Intersection vehicle guiding method
By optimizing the speed and acceleration of vehicles in the guidance area of the intersection, the problems of low traffic efficiency, high fuel consumption and poor emissions caused by traffic congestion at the intersection are solved, and more efficient vehicle traffic and lower fuel consumption and emissions are achieved.
Patent Information
- Application Number
- CN202411787494.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-06
- Publication Date
- 2025-03-18
AI Technical Summary
Traffic congestion in the intersection area leads to low vehicle traffic efficiency, high fuel consumption and poor emission indicators, and the existing technology is difficult to effectively solve these problems.
By obtaining the initial speed of the vehicle entering the guidance area, the distance from multiple intersections and the traffic light phase time, the vehicle's second-by-second speed and second-by-second acceleration in the guidance area are optimized to minimize the total time, fuel consumption and emissions of the vehicle passing through the intersection.
The traffic efficiency of vehicles passing through intersections has been improved, and fuel consumption and emission indicators have been reduced, which is specifically manifested as a reduction in fuel consumption by 10.20%, NOX, CH, and CO emissions have been reduced by 8.30%, 10.83% and 12.33%, and the total duration has been reduced by 5.22%.
Smart Images
Figure BDA0005174439410000021 
Figure BDA0005174439410000022 
Figure BDA0005174439410000023
Abstract
Description
Technical Field
[0001] The invention belongs to the field of intelligent transportation technology, and in particular relates to a vehicle guiding method at an intersection. Background Art
[0002] With the rapid development and continuous breakthroughs in computing, sensor fusion, communication interaction, and artificial intelligence in recent years, the research and exploration of the next generation of intelligent transportation systems and intelligent connected vehicles has been put on the agenda. Intersections, as the areas where vehicles most frequently meet and evacuate in the road environment, have attracted much attention. More and more economic losses and safety accidents are also related to traffic congestion in intersections. Therefore, how to improve the traffic safety and efficiency of the transportation system is the main problem at present. Summary of the invention
[0003] The purpose of the present invention is to provide a method for guiding vehicles at an intersection, which can guide vehicles passing through the intersection, improve vehicle traffic efficiency, and reduce fuel consumption and emission indicators of vehicles passing through the intersection.
[0004] The technical solution provided by the present invention is:
[0005] A method for guiding vehicles at an intersection comprises the following steps:
[0006] Step 1: Obtain the initial speed of the vehicle entering the guidance area, the distances between the vehicle and multiple intersections in front of the vehicle, and the phase durations of traffic lights at the multiple intersections;
[0007] Step 2: The total time for the vehicle to pass through the multiple intersections in front of the continuous straight line, the fuel consumption of the vehicle passing through the multiple intersections in front of the continuous straight line, and the NO X Taking the minimum CH and CO emissions as the optimization goal, the second-by-second speed and acceleration of the vehicle in the guidance area are optimized;
[0008] Step 3: Guide the speed of the vehicle in the guidance area with the optimized second-by-second speed and second-by-second acceleration.
[0009] Preferably, the step 2 further includes:
[0010] The optimization objective function is established as: min(f1+f2+f3);
[0011] Among them, f1 is the time cost function of the vehicle passing through multiple intersections ahead with continuous straight driving, f2 is the fuel consumption cost function of the vehicle passing through multiple intersections ahead with continuous straight driving, and f3 is the emission cost function of the vehicle passing through multiple intersections ahead with continuous straight driving.
[0012] Preferably, the calculation model of the time cost function of the vehicle passing through multiple intersections in front of the vehicle is:
[0013]
[0014] Where T is the total time it takes for the vehicle to pass through multiple intersections in a row, T y It is the total time it takes for a vehicle to pass through multiple intersections ahead at a constant speed.
[0015] Preferably, the calculation model of the fuel consumption cost function of the vehicle passing through multiple intersections in front of the vehicle is:
[0016]
[0017] Among them, F is the fuel consumption of the vehicle passing through multiple intersections in a row, F y It is the fuel consumption of the vehicle passing through multiple intersections with continuous straight traffic ahead at a constant speed.
[0018] Preferably, the calculation model of the emission cost function of the vehicle passing through multiple intersections in front of the vehicle is:
[0019]
[0020] in, E CO 、E CH They are the NO and NO of the vehicles passing through the multiple intersections ahead. X , CH, CO emissions, They are the NO and X , CH , CO emissions, w1, w2, w3 are weight coefficients respectively.
