Vehicle and road cloud collaborative decision framework based on time window

Abstract

The invention provides a vehicle and road cloud collaborative decision framework based on a time window, and belongs to the field of vehicle and road cloud integrated collaborative decision, and the framework comprises the following steps: 1) calculating a feasible driving state space of a guided vehicle; 2) dividing a time window guide sequence; 3) obtaining the probability that the traffic signal is a green light in the feasible driving state space range at the last decision point; 4) calculating the costs of all time window guide sequences; and 5) optimizing an optimal time window guiding sequence, and transmitting the optimal time window guiding sequence to the guided vehicle. Compared with the prior art, the method has the advantages that the cooperative guidance decision in the'vehicle-road cloud 'integrated environment is completed based on the time window, the fault-tolerant capability of the'vehicle-road cloud' integrated cooperative decision is improved, the operation efficiency of a traffic system is improved, and the energy consumption and pollution of vehicle driving are reduced.

Description

Technical Field

[0001] The present invention belongs to the field of "vehicle-road-cloud" integrated collaborative decision-making, and in particular relates to a "vehicle-road-cloud" collaborative decision-making framework based on a time window. Background Art

[0002] The integration of "vehicle, road and cloud" aims to combine traffic participants, autonomous vehicles, cloud control centers, roadside infrastructure, related support platforms, and communication networks into a large and complex system through intelligent network technology, and ultimately form smart cars, smart roads, high-speed ubiquitous networks, and clouds with powerful computing capabilities. Compared with traditional single-vehicle intelligence, the integration of "vehicle, road and cloud" greatly improves the operating efficiency of the transportation system, enhances traffic safety, and reduces environmental pollution through beyond-visual-range perception of traffic situations, heterogeneous granularity management of traffic participants, and multi-dimensional prediction of traffic conditions.

[0003] Based on the "vehicle-road-cloud" integrated system, collaborative decision-making technology has experienced explosive growth. By assisting vehicles in making decisions about driving behavior, collaborative decision-making technology optimizes the vehicle's driving trajectory, improves driving safety, ensures driving efficiency, and effectively reduces the vehicle's energy consumption and environmental pollution.

[0004] However, traditional collaborative decision-making technology often focuses on driving speed decisions, guiding vehicles by providing real-time feedback on the optimal speed. When applied to intelligent connected vehicles with high computing power and strong agility, it usually achieves certain results. However, traditional collaborative decision-making technology cannot be applied to human-driven vehicles, because drivers not only need to pay attention to road conditions at all times, but also need to accurately track the time-varying optimal speed, which will cause major safety hazards. In summary, traditional collaborative decision-making technology has defects and cannot be applied to traffic environments where intelligent connected vehicles and human-driven vehicles are mixed. Summary of the invention

[0005] The purpose of the present invention is to provide a time window-based "vehicle-road-cloud" collaborative decision-making framework, which is characterized by comprising the following steps:

[0006] S1. Calculate the feasible driving state space of the guided vehicle; the feasible driving state space is Figure 2 Gray area number 1.

[0007] S2. Based on the feasible driving state space, the time window guidance sequence is divided; the time window guidance sequence refers to Figure 2 Gray area number 2 in the diagram.

[0008] S3, obtaining the probability that the traffic signal is green within the feasible driving state space at the last decision point;

[0009] S4, calculating the costs of all time window guide sequences;

[0010] S5. Optimize the optimal time window guidance sequence and transmit it to the guided vehicle.

[0011] Furthermore, in S1, the feasible driving state space can be expressed as and A collection of i = 0 ~ I, see the schematic diagram Figure 2 (I), where and At decision point s i At , the upper and lower limits of the feasible driving state space are calculated as follows:

[0012]

[0013] If the constraint Be satisfied,

[0014] So

[0015] otherwise

[0016] Where i is the subscript of the decision point; i is the last decision point s I Subscript of; s I is the position of the stop line;

[0017] and At decision point s i The upper and lower limits of vehicle speed;

[0018] a max with a min are the maximum and minimum acceleration of the vehicle respectively;

[0019] Δs i is the distance between two adjacent decision points;

[0020] v max With v min These are the maximum and minimum speed limits on the road.

