Dynamic speed limiting control method and system for CAV vehicle leading vehicle group based on hierarchical cooperative control and storage medium

Abstract

The application provides a kind of based on hierarchical cooperative control CAV vehicle navigation car group dynamic speed limit control method and system and storage medium, method is: obtaining the real-time traffic flow data in the upstream control range of bottleneck area;Real-time traffic flow data is input into the Mask-DQN model trained, to maximize the target output several optimal car groups of CAV vehicle navigation car group coefficient;Wherein, according to the maximum passing capacity of bottleneck area, the optimal car group size is calculated, and the car group coefficient is constructed based on the optimal car group size and CAV vehicle navigation principle;According to the real-time passing capacity of bottleneck area, the target speed of each optimal car group when reaching bottleneck area is calculated respectively;According to the target speed of each optimal car group, the acceleration value of the lead CAV vehicle in each optimal car group is calculated in real time.The application can solve the problem that the existing car group division mechanism cannot match the passing capacity of downstream bottleneck area and there is lack of cooperative speed control between multiple CAV control units.

Description

Technical Field

[0001] This invention relates to the field of intelligent traffic control technology, specifically to a dynamic speed limit control method, system, and storage medium for a CAV (Carrier Aerial Vehicle) navigator group based on hierarchical collaborative control. Background Technology

[0002] With the rapid development of autonomous driving and vehicle-to-everything (V2X) communication technologies, intelligent connected vehicles are gradually gaining advantages such as precise control, information sharing, and rapid response. Dynamic speed limit control based on intelligent connected vehicles has thus become a research hotspot in traffic management. Existing technologies mainly calculate dynamic speed limit values ​​through algorithm optimization and reinforcement learning, and then issue deceleration commands to intelligent connected vehicles in mixed traffic flows. This allows intelligent connected vehicles to guide neighboring manually driven vehicles to simultaneously implement deceleration, thereby achieving dynamic speed limit control of the overall traffic flow.

[0003] However, existing dynamic speed limit control methods based on intelligent connected vehicles still have the following technical shortcomings: First, there is a lack of vehicle group segmentation mechanisms in multi-lane scenarios. Existing technologies mostly adopt segmentation methods based on fixed thresholds or fixed rules, mechanically dividing traffic flow into multiple discrete vehicle groups in single-lane scenarios. They fail to incorporate the heterogeneous spatial distribution of vehicles in multi-lane scenarios, vehicle type composition, and downstream bottleneck capacity into the segmentation optimization mechanism. This makes it difficult to adapt to the complex vehicle topology in multi-lane scenarios, resulting in the segmented vehicle group flow not matching the actual road capacity and reducing the controllability of the vehicle group.

[0004] Second, there is insufficient modeling of collaborative control among the control units of intelligent connected vehicles. Existing technologies acquire traffic flow information around intelligent connected vehicles and in bottleneck areas through real-time information transmission and independently calculate the deceleration value of each intelligent connected vehicle within its control cycle, without explicitly modeling collaborative control methods among multiple intelligent connected vehicle control units. In real-world traffic scenarios, the superposition effect of multiple independent control commands may introduce more uncertain disturbances to traffic flow, making it difficult to adapt to traffic oscillations caused by complex interactions in heterogeneous traffic flows.

[0005] In summary, existing technologies cannot effectively address the issues of vehicle group segmentation and collaborative control of multiple intelligent connected vehicle control units in multi-lane scenarios for dynamic speed limit management upstream of bottleneck areas. Therefore, there is an urgent need for a dynamic speed limit management method capable of optimizing the segmentation of multi-lane vehicle groups and implementing collaborative speed control of multiple control units. Summary of the Invention

[0006] The purpose of this invention is to provide a dynamic speed limit control method for CAV (Caravan Leader) vehicle groups based on hierarchical cooperative control. This method aims to address the problems in existing technologies, such as the lack of vehicle group segmentation mechanisms in multi-lane scenarios with mixed traffic flow, inability to match downstream bottleneck capacity, and lack of coordinated speed control among multiple CAV control units, making it difficult to adapt to complex interactive disturbances in heterogeneous traffic flows. The specific technical solution is as follows: A dynamic speed limit control method for a CAV (Continuous Aerial Vehicle) lead vehicle group based on hierarchical collaborative control includes: Obtain real-time traffic flow data within the upstream control area of ​​the bottleneck region; Real-time traffic flow data is input into the trained Mask-DQN model, and the optimal vehicle groups led by several CAVs are output with the goal of maximizing the vehicle group coefficient. The optimal vehicle group size is calculated based on the maximum capacity of the bottleneck area, and the vehicle group coefficient is constructed based on the optimal vehicle group size and the CAV vehicle leading principle. Calculate the target speed of each optimal vehicle group when it arrives at the bottleneck area based on the real-time traffic capacity of the bottleneck area. Based on the target speed of each optimal vehicle group, the acceleration value of the lead CAV vehicle in each optimal vehicle group is calculated in real time.

[0007] Preferably, the training method for the Mask-DQN model is as follows: The road segment is divided into a first traffic area, a second traffic area, and a bottleneck area along the direction of vehicle travel. Car-following behavior model and lane-changing behavior model are constructed for CAV vehicles and HDV vehicles, respectively. The optimal vehicle group size is calculated based on the maximum traffic capacity of the bottleneck area, and the vehicle group coefficient is constructed based on the optimal vehicle group size and the CAV vehicle navigation principle. The initial vehicle group set is obtained by first dividing the simulated traffic flow data within the upstream control range of the bottleneck area. The feature vector of the vehicle group set is used as the state space, the merging, splitting and migration between vehicle groups are used as the action space, the single-step improvement of the vehicle group coefficient is used as the immediate reward, and the Mask-DQN model is trained with the goal of maximizing the vehicle group coefficient.

[0008] Preferably, the lane-changing behavior models of the CAV vehicle and the HDV vehicle are the same, wherein the lane-changing motivation is expressed as: Lane change safety verification is represented as follows: in, For lane changing motives in the first traffic zone, The lane-changing motive for the second passage area; 0 indicates no lane-changing motive, 1 indicates free lane-changing motive, and 2 indicates forced lane-changing motive. The speed difference between the vehicle in front and the vehicle in front; The speed difference threshold; For the exit lane, To reduce the number of lanes; This marks the boundary between the upstream and downstream sections of the second passage area. This is the current location of this vehicle. This vehicle, The position of vehicles behind the target lane; Position of the vehicle ahead in the target lane; This is the minimum acceptable clearance for lane changes.

[0009] Preferably, the optimal vehicle group size is calculated based on the maximum traffic capacity of the bottleneck area, specifically: in, To achieve the optimal vehicle group size; This represents the maximum traffic capacity of the bottleneck area. The expected speed of the vehicle group in the bottleneck area; The length of road occupied by the group of vehicles; The desired spacing between the vehicles; The critical density of the bottleneck region; The critical velocity for the bottleneck region; The vehicle lane-changing rate for the downstream section of the second traffic zone; This is the capacity loss coefficient caused by lane-changing conflicts.

[0010] Preferably, the vehicle group coefficient is constructed based on the optimal vehicle group size and the CAV vehicle navigation principle, specifically: in, For vehicle group coefficient, Matching item to vehicle group size; For CAV vehicle navigation gain; For the first The size of a vehicle group; The number of vehicles in the group; The penetration rate of CAV vehicles within the upstream control area of ​​the bottleneck region; For the first CAV vehicle navigation gain coefficient for a vehicle group; The standard deviation is Gaussian.