[0021] Preferably, in step 2, a particle swarm algorithm is used to optimize the second-by-second speed and acceleration of the vehicle in the guidance area, including:
[0022] Connect the second-by-second speed and acceleration of the vehicle in the guidance area into a vector, and use the vector as a particle in the solution space;
[0023] The fitness function is established as:
[0024] Among them, p i (x) is the i-th penalty function, i = 1, 2, 3;
[0025] Iteratively optimize the second-by-second speed and acceleration with the maximum fitness function, and obtain the global optimal solution for each iterative update;
[0026] When the number of iterations reaches the set maximum number of iterations, the iteration process stops;
[0027] The global optimal solution updated in the last iteration is used as the second-by-second speed and acceleration of the vehicle in the guidance area.
[0028] Preferably, the value of the first penalty function is:
[0029]
[0030] Among them, t p is the time when the vehicle passes through the signal intersection, g nm is the start time of the nth cycle green light at intersection m, r nm The time when the nth cycle red light starts at intersection m.
[0031] Preferably, the value of the second penalty function is:
[0032]
[0033] Where, v is the vehicle speed, v max The maximum speed limit for the current driving section.
[0034] Preferably, the value of the third penalty function is:
[0035]
[0036] Among them, d is the distance between the vehicle and the vehicle in front, and dmin is the minimum safe distance.
[0037] Preferably, the minimum safety distance is:
[0038]
[0039] Among them, a max is the maximum braking acceleration of the vehicle.
[0040] The beneficial effects of the present invention are:
[0041] The intersection vehicle guidance method provided by the present invention can guide vehicles passing through the intersection, improve vehicle traffic efficiency, and reduce fuel consumption and emission indicators of vehicles passing through the intersection. DETAILED DESCRIPTION
[0042] The present invention is described in further detail below so that those skilled in the art can implement it according to the description.
[0043] The present invention provides a method for guiding vehicles at an intersection, and the specific implementation process is as follows.
[0044] 1. Obtain the initial speed of the vehicle entering the guidance area, the distances between the vehicle and multiple intersections ahead that are continuously moving straight ahead, and the phase durations of traffic lights at the multiple intersections.
[0045] The starting line of the guidance area is set at 200 to 300 meters from the stop line of the intersection. The traffic light phase duration includes: red light phase duration, green light phase duration and yellow light phase duration.
[0046] Second, the total time it takes for a vehicle to pass through multiple intersections with continuous straight traffic ahead, the fuel consumption of a vehicle passing through multiple intersections with continuous straight traffic ahead, and the number of NO X The minimum CH4 and CO2 emissions are taken as the optimization objectives, and the second-by-second speed and acceleration of the vehicle in the guidance area are optimized.
[0047] In one embodiment, the optimization method is as follows.
[0048] The optimization objective function is established as: min(f1+f2+f3); and the second-by-second speed and acceleration of the vehicle in the guidance area are optimized according to the optimization objective function.
[0049] Among them, f1 is the time cost function of the vehicle passing through multiple intersections ahead with continuous straight driving, f2 is the fuel consumption cost function of the vehicle passing through multiple intersections ahead with continuous straight driving, and f3 is the emission cost function of the vehicle passing through multiple intersections ahead with continuous straight driving.
[0050] The calculation model of the time cost function of the vehicle passing through multiple intersections in front of the vehicle is:
[0051]
[0052] Where T is the total time it takes for the vehicle to pass through multiple intersections in a row, T y It is the total time it takes for a vehicle to pass through multiple intersections ahead at a constant speed.
[0053] The total time it takes for the vehicle to pass through multiple intersections ahead where it continues to go straight can be directly calculated based on the vehicle's second-by-second speed and second-by-second acceleration in the guidance area. The total time it takes for the vehicle to pass through multiple intersections ahead where it continues to go straight at a constant speed can also be directly calculated. Constant speed means that the vehicle's speed in the guidance area is always equal to the vehicle's initial speed when it enters the guidance area.
[0054] The calculation model of the fuel consumption cost function of the vehicle passing through multiple intersections in front of the vehicle is:
[0055]
[0056] Among them, F is the fuel consumption of the vehicle passing through multiple intersections in a row, F y It is the fuel consumption of the vehicle passing through multiple intersections with continuous straight traffic ahead at a constant speed.
[0057] The calculation model of the emission cost function of the vehicle passing through multiple intersections in front of the vehicle is:
[0058]
[0059] in, E CO 、E CH They are the NO and NO of the vehicles passing through the multiple intersections ahead. X , CH, CO emissions, They are the NO and X , CH , CO emissions, w1, w2, w3 are weight coefficients respectively.
