An intelligent automobile low-computing-power speed planning method based on road diffusion risk area

Abstract

The present application belongs to the technical field of automatic driving test, and specifically relates to a low-computing-power speed planning method for intelligent vehicles based on road diffusion risk zones, which comprises the following steps: step one, establishing a quarter-vehicle suspension dynamics equation and a continuous-time state space equation, and performing state space equation discretization; step two, preprocessing the forward-looking information obtained by the intelligent vehicle; the intelligent vehicle performs road section division and speed change event determination by using global road information obtained through the Internet of Vehicles, and then establishes a road diffusion risk zone and generates a speed adjustment position; step three, generating an optimal speed sequence; a cost function is established according to a planning target and a generated vertical cost, and a dynamic planning speed sequence generation method is designed, and a speed sequence is generated in combination with the preprocessed forward-looking information. The present application helps the intelligent vehicle to plan a smooth speed with low computing power, and provides a new solution for intelligent vehicle speed planning.

Description

Technical Field

[0001] The present invention belongs to the technical field of autonomous driving testing, and specifically provides a low-computing-power speed planning method for intelligent vehicles based on road diffusion risk zones. Background Art

[0002] Smart cars are at the forefront of future automotive development. Speed ​​planning, a necessary process in smart car operation, not only ensures efficient traffic flow but also improves ride comfort by accounting for road bumps. On bumpy roads, the vehicle's suspension system alone cannot effectively filter the impact of the road surface. The vehicle must reduce speed to navigate smoothly. Therefore, speed planning based on road bumps is both feasible and necessary.

[0003] Smart car speed planning typically involves two steps: preprocessing forward-looking information and generating speed sequences. Rapidly developing Internet of Vehicles (IoV) technologies can provide smart cars with comprehensive forward-looking information, such as traffic light signals, vehicle location, and road elevation. This information is then preprocessed based on planning objectives. Using this preprocessed forward-looking information, smart cars can generate speed sequences for the entire road.

[0004] However, current research still has some limitations. For one thing, current forward-looking information preprocessing methods simply distinguish events that affect the planning objective from ordinary roads and fail to predict the approach or departure of these events. This directly leads to the planned vehicle speed being prone to sudden changes when approaching these events, affecting the longitudinal performance of intelligent vehicles. Furthermore, current speed sequence generation methods are generally based on optimization concepts, and the iterative optimization process requires a large amount of computing resources, resulting in high computing power requirements and long calculation times. Summary of the Invention

[0005] To solve the above problems, the present invention provides a low-computing-power speed planning method for smart cars based on road diffusion risk zones, which helps smart cars plan a stable speed with lower computing power, providing a new solution for smart car speed planning.

[0006] The technical solution of the present invention is described as follows in conjunction with the accompanying drawings:

[0007] A low-computing-power speed planning method for intelligent vehicles based on road diffusion risk zones includes the following steps:

[0008] Step 1: Establish the quarter vehicle suspension dynamics equation and continuous-time state-space equation, and discretize the state-space equation;

[0009] Step 2: Preprocess the forward-looking information obtained by the smart car. The smart car uses the global road information obtained by the Internet of Vehicles to divide road sections and determine speed change events, thereby establishing road diffusion risk areas and generating speed adjustment positions.

[0010] Step 3: Generate the optimal speed sequence; establish a cost function based on the planning goal and the generated vertical cost, and design a dynamic planning speed sequence generation method, and generate the speed sequence by combining the preprocessed forward information.

[0011] Furthermore, the specific method of step one is as follows:

[0012] 11) Based on the quarter-car suspension model and vehicle dynamics principles, the quarter-car suspension dynamics equation is obtained as follows:

[0013]

[0014] Where m s is the sprung mass, m u is the unsprung mass, k s is the spring stiffness, c s is the suspension damping coefficient, c t is the vertical equivalent damping of the tire, k t is the vertical equivalent stiffness of the tire, z s is the vertical displacement of the sprung mass, z u is the vertical displacement of the unsprung mass, z r is the road surface height;

[0015] 12) Select the sprung mass displacement z s (t), unsprung mass displacement z u (t), sprung mass displacement velocity Unsprung mass displacement velocity As the state variable; choose sprung mass acceleration Suspension travel z u (t)-z s (t), tire dynamic deflection z r (t)-z u (t) is the output variable of the system; then the road height z is selected r and its rate of change is the disturbance of the system; then the quarter vehicle suspension dynamics equation (1) is rewritten as the system state space equation under continuous time, as shown below:

[0016]

[0017] in,

[0018]

[0019] Where x(t) is the state variable; is the derivative of the state variable; y(t) is the output variable; ω(t) is the disturbance variable; A is the suspension system matrix; C is the suspension output matrix; E is the state disturbance matrix; L is the output disturbance matrix; z s (t) is the displacement of the sprung mass; z u (t) is the unsprung mass displacement; is the sprung mass displacement velocity; is the displacement velocity of the unsprung mass; z r is the road surface height; m s is the sprung mass; m u is the unsprung mass; k s is the spring stiffness; c s is the suspension damping coefficient; c t is the vertical equivalent damping of the tire; k t is the vertical equivalent stiffness of the tire;

[0020] 13) The continuous time matrix in Equation (2) is discretized using the zero-order hold discretization method, and the discretized system state space equation is obtained as follows:

[0021]

[0022] Where A is the suspension system matrix; E is the state interference matrix; C is the suspension output matrix; L is the output interference matrix; T s is the sampling period of the suspension system; is the discrete suspension system matrix; is the discrete state interference matrix; x(k) is the state variable of the kth period; y(k) is the output variable of the kth period; ω(k) is the interference variable of the kth period.

[0023] Furthermore, the specific method of step 2 is as follows:

[0024] 21) The intelligent vehicle obtains forward-looking information, namely global road elevation information, through the Internet of Vehicles, and uses the global road elevation information to divide the entire road to be driven into bumpy sections B i and flat road section S i ;

[0025] 22) Divide the entire road to be driven into N s Vehicle speed adjustment position P i Each speed adjustment bit includes a speed change event speed adjustment bit T i and normal speed adjustment position A i .

