CN109669461B - A decision-making system and its trajectory planning method for autonomous vehicles under complex working conditions - Google Patents

Abstract

The invention discloses a decision-making system for an automatic driving vehicle under a complex working condition and a track planning method thereof. In the running process of the vehicle, the environment sensing unit transmits the sensed surrounding vehicle motion information to the real-time decision unit for deciding the optimal driving behavior of the automatic driving vehicle in the current state. After the driving behavior is decided, the track planning unit performs double planning on the path and the speed of the vehicle by a set track planning method to obtain the optimal track in the current state, and corresponding control signals are input to an execution mechanism through an ECU (electronic control Unit) to ensure safe and reliable running of the vehicle. The invention can plan a safe and collision-free track for the vehicle in real time under the complex working conditions of the multi-lane and multi-obstacle vehicle, thereby realizing the automatic driving of the vehicle.

Description

A decision-making system and its trajectory planning method for autonomous vehicles under complex working conditions

technical field

The invention belongs to the technical field of automatic driving of vehicles, and in particular relates to a decision-making system for an automatic driving vehicle under complex working conditions and a trajectory planning method thereof.

Background technique

With the improvement of sensor accuracy, the development of chip technology, and the arrival of 5G communication, there are more and more researches on autonomous driving of vehicles. The main purpose of research is to reduce traffic accidents, ease traffic congestion, and reduce the driving burden of drivers. At present, many international companies, such as Google, GM, and Tesla, have invested a lot of energy in researching high-level autonomous vehicles.

As the core part of vehicle autonomous driving technology, it is particularly important for the decision-making system to decide in real time a safe and reliable trajectory that can avoid surrounding obstacles. The system is the brain of autonomous driving. It mainly plans a safe trajectory for the autonomous vehicle based on the traffic information sensed by the vehicle sensors, such as surrounding vehicle speed, yaw rate, lane line and road boundary information. After the corresponding trajectory is obtained, the corresponding control amount is obtained through the dynamic model of the vehicle and transmitted to the lower-level execution system, so as to control the steering wheel, brake and accelerator to realize the automatic driving of the vehicle. At present, the research on the vehicle decision-making system mainly focuses on the decision-making planning under static conditions, that is, the traffic conditions determined by the movement of the surrounding vehicles, while in the actual complex traffic, the future movements of the surrounding vehicles may change and need to be predicted. It is not a regular car-following and lane-changing condition. In this situation, the decision-making system needs to ensure that the vehicle avoids the surrounding obstacles in real time, so as to improve the driving safety of the vehicle.

In addition, trajectory planning technology is the key technology of the decision-making system of autonomous vehicles. The current research mainly focuses on the single planning of speed or path. For example, when following a car, only the speed is planned, and when changing lanes, the speed is kept constant and only the planning is performed. path. In order to realize automatic driving in the true sense, especially in the face of overtaking conditions, it is necessary to plan the speed and path at the same time during trajectory planning. Therefore, it is very important to plan a collision-free trajectory by controlling the speed and movement direction of the vehicle under the actual complex traffic conditions.

SUMMARY OF THE INVENTION

In view of the above-mentioned deficiencies of the prior art, the purpose of the present invention is to provide a decision-making system and a trajectory planning method for an autonomous driving vehicle under complex working conditions, so as to solve the problems in the prior art under complex working conditions such as multi-lane and high-speed scenarios. For the problem of intelligent decision-making and trajectory planning, through the technical solution of the present invention, a safe and stable trajectory can be planned in real time, so as to realize the automatic driving of the vehicle.

For achieving the above object, the technical scheme adopted in the present invention is as follows:

The invention discloses a decision-making system for an automatic driving vehicle under complex working conditions, comprising: an environment perception unit, a real-time decision-making unit, a trajectory planning unit and a control unit; wherein,

The environment perception unit is used to perceive the motion information of autonomous vehicles and surrounding vehicles in real time;

The real-time decision-making unit includes the on-board computer on the autonomous driving vehicle and the CAN communication module connected to it; the CAN communication module is connected with the above-mentioned environmental perception unit, and receives the above-mentioned motion information; the on-board computer decides the autonomous driving vehicle in the current state according to the motion information optimal driving behavior;

A trajectory planning unit, connected with the above-mentioned real-time decision-making unit, which double-plans the path and speed of the vehicle according to the optimal driving behavior of the autonomous driving vehicle determined by the real-time decision-making unit to obtain the optimal trajectory;

The control unit includes the electronic control unit and the active steering motor, the brake and accelerator pedal displacement motors electrically connected to it; The control command of the pedal displacement motor, thereby controlling the driving state of the vehicle.