[0021] Furthermore, in S2, the time window guidance sequence is divided based on the feasible driving state space, and the specific steps are as follows:

[0022] S21, the interval Divide into sub-intervals The length of each subinterval is Δt, and the interval between adjacent subintervals is τ. and are respectively the mth time window guide sequence at the decision point s I The lower and upper limits of the guidance time at are expressed as follows:

[0023]

[0024] and The constraints that need to be satisfied are expressed as:

[0025]

[0026] S22, calculating the sub-interval described in S21 The median value The calculation formula is expressed as:

[0027]

[0028] S23, assuming that the vehicle starts to move at a uniform speed from the initial position s0, the initial speed is v0, and the end point of the movement is s I , exercise duration is Then we can get The calculation formula is expressed as:

[0029]

[0030] in, is the guidance acceleration of the guidance sequence in the mth time window;

[0031] S24, assuming that the vehicle Perform uniformly accelerated motion, with the starting point being the initial position s0, the initial velocity being v0, the initial time being t0, and the end point being s i , we can get The calculation formula is expressed as:

[0032]

[0033] in, is the mth time window guiding sequence at decision point s i The guiding speed at

[0034] and are the mth time window guide sequence at decision point s i The upper and lower limits of the boot time at ;

[0035] S25, the mth time window guide sequence is expressed as and A set of, i = 0 ~ i, see the schematic diagram Figure 2 (II).

[0036] Furthermore, in S3, the feasible driving state space range at the last decision point refers to the interval The time range included; the probability that the traffic signal is green can be obtained through the technology in the existing invention patent with patent number 202410029137.3.

[0037] Furthermore, in S4, the costs of all time window guide sequences are calculated, as shown in the schematic diagram. Figure 2 (III), specifically comprising the following steps:

[0038] S41. Calculate the energy consumption cost of the time window. The calculation formula is expressed as:

[0039]

[0040] in, is the time window energy cost of the mth time window guided sequence;

[0041] v0 is the initial velocity;

[0042] is the guidance acceleration of the guidance sequence in the mth time window;

[0043] is the mth time window guiding sequence at decision point s I The median boot time at ;

[0044] VTmicro(v0,a,t) represents the energy consumption calculated by the VTmicro model when the initial velocity is v0, the acceleration is a, and the movement time is t.

[0045] S42. Calculate the cost of traffic efficiency. The calculation formula is:

[0046]

[0047] in, is the travel efficiency cost of the mth time window guidance sequence;

[0048] is the mth time window guiding sequence at decision point s I The median boot time at ;

[0049] It's in time The probability that the traffic light is green at ;

[0050] S43, calculating the cost of successful passage, the calculation formula is expressed as:

[0051]

[0052] in, is the cost of successful passage of the mth time window guidance sequence;

[0053] is the mth time window guiding sequence at decision point s I The guiding speed at

[0054] a ref is the reference ecological acceleration;

[0055] v des is the expected speed;

[0056] S44. Calculate the cost of failed passage, the calculation formula is expressed as:

[0057]

[0058] in, is the failure pass cost of the m-th time window guidance sequence.

[0059] Further, in S5, the optimal time window guidance sequence is selected and transmitted to the guided vehicle, which specifically includes the following steps:

[0060] S51, calculate the total cost of all time window guide sequences, the calculation formula is expressed as:

[0061]

[0062] in, The total cost of the mth time window guide sequence;

[0063] κ is the weight, ranging from 0 to 1;

[0064] S52. Compare the total costs described in S51. The smallest one is the optimal time window guide sequence. See the schematic diagram. Figure 2 (IV);

[0065] S53, transmit the optimal time window guidance sequence to the intelligent network driving vehicle through the vehicle-road-cloud integrated system; transmit the optimal time window guidance sequence to the human driving vehicle through the navigation platform, as shown in the schematic diagram Figure 3 . BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 This is a flow chart of a vehicle-road-cloud collaborative decision-making framework based on a time window of the present invention.