[0026] Furthermore, the specific method for determining the vehicle speed adjustment position is as follows:

[0027] (1) The starting point, end point and bumpy road section are called speed change event speed adjustment positions;

[0028] (2) Three common speed adjustment positions, A1, A2, and A3, are set before and after each speed change event to change the speed in time;

[0029] (3) The area between A3 in the normal speed adjustment position and the adjacent speed change event speed adjustment position is called the road diffusion risk area, which includes the normal speed adjustment positions A1, A2, and A3. The distance between the normal speed adjustment position and the speed change event speed adjustment position is set as follows:

[0030] l i =5i 2 , i=1,2,3 (5)

[0031] Where i is the normal speed adjustment position A i Serial number; l i Adjust position A for normal speed i The distance to the speed adjustment position of the speed change event;

[0032] (4) When a vehicle passes through a flat road section between two speed change events, it is stipulated that, except for the speed adjustment position set in (2), no other speed adjustment position shall be set between the two speed change events to avoid frequent acceleration and deceleration of the vehicle;

[0033] (5) For each speed adjustment position, there is a δV interval, starting from the lowest speed V min To the maximum speed V max N v Candidate speeds.

[0034] Furthermore, the specific method of step three is as follows:

[0035] 31) Determine planning objectives;

[0036] The planning objectives include vertical performance objectives, longitudinal performance objectives and traffic performance objectives;

[0037] The vertical performance includes sprung mass acceleration, tire dynamic deflection, and suspension dynamic travel. The global road elevation information obtained by the Internet of Vehicles is injected into the passive suspension model, that is, the quarter-vehicle suspension model is established. The output variable y(k) at each sampling period is obtained through the discretized system state space equation (3), and the vertical performance of the corresponding vehicle speed adjustment position is calculated as follows:

[0038]

[0039] Where, is the vertical performance of the vehicle passing the i-th speed adjustment position at the p-th candidate speed; N i is the number of suspension system samples at the i-th vehicle speed adjustment position; y1(k) is the sprung mass acceleration of the k-th sampling period; y2(k) is the suspension dynamic travel of the k-th sampling period; y3(k) is the tire dynamic deflection of the k-th sampling period; σ1 is the weight coefficient of sprung mass acceleration; σ2 is the weight coefficient of suspension dynamic travel; σ3 is the weight coefficient of tire dynamic deflection; l i is the length of the i-th speed adjustment position, V i is the speed of the vehicle passing through the i-th speed adjustment position, T s is the sampling time of the suspension system;

[0040] Set the speed adjustment position P representing the bumpy road section k The vertical performance of the vehicle speed adjustment position within the front and rear road diffusion risk areas is as follows:

[0041]

[0042] Where, is the vertical performance of the vehicle passing the kth speed adjustment position representing the bumpy road section at the pth candidate speed; is the vertical performance of passing the k-1th speed adjustment position at the pth candidate speed; is the vertical performance of passing the k-2th speed adjustment position at the pth candidate speed; is the vertical performance of passing the k-3th speed adjustment position at the pth candidate speed;

[0043] The cost function of the vertical performance objective is established as follows:

[0044]

[0045] Where, is the vertical cost of the vehicle passing the i-th speed adjustment position at the p-th candidate speed; is the vertical performance of the vehicle passing the i-th speed adjustment position at the p-th candidate speed; N s Adjust the number of bits for vehicle speed;

[0046] The vehicle's speed changes linearly between adjacent speed adjustment positions, meaning the acceleration is a constant. Therefore, the cost function for defining the longitudinal performance objective is the absolute value of the vehicle's longitudinal acceleration between two adjacent speed adjustment positions, reflecting the vehicle's acceleration and deceleration, as follows:

[0047]

[0048] Where, V is the longitudinal cost of the vehicle from the kth candidate speed at the i+1th speed adjustment position to the pth candidate speed at the ith speed adjustment position; p is the pth candidate vehicle speed; Ls i Le is the distance from the starting point of the i-th speed adjustment position to the starting point of the entire road; i is the distance from the end point of the i-th speed adjustment position to the starting point of the entire road; N s Adjust the number of bits for vehicle speed;

[0049] The traffic performance target represents the time between two adjacent speed adjustment positions, and its cost function is expressed as follows:

[0050]

[0051] Where, V is the cost of the vehicle traveling from the kth candidate speed at the i+1th speed adjustment position to the pth candidate speed at the ith speed adjustment position; p is the pth candidate vehicle speed; N s The number of vehicle speed adjustment positions; Ls i Le is the distance from the starting point of the i-th speed adjustment position to the starting point of the entire road; i is the distance from the end point of the i-th speed adjustment position to the starting point of the entire road;

[0052] A total cost function including vertical performance, longitudinal performance and traffic performance is established; the specific form of the total cost function is shown in the following formula:

[0053]

[0054] Where, J pk (i) is the cost of the vehicle moving from the kth candidate speed at the i+1th speed adjustment position to the pth candidate speed at the ith speed adjustment position; is the vertical cost of the vehicle passing the i-th speed adjustment position at the p-th candidate speed; is the longitudinal cost of the vehicle from the kth candidate speed at the i+1th speed adjustment position to the pth candidate speed at the ith speed adjustment position; is the cost of the vehicle traveling from the kth candidate speed at the i+1th speed adjustment position to the pth candidate speed at the ith speed adjustment position; α is the vertical cost weight coefficient; β is the longitudinal cost weight coefficient; γ is the travel cost weight coefficient; is the maximum vertical cost among all speed adjustment positions; is the maximum longitudinal cost among all adjacent vehicle speed adjustment positions; is the maximum longitudinal cost among all adjacent vehicle speed adjustment positions; is the maximum travel cost among all adjacent speed adjustment positions; c i V is the vertical performance of the vehicle passing through the i-th speed adjustment position; max is the maximum speed of the vehicle; V min is the minimum speed of the vehicle; L max is the maximum distance between all adjacent speed adjustment positions on the road; l max is the maximum length of all bumpy sections on the road;

[0055] 32) Generate the vehicle speed sequence based on the established cost function of vertical performance target, longitudinal performance target and traffic performance target; the entire road contains N s Speed ​​adjustment bits, each of which contains N v candidate speeds; the dynamic programming method calculates the cost of each speed adjustment position from back to front and performs speed planning.