Further, the environment perception unit includes GPS, lidar, camera, ultrasonic radar and yaw rate sensor provided on the autonomous vehicle.

Further, the motion information includes: position information, speed information and yaw angle information.

Further, the trajectory planning unit considers the safety constraints, efficiency constraints and stability constraints of the vehicle when planning.

即保证最优轨迹对应的危险度R小于乘客可接受的危险等级

根据该危险性约束，即可将三维决策场约束成一个二维平面；具体求解如下：Further, the described risk restriction:

That is to ensure that the risk R corresponding to the optimal trajectory is less than the acceptable risk level for passengers

According to the risk constraint, the three-dimensional decision field can be constrained to a two-dimensional plane; the specific solution is as follows:

In the formula, γ is the weight factor; s _t represents the state parameters corresponding to the given trajectory at time t, including the horizontal and vertical coordinates, speed, and yaw angle information; p _t represents the state parameters corresponding to the surrounding vehicles at time t, including the horizontal and vertical coordinates. Coordinate, speed, yaw angle information; F is the risk assessment function;

该约束保证车辆沿着交通道路提供的最佳车速行驶，根据该高效性约束，即可将上述二维平面约束成一条曲线；其中，v_final为给定轨迹若干个周期后对应的速度，

为当前交通状况下对应的车辆最佳车速；Efficiency constraints:

This constraint ensures that the vehicle travels along the optimal speed provided by the traffic road. According to this efficiency constraint, the above-mentioned two-dimensional plane can be constrained into a curve; where v _final is the speed corresponding to a given trajectory after several cycles,

is the best speed of the vehicle corresponding to the current traffic condition;

Stationarity constraint: minΔy, which ensures that the vehicle changes lanes less frequently, thereby improving ride comfort; according to this constraint, the above curve can be constrained into an optimal decision point, and the decision point is used to determine where the autonomous vehicle will go. The optimal driving trajectory at a moment; among them, Δy is the longitudinal deviation between the decided trajectory and the current road.

The invention also discloses a trajectory planning method for an automatic driving vehicle decision-making system under complex working conditions, based on the above system, comprising the following steps:

1) Obtain the traversal trajectory: first, the target position points that the vehicle may reach after a number of cycles are given, and each target position point represents a trajectory, that is, the traversal trajectory;

2) Carry out an optimization search according to the above traversal trajectory, and optimize an optimal trajectory of the vehicle at the current moment through the constraints of danger, efficiency and stability faced by the vehicle.

Further, the method for obtaining the traversal track in the step 1) specifically includes the following steps:

11) According to the current position of the vehicle and the given target position point, a polynomial is used to fit the path corresponding to the future traversal trajectory of the vehicle, and four constraints are used to fit a third-order polynomial, as follows:

y=a ₀ +a ₁ x+a ₂ x ² +a ₃ x ³

为当前时刻车辆对应的横摆角，(x_k,y_k)为当前状态自动驾驶车辆对应的位置坐标，(x_p,y_p)为给定的若干个周期之后自动驾驶车辆到达的目标点；Among them, a ₀ , a ₁ , a ₂ , a ₃ are the fitting parameters corresponding to the polynomial path, respectively,

is the yaw angle corresponding to the vehicle at the current moment, (x _k , y _k ) is the position coordinate corresponding to the current state of the autonomous vehicle, (x _p , y _p ) is the target point that the autonomous vehicle will reach after a given number of cycles ;

12) Use the integral to find the length corresponding to the above path, and regard the process as a uniform acceleration motion process to obtain the speed corresponding to the traversing track;

The length S of each decision path:

where y' is the slope of the polynomial path;

Consider the process as a uniformly accelerated motion; thus, the acceleration corresponding to each decision point is obtained:

Among them, T is the time corresponding to each cycle, v _k is the current speed of the vehicle, and a is the acceleration corresponding to the process;

The speed corresponding to this process is expressed as follows:

v _t =v _k +a*(tk)

Among them, v _k is the speed corresponding to the vehicle at the current moment, and v _t represents the speed corresponding to the vehicle after t cycles;

13) According to the path fitted in step 11) and the speed on the path obtained in step 12), the parameter information (path + speed) of the traversing trajectory of the vehicle is obtained.

