamic obstacle brakes urgently, the current distance is not enough to brake to avoid the risk. However, due to the low relative speed, TTC cannot represent the risk. At this time, the THW value is small, which can represent a greater risk and make up for the shortcomings of TTC. Therefore, the longitudinal risk time is defined according to the threshold.

[0057] S202: Determine the lateral risk time according to the lateral position, lateral speed and vehicle width of the vehicle and the lateral position and lateral speed of the dynamic obstacle. The lateral risk time is expressed as:

[0058]

[0059] Where x0 represents the lateral position of the vehicle, x i represents the lateral position of the ith dynamic obstacle, b represents the vehicle width, and v xi represents the lateral speed of the ith dynamic obstacle, v x0 Indicates the vehicle's lateral speed.

[0060] S203, determine the risk index according to the longitudinal risk time and the lateral risk time; if the risk index is greater than the preset risk threshold, it is considered that there is a potential collision risk. The risk index is expressed as:

[0061]

[0062] In the formula, η is a very small number to prevent calculation errors.

[0063] As an implementation method, the big data model predicts the behavior of other vehicles and pedestrians by analyzing a large amount of real-time traffic data, including the location, speed, direction, environment, etc. of other vehicles, and predicts the best collision avoidance strategy, including:

[0064] S301, input the position, speed, direction and environmental information of other vehicles and pedestrians at the previous moment into the trained behavior prediction model to obtain the behavior prediction result.

[0065] In this embodiment, an improved BiLSTM network is used as a behavior prediction model, the input is position, speed, direction and environmental information, and the output is a behavior prediction result, such as: changing lanes, crossing the road, turning, etc.

[0066] Specifically, the difference from the existing BiLSTM network is that it includes an input layer, a BiLSTM layer, an Attention layer, and an output layer. The Attention layer is the output of the learning function F added on the basis of the BiLSTM layer, expressed as:

[0067]

[0068] ξ t =F(h′ t );

[0069]

[0070] S302: Screening is performed in a preset collision avoidance strategy library based on the behavior prediction results of other vehicles and pedestrians, and the best collision avoidance strategy is determined through correlation analysis and sent to the vehicle side unit.

[0071] For example, it can suggest vehicles to slow down, change lanes or stop, and coordinate traffic lights and other infrastructure to optimize traffic flow and reduce the risk of collision. 5G communication ensures that information can be instantly transmitted to all relevant parties, including vehicles, traffic lights and other infrastructure. After receiving the collision avoidance instructions, the vehicle can quickly execute them locally through edge computing, such as adjusting the driving route and speed to achieve collaborative collision avoidance.

[0072] Here, the correlation analysis is to calculate the Pearson correlation coefficient between the behavior prediction result and the collision avoidance strategy, and determine the optimal collision avoidance strategy based on the size of the Pearson correlation coefficient.

[0073] Embodiment 2

[0074] Based on the intelligent driving collaborative collision avoidance system based on the Internet of Vehicles described in Example 1, this embodiment discloses an intelligent driving collaborative collision avoidance method based on the Internet of Vehicles, including:

[0075] The onboard unit collects vehicle status information and surrounding environment information and sends it to the roadside unit and service platform;

[0076] The roadside unit collects road condition information, performs target detection based on the surrounding environment information and road condition information, and obtains obstacle information;

[0077] The service platform evaluates the collision risk based on vehicle status information and obstacle information, predicts the best collision avoidance strategy based on the collision risk, and sends instructions to the on-board unit for collision avoidance control.

[0078] The description of each embodiment in the above embodiments has different emphases. For parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0079] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. The intelligent driving cooperative collision avoidance system based on the Internet of Vehicles is characterized by: Including on-board unit, roadside unit and service platform; The on-board unit is used to collect vehicle status information and surrounding environment information and send them to the roadside unit and the service platform; the roadside unit is used to collect road condition information, perform target detection based on the surrounding environment information and road condition information, and obtain obstacle information; The service platform is used to evaluate the collision risk according to the vehicle status information and the obstacle information, predict the best collision avoidance strategy based on the collision risk, and send instructions to the vehicle-mounted unit to perform collision avoidance control.