[0056] Furthermore, the specific method of step 32) is as follows:

[0057] 321) Build an N v ×N s The cost matrix Q is used to record the cost of all candidate speeds in the speed adjustment position, and at the same time, establish an N v ×N s The speed matrix F is used to record the vehicle speed sequence; the element Q(p,k) in the kth column and pth row of the cost matrix Q represents the pth candidate speed V of the vehicle from the kth speed adjustment position p The minimum cost to the end of the road, the element F(p,k) in the kth column and pth row of the speed matrix F represents V to the kth speed adjustment position p The speed of the k+1th speed adjustment position with the minimum cost;

[0058] 322) Nth s Speed ​​adjustment position As the end of the road, set the speed adjustment position The cost is zero, that is, the Nth cost matrix Q s The elements of the column are all recorded as zero;

[0059] 323) For the Nth s -1 speed adjustment position The p-th candidate speed is calculated according to formula (12) s Speed ​​adjustment position All candidate vehicle speeds are converted to their process costs, and the minimum process cost is selected and recorded in the cost matrix Q. At the same time, the Nth vehicle corresponding to the minimum cost is recorded in the cost matrix Q. s The candidate vehicle speeds for the vehicle speed adjustment positions are recorded in the speed matrix F as follows:

[0060] Q(p,N s -1)=J(p,N s -1)=minJ p,k (N s ),p=1,2,...,N v ,k=1,2,...,N v (16)

[0061] Where Q is the cost matrix; N s N is the number of speed adjustment bits included in the entire road; v The number of candidate vehicle speeds for each vehicle speed adjustment position; J(p,N s -1) is the distance from the end of the road to the Nth s -1 The minimum total cost of the p-th candidate speed for the speed adjustment position; J p,k (N s ) is the vehicle from the Nth s The kth candidate vehicle speed of the vehicle speed adjustment position to the Nth candidate vehicle speed s -1 process cost between the pth candidate vehicle speeds of the vehicle speed adjustment position;

[0062] From the Nth s The speed adjustment position of the p-th candidate speed to the N-th candidate speed s The process cost of the j-th candidate vehicle speed at the -1 vehicle speed adjustment position is J j,p (N s ); Select the minimum cost J j,j+1 (N s ) is recorded as J(j,N s -1) and stored in the jth row and Nth column of the cost matrix Q s -1 column, at the same time, the j+1th candidate speed V corresponding to the minimum cost j+1 Stored in the jth row, Nth column of the velocity matrix F s -1 column, represents the Nth s The speed of the vehicle speed adjustment position should be V j+1 ;

[0063] 324) For the remaining speed adjustment positions, namely the Nth s -2 speed adjustment positions to the first speed adjustment position, calculate the adjacent speed adjustment position P according to step (3) i and P i+1 The process cost between the process cost and the speed adjustment position P i+1 The costs of the corresponding candidate speeds are added together, and the minimum cost is selected and recorded in the cost matrix, as shown below:

[0064] Q(p,i)=J(p,i)=min(J p,k(i+1)+J(p,i+1)),p=1,2,...,N v ,k=1,2,...,N v (17)

[0065] Where Q is the cost matrix; N v is the number of candidate speeds for each speed adjustment position; J(p,i+1) is the minimum total cost for the vehicle to reach the pth candidate speed at the i+1th speed adjustment position from the end of the road; J p,k (i+1) is the cost of the vehicle's process from the kth candidate speed at the i+1th speed adjustment position to the pth candidate speed at the ith speed adjustment position;

[0066] The cost of the process from the pth candidate speed at the n+1th speed adjustment position to the second candidate speed at the nth speed adjustment position is J 2,p (i+1); add the cost J(p,n+1) stored in the pth row of the n+1th column of the original cost matrix Q, select the minimum value and record it as J(2,n) and store it in the 2nd row and nth column of the cost matrix Q; at the same time, v -1 candidate speed The speed stored in the 2nd row and nth column of the speed matrix F represents the speed of the n+1th speed adjustment position.

[0067] Thus, the element Q(m,l) in the cost matrix Q is the minimum cost from the mth candidate speed of the lth speed adjustment position to the end point, and the element F(m,l) in the speed matrix F is the V to the l-1th speed adjustment position. m The speed of the lth speed adjustment position with the minimum cost;

[0068] The vehicle speed sequence obtained by the dynamic programming method is obtained according to the elements stored in the speed matrix F;

[0069] When the speed of the vehicle at the first speed adjustment position is V1, first, the speed stored in the first row and first column of the speed matrix F is searched for V2, which means the speed of the vehicle at the next speed adjustment position is V2. Then, the speed stored in the second row and second column of the speed matrix F is searched for V2, which means the speed of the vehicle at the next speed adjustment position is V2. Finally, this process is repeated until the speed matrix F is searched for V2 at the j+1th row and Nth column. s The speed stored in column -1 is V j+1 , represents the vehicle at the Nth s The speed of the vehicle speed adjustment position is V j+1 ; So far, the vehicle speed sequence V of the entire road is obtained through the dynamic programming method.

[0070] The beneficial effects of the present invention are:

[0071] 1) This invention provides a low-computing speed planning method for intelligent vehicles based on road diffusion risk zones. This method comprehensively considers the vehicle's vertical, longitudinal, and traffic performance during speed planning, improving driving comfort and traffic efficiency.

[0072] 2) This invention designs a forward-looking information preprocessing method based on the Internet of Vehicles. This method uses the Internet of Vehicles to obtain global road information, divide road sections, and identify speed change events. This method then establishes road diffusion risk zones and generates speed adjustment positions. This method provides comprehensive information for speed sequence generation and predicts the approach and departure of speed change events, enabling timely speed adjustments to adapt to road surfaces of varying degrees of bumpiness.

[0073] 3) This paper designs a dynamic programming method for generating vehicle speed sequences. This method utilizes dynamic programming to generate vehicle speed sequences, taking into account vertical performance, longitudinal performance, and trafficability during speed planning. This method reduces the computational effort required to generate the speed sequence while ensuring relevant vehicle performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0074] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0075] Figure 1 This is a schematic diagram of a low-computing-power speed planning method for intelligent vehicles based on road diffusion risk zones according to the present invention;

[0076] Figure 2 This is a schematic diagram of a quarter vehicle suspension model;

[0077] Figure 3 This is a schematic diagram of forward-looking information processing;

[0078] Figure 4 This is a schematic diagram of the dynamic planning speed sequence;

[0079] Figure 5 A schematic diagram of vehicle speed sequence comparison. DETAILED DESCRIPTION

[0080] The present invention will be further described in detail below with reference to the accompanying drawings and examples. It will be understood that the specific embodiments described herein are intended only to illustrate the present invention and are not intended to limit the present invention. It should also be noted that, for ease of description, the accompanying drawings only illustrate portions relevant to the present invention, not all structures.

