An intelligent vehicle cyber-physical system uncertainty perception speed optimization method

Abstract

This invention provides a speed optimization method for uncertainty perception in intelligent vehicle cyber-physical systems, belonging to the field of intelligent transportation technology. The method includes: collecting vehicle and traffic flow operational status data and transmitting it to the information layer for fusion analysis; constructing multi-temporal and spatial scale traffic state models at the vehicle, road, and regional levels; establishing speed optimization models for fuel consumption, congestion uncertainty, and travel time risks; using a swarm intelligence optimization algorithm to solve for recommended speeds for different road segments and distributing them; vehicles responding to the recommended speeds based on an information-guided intelligent driver model to achieve real-time control; and transmitting the vehicle's response data back to the information layer to update the model and re-execute optimization. This invention, through multi-temporal and spatial scale modeling and uncertainty feature quantification, constructs a closed-loop feedback mechanism for macro-level traffic optimization and micro-level vehicle behavior control, effectively improving traffic system operating efficiency, reducing fuel consumption, and shortening travel time.

Description

Technical Field

[0001] This invention belongs to the field of intelligent transportation technology, particularly the field of traffic cooperative optimization technology for connected and autonomous vehicles, and relates to an uncertainty perception speed optimization method for intelligent vehicle cyber-physical systems (IVCPS). Background Technology

[0002] Urban transportation systems are characterized by strong dynamism and uncertainty, with problems such as traffic congestion, excessive fuel consumption, and large fluctuations in travel time becoming increasingly prominent. Traditional human-driven vehicles, lacking global traffic information coordination, are prone to exacerbating macro-level traffic congestion due to micro-driving behaviors (such as unreasonable rapid acceleration and deceleration). Furthermore, existing speed optimization methods for connected and autonomous vehicles (CAVs) largely focus on single-vehicle local control or single-segment optimization, exhibiting two major drawbacks: 1) The systematic quantification and modeling of uncertainties such as traffic flow congestion status and travel time are neglected, resulting in poor adaptability of optimization strategies to complex dynamic traffic environments; 2) Macro-level traffic flow optimization and micro-level vehicle behavior control are disconnected. Global optimization decisions cannot be efficiently mapped to micro-level vehicle behavior, and the lack of a two-way feedback closed-loop control mechanism makes it difficult to implement optimization results.

[0003] Intelligent Vehicle Cyber-Physical Systems (IVCPS) achieve real-time control of traffic data perception, transmission, computation, and vehicle behavior through the fusion and collaboration of the information and physical layers, providing a technological foundation for solving the aforementioned problems. While existing IVCPS research has achieved multi-level acquisition of traffic data, it has not constructed a multi-temporal and spatial scale traffic state quantification model, nor has it established a macro-micro closed-loop speed optimization system based on uncertainty characteristics, thus failing to achieve global collaborative optimization of the traffic system.

[0004] Based on this, this invention proposes an uncertainty-perceived speed optimization method for IVCPS. By modeling traffic conditions at multiple spatiotemporal scales, quantifying uncertainty features, solving macro-optimization objectives, and implementing information-guided vehicle behavior responses, a closed-loop feedback control mechanism for macro-traffic optimization and micro-vehicle behavior is constructed, solving the technical problems of existing methods such as "poor adaptability, macro-micro separation, and difficulty in implementing optimization effects". Summary of the Invention

[0005] In view of this, the purpose of this invention is to provide an uncertainty-perceived speed optimization method for intelligent vehicles, addressing the shortcomings of existing intelligent vehicle speed optimization methods, such as lack of uncertainty perception, separation of macro and micro optimization, and poor adaptability to complex traffic environments.