2. The intelligent driving cooperative collision avoidance system based on the Internet of Vehicles as claimed in claim 1, characterized in that: The target detection based on the surrounding environment information and the road condition information and the acquisition of obstacle information are specifically as follows: the environment image and the road traffic image are processed by a trained target detection model to obtain the obstacle detection result; the obstacle detection result in a continuous time is processed by a trained trajectory tracking model to obtain the motion trajectory of the dynamic obstacle.

3. The intelligent driving cooperative collision avoidance system based on the Internet of Vehicles as claimed in claim 2, characterized in that: The target detection model is a YOLOv8s model, and the trajectory tracking model is a ReID model.

4. The intelligent driving cooperative collision avoidance system based on the Internet of Vehicles as claimed in claim 1, characterized in that: The assessing of the collision risk according to the vehicle state information and the obstacle information comprises: Determine the longitudinal risk time based on the longitudinal position, longitudinal speed and length of the vehicle and the longitudinal position and longitudinal speed of the dynamic obstacle; Determine the lateral risk time based on the lateral position, lateral speed and vehicle width of the vehicle and the lateral position and lateral speed of the dynamic obstacle; The risk index is determined based on the longitudinal risk time and the lateral risk time; if the risk index is greater than the preset risk threshold, it is considered that there is a potential collision risk.

5. The intelligent driving cooperative collision avoidance system based on the Internet of Vehicles as claimed in claim 4, characterized in that: Determining the longitudinal risk time according to the longitudinal position, longitudinal speed and vehicle length of the vehicle and the longitudinal position and longitudinal speed of the dynamic obstacle is specifically as follows: calculating the longitudinal collision time and longitudinal inter-vehicle time of the vehicle and the dynamic obstacle; and determining the lateral risk time according to the longitudinal collision time and longitudinal inter-vehicle time.

6. The intelligent driving cooperative collision avoidance system based on the Internet of Vehicles as claimed in claim 1, characterized in that: The optimal collision avoidance strategy based on collision risk prediction is specifically: using a behavior prediction model to process real-time traffic data to obtain behavior prediction results of dynamic obstacles; based on the behavior prediction results, screening in a preset collision avoidance strategy library to determine the optimal collision avoidance strategy.

7. The intelligent driving cooperative collision avoidance system based on the Internet of Vehicles as claimed in claim 6, characterized in that: The behavior prediction model is an improved BiLSTM network, including an input layer, a BiLSTM layer, an Attention layer and an output layer.

8. The intelligent driving cooperative collision avoidance system based on the Internet of Vehicles as claimed in claim 6, characterized in that: The method of screening a preset collision avoidance strategy library based on the behavior prediction result to determine the best collision avoidance strategy specifically comprises: calculating the Pearson correlation coefficient between the behavior prediction result and the collision avoidance strategy, and determining the best collision avoidance strategy based on the size of the Pearson correlation coefficient.

9. The intelligent driving cooperative collision avoidance system based on the Internet of Vehicles as claimed in claim 1, characterized in that: The on-board unit includes a first sensor module, a first communication module and a control module, the roadside unit includes a second sensor module, a second communication module and a data processing module, and the service platform is deployed on an edge computing device supported by a 5G network.

10. An intelligent driving collaborative collision avoidance method based on vehicle networking, characterized in that: include: The onboard unit collects vehicle status information and surrounding environment information and sends it to the roadside unit and service platform; The roadside unit collects road condition information, performs target detection based on the surrounding environment information and road condition information, and obtains obstacle information; The service platform evaluates the collision risk based on vehicle status information and obstacle information, predicts the best collision avoidance strategy based on the collision risk, and sends instructions to the on-board unit for collision avoidance control.

Images