[0060] After the vehicle enters the guidance area, the vehicle is controlled by the guidance strategy every second during the driving process. As a preferred embodiment, the VT-Micro model is used in this embodiment to calculate the fuel consumption and emissions of the vehicle during driving. The model uses unit efficiency (MOE) to calculate the fuel consumption and emissions of the vehicle. Simply input the speed and acceleration of the vehicle every second during driving into the formula to obtain the fuel consumption and emissions of the vehicle during driving. The MOE calculation formula is as follows:
[0061]
[0062] Among them, MOE e is the fuel consumption at time t (L·s -1 ) or emission (mg·s -1 ); v is the speed at time t (km·h -1 ); a is the acceleration at time t (km·h -1 ·s -1 ); i, j are speed and acceleration power exponents; is the regression coefficient when the velocity power index is i and the acceleration power index is j. X The NO emission of road vehicles can be calculated by using the regression coefficients of CH and CO emissions. X , CH and CO emissions. Using the VT-Micro model to calculate the fuel consumption and emissions of a vehicle during driving is an existing technology, which is only used as an example and will not be described in detail; other methods can also be used to calculate the fuel consumption and emissions of a vehicle during driving.
[0063] As a preference, in this embodiment, a particle swarm algorithm is used to optimize the second-by-second speed and acceleration of the vehicle in the guidance area, and the specific process includes:
[0064] The second-by-second speed and acceleration of the vehicle in the guidance area are connected into a vector, and the vector is used as a particle in the solution space.
[0065] The fitness function is established as:
[0066] Among them, p i (x) is the i-th penalty function, i=1,2,3.
[0067] The second-by-second speed and acceleration are iteratively optimized with the maximum fitness function, and the global optimal solution is obtained for each iterative update.
[0068] Among them, the update increment and updated value of particle i are expressed as:
[0069] ΔW i =kΔW i +c1r1(W pbest -W i )+c2r2(W gbest -W i );
[0070] W i+1 =W i +ΔW i ;
[0071] Where k is the inertia factor, which is a non-negative number, c1 and c2 are learning factors, r1 and r2 are random numbers uniformly distributed in the range (0,1), and W i+1 is the updated value of the particle, W i is the value before the example is updated, and ΔW is the incremental value used to update the particles.
[0072] When the number of iterations reaches the set maximum number of iterations, the iteration process stops.
[0073] The global optimal solution updated in the last iteration is used as the second-by-second speed and acceleration of the vehicle in the guidance area.
[0074] In this embodiment, the penalty function p is set according to the constraint conditions. i .
[0075] Constraint 1: The vehicle must pass through the intersection when the green light is on, so the first penalty function is set as:
[0076]
[0077] Among them, tp is the time when the vehicle passes through the signal intersection, g nm is the start time of the nth cycle green light at intersection m, r nm The time when the nth cycle red light starts at intersection m.
[0078] Constraint 2: The vehicle's speed cannot exceed the maximum speed limit of the driving section, so the second penalty function is set as:
[0079]
[0080] Where, v is the vehicle speed, v max The maximum speed limit for the current driving section.
[0081] Constraint 3: The distance between the vehicle and the vehicle in front cannot be less than the minimum safe distance, so the third penalty function is set as:
[0082]
[0083] Among them, d is the distance between the vehicle and the vehicle in front, and dmin is the minimum safe distance.
[0084] The minimum safety distance is:
[0085]
[0086] Among them, a max is the maximum braking acceleration of the vehicle.
[0087] Setting the constraints as penalty functions can quantify the constraints, improve the model training effect, and accelerate the convergence speed.
[0088] 3. Guide the speed of the vehicle in the guidance area with the optimized second-by-second speed and second-by-second acceleration.
[0089] In order to verify the effectiveness of the vehicle guidance method provided by the present invention, the V2X module and virtual sensor system in the intelligent vehicle simulation software PreScan were used to establish an intelligent network environment perception interaction system, and MATLAB / Simulink was used to develop and implement the control strategy for the moving vehicle. Finally, the traffic simulation software Vissim was used to quickly generate a traffic flow scene that was close to the real scene to simulate and verify the vehicle guidance method.
[0090] There are four intersections in the guidance area. The distance between the starting line of the guidance area and the adjacent intersections (signal lights) is set to 250m. The distances between the adjacent intersections that are planned to be passed straight through are 360m, 300m, and 220m respectively. The red light phase duration of the four intersections is set to be 20s, the green light phase duration is 30s, and the yellow light phase duration is 3s. The test shows that the NO lights of the guided vehicles passing through four consecutive signalized intersections are 20s, 30s, and 3s respectively. X The emissions of CH and CO (relative to the unguided case) were reduced by 8.30%, 10.83% and 12.33% respectively; the vehicle trajectory obtained by simulation was tested using a rotating hub test bench and it was found that compared with the unguided case, the fuel consumption of the optimized vehicle was reduced by 10.20%; the total passing time was reduced by 5.22%.