[0081] Example 1

[0082] See Figure 1 This embodiment provides a low-computing-power speed planning method for intelligent vehicles based on road diffusion risk zones, including the following steps:

[0083] Step 1: Refer to Figure 2 , establish the quarter vehicle suspension dynamics equation and continuous time state space equation, and discretize the state space equation, as follows:

[0084] 11) Based on the quarter-car suspension model and vehicle dynamics principles, the quarter-car suspension dynamics equation is obtained as follows:

[0085]

[0086] Where m s is the sprung mass; m u is the unsprung mass; k s is the spring stiffness; c s is the suspension damping coefficient; c t is the vertical equivalent damping of the tire; k t is the vertical equivalent stiffness of the tire; z s is the vertical displacement of the sprung mass; z u is the vertical displacement of the unsprung mass; z r is the road surface height;

[0087] 12) Select the sprung mass displacement z s (t), unsprung mass displacement z u (t), sprung mass displacement velocity Unsprung mass displacement velocity As the state variable; select sprung mass acceleration Suspension travel z u (t)-z s (t), tire dynamic deflection z r (t)-z u (t) is the output variable of the system; then the road height z is selected r and its rate of change is the disturbance quantity of the system; then the quarter vehicle suspension dynamics equation (1) can be rewritten as the system state space equation under continuous time, as shown below:

[0088]

[0089] in,

[0090]

[0091] Where x(t) is the state variable; is the derivative of the state variable; y(t) is the output variable; ω(t) is the disturbance variable; A is the suspension system matrix; C is the suspension output matrix; E is the state disturbance matrix; L is the output disturbance matrix; z s (t) is the displacement of the sprung mass; z u (t) is the unsprung mass displacement; is the sprung mass displacement velocity; is the displacement velocity of the unsprung mass; z r is the road surface height; m s is the sprung mass; m u is the unsprung mass; k s is the spring stiffness; c s is the suspension damping coefficient; c t is the vertical equivalent damping of the tire; k t is the vertical equivalent stiffness of the tire;

[0092] 13) The sensors in the suspension system are sampled at discrete time, and the state quantities obtained are discrete rather than continuous. Therefore, it is necessary to discretize the system state space equation under continuous time. The continuous time matrix in Equation (2) is discretized using the zero-order hold discretization method, and the discretized system state space equation is obtained as follows:

[0093]

[0094] Where A is the suspension system matrix; E is the state interference matrix; C is the suspension output matrix; L is the output interference matrix; T s is the sampling period of the suspension system; is the discrete suspension system matrix; is the discrete state interference matrix; x(k) is the state variable of the kth period; y(k) is the output variable of the kth period; ω(k) is the interference variable of the kth period.

[0095] Step 2: Preprocess the forward-looking information obtained by the smart car. The smart car uses the global road information obtained by the Internet of Vehicles to divide road sections and determine speed change events, thereby establishing road diffusion risk areas and generating speed adjustment positions. The details are as follows:

[0096] 21) The intelligent vehicle obtains forward-looking information, namely global road elevation information, through the Internet of Vehicles, and uses the global road elevation information to divide the entire road to be driven into bumpy sections B i and flat road section S i ,like Figure 3 As shown;

[0097] The forward-looking information includes traffic light information, intersection information, global road elevation information, etc., but the present invention only uses the global road elevation information;

[0098] 22) In order to facilitate the adjustment of vehicle speed, the entire road contains N s Vehicle speed adjustment position P i , corresponding to each vertical line in the figure, which contains the speed change event speed adjustment position T i and normal speed adjustment position A i .

[0099] by Figure 4 Taking as an example, the specific method for determining the vehicle speed adjustment position is as follows.

[0100] (1) Compared with normal driving, the vehicle will change its speed more frequently when starting, on bumpy roads, and nearing the end point. Therefore, the starting point, end point, and bumpy road section are called speed change events and speed adjustment positions, which are represented by orange solid lines, i.e. Figure 4 T in 1～5 ;

[0101] (2) In order to adapt to the frequent changes in vehicle speed when approaching the speed adjustment position of the "speed change event", three ordinary speed adjustment positions are set before and after each "speed change event" speed adjustment position for timely speed change, which are represented by blue solid lines, namely Figure 4 A in 1～3 ;

[0102] (3) The area between A3 in the normal speed adjustment position and the speed adjustment position of the adjacent speed change event is called the road diffusion risk area, which includes the normal speed adjustment position A 1～3 Considering that the vehicle speed will be adjusted more frequently as the distance approaches the speed adjustment position of the speed change event, the distance between the normal speed adjustment position and the speed change event speed adjustment position is set as follows:

[0103] l i =5i 2 , i=1,2,3 (5)

[0104] Where i is the normal speed adjustment position A i Serial number, l i Adjust position A for normal speed i The distance to the speed adjustment position of the "speed change event";

[0105] (4) When a vehicle is traveling on a flat road between two speed change event speed adjustment positions, it rarely accelerates or decelerates significantly to avoid excessive speed adjustments. Therefore, it is stipulated that, in addition to the ordinary speed adjustment position set in (2), no other speed adjustment position shall be set between the two speed change event speed adjustment positions to avoid frequent acceleration or deceleration of the vehicle;

[0106] (5) For each speed adjustment position, there is a δV interval, starting from the lowest speed V min To the maximum speed V max N v Candidate speeds. Figure 3 The dots of different colors represent different types of candidate vehicle speeds. The blue dots are common candidate vehicle speeds, and the red dots are the highest vehicle speed V max , the green dot is the minimum speed V min ;

[0107] At this point, the forward information preprocessing is completed, and the N s Speed ​​adjustment position.

