An automatic driving system and method fusing car-road cooperation and social network

Abstract

The application discloses an automatic driving system integrating car-road cooperation and social networks, comprising: a data acquisition module for collecting environmental information data around the vehicle, including vehicle sensor data and external data sources; a communication module for transmitting the collected environmental information data through cellular Internet of Vehicles technology; a decision module for comprehensively analyzing and making decisions on the collected environmental information data through a deep learning model, accurately predicting the current road conditions, and generating a speed control scheme; and an execution module for controlling the actual movement of the vehicle according to the specified decision output instructions. The application also discloses an automatic driving method integrating car-road cooperation and social networks. Through the integration of car-road cooperation technology and social network information, the application realizes multidimensional information interaction between the vehicle, road infrastructure and other vehicles, and enhances the accuracy of environmental perception and real-time decision making.

Description

Technical Field

[0001] The present invention relates to an automatic driving system and method integrating vehicle-road collaboration and social networking. Background Art

[0002] With the rapid development of intelligent transportation systems, autonomous driving technology has become a key direction for future transportation. Autonomous driving not only improves vehicle autonomy and operational efficiency but also significantly reduces traffic accidents. However, a major challenge currently facing autonomous driving technology is achieving efficient and safe driving in complex road environments. Relying solely on a vehicle's sensors and algorithms is unable to cope with changing road conditions and rapidly evolving traffic dynamics. Therefore, solutions based on vehicle-to-everything (V2X) collaboration are gradually gaining attention.

[0003] By exchanging information between vehicles and road infrastructure, V2X technology effectively expands a vehicle's perception range and enhances the decision-making capabilities of autonomous driving systems. Specifically, V2X technology enables real-time sharing of traffic signals, road conditions, and other vehicle status information, helping autonomous vehicles make more accurate decisions in complex environments. Compared to single-vehicle intelligence, V2X technology can further optimize traffic flow, reduce congestion, and improve the safety and reliability of the overall transportation system.

[0004] At the same time, with the widespread adoption of social networks, Internet of Vehicles (IoV) technology has brought new opportunities for autonomous driving. Information exchange between vehicles is not limited to traffic and road conditions. Social networks can also be used to build collaborative models of "vehicle groups." Through social networks, vehicles can share more diverse information, such as driving behavior patterns and emergency response, enabling a higher level of collaborative driving.

[0005] While significant progress has been made in autonomous driving technology, vehicles' decision-making capabilities remain limited in complex road environments, particularly in areas such as perception range and emergency response. Single-vehicle intelligent systems primarily rely on onboard sensors, making them difficult to address challenges posed by obstructions or dynamic traffic flows. To address this, vehicle-road collaboration (V2X) technology expands vehicles' environmental perception range and improves decision-making efficiency and safety through real-time information exchange between vehicles and road infrastructure. However, breakthroughs in data processing and optimization for practical applications of V2X technology are still needed. Meanwhile, the development of social networks has provided new ways to share information within the Internet of Vehicles (IoV). By integrating social networks, vehicles can share more information on driving behavior, traffic events, and other issues, further enhancing collaborative driving.

[0006] Therefore, an autonomous driving system and method that integrates vehicle-road collaboration and social networks are provided. Summary of the Invention

[0007] The purpose of the present invention is to overcome existing defects and provide an autonomous driving system and method that integrates vehicle-road collaboration and social networks. By integrating vehicle-road collaboration technology and social network information, multi-dimensional information interaction between vehicles and road infrastructure and other vehicles is achieved, thereby enhancing the accuracy of environmental perception and real-time decision-making.

[0008] The technical solution to achieve the above purpose is:

[0009] One aspect of the present invention is an autonomous driving system integrating vehicle-road collaboration and social networking, including:

[0010] The data acquisition module is used to collect environmental information data around the vehicle, including the vehicle's own sensor data and external data sources;

[0011] A communication module for transmitting collected environmental information data via cellular vehicle networking technology;

[0012] The decision-making module is used to comprehensively analyze the collected environmental information data and make decisions through deep learning models, accurately predict the current road conditions, and generate speed control plans;

[0013] The execution module is used to output instructions based on the specified decision to control the actual movement of the vehicle. The actual movement of the vehicle includes but is not limited to acceleration and deceleration.

[0014] Preferably, in the data acquisition module, the vehicle's own sensors include but are not limited to lidar, cameras, ultrasonic radar and GPS; external data sources include but are not limited to dynamic traffic data and unstructured user-generated data, which are obtained through social networking platforms.

[0015] Preferably, in the data acquisition module, data from different sensors are processed through a fusion algorithm and integrated into a consistent environmental model to generate accurate object recognition and positioning information. This is further extended to the communication between the vehicle and the roadside unit through vehicle-road collaborative perception technology, and edge computing technology is used to process the perception data at the edge node, so that the vehicle can perceive pedestrians, other vehicles or obstacles in blind spots or obstructions in advance and optimize driving decisions.

[0016] Preferably, the decision module includes:

[0017] The data fusion unit is used to model the relationship between dynamic traffic data and unstructured user-generated data into a graph structure through a graph neural network, and to pass messages on the graph to achieve dynamic fusion of multi-dimensional data;

[0018] A feature extraction unit, which is used to extract features from the vehicle's own sensor data through a convolutional neural network and process time series data through a long short-term memory network;

[0019] The vehicle speed guidance unit is used to establish a maximum green wave bandwidth optimization model based on a universal numerical solution algorithm for the maximum bidirectional green wave bandwidth, obtain a vehicle speed guidance model, and then generate vehicle acceleration and deceleration decisions;

[0020] The collaborative optimization unit is used to adjust the traffic signal timing according to the signal control, and the vehicle speed guidance model adjusts the vehicle's driving speed.