[0011] Preferably, if all lead vehicles in all lanes of an optimal vehicle group are CAV vehicles, then it is considered a CAV barrier vehicle group; otherwise, it is considered a CAV preceding barrier vehicle group. The calculation model for the target speed of the CAV barrier vehicle group is expressed as follows: in, This indicates the target speed of the CAV barrier vehicle group. To ensure real-time traffic flow in bottleneck areas; The length of road occupied by the CAV barrier vehicle group; The number of vehicles in the CAV barrier vehicle group; The desired spacing between the vehicles; The calculation model for the target velocity of the CAV preceding barrier vehicle group is expressed as follows: in, The total traffic flow of the CAV preceding barrier vehicle group; Traffic flow in the lane where the CAV vehicle is located; Traffic flow in the free-traffic lanes; The number of vehicles in the lane where the lead CAV is located in the preceding barrier vehicle group; The length of the group of vehicles in the lane where the lead CAV is located; The target speed for the CAV preceding barrier vehicle group; The free-flow speed in the free-movement lane; This represents the current density of the free-traffic lanes; The proportion of vehicles in the lane where the lead CAV vehicle is located that change lanes to the free-driving lane; The driving speed of the freely navigable lane obtained through iteration; Indicates the first The driving speed in the free-driving lane calculated in the next iteration; Indicates the first The driving speed in the free-driving lane calculated in the next iteration; This indicates the density of road congestion.

[0012] Preferably, the acceleration value of the lead CAV vehicle in the optimal vehicle group is expressed as: in, It is the first The optimal vehicle group's leading CAV vehicle in Calculated acceleration value at time t; For the first The target speed of the optimal vehicle group; For the first The optimal vehicle group's leading CAV vehicle in The vehicle speed at any given moment; For the first The actual distance between the optimal vehicle group and the downstream adjacent optimal vehicle group; For the first The maximum allowable acceleration of the lead CAV vehicle in an optimal vehicle group; For the first The distance decay function for an optimal vehicle group; For the first The optimal distance between the vehicle group and the bottleneck area; The attenuation coefficient; For the first The downstream adjacent optimal vehicle groups of the optimal vehicle groups are Average vehicle speed at any given time; , and All are proportional gain coefficients; It is the first The optimal vehicle group's leading CAV vehicle in The acceleration value at time t. For the first The optimal vehicle group's leading CAV vehicle in The acceleration value at any given moment; Constraints on the maximum change in acceleration between adjacent time points; For the first The minimum allowable acceleration for the lead CAV vehicle in an optimal vehicle group; This represents the desired spacing between the vehicles.

[0013] Preferably, the acceleration of the following CAV vehicle in the optimal vehicle group is calculated based on the speed of the lead CAV vehicle in the optimal vehicle group, and is expressed as: in, For the first The leading CAV vehicle in the optimal vehicle group The vehicle speed at any given moment; For the first In the optimal vehicle group, the following CAV vehicles The vehicle speed at any given moment; For the first In the optimal vehicle group, the following CAV vehicles Acceleration at any moment; For the first The longitudinal distance difference between the following CAV vehicle and the vehicle in front in the optimal vehicle group; This is the speed error gain coefficient; This is the distance error gain coefficient.

[0014] The present invention also provides a dynamic speed limit control system for a CAV (Carrier Automobile) navigator group based on hierarchical collaborative control, including a memory and a processor. The memory stores a computer program, and the processor executes the dynamic speed limit control method for the CAV navigator group based on hierarchical collaborative control when running the computer program.

[0015] The present invention also provides a storage medium storing a computer program, which, when executed by a processor, performs the described dynamic speed limit control method for a CAV vehicle navigator group based on hierarchical collaborative control.

[0016] The application of the technical solution of the present invention has the following beneficial effects: This invention calculates the optimal vehicle group size by introducing the maximum capacity of the bottleneck area. Based on the optimal vehicle group size and the CAV (Car Access Vehicle) leadership principle, it constructs a vehicle group coefficient that includes a vehicle group size matching term and a CAV leadership gain term. The rationality of the vehicle group segmentation structure is evaluated from two dimensions: the degree of deviation between the vehicle group size and the optimal size, and whether the vehicle group is led by CAVs. A larger vehicle group coefficient value indicates that the vehicle group size is close to the optimal size and the leading vehicle is a CAV, thus ensuring that the segmented vehicle group matches the bottleneck capacity and has the ability to be effectively controlled by the control system. This invention solves the problems of existing technologies where vehicle group segmentation relies on fixed rules and does not consider the heterogeneous spatial distribution of multi-lane traffic and the constraints of downstream bottleneck capacity.

[0017] This invention models the vehicle grouping problem as an objective optimization problem. Through a mask mechanism, it dynamically identifies and masks invalid merging, splitting, and migration actions in the current state, focusing the agent's attention on a subset of effective actions. This overcomes the inefficiency of standard DQN in exploring a large action space, significantly improving the training efficiency and policy quality of the vehicle grouping strategy. Furthermore, in the Mask-DQN model training, this invention uses the single-step improvement of the vehicle group coefficient as an immediate reward, ensuring the agent receives immediate feedback after each partitioning operation. This directly quantifies the contribution of actions to the vehicle group structure optimization, guiding the agent to quickly converge towards maximizing the vehicle group coefficient.

[0018] This invention establishes a hierarchical collaborative control strategy, decomposing the speed control of each optimal vehicle group into two levels: target speed calculation and collaborative speed control. At the target speed calculation level, based on the lead CAV (Car Access Vehicle) situation, the invention classifies the optimal vehicle group into a CAV barrier vehicle group and a CAV preceding barrier vehicle group, and establishes target speed calculation models for each. For the CAV preceding barrier vehicle group, the invention quantifies the disturbance of lane-changing behavior of vehicles not obeying HDV (High-Depth Vehicle) to the free-traveling lane by establishing a set of micro-evolutionary equations, and uses a numerical iteration method to deduce the control speed of the lead CAV, ensuring that vehicle groups not fully led by CAV also have a calculable target speed benchmark. At the collaborative speed control level, the invention integrates three core control objectives: target speed tracking, vehicle group safe distance adjustment, and vehicle group speed coordination. It uses a nonlinear control law to calculate the acceleration of the lead CAV and dynamically adjusts the control intensity based on the distance of the vehicle group from the bottleneck area using a distance decay function, ensuring both smooth driving at long distances and effective deceleration at close distances. Through the above-mentioned hierarchical collaborative control, the present invention enables each optimal vehicle group to pass through the bottleneck area in sequence with a smooth speed trajectory, avoiding traffic oscillations caused by the superposition of multiple independent control commands, and solving the problem of lack of collaborative speed control among multiple CAV control units in the prior art, which makes it difficult to adapt to the complex interactive disturbances of heterogeneous traffic flow.

[0019] In addition to the objectives, features, and advantages described above, the present invention has other objectives, features, and advantages. The invention will now be described in further detail with reference to the figures. Attached Figure Description

[0020] The accompanying drawings, which form part of this application, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 This is a flowchart of the dynamic speed limit control method for the CAV vehicle navigator group based on hierarchical collaborative control in Example 1; Figure 2 This is a schematic diagram of the optimal vehicle group division in Example 1; Figure 3 This is a schematic diagram of the hierarchical collaborative control in Example 1; Figure 4 This is a schematic diagram illustrating the change in the cumulative TET value in the simulation case of Example 1; Figure 5 This is a schematic diagram illustrating the change in the cumulative TIT value in the simulation case of Example 1; Figure 6 This is a schematic diagram of the uncontrolled travel time in the simulation case of Example 1; Figure 7 This is a schematic diagram of the driving time using the baseline model in the simulation case of Example 1; Figure 8 This is a schematic diagram of the driving time using the hierarchical collaborative control model in the simulation case of Example 1. Detailed Implementation

[0021] To facilitate understanding of the present invention, a more complete description is provided below, along with preferred embodiments. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a thorough and complete understanding of the disclosure of the present invention.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0023] Example 1: See Figure 1 This embodiment provides a dynamic speed limit control method for a CAV vehicle navigator group based on hierarchical collaborative control, including an offline training phase and an online control phase; The offline training phase includes: The road segment is divided into a first traffic area, a second traffic area, and a bottleneck area along the direction of vehicle travel. Car-following behavior model and lane-changing behavior model are constructed for CAV vehicles and HDV vehicles, respectively. The optimal vehicle group size is calculated based on the maximum traffic capacity of the bottleneck area, and the vehicle group coefficient is constructed based on the optimal vehicle group size and the CAV vehicle navigation principle. The initial vehicle group set is obtained by first dividing the simulated traffic flow data within the upstream control range of the bottleneck area. The feature vector of the vehicle group set is used as the state space, the merging, splitting and migration between vehicle groups are used as the action space, the single-step improvement of the vehicle group coefficient is used as the immediate reward, and the Mask-DQN model is trained with the goal of maximizing the vehicle group coefficient. The Mask-DQN model is used to output the optimal vehicle group led by several CAV vehicles. The online management phase includes: Obtain real-time traffic flow data within the upstream control area of ​​the bottleneck area, including vehicle location, speed, acceleration, and lane information; Real-time traffic flow data is input into the trained Mask-DQN model, and the optimal vehicle group with several CAV vehicles leading is output with the goal of maximizing the vehicle group coefficient. Calculate the target speed of each optimal vehicle group when it arrives at the bottleneck area based on the real-time traffic capacity of the bottleneck area. Based on the target speed of each optimal vehicle group, the acceleration value of the lead CAV vehicle in each optimal vehicle group is calculated in real time.