[0006] To achieve the above objectives, the present invention provides the following technical solution: A method for optimizing the uncertainty perception speed of an intelligent vehicle cyber-physical system, the method specifically includes the following steps: S1. Collect vehicle operation status data and traffic flow operation status data through the vehicle-mounted unit and the roadside unit, and transmit the data to the information layer for traffic status fusion analysis; S2. Construct a multi-temporal and spatial scale traffic state model at the vehicle layer, road layer, and regional layer to achieve a quantitative description of the multi-dimensional operation state of the traffic system; S3. Establish a speed optimization model based on the characteristics of fuel consumption, congestion uncertainty, and travel time risk in the operation of the traffic system. Use a swarm intelligence optimization algorithm to solve the speed optimization model to obtain recommended speeds for different road segments, and send the recommended speeds to the vehicle control system. S4. The vehicle responds to the recommended speed based on the information-guided intelligent driver model to achieve real-time control of vehicle behavior; S5. The vehicle's operational status data after response is sent back to the information layer to update the traffic status fusion analysis and the multi-temporal-scale traffic status model, and step S3 is re-executed.

[0007] Furthermore, in step S1, the vehicle operation status data and traffic flow operation status data include vehicle speed, vehicle acceleration, vehicle position, headway, traffic flow density, traffic volume, and average road speed.

[0008] Furthermore, in step S2, the multi-temporal and spatial scale traffic state model includes: 1) Vehicle layer model, used to describe the motion state of a single vehicle: Vehicle data is recorded in individual form, assuming the vehicle... On the road The state variables on the table include: position ,speed acceleration Distance from the vehicle in front ; 2) Road layer model, used to describe the traffic operation status of a single road segment; assuming the road... Include Each team Include vehicle ( ), define the fleet The average headway and average speed are and Its dynamic update formula is:

[0009] in, For the speed of the lead car in the convoy, For discrete time steps, This refers to the number of vehicles in the convoy. For the section The average headway and average speed are calculated as follows:

[0010]

[0011] Road segment density and traffic flow, derived from average headway and average speed, can be expressed as:

[0012] ; 3) Regional layer model, used to describe the overall operation of the traffic network: The density and flow of each road segment are weighted and mapped to the regional center, and a distance-based attenuation function is used to calculate the regional density and regional flow.

[0013]

[0014] in, As a weighting factor, it reflects the distance decay effect; For road section To the area The shortest path distance to the center; The attenuation coefficient; This is the normalization constant.

[0015] Furthermore, in step S3, the speed optimization model takes fuel consumption, congestion uncertainty, travel time risk, and vehicle driving comfort as optimization objectives, and uses the recommended speed for each road segment. The actual vehicle speed is obtained through a vehicle response model, serving as the decision variable. With acceleration The objective function is calculated accordingly; the objective function is constructed in a weighted single-objective form, and is expressed as:

[0016] st

[0017]

[0018] in, , , , These are the weighting coefficients for each optimization objective; For vehicles On the road section The actual driving speed For roads Speed ​​limit For vehicles acceleration, and These are the maximum and minimum permissible accelerations for the vehicle, respectively. For road section Average fuel consumption For road section The overall congestion uncertainty entropy mean, For road section The risk value of travel time.

[0019] Furthermore, the aforementioned road section average fuel consumption The calculation method is as follows: First, calculate the vehicle. Instantaneous fuel consumption rate:

[0020] in, It is the vehicle's instantaneous fuel consumption rate; and Representing the instantaneous speed of the vehicle and acceleration The index; represent and The corresponding model regression coefficients; Recalculate vehicles Passing through the section fuel consumption :

[0021] Final calculation of road segment average fuel consumption :

[0022] in For passing through the section The number of vehicles, For vehicles Passing through the section The time.

[0023] Furthermore, the aforementioned road section Overall congestion uncertainty mean The calculation method is as follows: First, calculate the road segment. At any moment Instantaneous uncertainty entropy :

[0024] in, For road section At any moment Instantaneous uncertainty entropy, Represents a discrete velocity range. The number of intervals to be divided. Indicates at time Below, section of road The speed of the vehicle inside fell into the first The probability of a speed range; Recalculate road segments Overall congestion uncertainty mean :

[0025] in, For passing through the section The number of vehicles; this indicator reflects the degree of fluctuation in the traffic status of a road segment by summarizing the road segment entropy over time.

[0026] Furthermore, the aforementioned road section Trip time risk value The calculation method is as follows:

[0027]

[0028]

[0029] in Indicates the vehicle Along a specific section of road Travel time, It is a trade-off factor; These are parameters used to adjust the system's sensitivity to extreme travel time deviations.