[0021] Preferably, in the vehicle speed guidance unit, based on the universal numerical solution algorithm for the maximum bidirectional green wave bandwidth, a maximum green wave bandwidth optimization model is established by determining the value space of adjacent ideal spacings, deriving the calculation formulas for the uplink and downlink offset green-to-signal ratios, and calculating the formula for the green-to-signal ratios above and below the ideal green light centerline; that is,

[0022] Ideal spacing and value range of adjacent intersections:

[0023] ;

[0024] ;

[0025] Where, is the ideal spacing between adjacent intersections, is the initial velocity of the vehicle arriving at the intersection, is the average speed of vehicles traveling at the intersection, Stopping sight distance is the minimum initial velocity of the vehicle arriving at the intersection, is the minimum stopping sight distance, is the maximum initial velocity of the vehicle arriving at the intersection, is the average initial velocity of vehicles arriving at the intersection, is the maximum stopping sight distance;

[0026] The offset green signal ratio refers to the amount of up and down offset of the actual green light midpoint relative to the ideal green light centerline due to the deviation of the actual intersection position from the ideal position. For the up and down directions of the main road, the concept of the offset green signal ratio is further expanded to the up and down offset green signal ratios of the main road, that is, the green signal ratios above and below the ideal green light centerline:

[0027] ;

[0028] ;

[0029] Where, is the green lane ratio of the upward deviation of the trunk road, is the green-signal ratio of the trunk road downward deviation, is the green wave offset;

[0030] By analyzing the uplink and downlink offset green signal ratio and the green signal ratio above and below the ideal green light center line and the corresponding calculation method, it can be obtained that the uplink and downlink green wave bandwidth is the sum of the minimum value of the green signal ratio set above the uplink and downlink ideal green light center line and the minimum value of the green signal ratio set below it. If the variable Indicates the upstream green wave bandwidth of the trunk road; variable The ideal green light center line represents the green signal ratio above and below the green wave bandwidth of the trunk road, then:

[0031] ;

[0032] ;

[0033] Taking the maximum sum of the two-way green wave bandwidth of the trunk road as the optimization goal, and using the upstream green wave design speed, downstream green wave design speed, and signal period as optimization variables, the corresponding maximum green wave bandwidth optimization model is established by combining the following formula:

[0034] ;

[0035] Where, is the green wave band width, which is a time width within the green wave control. Traffic arriving at the green wave control within this time range can pass through all intersections in the green wave band smoothly without encountering red lights.

[0036] Traffic flows composed of multiple vehicles are called mixed traffic flows. From a longitudinal perspective, mixed traffic flows include artificially following vehicles. , ACC vehicles and CACC vehicles;

[0037] Assuming that the mixed traffic flow is in equilibrium, the ACC and CACC vehicles guide the manually following vehicles so that the speeds of all vehicles in the mixed traffic flow are equal, i.e., the equilibrium speed.

[0038] In the equilibrium state, the distance between the front of the vehicles is equal, and the distance between the front of the vehicles is equal. 、 and Indicates the headway between manual following vehicles, ACC vehicles and CACC vehicles, using 、 、 Indicates the ratio of manual following vehicles, ACC vehicles and CACC vehicles in the vehicle population;

[0039] Then, let the length of the road section covered by the vehicle be , is the market share of automatic following vehicles, when the total number of vehicles on the road section When it is large enough, the length of the road segment can be regarded as the sum of the headway distances of all vehicles:

[0040] ;

[0041] Traffic flow density is the number of vehicles per unit distance in a road section, so the mixed traffic flow density k is:

[0042] ;

[0043] when When , the traffic density of mixed traffic flow is:

[0044] ;

[0045] when When , the traffic density of mixed traffic flow is:

[0046] ;

[0047] According to the above formula, density k is used to express the equilibrium velocity. :

[0048] ;

[0049] Where, is the equilibrium velocity, is the minimum safe stopping distance, The safe distance between vehicles. is the free flow velocity, is the proportion of ACC and CACC vehicles, is the expected vehicle headway parameter for ACC vehicles, is the expected vehicle headway parameter of CACC vehicles, For traffic flow.

[0050] Preferably, in the vehicle speed guidance unit, the vehicle speed guidance model includes an acceleration control model, and the objective function of the acceleration control model is to minimize the travel time of the vehicle to the next intersection stop line after the acceleration guidance, and its expression is:

[0051] ;

[0052]

[0053] Where, is the shortest time required to accelerate, is the actual sight distance at the intersection, The acceleration is the one that a driver generally feels comfortable with;

[0054] The constraints of the acceleration control model are:

[0055] ;

[0056] Where, is the green light time within the signal cycle, is the remaining time of the current red light phase, is the current intersection signal cycle, is the next adjacent intersection signal cycle, The remaining time for the vehicle to travel through the current intersection to the next intersection, The distance from the current intersection's starting stop line to the next intersection's ending stop line. is the initial velocity upon reaching the current intersection, is the final speed through the current intersection, Delays in driving, The distance between the stop lines of two adjacent intersections.

[0057] Preferably, in the vehicle speed guidance unit, the vehicle speed guidance model includes a deceleration control model. The objective function of the deceleration control model optimization is to maximize the speed of the vehicle when it decelerates and passes the stop line of the intersection. That is, the time it takes for the vehicle to decelerate and then travel at a constant speed in the speed control section is:

[0058] ;

[0059] Where, Actual sight distance at intersection, A deceleration rate that is generally comfortable for a driver;

[0060] By sorting out the above formula, the objective function expression of the deceleration control model optimization can be obtained as follows:

[0061] ;

[0062]

[0063] Where, The maximum initial velocity at which the vehicle can stop at the stop line of the current intersection after the decision that the vehicle cannot pass the next intersection is made. The time for deceleration and stopping;

[0064] The constraints of the deceleration control model are:

[0065] ;

[0066] Where, is the current intersection signal cycle.