[0067] Figure 2 Schematic diagram of modeling and calculation for time window guided sequence.

[0068] Figure 3 Schematic diagram of delivering the optimal time window guidance sequence to the human-driven vehicle through the navigation platform. DETAILED DESCRIPTION

[0069] The following will be described in more detail with reference to a schematic diagram of a time window-based vehicle-road-cloud collaborative decision-making framework of the present invention, in which a preferred embodiment of the present invention is shown. It should be understood that those skilled in the art can modify the present invention described herein and still achieve the beneficial effects of the present invention. Therefore, the following description should be understood as being widely known to those skilled in the art and not as a limitation to the present invention.

[0070] like Figure 1 As shown, a vehicle-road-cloud collaborative decision framework based on a time window specifically includes the following steps:

[0071] Step 1

[0072] Calculate the feasible driving state space of the guided vehicle.

[0073] The feasible driving state space can be expressed as and A collection of i = 0 ~ I, see the schematic diagram Figure 2 (I).

[0074] in, and At decision point s i At , the upper and lower limits of the feasible driving state space are calculated as follows:

[0075]

[0076] If the constraint Be satisfied,

[0077] So

[0078] otherwise

[0079] Where i is the subscript of the decision point; i is the last decision point s I Subscript of; s I is the position of the stop line;

[0080] and At decision point s i The upper and lower limits of vehicle speed;

[0081] a max with a min are the maximum and minimum acceleration of the vehicle respectively;

[0082] Δs i is the distance between two adjacent decision points;

[0083] v max With v minThese are the maximum and minimum speed limits on the road.

[0084] In this example, let Second, Meters per second, a max =3 meters per second squared, a min = -4 meters per second squared, v max = 25 m / s, v min =5 meters per second, Δs i =10 meters, I=10.

[0085] When i = 0, we can calculate Meters per second, Meters per second, constraints Satisfied, calculated, Second, Second.

[0086] By analogy, we can calculate: Second, Second.

[0087] Step 2

[0088] Based on the feasible driving state space, the time window guidance sequence is divided. The specific steps are as follows:

[0089] (1) The interval Divide into sub-intervals The length of each subinterval is Δt, and the interval between adjacent subintervals is τ. and are respectively the mth time window guide sequence at the decision point s I The lower and upper limits of the guidance time at are expressed as follows:

[0090]

[0091] and The constraints that need to be satisfied are expressed as:

[0092]

[0093] In this example, let Δt = 3 seconds, τ = 1 second, and m = 3. Then, we can calculate: Second, Seconds, constraints Be satisfied.

[0094] (2) Calculate the subinterval described in step 2(1) The median value The calculation formula is expressed as:

[0095]

[0096] In this example, from step 2(1), Second, Seconds, calculated, Second.

[0097] (3) Assume that the vehicle starts from the initial position s0 and moves at a uniform speed, with an initial velocity of v0 and a moving end point of s I , exercise duration is Then we can get The calculation formula is expressed as:

[0098]

[0099] in, is the guidance acceleration of the guidance sequence in the mth time window;

[0100] In this example, let Δs i =10 meters, I = 10, after calculation, we can get, s I = 100 m, assuming s0 = 0 m, v0 = 15 m / s, from step 2(2) we get Seconds, calculated, Meters per second squared.

[0101] (4) Assume that the vehicle Perform uniformly accelerated motion, with the starting point being the initial position s0, the initial velocity being v0, the initial time being t0, and the end point being s i , we can get The calculation formula is expressed as:

[0102]

[0103] in, is the mth time window guiding sequence at decision point s i The guiding speed at

[0104] and are the mth time window guide sequence at decision point s i The upper and lower limits of the boot time at ;

[0105] In this example, let i = 5, Δs i = 10 meters, we can calculate that s i =50 m, assuming v0 = 15 m / s, from step 2(3) we get Meters per second squared, calculated to be Meters per second, assuming Δt = 3 seconds, t0 = 0 seconds, we can calculate: Second, Second.

[0106] Similarly, when i=0~I, calculate the rest and

[0107] (5) The mth time window guide sequence is expressed as and A collection of i = 0 ~ I, see the schematic diagram Figure 2 (II).