[0108] Step 3: Generate the optimal speed sequence. A cost function is established based on the planning objectives and the generated vertical cost. A dynamic planning speed sequence generation method is designed. This method combines the preprocessed forward-looking information to generate the speed sequence, as follows:

[0109] 31) When generating a speed sequence, the planning objective should be determined first, and then a corresponding cost function should be established to generate the optimal speed sequence. To ensure vehicle driving comfort and traffic efficiency, the planning objectives in this invention are mainly defined as follows:

[0110] (1) Vertical performance objectives;

[0111] (2) vertical performance goals;

[0112] (3) Traffic performance objectives;

[0113] The vertical performance includes sprung mass acceleration, tire deflection, and suspension travel. To obtain the vertical performance of the vehicle as it passes through the speed adjustment position during the speed planning phase, the global road elevation information obtained by the Internet of Vehicles is injected into the passive suspension model. The output variable y(k) at each sampling period is obtained through the discretized system state space equation (3), and the vertical performance of the corresponding speed adjustment position is calculated:

[0114]

[0115] Where, is the vertical performance of the vehicle passing the i-th speed adjustment position at the p-th candidate speed; N i is the number of suspension system samples at the i-th vehicle speed adjustment position; y1(k) is the sprung mass acceleration of the k-th sampling period; y2(k) is the suspension dynamic travel of the k-th sampling period; y3(k) is the tire dynamic deflection of the k-th sampling period; σ1 is the weight coefficient of sprung mass acceleration; σ2 is the weight coefficient of suspension dynamic travel; σ3 is the weight coefficient of tire dynamic deflection; l iis the length of the i-th speed adjustment position; V i is the speed of the vehicle passing through the i-th speed adjustment position; T s is the sampling time of the suspension system;

[0116] In order to predict the approach and departure of the bumpy road section, the speed adjustment position P representing the bumpy road section is set. k The vertical performance of the vehicle speed adjustment position within the front and rear road diffusion risk areas is as follows:

[0117]

[0118] Where, is the vertical performance of the vehicle passing the kth speed adjustment position representing the bumpy road section at the pth candidate speed; is the vertical performance of passing the k-1th speed adjustment position at the pth candidate speed; is the vertical performance of passing the k-2th speed adjustment position at the pth candidate speed; is the vertical performance of passing the k-3th speed adjustment position at the pth candidate speed;

[0119] From this, the cost function of the vertical performance target can be established as shown below:

[0120]

[0121] Where, is the vertical cost of the vehicle passing the i-th speed adjustment position at the p-th candidate speed; is the vertical performance of the vehicle passing the i-th speed adjustment position at the p-th candidate speed; N s Adjust the number of bits for vehicle speed;

[0122] The vehicle's speed changes linearly between adjacent speed adjustment positions, meaning its acceleration remains constant. Therefore, the cost function for the longitudinal performance objective is defined as the absolute value of the vehicle's longitudinal acceleration between two adjacent speed adjustment positions, reflecting the vehicle's acceleration and deceleration. Specifically, it is as follows:

[0123]

[0124] Where, V is the longitudinal cost of the vehicle from the kth candidate speed at the i+1th speed adjustment position to the pth candidate speed at the ith speed adjustment position; p is the pth candidate vehicle speed; Ls i Le is the distance from the starting point of the i-th speed adjustment position to the starting point of the entire road; i is the distance from the end point of the i-th speed adjustment position to the starting point of the entire road; N s Adjust the number of bits for vehicle speed;

[0125] The traffic performance target represents the time between two adjacent speed adjustment positions, and its cost function can be expressed as follows:

[0126]

[0127] Where, V is the cost of the vehicle traveling from the kth candidate speed at the i+1th speed adjustment position to the pth candidate speed at the ith speed adjustment position; p is the pth candidate vehicle speed; N s The number of vehicle speed adjustment positions; Ls i Le is the distance from the starting point of the i-th speed adjustment position to the starting point of the entire road; i is the distance from the end point of the i-th speed adjustment position to the starting point of the entire road;

[0128] Next, a total cost function is established that includes vertical performance, longitudinal performance, and traffic performance. Since the three performances have different dimensions, they need to be normalized. The specific form of the total cost function is shown in the following formula:

[0129]

[0130] Where, J pk (i) is the cost of the vehicle moving from the kth candidate speed at the i+1th speed adjustment position to the pth candidate speed at the ith speed adjustment position; is the vertical cost of the vehicle passing the i-th speed adjustment position at the p-th candidate speed; is the longitudinal cost of the vehicle from the kth candidate speed at the i+1th speed adjustment position to the pth candidate speed at the ith speed adjustment position; is the cost of the vehicle traveling from the kth candidate speed at the i+1th speed adjustment position to the pth candidate speed at the ith speed adjustment position; α is the vertical cost weight coefficient; β is the longitudinal cost weight coefficient; γ is the travel cost weight coefficient; is the maximum vertical cost among all speed adjustment positions; is the maximum longitudinal cost among all adjacent vehicle speed adjustment positions; is the maximum longitudinal cost among all adjacent vehicle speed adjustment positions; is the maximum travel cost among all adjacent speed adjustment positions; c i V is the vertical performance of the vehicle passing through the i-th speed adjustment position; max is the maximum speed of the vehicle; V min is the minimum speed of the vehicle; L max is the maximum distance between all adjacent speed adjustment positions on the road; l max is the maximum length of all bumpy sections on the road;

[0131] 32) Based on the established cost function, this paper uses the dynamic programming method to generate the vehicle speed sequence. Figure 4 As shown, the entire road contains N s Speed ​​adjustment bits, each of which contains N v The dynamic programming method calculates the cost of each speed adjustment position from back to front and performs speed planning. The specific steps are as follows:

[0132] 321) Build an N v ×N s The cost matrix Q is used to record the cost of all candidate speeds in the speed adjustment position, and at the same time, establish an N v ×N s The speed matrix F is used to record the vehicle speed sequence. The element Q(p,k) in the kth column and pth row of the cost matrix Q represents the pth candidate speed V of the vehicle from the kth speed adjustment position. p The minimum cost to the end of the road, the element F(p,k) in the kth column and pth row of the speed matrix F represents V to the kth speed adjustment position p The speed of the k+1th speed adjustment position with the minimum cost;

[0133] 322) Nth s Speed ​​adjustment position As the end of the road, set the speed adjustment position The cost is zero, that is, the Nth cost matrix Q s The elements of the column are all recorded as zero;

[0134] 323) For the Nth s -1 speed adjustment position The p-th candidate speed is calculated according to formula (12) s Speed ​​adjustment position All candidate vehicle speeds are converted to their process costs, and the minimum process cost is selected and recorded in the cost matrix Q. At the same time, the Nth vehicle corresponding to the minimum cost is recorded in the cost matrix Q. s The candidate vehicle speeds for the vehicle speed adjustment positions are recorded in the speed matrix F:

[0135] Q(p,N s -1)=J(p,N s -1)=minJ p,k (Ns),p=1,2,...,N v ,k=1,2,...,N v (16)

[0136] Where Q is the cost matrix; N s N is the number of speed adjustment bits included in the entire road; vThe number of candidate vehicle speeds for each vehicle speed adjustment position; J(p,N s -1) is the distance from the end of the road to the Nth s -1 The minimum total cost of the p-th candidate speed for the speed adjustment position; J p,k (N s ) is the vehicle from the Nth s The kth candidate vehicle speed of the vehicle speed adjustment position to the Nth candidate vehicle speed s -1 process cost between the pth candidate vehicle speeds of the vehicle speed adjustment position;

[0137] by Figure 4 For example, from the Nth s The speed adjustment position of the p-th candidate speed to the N-th candidate speed s The process cost of the j-th candidate vehicle speed at the -1 vehicle speed adjustment position is J j,p (N s ); Select the minimum cost J j,j+1 (N s ) is recorded as J(j,N s -1) and stored in the jth row and Nth column of the cost matrix Q s -1 column, at the same time, the j+1th candidate speed V corresponding to the minimum cost j+1 Stored in the jth row, Nth column of the velocity matrix F s -1 column, represents the Nth s The speed of the vehicle speed adjustment position should be V j+1 ;

[0138] 324) For the remaining speed adjustment positions, namely the Nth s -2 speed adjustment positions to the first speed adjustment position, calculate the adjacent speed adjustment position P according to step (3) i and P i+1 The process cost between the process cost and the speed adjustment position P i+1 The costs of the corresponding candidate speeds are added together, and the minimum cost is selected and recorded in the cost matrix:

[0139] Q(p,i)=J(p,i)=min(J p,k (i+1)+J(p,i+1)),p=1,2,...,N v ,k=1,2,...,N v (17)

[0140] Where Q is the cost matrix; N v is the number of candidate speeds for each speed adjustment position; J(p,i+1) is the minimum total cost for the vehicle to reach the pth candidate speed at the i+1th speed adjustment position from the end of the road; J p,k(i+1) is the cost of the vehicle's process from the kth candidate speed at the i+1th speed adjustment position to the pth candidate speed at the ith speed adjustment position;

[0141] by Figure 4 For example, the cost of the process from the pth candidate speed of the n+1th speed adjustment position to the second candidate speed of the nth speed adjustment position is J 2,p (i+1); add it to the cost J(p,n+1) stored in the pth row of the n+1th column of the original cost matrix Q, select the minimum value and record it as J(2,n) and store it in the 2nd row and nth column of the cost matrix Q; at the same time, v -1 candidate speed The speed stored in the 2nd row and nth column of the speed matrix F represents the speed of the n+1th speed adjustment position.

[0142] Thus, the element Q(m,l) in the cost matrix Q is the minimum cost from the mth candidate speed of the lth speed adjustment position to the end point, and the element F(m,l) in the speed matrix F is the V to the l-1th speed adjustment position. m The speed of the lth vehicle speed adjustment position with the smallest cost.

[0143] According to the elements stored in the speed matrix F, the speed sequence obtained by dynamic programming can be obtained. Figure 4 As shown, when the speed of the vehicle at the first speed adjustment position is V1, first, the speed stored in the first row and first column of the speed matrix F is searched for V2, which means the speed of the vehicle at the next speed adjustment position is V2. Then, the speed stored in the second row and second column of the speed matrix F is searched for V2, which means the speed of the vehicle at the next speed adjustment position is V2. Finally, this process is repeated until the speed matrix F is searched for the speed stored in the j+1th row and the Nth column. s The speed stored in column -1 is V j+1 , represents the vehicle at the Nth s The speed of the vehicle speed adjustment position is V j+1 At this point, the vehicle speed sequence V of the entire road is obtained through the dynamic programming method.

[0144] Example 2

[0145] In order to verify the effectiveness and superiority of the method proposed in this patent, the following Figure 5 The road shown in the figure is simulated and verified, where the orange part is the bumpy road section and the white part is the flat road section. The traditional dynamic programming method is compared with the dynamic programming method based on the road diffusion risk zone proposed in this patent. The speed sequence comparison diagram is as follows Figure 5 shown.

[0146] As can be seen, the speed sequence planned by the dynamic planning method based on the road diffusion risk zone proposed in this paper can decelerate in advance when approaching bumpy sections and the end point, resulting in smooth speed changes. This shows that the proposed method can predict the approach and departure of speed change events, helping smart cars plan better speed sequences.

[0147] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A low-computing speed planning method for intelligent vehicles based on road diffusion risk zones, characterized in that: The following steps are involved: Step 1: Establish the quarter vehicle suspension dynamics equation and continuous-time state-space equation, and discretize the state-space equation; Step 2: Preprocess the forward-looking information obtained by the smart car. The smart car uses the global road information obtained by the Internet of Vehicles to divide road sections and determine speed change events, thereby establishing road diffusion risk areas and generating speed adjustment positions. Step 3: Generate the optimal speed sequence. A cost function is established based on the planning goal and the generated vertical cost. A dynamic planning speed sequence generation method is designed, and the speed sequence is generated by combining the preprocessed forward information. The specific method of step 2 is as follows: 21) The intelligent vehicle obtains forward-looking information, namely global road elevation information, through the Internet of Vehicles, and uses the global road elevation information to divide the entire road to be driven into bumpy sections B i and flat road section S i ; 22) Divide the entire road to be driven into N s Vehicle speed adjustment position P i Each speed adjustment position includes a speed change event speed adjustment position T i and normal speed adjustment position A i ; The specific method for determining the vehicle speed adjustment position is as follows: (1) The starting point, end point and bumpy road section are called speed change event speed adjustment positions; (2) Three common speed adjustment positions, A1, A2, and A3, are set before and after each speed change event to change the speed in time; (3) The area between A3 in the normal speed adjustment position and the adjacent speed change event speed adjustment position is called the road diffusion risk area, which includes the normal speed adjustment positions A1, A2, and A3. The distance between the normal speed adjustment position and the speed change event speed adjustment position is set as follows: l i =5i 2 ,i=1,2,3 (5) Where i is the normal speed adjustment position A i Serial number; l i Adjust position A for normal speed i The distance to the speed adjustment position of the speed change event; (4) When a vehicle passes through a flat road section between two speed change events, it is stipulated that, except for the speed adjustment position set in (2), no other speed adjustment position shall be set between the two speed change events to avoid frequent acceleration and deceleration of the vehicle; (5) For each speed adjustment position, there is a δV interval, starting from the lowest speed V min To the maximum speed V max N v Candidate speeds.