[0024] The dynamic speed limiting control method of this embodiment will be described in detail below: In this embodiment, CAV vehicles refer to connected and automated vehicles (CAVs), HDV vehicles refer to human-driven vehicles (HDVs), and the Mask-DQN model is an improved model that combines the action mask mechanism with the classic reinforcement learning algorithm DQN (Deep Q-Network).

[0025] In this embodiment, the bottleneck area refers to the bottleneck area of ​​a highway. A bottleneck area is a critical road segment where traffic capacity is significantly reduced and traffic flow easily transitions from free flow to congested or even blocked flow due to factors such as road geometry, traffic demand, traffic composition, and driving behavior. Based on the characteristics of the bottleneck and whether its spatial location changes over time, it can generally be divided into two main categories: fixed bottlenecks and moving bottlenecks.

[0026] To construct a simulation environment for training the Mask-DQN model, this embodiment divides the road segment within the upstream control area of ​​the bottleneck region into a first traffic area and a second traffic area along the vehicle's direction of travel. That is, vehicles will sequentially pass through the first traffic area, the second traffic area, and the bottleneck region along the travel direction. The control area can be set according to actual conditions; for example, the road segment 0-3 kilometers upstream of the bottleneck region can be set as the control area.

[0027] The congestion and disturbances in the bottleneck area mainly stem from three types of behaviors: free lane changing, slowing down and waiting, and forced lane changing. Free lane changing often occurs in the first traffic zone upstream of the bottleneck, where vehicles actively change lanes to achieve higher speeds. This behavior prematurely increases the traffic density in the bottleneck area, exacerbating congestion. Slowing down and forced lane changing are concentrated in the second traffic zone. In this zone, limited by the bottleneck's capacity, vehicles must slow down and wait for an acceptable lane-changing gap to merge. This process directly leads to a decrease in traffic speed, gradually forming congestion and queues. Simultaneously, due to road conditions, vehicles often force lane changes within small gaps, causing significant speed fluctuations for following vehicles and further increasing the risk of rear-end collisions.

[0028] Therefore, in this embodiment, CAV vehicles and HDV vehicles are mixed within the upstream control range of the bottleneck area to construct a simulation environment upstream of the bottleneck area. The first passage area is located at the very upstream, where vehicles mainly engage in free lane changing and straight-line travel. This area is also where vehicle control begins to significantly reduce traffic pressure on subsequent road sections. The second passage area is located in the middle, where forced lane changing behavior increases significantly, and vehicles will also be controlled in this area. The bottleneck area is located downstream, where traffic capacity is limited. Vehicles will reach the target speed before reaching this area, thus passing through the bottleneck area more smoothly.

[0029] Furthermore, in order to achieve accurate simulation of mixed traffic flow, it is necessary to perform car-following behavior modeling and lane-changing behavior modeling for CAV vehicles and HDV vehicles respectively.

[0030] Specifically, in this implementation, an Intelligent Driver Model (IDM) is used to model the following behavior of HDV vehicles. The Intelligent Driver Model (IDM) is represented as follows: in, The acceleration to be used by the following vehicle in the next moment; The maximum acceleration that can be used by following vehicles; To follow the current speed of the vehicle, To match the desired speed of the vehicle, The speed difference between the following vehicle and the vehicle in front; For acceleration exponent, in this embodiment we take... =4; The expected safe headway for following vehicles; The current actual headway between the following vehicle and the vehicle in front; This is the minimum safe distance when stationary; For safe headway; To reduce the speed of vehicles following the car.

[0031] The Intelligent Driver Model (IDM) takes the current vehicle speed, relative speed to the vehicle in front, actual vehicle distance, and expected safe distance as inputs, and outputs the specific acceleration value of the following vehicle at each step, thereby quantitatively describing the dynamic change process of the following vehicle's acceleration. It can reproduce the phase transition phenomenon of traffic flow from free flow and synchronous flow to congested flow, as well as real driving characteristics such as bias towards the expected driving speed and sudden braking.

[0032] Specifically, the following behavior of CAV vehicles is divided into two types depending on the type of vehicle in front. When a CAV vehicle follows an HDV vehicle, an adaptive cruise control (ACC) model is used, which is represented as follows: in, This is the current position of the vehicle in front. The current location of the vehicle being followed; The length of the vehicle in front; The current speed of the vehicle in front. The current speed of the vehicle following it; For cruise control of the vehicle's headway; This is the gain coefficient for the positioning error. This is the gain coefficient for the speed error; The acceleration of the following vehicle output by the adaptive cruise control model; Indicates the vehicle in front. Indicates a vehicle following another vehicle.

[0033] The adaptive cruise control model (ACC) takes safe distance constraints and desired vehicle speed as its core control objectives, and outputs smooth acceleration commands in real time. It reflects the performance characteristics of adaptive cruise control such as vehicle speed maintenance and distance adjustment, and can accurately characterize the micro-behavioral features of CAV vehicles when acquiring external information and using it for longitudinal control.

[0034] Furthermore, when CAV vehicles form a platoon with other CAV vehicles, a cooperative adaptive cruise control (CACC) model is used, represented as: in, This refers to the following distance error; The first derivative of the spacing error is expressed as the relative velocity deviation. The real-time acceleration of the vehicle in front; For proportional gain, For differential gain, This is the feedforward gain.

[0035] As can be seen from the first derivative of the error term, the error variation is closely related to the speed and acceleration of the vehicle in front, as well as the speed and acceleration of the vehicle itself. The key to CACC's superiority over ACC lies in the acceleration of the vehicle in front obtained through communication. As a feedforward term, it affects the acceleration value of the final output.

[0036] Since the first passage area, the second passage area, and the bottleneck area have different vehicle driving characteristics, after constructing a car-following model for the vehicle, different parameters can be selected to simulate the driving style of the corresponding road segment. The specific parameter values ​​can be calibrated with reference to common knowledge in the field or actual test data.

[0037] Preferably, this embodiment proposes an improved lane-changing model for the upstream of the bottleneck region based on the LC2013 lane-changing model and the lane-changing behavior characteristics of vehicles upstream of the bottleneck region. The LC2013 lane-changing model is a hierarchical microscopic vehicle lane-changing model developed by the German Aerospace Center for the open-source microscopic traffic simulation platform SUMO.

[0038] The improved lane-changing model in this embodiment divides vehicle lane-changing behavior into two stages: lane-changing motivation generation and lane-changing safety verification and execution. Since the upstream of the highway bottleneck area in this embodiment is not subject to traffic rule constraints and the proactive yielding behavior of vehicles is ignored, in order to recreate the road congestion and high-risk driving conditions caused by lane-changing behavior upstream of the bottleneck area, this embodiment only considers tactical and strategic lane-changing motivations, corresponding to free lane-changing and forced lane-changing scenarios, respectively. Specifically, free lane-changing is used in the first traffic area, free lane-changing is used in the upstream section of the second traffic area, and forced lane-changing is used in the downstream section.

[0039] Specifically, in the first traffic zone, HDV vehicles apply tactical lane-changing mechanisms, while CAV vehicles do not perform lane-change control. In the second traffic zone, based on the vehicle's position, free lane-changing or forced lane-changing mechanisms are applied to each CAV and HDV vehicle, forcing them to change lanes to a lane where they can continue driving. The expression for the lane-changing mechanism is: in, For lane changing motives in the first traffic zone, The lane-changing motive for the second passage area; 0 indicates no lane-changing motive, 1 indicates free lane-changing motive, and 2 indicates forced lane-changing motive. The speed difference between the vehicle in front and the vehicle in front; The speed difference threshold; For the exit lane, To reduce the number of lanes; This marks the boundary between the upstream and downstream sections of the second passage area. This is the current location of this vehicle. This refers to this vehicle.