[0108] Step 3

[0109] Get the probability that the traffic signal is green within the feasible driving state space at the last decision point.

[0110] Among them, the feasible driving state space range at the last decision point refers to the interval The time range included; the probability that the traffic signal is green can be obtained through the technology in the existing invention patent with patent number 202410029137.3.

[0111] In this example, step 2(2) yields Seconds, set at time At , the probability that the traffic light is green is 0.61.

[0112] Step 4

[0113] Calculate the costs of all time window guide sequences, see the schematic diagram Figure 2 (III), specifically comprising the following steps:

[0114] (1) Calculate the energy consumption cost of the time window. The calculation formula is expressed as:

[0115]

[0116] in, is the time window energy cost of the mth time window guided sequence;

[0117] v0 is the initial velocity;

[0118] is the guidance acceleration of the guidance sequence in the mth time window;

[0119] is the mth time window guiding sequence at decision point s I The median boot time at ;

[0120] VTmicro(v0,a,t) represents the energy consumption calculated by the VTmicro model when the initial velocity is v0, the acceleration is a, and the movement time is t.

[0121] In this example, let v0 = 15 m / s. From step 2(3), we can get Meters per second squared, from step 2(2), Seconds. Calculation shows, Lift.

[0122] (2) Calculate the cost of traffic efficiency. The calculation formula is:

[0123]

[0124] in, is the travel efficiency cost of the mth time window guidance sequence;

[0125] is the mth time window guiding sequence at decision point s I The median boot time at ;

[0126] It's in time The probability that the traffic light is green at ;

[0127] In this example, from step 3, we can get that at time At , the probability that the traffic light is green is 0.61, so

[0128] (3) Calculate the cost of successful passage. The calculation formula is expressed as:

[0129]

[0130] in, is the cost of successful passage of the mth time window guidance sequence;

[0131] is the mth time window guiding sequence at decision point s i The guiding speed at

[0132] a ref is the reference ecological acceleration;

[0133] v des is the expected speed;

[0134] In this example, step 4(2) yields From step 2(4), we can get Meters per second, let a ref = 1.5 meters per second squared, v des = 24 meters per second, we can calculate Lift.

[0135] (4) Calculate the cost of failed passage. The calculation formula is expressed as:

[0136]

[0137] in, is the failure pass cost of the m-th time window guidance sequence.

[0138] In this example, step 4(2) yields Assume a ref = 1.5 meters per second squared, v des = 24 meters per second, we can calculate, Lift.

[0139] Step 5

[0140] The optimal time window guidance sequence is selected and transmitted to the guided vehicle. Specifically, the following steps are included:

[0141] (1) Calculate the total cost of all time window guide sequences. The calculation formula is expressed as:

[0142]

[0143] in, The total cost of the mth time window guide sequence;

[0144] κ is the weight, ranging from 0 to 1;

[0145] In this example, from step 4, we can get: Lift, Lift, Assuming κ = 0.1, we can calculate:

[0146] (2) Compare the total costs described in S51, and the smallest one is the optimal time window guidance sequence. See the schematic diagram for details. Figure 2 (IV).

[0147] (3) The optimal time window guidance sequence is transmitted to the intelligent connected driving vehicle through the vehicle-road-cloud integrated system; the optimal time window guidance sequence is transmitted to the human driving vehicle through the navigation platform. See the schematic diagram Figure 3 .

[0148] The above is only a preferred embodiment of the present invention and does not limit the present invention in any way. Any technician in the relevant technical field, without departing from the scope of the technical solution of the present invention, makes any form of equivalent replacement or modification to the technical solution and technical content disclosed in the present invention, which does not depart from the content of the technical solution of the present invention and still falls within the protection scope of the present invention.

Claims

1. A vehicle-road-cloud collaborative decision-making framework based on time windows, characterized in that: The steps include: S1. Calculate the feasible driving state space of the guided vehicle; S2, based on the feasible driving state space, divide the time window guidance sequence; S3, obtaining the probability that the traffic signal is green within the feasible driving state space at the last decision point; S4, calculating the costs of all time window guide sequences; S5. Optimize the optimal time window guidance sequence and transmit it to the guided vehicle.