2. The low-computing speed planning method for intelligent vehicles based on road diffusion risk zones according to claim 1 is characterized in that: The specific method of step one is as follows: 11) Based on the quarter-car suspension model and vehicle dynamics principles, the quarter-car suspension dynamics equation is obtained as follows: Where m s is the sprung mass, m u is the unsprung mass, k s is the spring stiffness, c s is the suspension damping coefficient, c t is the vertical equivalent damping of the tire, k t is the vertical equivalent stiffness of the tire, z s is the vertical displacement of the sprung mass, z u is the vertical displacement of the unsprung mass, z r is the road surface height; 12) Select the sprung mass displacement z s (t), unsprung mass displacement z u (t), sprung mass displacement velocity Unsprung mass displacement velocity As the state variable; choose sprung mass acceleration Suspension travel z u (t)-z s (t), tire dynamic deflection z r (t)-z u (t) is the output variable of the system; then the road height z is selected r and its rate of change is the disturbance of the system; then the quarter vehicle suspension dynamics equation (1) is rewritten as the system state space equation under continuous time, as shown below: in, Where x(t) is the state variable; is the derivative of the state variable; y(t) is the output variable; ω(t) is the disturbance variable; A is the suspension system matrix; C is the suspension output matrix; E is the state disturbance matrix; L is the output disturbance matrix; z s (t) is the displacement of the sprung mass; z u (t) is the unsprung mass displacement; is the sprung mass displacement velocity; is the displacement velocity of the unsprung mass; z r is the road surface height; m s is the sprung mass; m u is the unsprung mass; k s is the spring stiffness; c s is the suspension damping coefficient; c t is the vertical equivalent damping of the tire; k t is the vertical equivalent stiffness of the tire; 13) The continuous time matrix in Equation (2) is discretized using the zero-order hold discretization method, and the discretized system state space equation is obtained as follows: Where A is the suspension system matrix; E is the state interference matrix; C is the suspension output matrix; L is the output interference matrix; T s is the sampling period of the suspension system; is the discrete suspension system matrix; is the discrete state interference matrix; x(k) is the state variable of the kth period; y(k) is the output variable of the kth period; ω(k) is the interference variable of the kth period.

3. The low-computing speed planning method for intelligent vehicles based on road diffusion risk zones according to claim 1 is characterized in that: The specific method of step three is as follows: 31) Determine planning objectives; The planning objectives include vertical performance objectives, longitudinal performance objectives and traffic performance objectives; The vertical performance includes sprung mass acceleration, tire dynamic deflection, and suspension dynamic travel. The global road elevation information obtained by the Internet of Vehicles is injected into the passive suspension model, that is, the quarter-vehicle suspension model is established. The output variable y(k) at each sampling period is obtained through the discretized system state space equation (3), and the vertical performance of the corresponding vehicle speed adjustment position is calculated as follows: Where, is the vertical performance of the vehicle passing the i-th speed adjustment position at the p-th candidate speed; N i is the number of suspension system samples at the i-th vehicle speed adjustment position; y1(k) is the sprung mass acceleration of the k-th sampling period; y2(k) is the suspension dynamic travel of the k-th sampling period; y3(k) is the tire dynamic deflection of the k-th sampling period; σ1 is the weight coefficient of sprung mass acceleration; σ2 is the weight coefficient of suspension dynamic travel; σ3 is the weight coefficient of tire dynamic deflection; l i is the length of the i-th speed adjustment position, V i is the speed of the vehicle passing through the i-th speed adjustment position, T s is the sampling time of the suspension system; Set the speed adjustment position P representing the bumpy road section k The vertical performance of the vehicle speed adjustment position within the front and rear road diffusion risk areas is as follows: Where, is the vertical performance of the vehicle passing the kth speed adjustment position representing the bumpy road section at the pth candidate speed; is the vertical performance of passing the k-1th speed adjustment position at the pth candidate speed; is the vertical performance of passing the k-2th speed adjustment position at the pth candidate speed; is the vertical performance of passing the k-3th speed adjustment position at the pth candidate speed; The cost function of the vertical performance objective is established as follows: Where, is the vertical cost of the vehicle passing the i-th speed adjustment position at the p-th candidate speed; is the vertical performance of the vehicle passing the i-th speed adjustment position at the p-th candidate speed; N s Adjust the number of bits for vehicle speed; The vehicle's speed changes linearly between adjacent speed adjustment positions, meaning the acceleration is a constant. Therefore, the cost function for defining the longitudinal performance objective is the absolute value of the vehicle's longitudinal acceleration between two adjacent speed adjustment positions, reflecting the vehicle's acceleration and deceleration, as follows: Where, V is the longitudinal cost of the vehicle from the kth candidate speed at the i+1th speed adjustment position to the pth candidate speed at the ith speed adjustment position; p is the pth candidate vehicle speed; Ls i Le is the distance from the starting point of the i-th speed adjustment position to the starting point of the entire road; i is the distance from the end point of the i-th speed adjustment position to the starting point of the entire road; N s Adjust the number of bits for vehicle speed; The traffic performance target represents the time between two adjacent speed adjustment positions, and its cost function is expressed as follows: Where, V is the cost of the vehicle traveling from the kth candidate speed at the i+1th speed adjustment position to the pth candidate speed at the ith speed adjustment position; p is the pth candidate vehicle speed; N s The number of vehicle speed adjustment positions; Ls i Le is the distance from the starting point of the i-th speed adjustment position to the starting point of the entire road; i is the distance from the end point of the i-th speed adjustment position to the starting point of the entire road; A total cost function including vertical performance, longitudinal performance and traffic performance is established; the specific form of the total cost function is shown in the following formula: Where, J pk (i) is the cost of the vehicle's process from the kth candidate speed at the (i+1)th speed adjustment position to the pth candidate speed at the i-th speed adjustment position; is the vertical cost of the vehicle passing the i-th speed adjustment position at the p-th candidate speed; is the longitudinal cost of the vehicle from the kth candidate speed at the i+1th speed adjustment position to the pth candidate speed at the ith speed adjustment position; is the cost of the vehicle traveling from the kth candidate speed at the i+1th speed adjustment position to the pth candidate speed at the ith speed adjustment position; α is the vertical cost weight coefficient; β is the longitudinal cost weight coefficient; γ is the travel cost weight coefficient; is the maximum vertical cost among all speed adjustment positions; is the maximum longitudinal cost among all adjacent vehicle speed adjustment positions; is the maximum longitudinal cost among all adjacent vehicle speed adjustment positions; is the maximum travel cost among all adjacent speed adjustment positions; c i V is the vertical performance of the vehicle passing through the i-th speed adjustment position; max is the maximum speed of the vehicle; V min is the minimum speed of the vehicle; L max is the maximum distance between all adjacent speed adjustment positions on the road; l max is the maximum length of all bumpy sections on the road; 32) Generate the vehicle speed sequence based on the established cost function of vertical performance target, longitudinal performance target and traffic performance target; the entire road contains N s Speed ​​adjustment bits, each of which contains N v candidate speeds; the dynamic programming method calculates the cost of each speed adjustment position from back to front and performs speed planning.