[0040] Furthermore, lane-change safety verification is based on the minimum acceptable distance in the target lane, ensuring that the distance between the vehicle in front and the vehicle behind in the target lane is large enough to avoid a collision. Its expression is: in, The position of vehicles behind the target lane; Position of the vehicle ahead in the target lane; This is the minimum acceptable clearance for lane changes.

[0041] In this embodiment, HDV vehicles' free lane changing and forced lane changing correspond to Take 30m and 18m respectively; CAV vehicles' free lane changing and forced lane changing correspond to The distances were set to 25m and 15m respectively. Because CAV vehicles have a rapid following response, their minimum acceptable clearance is relatively small; while vehicles with mandatory lane-changing motivation have more lenient requirements on following distance in lane-changing behavior. Furthermore, to simulate the deceleration and waiting behavior of vehicles with mandatory lane-changing motivation but lacking safe lane-changing conditions, the car-following model further reduces the target speed, increases the target following distance, and adjusts the target minimum distance based on road segment parameters.

[0042] After the simulation environment is built, the vehicle grouping strategy can be trained within it. Preferably, in this embodiment, the optimal vehicle group size is calculated based on the maximum capacity of the bottleneck area as follows: in, To achieve the optimal vehicle group size; This represents the maximum traffic capacity of the bottleneck area. The expected speed of the vehicle group in the bottleneck area; The length of road occupied by the group of vehicles; The desired spacing between the vehicles; The critical density of the bottleneck area (i.e., the traffic density at which the traffic flow in the bottleneck area reaches its maximum value). The critical speed of the bottleneck area (the vehicle speed corresponding to the traffic density of the bottleneck area equaling the critical density); The vehicle lane change rate is the vehicle lane change rate in the downstream section of the second traffic area, which is included in the control area. The vehicle lane change rate is expressed as the number of lane-changing vehicles / the number of vehicles passing through. The capacity loss coefficient caused by lane-changing conflicts is set to 0.8 in this embodiment. The minimum safe distance between vehicles; The expected safe distance for the vehicle group; The desired distance between vehicles within the vehicle group; This refers to the length of the vehicle body; For the first The speed of the vehicle; For the first The maximum acceleration of the vehicle.

[0043] Considering the frequent lane-changing behavior upstream of the bottleneck area, which causes additional disturbances, speed fluctuations, and effective clearance loss, the actual throughput capacity will decrease to some extent compared to the theoretical capacity. Therefore, this embodiment introduces lane-changing rate and lane-changing conflict loss coefficient to reduce the bottleneck capacity. At the micro level, the longitudinal organization of the vehicle group should ideally ensure safety during driving. Therefore, this embodiment uses a spacing strategy based on safe time distance to calculate the expected spacing of the vehicle group, which is jointly determined by the minimum static safe clearance and the dynamic safe clearance based on the expected time distance, i.e., the larger of the two values ​​is taken. Similarly, adjacent vehicles within the vehicle group should also maintain a reasonable and safe time distance to ensure the stability of the vehicle group when the vehicle group speed is limited. The expected spacing within the vehicle group consists of the safe time distance and the safe braking distance, reflecting the collision avoidance requirements under the expected time distance and the maximum deceleration constraint, respectively. Thus, the total length of the vehicle group can be expressed as a linear combination of the vehicle body length and the spacing between vehicles. Among them, the minimum safe distance, safe time distance, and braking distance are all calculated with reference to the parameters in the car-following model.

[0044] Preferably, the vehicle group coefficient is constructed based on the optimal vehicle group size and the CAV vehicle navigation principle, specifically as follows: in, For vehicle group coefficient, Matching item to vehicle group size; For CAV vehicle navigation gain; For the first The size of a vehicle group (i.e., the total number of vehicles). The number of vehicles in the group; The penetration rate of CAV vehicles within the upstream control area of ​​the bottleneck region; For the first CAV vehicle navigation gain coefficient for a vehicle group; The standard deviation is Gaussian.

[0045] In this embodiment, the vehicle group coefficient evaluates vehicle group segmentation from two dimensions: vehicle group size matching degree and CAV vehicle leadership. A Gaussian kernel is used to establish a vehicle group size matching term to characterize the impact of offset on the vehicle group structure. The vehicle group size matching term reaches its maximum value when the vehicle group size equals the optimal size; as the degree of deviation increases, its contribution decreases exponentially, reflecting the losses caused by the vehicle group structure deviating from the optimal operating state. The CAV vehicle leadership gain term is used to evaluate whether the vehicle group has the ability to be effectively controlled by the control system. In vehicle group control, the lead vehicle usually determines the dynamic behavior of the entire vehicle group. When the lead vehicle is a CAV vehicle, the system can implement variable speed limit or cooperative speed limit control better. Therefore, when all lanes in the vehicle group are led by CAV vehicles, the highest gain value will be obtained; if only some lanes are led by CAV vehicles, the gain value drops to 1; when the entire vehicle group is led by HDV vehicles, the system will exhibit stronger randomness and uncertainty, and the gain will be 0.

[0046] Specifically, the larger the vehicle group coefficient value, the closer the vehicle group division result is to the expected distribution, that is, the number of vehicles in the group approaches the optimal size and the leading vehicle is a CAV vehicle; conversely, the smaller the vehicle group coefficient value, the worse the vehicle group control performance under the current division strategy is, and a second division is needed to further optimize the vehicle group division strategy.

[0047] Preferably, the initial vehicle group division is performed based on simulated traffic flow data within the upstream control area of ​​the bottleneck region, specifically: Vehicles within the upstream control area of ​​the bottleneck zone will be numbered sequentially from downstream to upstream according to their spatial location. The vehicle closest to the bottleneck area is defined as the first vehicle.

[0048] Will The initial vehicle grouping is performed based on the headway of consecutive vehicles: vehicle number 1 is taken as the first vehicle of the first vehicle group, and the vehicle groups are divided sequentially. Within all lanes, if the headway between the target vehicle and the vehicle in front is less than a set threshold (100m in this embodiment), the target vehicle is divided into the same vehicle group as the vehicle in front; otherwise, it is divided into a new vehicle group.

[0049] After the initial vehicle grouping, traffic flow can be defined as an initial set of vehicle groups consisting of multiple vehicle groups. , among which, the Individual car groups The size (i.e., the total number of vehicles) is denoted as After vehicle grouping is performed, the current vehicle grouping situation can be evaluated based on the vehicle grouping coefficient.

[0050] Furthermore, this embodiment models the vehicle grouping problem as an objective optimization problem and uses the Mask-DQN model to solve for the optimal vehicle grouping strategy. The essence of vehicle grouping is to adjust the vehicle group structure through three types of operations—merging, splitting, and migrating—based on the initial partitioning, so that the overall partitioning result reaches the optimal level, thus obtaining the vehicle group coefficient. maximize.

[0051] Specifically, in this embodiment, the merging operation refers to merging adjacent vehicle groups. With a group of cars Merging; splitting operations refer to dividing a group of vehicles segmentation Vehicles form a sub-vehicle group and The original vehicle group numbers are sequentially incremented; the migration operation refers to transferring the vehicle group... Upstream (or downstream) Vehicles moved to adjacent vehicle groups (or The total number of vehicles remains unchanged. The maximum value is determined by the number of vehicles in the vehicle group, and the specific segmentation is obtained by the learning strategy, such as: The value can be 1-3. Reinforcement learning can use model training to determine whether to segment 1, 2 or 3 vehicles, or choose other two types of actions.

[0052] Preferably, the feature vector of the vehicle group includes five types of feature vectors: total number of vehicles in the group, size of each group, type of lead vehicle in each group, CAV vehicle penetration rate within the control range, and distance between vehicle groups. The state space of the Mask-DQN model is constructed based on these five types of feature vectors. It can comprehensively reflect the rationality of the vehicle group division structure, and the dimensions are moderate, which is conducive to the convergence of reinforcement learning and training.