[0067] Preferably, in the collaborative optimization unit, the signal control and vehicle speed guidance are coordinated to optimize a system having a two-layer hierarchical structure, and are solved using a two-layer programming model; the upper-layer model takes maximizing the continuous throughput of the trunk line as the objective function and the guidance speed as the control variable; the lower-layer model takes minimizing the weighted average of the delay value and the average number of stops as the objective function and the phase difference as the control variable;

[0068] The upper model uses the guide speed as the decision variable and sets the maximum continuous throughput of the trunk line as the objective function;

[0069] The rolling time algorithm is used to analyze the traffic flow in the time series and construct the objective function;

[0070] Through the rolling time algorithm, traffic volume is counted within a given sliding window, and as the sliding window moves backward, the changes in traffic volume are accurately reflected, providing direction for signal timing adjustments.

[0071] The optimization objective function of the upper model is to maximize the sum of vehicles that continuously pass through each intersection artery while taking into account the vehicle travel time. The objective function of the upper model can be expressed as follows:

[0072] ;

[0073] Where, is the continuous throughput of the trunk line, is the number of intersections involved in decision-making, is the initial value of the decision sequence, i.e. the first intersection, is the given number of sliding windows, is the sliding window backward displacement, is the number of intersections, is the intersection number, is the number of decision logic cycles, is the vehicle travel time, is the deceleration and braking distance;

[0074] The constraints of the upper model are vehicle speed The speed change relationship is satisfied during the guidance process, as shown in the following formula:

[0075] ;

[0076] Where, is the minimum acceleration / deceleration of the vehicle, is the maximum acceleration / deceleration of the vehicle;

[0077] The lower planning model considers the delay of vehicles in non-coordinated phases and takes the weighted average of the delay value and the average number of stops as the objective function. Comprehensive evaluation indicators Optimize and provide an optimization solution for the upper model; the expression of the objective function is as follows:

[0078] ;

[0079] ;

[0080] Where, is the rolling window ordinal number m, is the rolling window ordinal number n, is the sight distance after the intersection decision, is the weight, is the average number of stops, is an ordinal number;

[0081] In addition to meeting the minimum and maximum green light time requirements for signal adjustment, the constraints also include controlling the compressed green light duration of the uncoordinated phase within an acceptable range. The specific constraints are:

[0082] ;

[0083] Where, Extend the green light time at decision-making intersections, For acceptable time, Extend the green light time for the actual intersection, For acceptable time, The actual time when the green light at the intersection turns on early. Extended time for decision-making green light, The time for the green light to make decisions early, The minimum time for the green light to be extended or turned on early. The maximum time for the green light to be extended or turned on early.

[0084] A second aspect of the present invention provides an autonomous driving method integrating vehicle-road collaboration and social networking, including:

[0085] Step S1, collecting environmental information data around the vehicle, including the vehicle's own sensor data and external data;

[0086] Step S2: Comprehensively analyze and make decisions based on the collected environmental information data through a deep learning model, accurately predict the current road conditions, and generate a speed control plan;

[0087] Step S3: controlling the actual movement of the vehicle according to the designated decision output instruction, where controlling the actual movement of the vehicle includes but is not limited to acceleration and deceleration.

[0088] Preferably, in step S1, the vehicle's own sensors include but are not limited to lidar, camera, ultrasonic radar and GPS; the external data source includes but is not limited to dynamic traffic data and unstructured user-generated data, which is obtained through social network platforms;

[0089] The step S2 comprises:

[0090] Step S21: Model the relationship between dynamic traffic data and unstructured user-generated data into a graph structure through a graph neural network, and perform message passing on the graph to achieve dynamic fusion of multi-dimensional data;

[0091] Step S22, extracting features of the vehicle's own sensor data through a convolutional neural network, and processing the time series data through a long short-term memory network;

[0092] Step S23: Based on the universal numerical solution algorithm for the maximum bidirectional green wave bandwidth, a maximum green wave bandwidth optimization model is established to obtain a vehicle speed guidance model, thereby generating vehicle acceleration and deceleration decisions;

[0093] In step S24, the traffic signal timing is adjusted according to the signal control, and the vehicle speed guidance model adjusts the vehicle's driving speed, thereby generating a speed control plan.

[0094] The beneficial effects of this invention are as follows: By combining vehicle-road collaboration with social networks, the system can obtain more comprehensive environmental information, compensating for the shortcomings of single-vehicle perception. The use of cellular vehicle networking and edge computing technologies ensures real-time and reliable data transmission, meeting the stringent requirements of autonomous driving for efficient communication. Furthermore, the system integrates deep learning algorithms, enabling the system to predict and respond to complex traffic environments, improving decision-making accuracy. It also enables multi-dimensional information exchange between vehicles, road infrastructure, and other vehicles, enhancing environmental perception and the accuracy of real-time decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0095] Figure 1 This is a module diagram of an autonomous driving system that integrates vehicle-road collaboration and social networking in the present invention;

[0096] Figure 2 It is a specific module diagram of the decision module in the present invention;

[0097] Figure 3 This is a flow chart of an autonomous driving method integrating vehicle-road collaboration and social networks according to the present invention;

[0098] Figure 4 This is a specific flow chart for accurately predicting the current road conditions and generating a speed control solution in the present invention;

[0099] Figure 5This is a judgment flow chart of the lower-level planning model of the present invention when considering the delay of vehicles passing through non-coordinated phases. DETAILED DESCRIPTION

[0100] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. In the description of the present invention, it should be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance.