4. The low-computing speed planning method for intelligent vehicles based on road diffusion risk zones according to claim 3 is characterized in that: The specific method of step 32) is as follows: 321) Build an N v ×N s The cost matrix Q is used to record the cost of all candidate speeds in the speed adjustment position, and at the same time, establish an N v ×N s The speed matrix F is used to record the vehicle speed sequence; the element Q(p,k) in the kth column and pth row of the cost matrix Q represents the pth candidate speed V of the vehicle from the kth speed adjustment position p The minimum cost to the end of the road, the element F(p,k) in the kth column and pth row of the speed matrix F represents V to the kth speed adjustment position p The speed of the k+1th speed adjustment position with the minimum cost; 322) Nth s Speed ​​adjustment position As the end of the road, set the speed adjustment position The cost is zero, that is, the Nth cost matrix Q s The elements of the column are all recorded as zero; 323) For the Nth s -1 speed adjustment position The p-th candidate speed is calculated according to formula (12) s Speed ​​adjustment position All candidate vehicle speeds are converted to their process costs, and the minimum process cost is selected and recorded in the cost matrix Q. At the same time, the Nth vehicle corresponding to the minimum cost is recorded in the cost matrix Q. s The candidate vehicle speeds for the vehicle speed adjustment positions are recorded in the speed matrix F as follows: Q(p,N s −1)=J(p,N s -1)=minJ p,k (N s ),p=1,2,…,N v ,k=1,2,...,N v (16) Where Q is the cost matrix; N s N is the number of speed adjustment bits included in the entire road; v The number of candidate vehicle speeds for each vehicle speed adjustment position; J(p,N s -1) is the distance from the end of the road to the Nth s -1 The minimum total cost of the p-th candidate speed for the speed adjustment position; J p,k (N s ) is the vehicle from the Nth s The kth candidate vehicle speed of the vehicle speed adjustment position to the Nth candidate vehicle speed s -1 process cost between the pth candidate vehicle speeds of the vehicle speed adjustment position; From the Nth s The speed adjustment position of the p-th candidate speed to the N-th candidate speed s The process cost of the j-th candidate vehicle speed at the -1 vehicle speed adjustment position is J j,p (N s ); Select the minimum cost J j,j+1 (N s ) is recorded as J(j,N s -1) and stored in the jth row and Nth column of the cost matrix Q s -1 column, at the same time, the j+1th candidate speed V corresponding to the minimum cost j+1 Stored in the jth row, Nth column of the velocity matrix F s -1 column, represents the Nth s The speed of the vehicle speed adjustment position should be V j+1 ; 324) For the remaining speed adjustment positions, namely the Nth s -2 speed adjustment positions to the first speed adjustment position, calculate the adjacent speed adjustment position P according to step (3) i and P i+1 The process cost between Adjust the process cost and vehicle speed to P i+1 The costs of the corresponding candidate speeds are added together, and the minimum cost is selected and recorded in the cost matrix, as shown below: Q(p,i)=J(p,i)=min(J p,k (i+1)+J(p,i+1)),p=1,2,...,N v ,k=1,2,...,N v (17) Where Q is the cost matrix; N v is the number of candidate speeds for each speed adjustment position; J(p,i+1) is the minimum total cost for the vehicle to reach the pth candidate speed at the i+1th speed adjustment position from the end of the road; J p,k (i+1) is the cost of the vehicle's process from the kth candidate speed at the i+1th speed adjustment position to the pth candidate speed at the ith speed adjustment position; The cost of the process from the pth candidate speed at the n+1th speed adjustment position to the second candidate speed at the nth speed adjustment position is J 2,p (i+1); add the cost J(p,n+1) stored in the pth row of the n+1th column of the original cost matrix Q, select the minimum value and record it as J(2,n) and store it in the 2nd row and nth column of the cost matrix Q; at the same time, v -1 candidate speed The speed stored in the 2nd row and nth column of the speed matrix F represents the speed of the n+1th speed adjustment position. Thus, the element Q(m,l) in the cost matrix Q is the minimum cost from the mth candidate speed of the lth speed adjustment position to the end point, and the element F(m,l) in the speed matrix F is the V to the l-1th speed adjustment position. m The speed of the lth speed adjustment position with the minimum cost; The vehicle speed sequence obtained by the dynamic programming method is obtained according to the elements stored in the speed matrix F; When the speed of the vehicle at the first speed adjustment position is V1, first, the speed stored in the first row and first column of the speed matrix F is searched for V2, which means the speed of the vehicle at the next speed adjustment position is V2. Then, the speed stored in the second row and second column of the speed matrix F is searched for V2, which means the speed of the vehicle at the next speed adjustment position is V2. Finally, this process is repeated until the speed matrix F is searched for the speed stored in the j+1th row and the Nth column. s The speed stored in column -1 is V j+1 , represents the vehicle at the Nth s The speed of the vehicle speed adjustment position is V j+1 ; So far, the vehicle speed sequence V of the entire road is obtained through the dynamic programming method.

Images