[0053] The action space of the Mask-DQN model consists of the three types of actions for the aforementioned vehicle group partitioning decision variables, represented as follows: However, under certain conditions, not all actions are effective or feasible. For example, when the number of vehicles in a group... The segmentation action cannot be performed when the vehicle group size is large. Less than the number to be migrated Transfer actions cannot be executed at this time. Directly exploring and learning across the entire action space leads to a large number of invalid attempts, significantly reducing learning efficiency and policy quality. To address this, this embodiment introduces a Mask mechanism. The core idea is to dynamically identify and mask invalid actions in the current action space state during the two key stages of action selection and Q-value update, thus focusing the agent's attention on a subset of valid actions.

[0054] Specifically, the optimal action selection (i.e., selecting the action with the largest Q value) and the calculation of the target Q value are expressed as follows: in, for t The execution of actions at any given moment for t The state space at any given moment; For state space The effective action space below; In the state space The main evaluation network parameters are: Take action below The cumulative expected return that can be obtained afterward; Represents the current state space Take action below The cumulative expected return of the target at that time; express Instant reward refers to the immediate reward after taking an action; This represents the discount factor, indicating the importance of future rewards. These represent the parameters of the target evaluation network; Represents the state space at the next time step. Take action below Estimated cumulative expected return at that time; This is an indicator function; if a valid action exists in the state, the function value is 1; otherwise, it is 0.

[0055] The Mask mechanism used in this embodiment is a common technique in reinforcement learning for handling invalid actions. Its basic idea is to mark the validity of each action in the current state by using a binary mask vector, and to mask the Q value corresponding to invalid actions, so that the agent can only select and update in the subset of valid actions.

[0056] Furthermore, to guide the agent in learning the optimal vehicle grouping strategy, a suitable reward signal needs to be designed. This embodiment uses the single-step improvement in the vehicle group coefficient as the immediate reward, and constructs a loss function based on the mean squared error (MSE) between the current Q-value and the target Q-value. Guide the agent to learn the optimal vehicle grouping strategy: in, for The vehicle group coefficient at any given time This represents the single-step improvement amount of the vehicle group coefficient. Instant rewards for moments The reward design directly quantifies the actions performed. The real-time changes in the optimization effect of the rear vehicle group structure encourage the agent to take actions that can improve the overall vehicle group coefficient. S Value partitioning strategy.

[0057] like Figure 2 As shown, in this embodiment, the Mask-DQN model is trained to output several optimal vehicle groups led by CAV vehicles. The specific method is as follows: S1. Obtain simulated traffic flow data within the upstream control area of ​​the bottleneck area, number the vehicles according to their spatial location and divide them into an initial vehicle group set based on the headway. Among them, consecutive vehicles with a headway less than a set threshold are divided into the same vehicle group, otherwise they are divided into a new vehicle group. S2. Use the feature vectors of the current vehicle group set as the state space of the Mask-DQN model. The merging, splitting, and migrating of vehicles within a group are treated as the action space, and a mask mechanism is used to identify the current state space. The effective action space below; S3. Calculate the Q-value (cumulative expected return) of each effective action through the main evaluation network, select the action with the largest Q-value to execute, and update the vehicle group set to obtain the next state space. ; Calculate the change in the vehicle group coefficient before and after the action is executed as the immediate reward. The state space before the action Current action being performed Instant rewards after an action and the state space after the action Stored as experience in the experience pool; S4. Calculate the target Q value (target cumulative expected return) using the target evaluation network, and use the mean square error between the Q value output by the main evaluation network and the target Q value as the loss function to backpropagate and update the parameters of the main evaluation network. S5. Repeat steps S2 through S4, each loop... The parameters of the main evaluation network are then synchronized to the target evaluation network. When the Mask-DQN model converges, the optimal vehicle grouping strategy that maximizes the vehicle group coefficient is output, resulting in several optimal vehicle groups led by CAV vehicles.

[0058] Specifically, the convergence of the Mask-DQN model refers to the following: when the increase in the vehicle group coefficient between any two adjacent iterations is less than a preset threshold in a series of consecutive iterations, or when the maximum number of training iterations is reached. In this embodiment... The value range is set to 5-10.

[0059] At this point, the Mask-DQN model has been trained and can be deployed on the road to classify traffic flow within the upstream control area of ​​the bottleneck region for subsequent speed limit control.

[0060] like Figure 3 As shown, in order to implement coordinated speed limit control for various vehicle groups within the road, reduce driving risks and improve traffic efficiency in the upstream control area of ​​highway bottleneck zones, this embodiment proposes a hierarchical coordinated speed limit control strategy (i.e., a hierarchical coordinated control model) for CAV (Caravan Leader) leading vehicle groups. This model comprises two parts: a calculation model for the target speed of the vehicle group and a coordinated speed control model for the vehicle group. The core control logic of the hierarchical coordinated speed limit control strategy in this embodiment is: using the speed of the leading CAV as a benchmark, guiding the speed of the entire vehicle group to converge towards this benchmark speed, thereby achieving orderly passage of the vehicle group.

[0061] Among them, the vehicle group target speed model serves as a control premise. Based on the real-time traffic capacity of the bottleneck area and the operating status information of each optimal vehicle group, it calculates the target speed that each optimal vehicle group should reach when it arrives at the bottleneck area, providing a key control target for subsequent speed control.

[0062] Building upon this foundation, the vehicle group cooperative speed control model, based on the target speed output from the upper layer, further considers key factors such as vehicle group spacing and the speeds of adjacent vehicle groups, and calculates and outputs in real time the acceleration value of the lead CAV vehicle in the optimal vehicle group. The lead CAV vehicle adjusts its driving state according to this acceleration value, thereby guiding each optimal vehicle group to approach the target speed with a smooth speed trajectory, ultimately enabling multi-vehicle groups to cooperate in passing through bottleneck areas and effectively reducing driving risks.

[0063] Based on whether the leading vehicles in each lane of the optimal vehicle group are all CAV vehicles, the optimal vehicle groups are divided into two types: CAV barrier vehicle groups and CAV preceding barrier vehicle groups. CAV barrier vehicle groups refer to a single optimal vehicle group in which all lanes are led by CAV vehicles, while CAV preceding barrier vehicle groups refer to a single optimal vehicle group in which only some lanes are led by CAV vehicles.

[0064] The control capabilities and effectiveness of CAV barrier vehicle groups and CAV preceding barrier vehicle groups differ, therefore, separate calculation models for target speeds need to be designed. The core control objective of the CAV barrier vehicle group is to ensure that its overall traffic capacity matches the real-time traffic capacity of the bottleneck area, thus avoiding the formation of new congestion sources or exacerbating existing congestion. Its calculation method is consistent with the calculation approach for optimal vehicle group size. The calculation model for the target speed of the CAV barrier vehicle group is expressed as follows: in, This indicates the target speed of the CAV barrier vehicle group. The real-time traffic capacity of the bottleneck area is expressed as the real-time density of the bottleneck area multiplied by the real-time average speed. The length of road occupied by the CAV barrier vehicle group; The number of vehicles in the CAV barrier vehicle group; This represents the desired spacing between the vehicles.

[0065] Due to the incomplete control of the CAV preceding barrier vehicle group over the following traffic flow, the speed limit control of the lead CAV will reduce the speed of the following traffic flow in its lane. Meanwhile, some non-compliant HDVs may change lanes based on the speed difference between their current lane and the adjacent (free-roaming) lane, thus disturbing the traffic flow in the free-roaming lane. Therefore, for a two-lane highway, the calculation model for the target speed of the CAV preceding barrier vehicle group in this embodiment is expressed as follows: in, The total traffic flow of the CAV preceding barrier vehicle group; Traffic flow in the lane where the CAV vehicle is located; Traffic flow in the free-traffic lanes; The number of vehicles in the lane where the lead CAV is located in the preceding barrier vehicle group; The length of the group of vehicles in the lane where the lead CAV is located; The target speed for the CAV preceding barrier vehicle group; The free-flow speed in the free-movement lane; This represents the current density of the free-traffic lanes; The percentage of vehicles in the lane where the lead CAV vehicle is located to change lanes to the free-moving lane (HDV vehicle non-compliance rate). The driving speed of the freely navigable lane obtained through iteration; Indicates the first The driving speed in the free-driving lane calculated in the next iteration; Indicates the first The driving speed in the free-driving lane calculated in the next iteration; This indicates the density of road congestion.