[0101] The present invention will be further described below with reference to the accompanying drawings.

[0102] like Figure 1 As shown, an autonomous driving system integrating vehicle-road collaboration and social network includes: a data acquisition module 1, a communication module 2, a decision module 3 and an execution module 4.

[0103] The data acquisition module 1 is used to collect environmental information data around the vehicle, including the vehicle's own sensor data and external data sources.

[0104] In the embodiments, the vehicle's own sensors include but are not limited to lidar, cameras, ultrasonic radar and GPS; external data sources include but are not limited to dynamic traffic data and unstructured user-generated data, which are obtained through social networking platforms; for example, drivers' feedback on real-time road conditions, reports of sudden traffic incidents and other driving behavior patterns; social networks can form a "virtual traffic network" through the integration of multi-source data, and transmit key information in real time between vehicles to help autonomous driving vehicles predict potential dangerous scenarios, traffic congestion or emergencies; this information sharing not only helps to improve the efficiency of collaborative driving, but also enhances the overall safety and adaptability of the system, and achieves more accurate perception of complex road environments.

[0105] In the embodiment, data from different sensors are processed through a fusion algorithm and integrated into a consistent environmental model to generate accurate object recognition and positioning information. This is further extended to the communication between the vehicle and the roadside unit through vehicle-road collaborative perception technology, and edge computing technology is used to process the perception data at the edge node, so that the vehicle can perceive pedestrians, other vehicles or obstacles in blind spots or obstructions in advance and optimize driving decisions.

[0106] Communication Module 2 is used to transmit collected environmental information data via cellular vehicle-to-vehicle (V2V) technology and leverages blockchain technology to provide security for information transmission within the V2V network. It supports vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), and vehicle-to-network (V2N) communications. It also incorporates edge computing technology, offloading some computing tasks to edge nodes to reduce data transmission latency. Blockchain technology is also used to ensure the security and reliability of data transmission, preventing data tampering and unauthorized access. Blockchain, through decentralized distributed ledger technology, ensures that communications between vehicles and infrastructure are trustworthy, preventing information tampering or attacks. Furthermore, the system incorporates homomorphic encryption algorithms to protect vehicle privacy during data processing, achieving comprehensive security protection.

[0107] Decision module 3 is used to conduct comprehensive analysis and decision-making on the collected environmental information data through a deep learning model, accurately predict the current road conditions, and generate a speed control plan.

[0108] The execution module 4 is used to output instructions according to the specified decision to control the actual movement of the vehicle. The actual movement of the vehicle includes but is not limited to acceleration and deceleration.

[0109] like Figure 2 As shown, the decision module 3 includes: a data fusion unit 31 , a feature extraction unit 32 , a vehicle speed guidance unit 33 and a collaborative optimization unit 34 .

[0110] The data fusion unit 31 is used to model the relationship between dynamic traffic data and unstructured user-generated data into a graph structure through a graph neural network, and to pass messages on the graph to achieve dynamic fusion of multi-dimensional data. This technology can not only extract useful information from multi-source data, but also help vehicles predict future traffic flow changes by analyzing the historical behavior of other vehicles, thereby further optimizing the decision-making process.

[0111] The feature extraction unit 32 is used to extract the features of the vehicle's own sensor data through a convolutional neural network and process the time series data through a long short-term memory network.

[0112] This invention uses a deep learning model combining convolutional neural networks (CNNs) and long short-term memory networks (LSTMs) to process large amounts of data from the perception layer. CNNs are primarily used to extract features from image data, such as real-time road images captured by cameras, while LSTMs are capable of processing time-series data, such as historical data on traffic flow changes. By combining these two technologies, the system can accurately predict current road conditions and generate optimal route planning and speed control solutions.

[0113] The vehicle speed guidance unit 33 is used to establish a maximum green wave bandwidth optimization model based on a universal numerical solution algorithm for maximizing the bidirectional green wave bandwidth, obtain a vehicle speed guidance model, and then generate vehicle acceleration and deceleration decisions.

[0114] In this embodiment, based on a universal numerical solution algorithm for maximizing bidirectional green wave bandwidth, a maximum green wave bandwidth optimization model was established by determining the value space of adjacent ideal spacings, deriving formulas for calculating the uplink and downlink offset green-to-signal ratios, and calculating the green-to-signal ratios above and below the ideal green light centerline. This model optimizes the sum of the bidirectional green wave bandwidths as the optimization objective and uses the uplink and downlink green wave design speeds and signal periods as optimization variables. This model overcomes the fixed value limitations of existing numerical solutions and has broad applicability.

[0115] In the embodiment, based on the universal numerical solution algorithm for the maximum bidirectional green wave bandwidth, a maximum green wave bandwidth optimization model is established by determining the value space of adjacent ideal spacings, deriving the calculation formulas for the uplink and downlink offset green signal ratios, and calculating the formulas for the green signal ratios above and below the ideal green light centerline; that is,

[0116] Ideal spacing and value range of adjacent intersections:

[0117] ;

[0118] ;

[0119] Where, is the ideal spacing between adjacent intersections, is the initial velocity of the vehicle arriving at the intersection, is the average speed of vehicles traveling at the intersection, Stopping sight distance is the minimum initial velocity of the vehicle arriving at the intersection, is the minimum stopping sight distance, is the maximum initial velocity of the vehicle arriving at the intersection, is the average initial velocity of vehicles arriving at the intersection, is the maximum stopping sight distance;

[0120] The offset green signal ratio refers to the amount of up and down offset of the actual green light midpoint relative to the ideal green light centerline due to the deviation of the actual intersection position from the ideal position. For the up and down directions of the main road, the concept of the offset green signal ratio is further expanded to the up and down offset green signal ratios of the main road, that is, the green signal ratios above and below the ideal green light centerline:

[0121] ;

[0122] ;

[0123] Where, is the green lane ratio of the upward deviation of the trunk road, is the green-signal ratio of the trunk road downward deviation, is the green wave offset;

[0124] By analyzing the uplink and downlink offset green signal ratio and the green signal ratio above and below the ideal green light center line and the corresponding calculation method, it can be obtained that the uplink and downlink green wave bandwidth is the sum of the minimum value of the green signal ratio set above the uplink and downlink ideal green light center line and the minimum value of the green signal ratio set below it. If the variable Indicates the upstream green wave bandwidth of the trunk road; variable The ideal green light center line represents the green signal ratio above and below the green wave bandwidth of the trunk road, then:

[0125] ;

[0126] ;

[0127] Taking the maximum sum of the two-way green wave bandwidth of the trunk road as the optimization goal, and using the upstream green wave design speed, downstream green wave design speed, and signal period as optimization variables, the corresponding maximum green wave bandwidth optimization model is established by combining the following formula:

[0128] ;

[0129] Where, Green wave width, that is, a time width in green wave control. Within this time range, the traffic arriving at the green wave control can pass through the various intersections of the green wave band smoothly without encountering red lights.

[0130] Traffic flows composed of multiple vehicles are called mixed traffic flows. From a longitudinal perspective, mixed traffic flows include artificially following vehicles. , ACC vehicles and CACC vehicles;

[0131] Assuming that the mixed traffic flow is in equilibrium, the ACC and CACC vehicles guide the manually following vehicles so that the speeds of all vehicles in the mixed traffic flow are equal, i.e., the equilibrium speed.

[0132] In the equilibrium state, the distance between the front of the vehicles is equal, and the distance between the front of the vehicles is equal. 、 and Indicates the headway between manual following vehicles, ACC vehicles and CACC vehicles, using 、 、 Indicates the ratio of manual following vehicles, ACC vehicles and CACC vehicles in the vehicle population;

[0133] Then, let the length of the road section covered by the vehicle be , is the market share of automatic following vehicles, when the total number of vehicles on the road section When it is large enough, the length of the road segment can be regarded as the sum of the headway distances of all vehicles:

[0134] ;

[0135] Traffic flow density is the number of vehicles per unit distance in a road section, so the mixed traffic flow density k is:

[0136] ;

[0137] when When , the traffic density of mixed traffic flow is:

[0138] ;

[0139] when When , the traffic density of mixed traffic flow is:

[0140] ;

[0141] According to the above formula, density k is used to express the equilibrium velocity. :

[0142] ;

[0143] Where, is the equilibrium velocity, is the minimum safe stopping distance, The safe distance between vehicles. is the free flow velocity, is the proportion of ACC and CACC vehicles, is the expected vehicle headway parameter for ACC vehicles, is the expected vehicle headway parameter of CACC vehicles, For traffic flow.

[0144] In the embodiment, the vehicle speed guidance model includes an acceleration control model. A vehicle starting at time 0 with an initial speed immediately obtains the state of the next intersection signal light after entering the road section. If the straight phase of the current intersection signal is red, the remaining time of the current red light phase is obtained. , judge whether the vehicle entering the road section at the initial speed can reach the intersection stop line before the end of the next phase green light time at this speed. If not, but the vehicle can reach the next intersection stop line within the next phase green light time after acceleration, the red light acceleration induction strategy is activated: select an acceleration that drivers generally feel comfortable with , guide the vehicle to accelerate to the maximum speed limit of the road section and drive at this speed until it passes the next intersection; then

[0145] The objective function of the acceleration control model is to minimize the travel time of the vehicle to the next intersection stop line after the acceleration guidance, and its expression is:

[0146] ;

[0147] ;

[0148] Where, is the shortest time required to accelerate, The actual sight distance of the intersection The acceleration is the one that a driver generally feels comfortable with;

[0149] The constraints of the acceleration control model are:

[0150] ;

[0151] Where, is the green light time within the signal cycle, is the remaining time of the current red light phase, is the current intersection signal cycle, is the next adjacent intersection signal cycle, The remaining time for the vehicle to travel through the current intersection to the next intersection, The distance from the current intersection's starting stop line to the next intersection's ending stop line. is the initial velocity upon reaching the current intersection, is the final speed through the current intersection, Delays in driving, The distance between the stop lines of two adjacent intersections.

[0152] In the embodiment, the vehicle speed guidance model includes a deceleration control model. A vehicle starting at time 0 with an initial speed immediately obtains the state of the next intersection signal light after entering the road section. If the straight-ahead phase of the current intersection signal is red, the remaining time of the current red light phase is obtained to determine whether the vehicle entering the road section at the initial speed can reach the intersection stop line within the green light time of the next phase according to this speed. If not, it is determined whether the vehicle entering the road section at the initial speed can reach the intersection stop line within the green light time of the next phase by decelerating. If so, the red light deceleration induction strategy is activated: a deceleration speed that drivers generally feel comfortable with is selected to guide the vehicle to decelerate, so that the vehicle starts to decelerate at an appropriate position and can reach the intersection stop line within the green light time of the next cycle, avoiding the vehicle from stopping and waiting;

[0153] The objective function of the deceleration control model optimization is to maximize the speed of the vehicle when it passes the stop line of the intersection after deceleration. That is, the time it takes for the vehicle to decelerate and then travel at a constant speed in the speed control section is:

[0154] ;

[0155] Where, Actual sight distance at intersection A deceleration rate that is generally comfortable for a driver;

[0156] By sorting out the above formula, the objective function expression of the deceleration control model optimization can be obtained as follows:

[0157] ;

[0158] ;

[0159] Where, The maximum initial velocity at which the vehicle can stop at the stop line of the current intersection after the decision that the vehicle cannot pass the next intersection is made. The time for deceleration and stopping;

[0160] The constraints of the deceleration control model are:

[0161] ;

[0162] Where, is the current intersection signal cycle.