[0030] Furthermore, in step S4, the expression for the information-guided intelligent driver model is:

[0031] The expressions for the weighted speed difference of multiple preceding vehicles and the weighted headway are as follows:

[0032]

[0033] in, For the first The weighting coefficient of the preceding vehicle is expressed as:

[0034] in, Indicates vehicle acceleration. For the desired maximum acceleration, For vehicle speed, Recommended traffic speeds for road sections issued by the information layer. Indicates reaction time. Indicates comfortable deceleration; Indicates consideration of the future The weighted average speed difference between the vehicle and the optimal speed; Indicates consideration of the future The weighted average distance between vehicles. Indicates the first The distance between the vehicles in front; For the first The distance between the vehicle in front and the main vehicle.

[0035] Furthermore, the swarm intelligence optimization algorithm described in step S3 is a genetic algorithm.

[0036] The beneficial effects of this invention are as follows: This invention incorporates fuel consumption, congestion uncertainty, and travel time risk into speed optimization objectives. Through quantitative modeling, it achieves precise perception of the multi-dimensional uncertainties in the traffic system, significantly improving the adaptability of optimization strategies to complex and dynamic traffic environments. Based on the IVCPS information-physical layer architecture, it achieves bidirectional feedback between macro-level traffic network optimization decisions and micro-level vehicle behavior control, solving the core problem of existing methods' "separation of macro and micro levels, and difficulty in implementing optimization effects." It constructs a multi-temporal-scale model at the vehicle, road, and regional levels, realizing a full-dimensional description of the operational status from individual vehicles to regional traffic networks, providing a precise quantitative foundation for global optimization. Through an information-guided intelligent driver model, it achieves collaborative control of vehicle behavior. Simulation verification shows that this invention can effectively reduce traffic congestion, decrease vehicle fuel consumption, shorten travel time, and reduce travel time risk.

[0037] Other advantages, objectives, and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination, or may be learned from practice of the invention. The objectives and other advantages of the invention can be realized and obtained through the following description. Attached Figure Description

[0038] To make the objectives, technical solutions, and advantages of the present invention clearer, the preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings, wherein: Figure 1 This is a schematic diagram of the overall framework of the speed optimization method for intelligent vehicle cyber-physical systems of the present invention; Figure 2 This is a comparison chart of the average vehicle travel time under the IG-IDM model and the traditional IDM model in this embodiment of the invention; Figure 3 This is a comparison chart of the average travel speed of vehicles under the IG-IDM model and the traditional IDM model in this embodiment of the invention; Figure 4 This is a scatter plot of the time distribution of vehicle loss in a traditional IDM model. Figure 5 This is a scatter plot of the vehicle loss time distribution of the IG-IDM model in an embodiment of the present invention. Detailed Implementation

[0039] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Unless otherwise specified, the following embodiments and features can be combined with each other.

[0040] The accompanying drawings are for illustrative purposes only and are schematic diagrams, not actual pictures. They should not be construed as limiting the invention. To better illustrate the embodiments of the invention, some parts in the drawings may be omitted, enlarged, or reduced, and do not represent the actual product dimensions. It is understandable to those skilled in the art that some well-known structures and their descriptions may be omitted in the drawings.

[0041] In the accompanying drawings of the embodiments of the present invention, the same or similar reference numerals correspond to the same or similar components. In the description of the present invention, it should be understood that if terms such as "upper," "lower," "left," "right," "front," and "rear" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, they 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, or be constructed and operated in a specific orientation. Therefore, the terms used to describe positional relationships in the drawings are only for illustrative purposes and should not be construed as limiting the present invention. For those skilled in the art, the specific meaning of the above terms can be understood according to the specific circumstances.

[0042] Please see Figures 1-5 This invention provides a method for speed optimization based on uncertainty perception in an intelligent vehicle cyber-physical system. Example 1: 1. Basic setup for simulation experiments To verify the effectiveness of the uncertainty-aware speed optimization method for intelligent vehicle cyber-physical systems described in this invention, this embodiment uses a co-simulation platform built with Python and SUMO for experimental verification. The specific experimental setup is as follows: Simulation scenario: Urban road network; The fuel consumption model parameters are shown in Table 1.