[0066] Specifically, after constructing a calculation model for the target speed of the CAV preceding barrier vehicle group, the speed limit control target is then... The numerical iteration method is used to calculate And inversely deduce the control speed of the pilot CAV vehicle. .

[0067] Furthermore, after obtaining the target speed when the optimal vehicle group reaches the bottleneck area, the acceleration values ​​of the leading CAV and following CAV vehicles in the optimal vehicle group can be calculated in real time to achieve reasonable speed coordination control between and within the vehicle group.

[0068] This embodiment integrates three core control objectives: target speed tracking, vehicle group safe distance adjustment, and vehicle group speed coordination. It employs a nonlinear control law to calculate the time-to-time ratio of the lead CAV vehicle. The acceleration is expressed as: in, It is the first The optimal vehicle group's leading CAV vehicle in Calculated acceleration value at time t; For the first The target speed of the optimal vehicle group (i.e., the target speed of the lead CAV vehicle), the... If the optimal vehicle group is a CAV barrier vehicle group, then Take as If it is a CAV preceding a barrier vehicle group, then Take as ; For the first The optimal vehicle group's leading CAV vehicle in The vehicle speed at any given moment; For the first The actual distance between the optimal vehicle group and the downstream adjacent optimal vehicle group (i.e. the optimal vehicle group in front); For the first The maximum allowable acceleration of the lead CAV vehicle in an optimal vehicle group; For the first The distance decay function of the optimal vehicle group is based on the th . The distance of the optimal vehicle group from the bottleneck area The control intensity is dynamically adjusted. When the distance is far, the control effect is weaker, which is conducive to smooth driving; when approaching the bottleneck, the control effect is strengthened to ensure effective speed control. The attenuation coefficient; For the first The downstream adjacent optimal vehicle groups of the optimal vehicle groups are Average vehicle speed at any given time; , and All of these are proportional gain coefficients.

[0069] Furthermore, to ensure driving comfort, safety, and vehicle dynamics feasibility, the following constraints are imposed on the calculated acceleration command: in, It is the first The optimal vehicle group's leading CAV vehicle in The acceleration value at time t. For the first The optimal vehicle group's leading CAV vehicle in The acceleration value at any given moment; Constraints on the maximum change in acceleration between adjacent time points; For the first The minimum allowable acceleration for the lead CAV vehicle in an optimal vehicle group; For the first The maximum allowable acceleration of the lead CAV vehicle in an optimal vehicle group.

[0070] Furthermore, after calculating the acceleration of the lead CAV in the optimal vehicle group, the acceleration of the following CAVs within the optimal vehicle group can be calculated based on the speed of the lead CAV. In this embodiment, the speed of the following CAVs within the optimal vehicle group adopts a modified cooperative adaptive cruise control (MCACC) following model, and the acceleration of the following CAVs is calculated in real time based on the state of the lead CAV. in, For the first The leading CAV vehicle in the optimal vehicle group The vehicle speed at any given moment; For the first In the optimal vehicle group, the following CAV vehicles The vehicle speed at any given moment; For the first In the optimal vehicle group, the following CAV vehicles Acceleration at any moment; For the first The longitudinal distance difference between the following CAV vehicle and the vehicle in front in the optimal vehicle group; This is the speed error gain coefficient; This is the distance error gain coefficient.

[0071] This embodiment of the dynamic speed limit control method for CAV (Caravan Leader) vehicle groups based on hierarchical collaborative control relies on the collaborative interaction between CAV vehicles and roadside units during actual use. Simultaneously, based on the control strategy of this embodiment, a vehicle group segmentation module and a speed limit control module are constructed. The synchronous operation of these two modules achieves variable speed limit control on the road. The specific operation flow is as follows: First, the traffic detection zone and the collaborative control zone are delineated. Starting from a point several meters (e.g., 500m) upstream of the bottleneck area, the traffic detection zone extends upwards to a designated area upstream of the bottleneck. Real-time traffic flow data (including vehicle position, speed, acceleration, and lane information) is collected via roadside units. Specifically, several roadside sensing devices are installed upstream of the traffic detection zone. These devices are capable of vehicle information collection, CAV (Continuous Aerial Vehicle) communication, and control command issuance. After collecting vehicle information, the roadside sensing devices can upload the data to the cloud for global decision-making. The communication coverage area of ​​the upstream roadside sensing devices is considered the collaborative speed limit control zone. Here, the traffic detection zone and the collaborative control zone refer to the road segment division in actual speed limit control, while the first and second traffic areas refer to the road segment division during simulation training. The road segment division in actual speed limit control can be the same as or different from the road segment division in simulation training.

[0072] Secondly, when the density of the traffic detection zone exceeds the set critical density, variable speed limit control is automatically activated. After receiving the activation command, the roadside sensing equipment in the upstream section acquires the location information of all vehicles within the current road area in real time and uploads it to the vehicle group segmentation module. The vehicle group segmentation module outputs the optimal vehicle group segmentation strategy in real time through a pre-trained Mask-DQN model, and forms several optimal vehicle groups led by CAVs. At the same time, it synchronizes the vehicle group segmentation results to all leading CAVs in the road to ensure accurate synchronization of segmentation information.

[0073] Furthermore, the cloud-based system combines real-time traffic flow data from the traffic detection zone with the location distribution of each vehicle group. The speed limit control module calculates the target speed for each optimal vehicle group and then synchronizes the target speed value to the corresponding lead CAV vehicle of the optimal vehicle group, providing a benchmark for subsequent speed control.

[0074] Finally, the lead CAVs in each optimal vehicle group acquire real-time operational status information such as position and speed of other lead CAVs within their range via vehicle-to-vehicle communication, and calculate reasonable deceleration values ​​(i.e., acceleration values) in real time through the speed limit control module, achieving coordinated control among the vehicle groups. Ultimately, each lead CAV accurately executes deceleration actions based on its own autonomous driving control system, synchronously guiding vehicles behind it in the group to complete speed adjustments, achieving the goal of variable speed limit control.

[0075] Simulation Case: This embodiment constructs a simulation environment to compare and analyze the uncontrolled, existing dynamic speed limit control strategies, and the hierarchical collaborative control strategy of this embodiment. The selected analysis indicators include the cumulative TET value, the cumulative TIT value, and the average travel time (ATT). At the same time, five CAV vehicle penetration scenarios of 30%, 35%, 40%, 45%, and 50% are set to verify the robustness of dynamic speed limit control.

[0076] This embodiment uses an existing dynamic speed limit control strategy as a baseline model and conducts a comparative experiment with the hierarchical cooperative control model of this embodiment in the same scenario. The core control idea of ​​this baseline model is to use a single CAV (Continuously Operated Vehicle) as a control unit, and to control the overall mixed traffic flow through the coordinated speed regulation of upstream and downstream CAV vehicles. Its core deceleration calculation expression is as follows: in, For the first The final output deceleration value of a CAV vehicle; Indicates the first The deceleration value calculated for each CAV vehicle based on its own vehicle condition; Indicates the first The expected speed of a CAV vehicle; Indicates the first The desired longitudinal position of a CAV vehicle; They represent the first The speed of the CAV vehicle at the current moment; Indicates the first The longitudinal position of the CAV vehicle at the current moment; This is the set of speeds of all CAVs within the downstream communication range of the current CAV vehicle; This is the set of locations of all CAVs within the downstream communication range of the current CAV vehicle.

[0077] Based on the above formulas, CAV vehicles can adopt the safest deceleration strategy according to road conditions, thereby suppressing traffic flow disturbances. Furthermore, this embodiment only demonstrates two core calculation formulas from the baseline model; for any aspects of the baseline model not described in detail, please refer to existing technologies.

[0078] Furthermore, Time to Collision (TTC) is one of the most classic and widely used alternative safety indicators. It represents the remaining time required for a vehicle to collide with the vehicle in front while maintaining its current state of motion at a given moment, thus characterizing the instantaneous risk level. Its formula is as follows: In the formula, For the first The car is The risk of instantaneous collisions; for Net distance between the two workshops before and after the time; For the car behind The speed of time; For the car in front The speed of time.