[0163] The collaborative optimization unit 34 is used to adjust the traffic signal timing according to the signal control, and the vehicle speed guidance model adjusts the vehicle's driving speed.

[0164] In the embodiment, signal control and speed guidance are two key arterial control strategies in urban traffic systems. Signal control adjusts traffic signal timing, while speed guidance reduces traffic delays by adjusting vehicle speeds. Signal control and speed guidance work together to optimize a system with a two-level hierarchical structure, solved using a bi-level programming model. The upper-level model uses maximizing continuous arterial throughput as the objective function and guidance speed as the control variable. The lower-level model uses minimizing the weighted average of delay value and average number of stops as the objective function and phase difference as the control variable.

[0165] The upper model uses the guide speed as the decision variable and sets the maximum continuous throughput of the trunk line as the objective function;

[0166] The rolling time algorithm is used to analyze the traffic flow in the time series and construct the objective function;

[0167] Through the rolling time algorithm, traffic volume is counted within a given sliding window, and as the sliding window moves backward, the changes in traffic volume are accurately reflected, providing direction for signal timing adjustments.

[0168] The optimization objective function of the upper model is to maximize the sum of vehicles that continuously pass through each intersection artery while taking into account the vehicle travel time. The objective function of the upper model can be expressed as follows:

[0169] ;

[0170] Where, is the continuous throughput of the trunk line, is the number of intersections involved in decision-making, is the initial value of the decision sequence, i.e. the first intersection, is the given number of sliding windows, is the sliding window backward displacement, is the number of intersections, is the intersection number, is the number of decision logic cycles, is the vehicle travel time, is the deceleration and braking distance;

[0171] The constraints of the upper model are vehicle speed The speed change relationship is satisfied during the guidance process, as shown in the following formula:

[0172] ;

[0173] Where, is the minimum acceleration / deceleration of the vehicle, is the maximum acceleration / deceleration of the vehicle;

[0174] The lower planning model considers the delay of vehicles in non-coordinated phases and takes the weighted average of the delay value and the average number of stops as the objective function. Comprehensive evaluation indicators Optimize and provide an optimization solution for the upper model; the expression of the objective function is as follows:

[0175] ;

[0176] ;

[0177] Where, is the rolling window ordinal number m, is the rolling window ordinal number n, is the sight distance after the intersection decision, is the weight, is the average number of stops, is an ordinal number;

[0178] In addition to meeting the minimum and maximum green light time requirements for signal adjustment, the constraints also include controlling the compressed green light duration of the uncoordinated phase within an acceptable range. The specific constraints are:

[0179] ;

[0180] Where, Extend the green light time at decision intersections, For acceptable time, Extend the green light time for the actual intersection, For acceptable time, The actual time when the green light at the intersection turns on early. Extended time for decision-making green light, The time for the green light to make decisions early, The minimum time for the green light to be extended or turned on early. The maximum time for the green light to be extended or turned on early.

[0181] like Figure 3 As shown, an autonomous driving method integrating vehicle-road collaboration and social networks includes:

[0182] Step S1, collecting environmental information data around the vehicle, including the vehicle's own sensor data and external data.

[0183] In an embodiment, the vehicle's own sensors include but are not limited to lidar, cameras, ultrasonic radar and GPS; external data sources include but are not limited to dynamic traffic data and unstructured user-generated data, which are obtained through social networking platforms.

[0184] In step S2, the collected environmental information data is comprehensively analyzed and decision-making is carried out through a deep learning model to accurately predict the current road conditions and generate a speed control plan.

[0185] like Figure 4 As shown, step S2 includes:

[0186] In step S21, the relationship between dynamic traffic data and unstructured user-generated data is modeled as a graph structure through a graph neural network, and message passing is performed on the graph to achieve dynamic fusion of multi-dimensional data.

[0187] Step S22: extract the features of the vehicle's own sensor data through a convolutional neural network, and process the time series data through a long short-term memory network.

[0188] In step S23, a maximum green wave bandwidth optimization model is established based on a universal numerical solution algorithm for maximizing the bidirectional green wave bandwidth, a vehicle speed guidance model is obtained, and then a vehicle acceleration and deceleration decision is generated.

[0189] In step S24, the traffic signal timing is adjusted according to the signal control, and the vehicle speed guidance model adjusts the vehicle's driving speed, thereby generating a speed control plan.

[0190] Step S3: controlling the actual movement of the vehicle according to the designated decision output instruction, where controlling the actual movement of the vehicle includes but is not limited to acceleration and deceleration.

[0191] The lower-level planning model considers the delay of vehicles passing through non-coordinated phases, e.g. Figure 5 As shown, when the straight-ahead phase is green when the vehicle enters the speed guidance area, it is determined whether the straight-ahead phase is green when the vehicle arrives at the intersection. If it is green, the original plan remains unchanged; when the straight-ahead phase is red when the vehicle enters the speed guidance area, it is determined whether the straight-ahead phase is red when the vehicle arrives at the intersection. If it is not red, the original plan remains unchanged.

[0192] The proposed phase duration compression method has some impact on the delays of vehicles in uncoordinated phases, but the increased delays are relatively small and do not significantly impact the fluctuations in these vehicles. Furthermore, the reduction in overall delays on the arterial route demonstrates that the overall benefits of this method outweigh its negative impacts, improving the overall efficiency of arterial traffic flow.