[0043] Table 1

[0044] The remaining core model parameters are shown in Table 2: Table 2

[0045] The simulation lasted for 1000 seconds, and a total of 568 vehicles were deployed.

[0046] Comparison Models: The traditional Intelligent Driver Model (IDM) and the information-guided intelligent driver model (IG-IDM) of this invention were compared. Traffic operation index data were collected from both models (traditional IDM and IG-IDM) for statistical analysis and comparison.

[0047] 2. Experimental Results and Analysis This invention collected 11 core traffic operation indicators under two different models through the above simulation experiments, and performed statistical analysis using t-tests. The experimental results are shown in Table 3. Table 3

[0048] The following conclusions can be drawn from the experimental results: The IG-IDM model of this invention shows significant differences from the traditional IDM model in terms of the number of vehicles in operation and the number of vehicles that have arrived (p<0.0001). The number of vehicles in operation and arriving under the IG-IDM model is increased by 17.6%, indicating that the method of this invention can significantly improve the vehicle traffic efficiency of the transportation system and reduce road vehicle congestion. The model of this invention has significant advantages (p<0.0001) in terms of average travel duration, average travel waiting time, and average travel loss time, reducing them by 13.2%, 41.8%, and 29.0%, respectively. This indicates that the method of this invention can effectively shorten vehicle travel time and reduce vehicle road waiting and time loss. The model of this invention reduces the average fuel consumption by 13.5% (p<0.0001) and improves the average travel speed by 52.8% (p<0.0001) compared with the traditional IDM model, indicating that the method of this invention can significantly reduce vehicle fuel consumption while increasing vehicle speed, thus achieving energy-saving and efficient operation of the transportation system. There were no significant differences between the two models in terms of departing vehicles, average departure delay, and number of stops (p>0.05), indicating that the method of the present invention improves traffic efficiency without negatively affecting vehicle departure rules and parking behavior, and the model has good stability.

[0049] In summary, the uncertainty-aware speed optimization method for intelligent vehicle cyber-physical systems described in this invention can effectively improve the operational efficiency of transportation systems, reduce fuel consumption, and shorten vehicle travel time. It solves the problems of macro-micro optimization separation and lack of uncertainty awareness in existing methods, and has significant technical advantages and engineering application value.

[0050] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for optimizing the speed of uncertainty perception in an intelligent vehicle cyber-physical system, characterized in that, The method specifically includes the following steps: S1. Collect vehicle operation status data and traffic flow operation status data through the vehicle-mounted unit and the roadside unit, and transmit the data to the information layer for traffic status fusion analysis; S2. Construct a multi-temporal and spatial scale traffic state model at the vehicle layer, road layer, and regional layer to achieve a quantitative description of the multi-dimensional operation state of the traffic system; S3. Establish a speed optimization model based on the characteristics of fuel consumption, congestion uncertainty, and travel time risk in the operation of the traffic system. Use a swarm intelligence optimization algorithm to solve the speed optimization model to obtain recommended speeds for different road segments, and send the recommended speeds to the vehicle control system. S4. The vehicle responds to the recommended speed based on the information-guided intelligent driver model to achieve real-time control of vehicle behavior; S5. The vehicle's operational status data after response is sent back to the information layer to update the traffic status fusion analysis and the multi-temporal-scale traffic status model, and step S3 is re-executed.

2. The method for speed optimization of uncertainty perception in intelligent vehicle cyber-physical systems according to claim 1, characterized in that, In step S1, the vehicle operation status data and traffic flow operation status data include vehicle speed, vehicle acceleration, vehicle position, headway, traffic flow density, traffic volume, and average road speed.