[0079] When the speed of the following vehicle is less than or equal to that of the vehicle in front, the following vehicle will not continue to approach the vehicle in front. This is generally considered... If the value is infinity, then there is no risk of collision. A smaller value indicates that the following vehicle approaches the preceding vehicle at a faster speed, and its reaction and braking time are also shorter, indicating a more serious collision between vehicles. It is generally believed that when... Below a certain critical threshold When the vehicle is in a high-risk state, the critical threshold value is 4 in this case.

[0080] Furthermore, the cumulative TET value represents the state of the agent at the critical threshold throughout the entire experimental period. The cumulative duration of the following conditions, i.e., the total time a vehicle is exposed to hazardous conditions, is expressed as: The cumulative TIT value indicates that TTC is at a critical threshold. The combined effect of severity and duration is expressed as follows: in, This represents the total number of steps in the simulation experiment; For characteristic functions, i.e. when The value is 1 if the condition is true, and 0 otherwise. It was a short period of time.

[0081] Furthermore, Average Travel Time (ATT) comprehensively reflects the impact of operating speed levels, queuing conditions, congestion propagation, and speed control strategies on vehicle passage within a road segment. The formula can be expressed as: in, The total number of vehicles covered in the experiment; For the first The time it takes for a vehicle to enter a simulated road section; For the first The time it takes for a vehicle to leave the simulated road section.

[0082] Figure 4 and Figure 5 The cumulative TET and TIT curves of the three strategies are presented under the same experimental parameters. The results show that both the baseline model and the hierarchical cooperative control model in this embodiment can reduce driving risks to some extent. Specifically, in the initial 0-7 minute phase, the risk management effects of the baseline model and the hierarchical cooperative control model are quite similar. However, as the experiment progresses and traffic flow gradually accumulates in the bottleneck area, although the baseline model reduces the frequency of risk occurrence, its TIT curve still reflects a large number of high-risk operating states. In comparison, the hierarchical cooperative control model performs better in both TET and TIT curves, and can continuously and significantly reduce the overall traffic risk level throughout the entire experimental period.

[0083] Furthermore, Table 1 summarizes the risk improvement ratios of the baseline model and the hierarchical collaborative control model under various CAV vehicle penetration rates. Overall, the hierarchical collaborative control model shows a higher risk improvement ratio at all penetration rates compared to the baseline model. Moreover, as the CAV vehicle penetration rate gradually increases, the effectiveness of the baseline model in improving traffic risk shows a downward trend: at 30%, the baseline model has the highest TET and TIT risk improvement ratios of -12.06% and -7.48%, respectively; while as the CAV vehicle penetration rate increases to 50%, its optimization ratios drop to -8.79% and -0.73%, respectively. Conversely, the hierarchical collaborative control model does not significantly decrease with the increase in CAV vehicle penetration rate, showing an upward trend in the 45% and 50% scenarios.

[0084] Table 1. Improvement rate of vehicle risk under different CAV vehicle penetration rates This result demonstrates that in scenarios with high CAV (Autonomous Vehicle) penetration, speed-limiting strategies based on single-vehicle control units are less adaptable to high-pressure bottleneck areas and complex vehicle interactions, generating additional traffic disturbances within the road segment. This phenomenon can be attributed to the surge in the number of deceleration commands and the lack of effective coordination among vehicles, leading to weakened control performance and difficulty in achieving optimal control objectives. In contrast, the hierarchical cooperative control model uses a vehicle group as the basic control unit, dynamically matching the traffic flow status with the real-time capacity of the bottleneck area through multi-vehicle group cooperative speed adjustment, thus ensuring stable and excellent control performance even under high CAV penetration. The above comparison results further confirm the advantages of the hierarchical cooperative control model in terms of coordination, robustness, and practicality, demonstrating its adaptability to different CAV penetration scenarios and showcasing its application potential in future high-proportion autonomous driving environments.

[0085] Furthermore, this case study analyzes road traffic efficiency under different control strategies. Figures 6-8Vehicle travel time data under three control strategies are presented. The results show that the vehicle travel time distribution under each strategy is concentrated in the range of 170 seconds to 230 seconds, but different control strategies have a significant impact on the distribution pattern and dispersion of travel time.

[0086] In the uncontrolled scenario, this road segment is prone to congestion, with a significantly high proportion of vehicles taking over 210 seconds to travel, reflecting low overall operational efficiency. After implementing baseline model control, the median vehicle travel time improved slightly, decreasing to around 200 seconds, and congestion was alleviated accordingly. However, a considerable proportion of vehicles still took over 230 seconds to travel, and their distribution showed a clear discrete characteristic, resulting in limited improvement in overall traffic efficiency. In fact, the ATT (Average Time To Travel) index increased from 204.3 seconds to 208.1 seconds. This may be due to the numerous independent deceleration commands from the baseline model, leading to frequent vehicle deceleration and consequently causing local traffic flow interruptions.

[0087] In contrast, the hierarchical cooperative control model in this embodiment effectively optimizes the coordination of vehicle trajectory and speed, making the distribution of vehicle travel time more compact, uniform, and concentrated. Its ATT (Action Time To Travel) index decreased from 204.3 seconds to 195.9 seconds, effectively reducing the proportion of vehicles traveling for extended periods. Comprehensive comparison shows that, compared to the uncontrolled scenario, the hierarchical cooperative control model in this embodiment not only reduces the volatility of overall travel time but also significantly shortens the average travel time, fully demonstrating superior traffic efficiency and operational stability. This verifies the advantages of the hierarchical cooperative control model in improving traffic efficiency in bottleneck areas.

[0088] Furthermore, this case study also conducted comparative experiments under different CAV vehicle penetration scenarios to analyze the impact of each strategy on the average vehicle driving time. The results are shown in Table 2.

[0089] Table 2 Average vehicle travel time under different CAV vehicle penetration rates Compared to the uncontrolled scenario, the baseline model only reduced the average travel time to some extent in the 30% and 45% CAV vehicle penetration scenarios; in other penetration scenarios, the average travel time remained basically the same or even increased. This reflects that the speed limit strategy corresponding to the baseline model can only maintain basic traffic capacity in this experimental scenario and is difficult to achieve effective improvement. In contrast, the hierarchical cooperative control model of this embodiment effectively reduced the average travel time of vehicles in all CAV vehicle penetration experimental scenarios, and the average travel time showed a continuous downward trend as the penetration increased. This result shows that the hierarchical cooperative control model of this embodiment can effectively reduce traffic operation risks without sacrificing vehicle traffic efficiency, while stabilizing and optimizing the overall traffic efficiency of the road segment, verifying its synergistic improvement capability in traffic safety and operational efficiency.

[0090] Example 2: This embodiment provides an optimal vehicle group segmentation method for dynamic speed limit control of vehicle groups, including an offline training phase and an online control phase; The offline training phase includes: The road segment is divided into a first traffic area, a second traffic area, and a bottleneck area along the direction of vehicle travel. Car-following behavior model and lane-changing behavior model are constructed for CAV vehicles and HDV vehicles, respectively. The optimal vehicle group size is calculated based on the maximum traffic capacity of the bottleneck area, and the vehicle group coefficient is constructed based on the optimal vehicle group size and the CAV vehicle navigation principle. The initial vehicle group set is obtained by first dividing the traffic flow data within the upstream control range of the bottleneck area. The feature vector of the vehicle group set is used as the state space, the merging, splitting and migration between vehicle groups are used as the action space, the single-step improvement of the vehicle group coefficient is used as the immediate reward, and the Mask-DQN model is trained with the goal of maximizing the vehicle group coefficient. The Mask-DQN model is used to output the optimal vehicle group led by several CAV vehicles. The online management and control phase includes: Real-time traffic flow data is collected from the upstream control area of ​​the bottleneck region. The real-time traffic flow data is then input into the trained Mask-DQN model to obtain several optimal vehicle groups led by CAV vehicles.

[0091] The specific details of the optimal vehicle group division in this embodiment are the same as those in Embodiment 1. Therefore, this embodiment will not provide a detailed explanation of the specific technical details.