[0193] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. An autonomous driving system integrating vehicle-road collaboration and social networking, characterized in that: include: The data acquisition module is used to collect environmental information data around the vehicle, including the vehicle's own sensor data and external data sources; A communication module for transmitting collected environmental information data via cellular vehicle networking technology; The decision-making module is used to comprehensively analyze the collected environmental information data and make decisions through deep learning models, accurately predict the current road conditions, and generate speed control plans; An execution module, configured to output instructions according to a specified decision to control the actual movement of the vehicle, wherein the actual movement of the vehicle includes but is not limited to acceleration and deceleration; In the data acquisition module, the vehicle's own sensors include but are not limited to lidar, cameras, ultrasonic radar and GPS; external data sources include but are not limited to dynamic traffic data and unstructured user-generated data, which are obtained through social network platforms; In the data acquisition module, data from different sensors is processed through a fusion algorithm and integrated into a consistent environmental model to generate accurate object recognition and positioning information. This is further extended to communication between vehicles and roadside units through vehicle-road collaborative perception technology. Edge computing technology is used to process the perception data at edge nodes, allowing the vehicle to perceive pedestrians, other vehicles, or obstacles in blind spots or obstructions in advance, thereby optimizing driving decisions. The decision module includes: The data fusion unit is used to model the relationship between dynamic traffic data and unstructured user-generated data into a graph structure through a graph neural network, and to pass messages on the graph to achieve dynamic fusion of multi-dimensional data; A feature extraction unit, which is used to extract features from the vehicle's own sensor data through a convolutional neural network and process time series data through a long short-term memory network; The vehicle speed guidance unit is used to establish a maximum green wave bandwidth optimization model based on a universal numerical solution algorithm for the maximum bidirectional green wave bandwidth, obtain a vehicle speed guidance model, and then generate vehicle acceleration and deceleration decisions; The collaborative optimization unit is used to adjust the traffic signal timing according to the signal control, and the vehicle speed guidance model adjusts the vehicle's driving speed.

2. The autonomous driving system integrating vehicle-road collaboration and social networking according to claim 1, characterized in that: In the vehicle speed guidance unit, based on the universal numerical solution algorithm for maximizing the bidirectional green wave bandwidth, a maximum green wave bandwidth optimization model is established by determining the value space of adjacent ideal spacings, deriving the calculation formulas for the uplink and downlink offset green signal ratios, and calculating the formula for the green signal ratios above and below the ideal green light centerline; that is, Ideal spacing and value range of adjacent intersections: Where, is the ideal spacing between adjacent intersections, is the initial velocity of the vehicle arriving at the intersection, is the average speed of vehicles traveling at the intersection, is the stopping sight distance, is the minimum initial velocity of the vehicle arriving at the intersection, is the average value of the minimum initial velocity of vehicles arriving at the intersection, is the minimum stopping sight distance, is the maximum initial velocity of the vehicle arriving at the intersection, is the average value of the maximum initial velocity of vehicles arriving at the intersection, is the maximum stopping sight distance; The offset green signal ratio refers to the amount of up and down offset of the actual green light midpoint relative to the ideal green light centerline due to the deviation of the actual intersection position from the ideal position. For the up and down directions of the main road, the concept of the offset green signal ratio is further expanded to the up and down offset green signal ratios of the main road, that is, the green signal ratios above and below the ideal green light centerline: Where, is the green lane ratio of the upward deviation of the trunk road, is the green-signal ratio of the trunk road downward deviation, is the green wave offset; By analyzing the uplink and downlink offset green signal ratio and the green signal ratio above and below the ideal green light center line and the corresponding calculation method, it can be obtained that the uplink and downlink green wave bandwidth is the sum of the minimum value of the green signal ratio set above the uplink and downlink ideal green light center line and the minimum value of the green signal ratio set below it. If the variable Indicates the upstream green wave bandwidth of the trunk road; variable The ideal green light center line represents the green signal ratio above and below the green wave bandwidth of the trunk road, then: Taking the maximum sum of the two-way green wave bandwidth of the trunk road as the optimization goal, and using the upstream green wave design speed, downstream green wave design speed, and signal period as optimization variables, the corresponding maximum green wave bandwidth optimization model is established by combining the following formula: ； Where, is the green wave band width, which is a time width within the green wave control. Traffic arriving at the green wave control within this time range can pass through all intersections in the green wave band smoothly without encountering red lights. Traffic flows composed of multiple vehicles are called mixed traffic flows. From a longitudinal perspective, mixed traffic flows include artificially following vehicles. , ACC vehicles and CACC vehicles; Assuming that the mixed traffic flow is in equilibrium, the ACC and CACC vehicles guide the manually following vehicles so that the speeds of all vehicles in the mixed traffic flow are equal, i.e., the equilibrium speed. In the equilibrium state, the distance between the front of the vehicles is equal, and the distance between the front of the vehicles is equal. 、 and Indicates the headway between manual following vehicles, ACC vehicles and CACC vehicles, using 、 、 Indicates the ratio of manual following vehicles, ACC vehicles and CACC vehicles in the vehicle population; Then, let the length of the road section covered by the vehicle be , is the market share of automatic following vehicles, when the total number of vehicles on the road section When it is large enough, the length of the road segment can be regarded as the sum of the headway distances of all vehicles: ； Traffic flow density is the number of vehicles per unit distance in a road section, so the mixed traffic flow density k is: ； when When , the traffic density of mixed traffic flow is: ； when When , the traffic density of mixed traffic flow is: ； According to the above formula, density k is used to express the equilibrium velocity. : ； Where, is the equilibrium velocity, is the minimum safe stopping distance, The safe distance between vehicles. is the free flow velocity, is the proportion of ACC and CACC vehicles, is the expected vehicle headway parameter for ACC vehicles, is the expected vehicle headway parameter of CACC vehicles, For traffic flow.