3. The method for speed optimization of uncertainty perception in intelligent vehicle cyber-physical systems according to claim 2, characterized in that, In step S2, the multi-temporal and spatial scale traffic state model includes: 1) Vehicle layer model, used to describe the motion state of a single vehicle: Vehicle data is recorded in individual form, assuming the vehicle... On the road The state variables on the table include: position ,speed acceleration Distance from the vehicle in front ; 2) Road layer model, used to describe the traffic operation status of a single road segment; assuming the road... Include Each team Include Vehicles, defining a fleet The average headway and average speed are and Its dynamic update formula is: in, For the speed of the lead car in the convoy, For discrete time steps, This refers to the number of vehicles in the convoy. For the section The average headway and average speed are calculated as follows: Road segment density and traffic flow, derived from average headway and average speed, can be expressed as: ； 3) Regional layer model, used to describe the overall operation of the traffic network: The density and flow of each road segment are weighted and mapped to the regional center, and a distance-based attenuation function is used to calculate the regional density and regional flow. in, As a weighting factor, it reflects the distance decay effect; For road section To the area The shortest path distance to the center; The attenuation coefficient; This is the normalization constant.

4. The method for speed optimization of uncertainty perception in intelligent vehicle cyber-physical systems according to claim 3, characterized in that, In step S3, the speed optimization model takes fuel consumption, congestion uncertainty, travel time risk, and vehicle driving comfort as optimization objectives, and uses the recommended speed for each road segment. The actual vehicle speed is obtained through a vehicle response model, serving as the decision variable. With acceleration The objective function is calculated accordingly; the objective function is constructed in a weighted single-objective form, and is expressed as: st in, , , , These are the weighting coefficients for each optimization objective; For vehicles On the road section The actual driving speed For roads Speed ​​limit For vehicles acceleration, and These are the maximum and minimum permissible accelerations for the vehicle, respectively. For road section Average fuel consumption For road section The overall congestion uncertainty entropy mean, For road section The risk value of travel time.

5. The method for speed optimization of uncertainty perception in intelligent vehicle cyber-physical systems according to claim 4, characterized in that, The road section average fuel consumption The calculation method is as follows: First, calculate the vehicle. Instantaneous fuel consumption rate: in, It is the vehicle's instantaneous fuel consumption rate; and Representing the instantaneous speed of the vehicle and acceleration The index; represent and The corresponding model regression coefficients; Recalculate vehicles Passing through the section fuel consumption : Final calculation of road segment average fuel consumption : in For passing through the section The number of vehicles, For vehicles Passing through the section The time.

6. The method for speed optimization of uncertainty perception in intelligent vehicle cyber-physical systems according to claim 4, characterized in that, The road section Overall congestion uncertainty mean The calculation method is as follows: First, calculate the road segment. At any moment Instantaneous uncertainty entropy : in, For road section At any moment Instantaneous uncertainty entropy, Represents a discrete velocity range. The number of intervals to be divided. Indicates at time Below, section of road The speed of the vehicle inside fell into the first The probability of a speed range; Recalculate road segments Overall congestion uncertainty mean : in, For passing through the section The number of vehicles; this indicator reflects the degree of fluctuation in the traffic status of a road segment by summarizing the road segment entropy over time.

7. The method for speed optimization of uncertainty perception in intelligent vehicle cyber-physical systems according to claim 4, characterized in that, The road section Trip time risk value The calculation method is as follows: in Indicates the vehicle Along a specific section of road Travel time, It is a trade-off factor; These are parameters used to adjust the system's sensitivity to extreme travel time deviations.

8. The method for speed optimization of uncertainty perception in intelligent vehicle cyber-physical systems according to claim 1, characterized in that, In step S4, the expression for the information-guided intelligent driver model is: The expressions for the weighted speed difference of multiple preceding vehicles and the weighted headway are as follows: in, For the first The weighting coefficient of the preceding vehicle is expressed as: in, Indicates vehicle acceleration. For the desired maximum acceleration, For vehicle speed, The recommended traffic speed for road sections is issued by the information layer. Indicates reaction time. Indicates comfortable deceleration; Indicates consideration of the future The weighted average speed difference between the vehicle and the optimal speed; Indicates consideration of the future The weighted average distance between vehicles, Indicates the first The distance between the vehicles in front; For the first The distance between the vehicle in front and the main vehicle.

9. The method for speed optimization of uncertainty perception in intelligent vehicle cyber-physical systems according to claim 1, characterized in that, The swarm intelligence optimization algorithm mentioned in step S3 is a genetic algorithm.

Images