[0092] Example 3: This embodiment provides a dynamic speed limit control system for a CAV (Carrier Automobile) navigator group based on hierarchical collaborative control, including a memory and a processor. The memory stores a computer program, and when the processor runs the computer program, it executes the dynamic speed limit control method for a CAV navigator group based on hierarchical collaborative control in Embodiment 1.

[0093] Example 4: This embodiment provides a storage medium storing a computer program, which, when executed by a processor, performs the dynamic speed limit control method for a CAV vehicle navigator group based on hierarchical collaborative control in Embodiment 1.

[0094] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A dynamic speed limit control method for a CAV (Continuous Aerial Vehicle) lead vehicle group based on hierarchical collaborative control, characterized in that, include: Obtain real-time traffic flow data within the upstream control area of ​​the bottleneck region; Real-time traffic flow data is input into the trained Mask-DQN model, and the optimal vehicle groups led by several CAVs are output with the goal of maximizing the vehicle group coefficient. The optimal vehicle group size is calculated based on the maximum capacity of the bottleneck area, and the vehicle group coefficient is constructed based on the optimal vehicle group size and the CAV vehicle leading principle. Calculate the target speed of each optimal vehicle group when it arrives at the bottleneck area based on the real-time traffic capacity of the bottleneck area. Based on the target speed of each optimal vehicle group, the acceleration value of the lead CAV vehicle in each optimal vehicle group is calculated in real time. The vehicle group coefficient is constructed based on the optimal vehicle group size and the CAV (Car Availability) vehicle navigation principle. Specifically: in, For vehicle group coefficient, Matching item to vehicle group size; For CAV vehicle navigation gain; For the first The size of a vehicle group; To achieve the optimal vehicle group size; The number of vehicles in the group; The penetration rate of CAV vehicles within the upstream control area of ​​the bottleneck region; For the first CAV vehicle navigation gain coefficient for a vehicle group; The standard deviation is Gaussian.

2. The dynamic speed limit control method for CAV vehicle navigator groups based on hierarchical collaborative control according to claim 1, characterized in that, The training method for the Mask-DQN model is as follows: The road segment is divided into a first traffic area, a second traffic area, and a bottleneck area along the direction of vehicle travel. Car-following behavior model and lane-changing behavior model are constructed for CAV vehicles and HDV vehicles, respectively. The optimal vehicle group size is calculated based on the maximum traffic capacity of the bottleneck area, and the vehicle group coefficient is constructed based on the optimal vehicle group size and the CAV vehicle navigation principle. The initial vehicle group set is obtained by first dividing the simulated traffic flow data within the upstream control range of the bottleneck area. The feature vector of the vehicle group set is used as the state space, the merging, splitting and migration between vehicle groups are used as the action space, the single-step improvement of the vehicle group coefficient is used as the immediate reward, and the Mask-DQN model is trained with the goal of maximizing the vehicle group coefficient.

3. The dynamic speed limit control method for CAV vehicle navigator groups based on hierarchical collaborative control according to claim 2, characterized in that, The lane-changing behavior models for CAV vehicles and HDV vehicles are the same, where the lane-changing motivation is expressed as: Lane change safety verification is represented as follows: in, For lane changing motives in the first traffic zone, The lane-changing motive for the second passage area; 0 indicates no lane-changing motive, 1 indicates free lane-changing motive, and 2 indicates forced lane-changing motive. The speed difference between the vehicle in front and the vehicle in front; The speed difference threshold; For the exit lane, To reduce the number of lanes; This marks the boundary between the upstream and downstream sections of the second passage area. This is the current location of this vehicle. This vehicle, The position of vehicles behind the target lane; Position of the vehicle ahead in the target lane; This is the minimum acceptable clearance for lane changes.

4. The dynamic speed limit control method for CAV vehicle navigator groups based on hierarchical collaborative control according to claim 1, characterized in that, The optimal vehicle group size is calculated based on the maximum capacity of the bottleneck area, specifically: in, This represents the maximum traffic capacity of the bottleneck area. The expected speed of the vehicle group in the bottleneck area; The length of the road occupied by the group of vehicles; The desired spacing between the vehicles; The critical density of the bottleneck region; The critical velocity for the bottleneck region; The vehicle lane-changing rate for the downstream section of the second traffic zone; This is the capacity loss coefficient caused by lane-changing conflicts.

5. The dynamic speed limit control method for CAV vehicle navigator groups based on hierarchical collaborative control according to claim 1, characterized in that, If all leading vehicles in all lanes of an optimal vehicle group are CAV vehicles, then it is considered a CAV barrier vehicle group; otherwise, it is considered a CAV preceding barrier vehicle group. The calculation model for the target speed of the CAV barrier vehicle group is expressed as follows: in, This indicates the target speed of the CAV barrier vehicle group. To ensure real-time traffic flow in bottleneck areas; The length of road occupied by the CAV barrier vehicle group; The number of vehicles in the CAV barrier vehicle group; The desired spacing between the vehicles; The calculation model for the target velocity of the CAV preceding barrier vehicle group is expressed as follows: in, The total traffic flow of the CAV preceding barrier vehicle group; Traffic flow in the lane where the CAV vehicle is located; Traffic flow in the free-traffic lanes; The number of vehicles in the lane where the lead CAV is located in the preceding barrier vehicle group; The length of the group of vehicles in the lane where the lead CAV is located; The target speed for the CAV preceding barrier vehicle group; The free-flow speed in the free-movement lane; This represents the current density of the free-traffic lanes; The proportion of vehicles in the lane where the lead CAV vehicle is located that change lanes to the free-driving lane; The driving speed of the freely navigable lane obtained through iteration; Indicates the first The driving speed in the free-driving lane calculated in the next iteration; Indicates the first The driving speed in the free-driving lane calculated in the next iteration; This indicates the density of road congestion.

6. The dynamic speed limit control method for CAV vehicle navigator groups based on hierarchical collaborative control according to claim 1, characterized in that, The acceleration value of the lead CAV in the optimal vehicle group is expressed as: in, It is the first The optimal vehicle group's leading CAV vehicle in Calculated acceleration value at time t; For the first The target speed of the optimal vehicle group; For the first The optimal vehicle group's leading CAV vehicle in The vehicle speed at any given moment; For the first The actual distance between the optimal vehicle group and the downstream adjacent optimal vehicle group; For the first The maximum allowable acceleration of the lead CAV vehicle in an optimal vehicle group; For the first The distance decay function for an optimal vehicle group; For the first The optimal distance between the vehicle group and the bottleneck area; The attenuation coefficient; For the first The downstream adjacent optimal vehicle groups of the optimal vehicle groups are Average vehicle speed at any given time; , and All are proportional gain coefficients; It is the first The optimal vehicle group's leading CAV vehicle in The acceleration value at time t. For the first The optimal vehicle group's leading CAV vehicle in The acceleration value at any given moment; Constraints on the maximum change in acceleration between adjacent time points; For the first The minimum allowable acceleration for the lead CAV vehicle in an optimal vehicle group; This represents the desired spacing between the vehicles.

7. The dynamic speed limit control method for CAV vehicle navigator groups based on hierarchical collaborative control according to claim 1, characterized in that, The acceleration of the following CAV vehicle within the optimal vehicle group is calculated based on the speed of the lead CAV vehicle within the optimal vehicle group, and is expressed as: in, For the first The leading CAV vehicle in the optimal vehicle group The vehicle speed at any given moment; For the first In the optimal vehicle group, the following CAV vehicles The vehicle speed at any given moment; For the first In the optimal vehicle group, the following CAV vehicles Acceleration at any moment; For the first The longitudinal distance difference between the following CAV vehicle and the vehicle in front in the optimal vehicle group; This is the speed error gain coefficient; This is the distance error gain coefficient.

8. A dynamic speed limit control system for a CAV (Continuous Aerial Vehicle) navigator group based on hierarchical collaborative control, characterized in that, It includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the dynamic speed limit control method for a CAV vehicle navigator group based on hierarchical collaborative control as described in any one of claims 1-7 when running the computer program.

9. A storage medium, characterized in that, The storage medium stores a computer program, which, when executed by a processor, performs the dynamic speed limit control method for a CAV vehicle navigator group based on hierarchical collaborative control as described in any one of claims 1-7.

Images