[0091] In this embodiment, the unguided condition is a real road section (the traffic conditions of the road section are basically the same as the simulation state) where 10 different drivers drive for more than 3 times, and the average value is taken to obtain the fuel consumption, NO X , CH , CO emissions and total transit time.
[0092] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation modes. They can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the embodiments shown and described herein.
Claims
1. A method for guiding vehicles at an intersection, characterized in that: The steps include: Step 1: Obtain the initial speed of the vehicle entering the guidance area, the distances between the vehicle and multiple intersections in front of the vehicle, and the phase durations of traffic lights at the multiple intersections; Step 2: The total time for the vehicle to pass through the multiple intersections in front of the continuous straight line, the fuel consumption of the vehicle passing through the multiple intersections in front of the continuous straight line, and the NO X Taking the minimum CH and CO emissions as the optimization goal, the second-by-second speed and acceleration of the vehicle in the guidance area are optimized; Step 3: Guide the speed of the vehicle in the guidance area with the optimized second-by-second speed and second-by-second acceleration.
2. The method for guiding vehicles at an intersection according to claim 1, characterized in that: In the step 2, it also includes: The optimization objective function is established as: min(f1+f2+f3); Among them, f1 is the time cost function of the vehicle passing through multiple intersections ahead with continuous straight driving, f2 is the fuel consumption cost function of the vehicle passing through multiple intersections ahead with continuous straight driving, and f3 is the emission cost function of the vehicle passing through multiple intersections ahead with continuous straight driving.
3. The method for guiding vehicles at an intersection according to claim 2, characterized in that: The calculation model of the time cost function of the vehicle passing through multiple intersections in front of the vehicle is: Where T is the total time it takes for the vehicle to pass through multiple intersections in a row, T y It is the total time it takes for a vehicle to pass through multiple intersections ahead at a constant speed.
4. The method for guiding vehicles at an intersection according to claim 3, characterized in that: The calculation model of the fuel consumption cost function of the vehicle passing through multiple intersections in front of the vehicle is: Among them, F is the fuel consumption of the vehicle passing through multiple intersections in a row, F y It is the fuel consumption of the vehicle passing through multiple intersections with continuous straight traffic ahead at a constant speed.
5. The intersection vehicle guidance method according to claim 3 or 4, characterized in that: The calculation model of the emission cost function of the vehicle passing through multiple intersections in front of the vehicle is: in, E CO 、E CH They are the NO and NO of the vehicles passing through the multiple intersections ahead. X , CH, CO emissions, They are the NO and X , CH , CO emissions, w1, w2, w3 are weight coefficients respectively.
6. The method for guiding vehicles at an intersection according to claim 5, characterized in that: In the step 2, a particle swarm algorithm is used to optimize the second-by-second speed and acceleration of the vehicle in the guidance area, including: Connect the second-by-second speed and acceleration of the vehicle in the guidance area into a vector, and use the vector as a particle in the solution space; The fitness function is established as: Among them, p i (x) is the i-th penalty function, i = 1, 2, 3; Iteratively optimize the second-by-second speed and acceleration with the maximum fitness function, and obtain the global optimal solution for each iterative update; When the number of iterations reaches the set maximum number of iterations, the iteration process stops; The global optimal solution updated in the last iteration is used as the second-by-second speed and acceleration of the vehicle in the guidance area.
7. The method for guiding vehicles at an intersection according to claim 6, characterized in that: The value of the first penalty function is: Among them, t p is the time when the vehicle passes through the signal intersection, g nm is the start time of the nth cycle green light at intersection m, r nm The time when the nth cycle red light starts at intersection m.
8. The method for guiding vehicles at an intersection according to claim 7, characterized in that: The value of the second penalty function is: Where, v is the vehicle speed, v max The maximum speed limit for the current driving section.
9. The method for guiding vehicles at an intersection according to claim 8, characterized in that: The value of the third penalty function is: Among them, d is the distance between the vehicle and the vehicle in front, and dmin is the minimum safe distance.
10. The method for guiding vehicles at an intersection according to claim 9, characterized in that: The minimum safety distance is: Among them, a max is the maximum braking acceleration of the vehicle.