2. The time window-based vehicle-road-cloud collaborative decision-making framework according to claim 1 is characterized in that: In S1, the feasible driving state space can be expressed as and The set of , i = 0 ~ I; in, and At the decision point s i At, the upper and lower limits of the feasible driving state space, The calculation formula is expressed as: If the constraint Be satisfied, So otherwise Where i is the subscript of the decision point; I is the last decision point s I Subscript of; s I is the position of the stop line; and At the decision point s i The upper and lower limits of vehicle speed; a max with a min are the maximum and minimum acceleration of the vehicle respectively; Δs i is the distance between two adjacent decision points; v max With v min These are the maximum and minimum speed limits on the road.

3. The time window-based vehicle-road-cloud collaborative decision-making framework according to claim 2 is characterized in that: In S2, the steps of dividing the time window guide sequence are as follows: S21, the interval Divide into sub-intervals The length of each subinterval is Δt, and the interval between adjacent subintervals is τ. and are respectively the mth time window guide sequence at the decision point s I The lower and upper limits of the guidance time at are expressed as follows: and The constraints that need to be satisfied are expressed as: S22, calculate the sub-interval described in S21 The median value The calculation formula is expressed as: S23, assuming that the vehicle starts to move at a uniform speed from the initial position s0, the initial speed is v0, and the end point of the movement is s I , exercise duration is Then we can get The calculation formula is expressed as: in, is the guidance acceleration of the guidance sequence in the mth time window; S24, assuming that the vehicle Perform uniformly accelerated motion, with the starting point being the initial position s0, the initial velocity being v0, the initial time being t0, and the end point being s i , we can get The calculation formula is expressed as: in, is the mth time window guiding sequence at decision point s i The guiding speed at and are the mth time window guide sequence at decision point s i The upper and lower limits of the boot time at ; S25, the mth time window guide sequence is expressed as and A set of , i=0~I.

4. The time window-based vehicle-road-cloud collaborative decision-making framework according to claim 3 is characterized in that: In S3, the feasible driving state space range at the last decision point refers to the interval The time range included.

5. The time window-based vehicle-road-cloud collaborative decision-making framework according to claim 3 is characterized in that: The S4 specifically includes the following steps: S41. Calculate the energy consumption cost of the time window. The calculation formula is expressed as: in, is the time window energy cost of the mth time window guided sequence; v0 is the initial velocity; is the guidance acceleration of the guidance sequence in the mth time window; is the mth time window guiding sequence at decision point s I The median boot time at ; VTmicro(v0,a,t) represents the energy consumption calculated by the VTmicro model when the initial velocity is v0, the acceleration is a, and the movement time is t. S42. Calculate the cost of traffic efficiency. The calculation formula is: in, is the travel efficiency cost of the mth time window guidance sequence; is the mth time window guiding sequence at decision point s I The median boot time at ; It's in time The probability that the traffic light is green at ; S43, calculating the cost of successful passage, the calculation formula is expressed as: in, is the cost of successful passage of the mth time window guidance sequence; is the mth time window guiding sequence at decision point s I The guiding speed at a ref is the reference ecological acceleration; v des is the expected speed; S44. Calculate the cost of failed passage, the calculation formula is expressed as: in, is the failure pass cost of the m-th time window guidance sequence.

6. The time window-based vehicle-road-cloud collaborative decision-making framework according to claim 5 is characterized in that: In S5, the step of selecting the optimal time window guidance sequence and transmitting it to the guided vehicle is as follows: S51, calculate the total cost of all time window guide sequences, the formula is as follows: in, The total cost of the mth time window guide sequence; κ is the weight, ranging from 0 to 1; S52, comparing the total costs in S51, the smallest one is the optimal time window guide sequence; S53. Transmitting the optimal time window guidance sequence to the intelligent connected driving vehicle through the vehicle-road-cloud integrated system; transmitting the optimal time window guidance sequence to the human-driven vehicle through the navigation platform.

Images