3. The autonomous driving system integrating vehicle-road collaboration and social networking according to claim 2, characterized in that: In the vehicle speed guidance unit, the vehicle speed guidance model includes an acceleration control model. The objective function of the acceleration control model is to minimize the travel time of the vehicle to the next intersection stop line after the acceleration guidance. The expression is: ； Where, The time required to accelerate, is the shortest time required to accelerate, is the actual sight distance at the intersection, The acceleration that a driver generally feels comfortable with; The constraints of the acceleration control model are: Where, is the green light time within the signal cycle, is the remaining time of the current red light phase, is the current intersection signal cycle, is the next adjacent intersection signal cycle, The remaining time for the vehicle to travel through the current intersection to the next intersection, The distance from the current intersection's starting stop line to the next intersection's ending stop line. is the initial velocity upon reaching the current intersection, is the final speed through the current intersection, Delays in driving, The distance between the stop lines of two adjacent intersections.

4. The autonomous driving system integrating vehicle-road collaboration and social networking according to claim 3, characterized in that: In the vehicle speed guidance unit, the vehicle speed guidance model includes a deceleration control model. The objective function optimized by the deceleration control model is to maximize the vehicle speed when passing the stop line of the intersection after deceleration. That is, the time it takes for the vehicle to decelerate and then travel at a constant speed in the speed-controlled section is: ； Where, Actual sight distance at intersection, A deceleration rate that is generally comfortable for a driver; By sorting out the above formula, the objective function expression of the deceleration control model optimization can be obtained as follows: ； Where, The maximum initial velocity at which the vehicle can stop at the stop line of the current intersection after the decision that the vehicle cannot pass the next intersection is made. The time for deceleration and stopping; The constraints of the deceleration control model are: Where, is the current intersection signal cycle.

5. The autonomous driving system integrating vehicle-road collaboration and social network according to claim 4, characterized in that: In the collaborative optimization unit, signal control and vehicle speed guidance are coordinated to optimize a system with a two-layer hierarchical structure, solved using a two-layer programming model. The upper-layer model uses maximizing the continuous throughput of the trunk line as the objective function and the guidance speed as the control variable. The lower-layer model uses minimizing the weighted average of the delay value and the average number of stops as the objective function and the phase difference as the control variable. The upper model uses the guide speed as the decision variable and sets the maximum continuous throughput of the trunk line as the objective function; The rolling time algorithm is used to analyze the traffic flow in the time series and construct the objective function; Through the rolling time algorithm, traffic volume is counted within a given sliding window, and as the sliding window moves backward, the changes in traffic volume are accurately reflected, providing direction for signal timing adjustments. The optimization objective function of the upper model is to maximize the sum of vehicles that continuously pass through each intersection artery while taking into account the vehicle travel time. The objective function of the upper model can be expressed as follows: ； Where, is the continuous throughput of the trunk line, is the number of intersections involved in decision-making, is the initial value of the decision sequence, i.e. the first intersection, is the given number of sliding windows, is the sliding window backward displacement, is the number of intersections, is the intersection number, is the number of decision logic cycles, is the vehicle travel time, is the deceleration and braking distance; The constraints of the upper model are vehicle speed The speed change relationship is satisfied during the guidance process, as shown in the following formula: Where, is the minimum acceleration / deceleration of the vehicle, is the maximum acceleration / deceleration of the vehicle; The lower planning model considers the delay of vehicles in non-coordinated phases and takes the weighted average of the delay value and the average number of stops as the objective function. Comprehensive evaluation indicators Optimize and provide an optimization solution for the upper model; the expression of the objective function is as follows: Where, is the rolling window ordinal number m, is the rolling window ordinal number n, is the sight distance after the intersection decision, is the weight, is the average number of stops, is an ordinal number; In addition to meeting the minimum and maximum green light time requirements for signal adjustment, the constraints also include controlling the compressed green light duration of the uncoordinated phase within an acceptable range. The specific constraints are: Where, Extend the green light time at decision intersections, For acceptable time, Extend the green light time for the actual intersection, For acceptable time, The actual time when the green light at the intersection turns on early. Extended time for decision-making green light, The time for the green light to make decisions early, The minimum time for the green light to be extended or turned on early. The maximum time for the green light to be extended or turned on early.

6. An autonomous driving method based on the autonomous driving system integrating vehicle-road collaboration and social network according to claim 1, characterized in that: include: Step S1, collecting environmental information data around the vehicle, including the vehicle's own sensor data and external data; Step S2: Comprehensively analyze and make decisions based on the collected environmental information data through a deep learning model, accurately predict the current road conditions, and generate a speed control plan; Step S3, controlling the actual movement of the vehicle according to the specified decision output instruction, wherein the actual movement of the vehicle is controlled including but not limited to acceleration and deceleration; In step S1, the vehicle's own sensors include but are not limited to lidar, camera, ultrasonic radar and GPS; external data sources include but are not limited to dynamic traffic data and unstructured user-generated data, which are obtained through social network platforms; The step S2 comprises: Step S21: Model the relationship between dynamic traffic data and unstructured user-generated data into a graph structure through a graph neural network, and perform message passing on the graph to achieve dynamic fusion of multi-dimensional data; Step S22, extracting features of the vehicle's own sensor data through a convolutional neural network, and processing the time series data through a long short-term memory network; Step S23: Based on the universal numerical solution algorithm for the maximum bidirectional green wave bandwidth, a maximum green wave bandwidth optimization model is established to obtain a vehicle speed guidance model, thereby generating vehicle acceleration and deceleration decisions; In step S24, the traffic signal timing is adjusted according to the signal control, and the vehicle speed guidance model adjusts the vehicle's driving speed, thereby generating a speed control plan.

Images