Further, the optimal trajectory search method in the step 2) specifically includes the following steps:

21) Obtain the risk degree corresponding to each trajectory, and the risk degree can form a three-dimensional danger field of a vehicle in the future, where the risk degree evaluation function F is established as follows:

Among them, S _r is the road safety factor; D _sf is the standard safety distance; b is the limit coefficient; _{De es} is the actual distance between the vehicle and the surrounding vehicles, t is the time for the surrounding vehicles to reach the front of the vehicle, and t _b is the braking time;

22) Constrain the above three-dimensional hazard field to obtain an optimal trajectory.

Further, in the step 22), constraining the three-dimensional hazardous field specifically includes:

即保证最优轨迹对应的危险度R小于乘客可接受的危险等级

根据该约束，即可将三维决策场约束成一个二维平面；具体求解如下：221) Dangerous restraint:

That is to ensure that the risk R corresponding to the optimal trajectory is less than the acceptable risk level for passengers

According to this constraint, the three-dimensional decision field can be constrained to a two-dimensional plane; the specific solution is as follows:

In the formula, γ is the weight factor; s _t represents the state parameters corresponding to the given trajectory at time t, including the horizontal and vertical coordinates, speed, and yaw angle information; p _t represents the state parameters corresponding to the surrounding vehicles at time t, including the horizontal and vertical coordinates. Coordinate, speed, yaw angle information; F is the risk assessment function;

将上述二维平面约束成一条曲线；其中，v_final为给定轨迹若干个周期后对应的速度，

为当前交通状况下对应的车辆最佳车速；222) Efficiency constraints:

Constrain the above two-dimensional plane into a curve; where v _final is the velocity corresponding to a given trajectory after several cycles,

is the best speed of the vehicle corresponding to the current traffic condition;

223) Stationarity constraint: minΔy, which constrains the above curve into an optimal decision point, and determines the optimal driving trajectory of the autonomous vehicle at time t+1 through this decision point; where Δy is the trajectory determined by the decision and the current road. longitudinal deviation.

Beneficial effects of the present invention:

1. The present invention can realize the automatic driving of vehicles in multi-lane complex traffic conditions, and can plan a safe and collision-free trajectory in real time.

2. The decision planning system designed by the present invention can fully consider the kinematics and dynamic constraints of the vehicle actuator, and the generated trajectory has continuity and can be applied to the real-time changing road environment.

3. The trajectory planning of the vehicle in the present invention is the dual planning of the path and the speed, that is, the speed of the vehicle at each point on the path is planned while the path is planned for the vehicle.

Description of drawings

FIG. 1 is an overall block diagram of the decision-making system of the present invention.

FIG. 2 is a schematic diagram corresponding to an optimal search method for a given target position point.

Detailed ways

In order to facilitate the understanding of those skilled in the art, the present invention will be further described below with reference to the embodiments and the accompanying drawings, and the contents mentioned in the embodiments are not intended to limit the present invention.

Referring to FIG. 1 , a decision-making system for an autonomous vehicle under complex working conditions of the present invention is characterized in that it includes: an environment perception unit, a real-time decision-making unit, a trajectory planning unit, and a control unit; wherein,

The environmental perception unit includes GPS, lidar, camera, ultrasonic radar and yaw rate sensor provided on the autonomous vehicle; it is used to perceive the motion information of the autonomous vehicle and surrounding vehicles in real time; the motion information includes: position information, Speed information and yaw angle information.

The real-time decision-making unit includes the on-board computer on the autonomous driving vehicle and the CAN communication module connected to it; the CAN communication module is connected with the above-mentioned environmental perception unit, and receives the above-mentioned motion information; the on-board computer decides the autonomous driving vehicle in the current state according to the motion information optimal driving behavior;

The trajectory planning unit is connected with the above-mentioned real-time decision-making unit, and according to the optimal driving behavior of the autonomous driving vehicle determined by the real-time decision-making unit, it double-plans the path and speed of the vehicle to obtain the optimal trajectory; considers the safety of the vehicle during planning Sex constraints, efficiency constraints, and stationarity constraints.

即保证最优轨迹对应的危险度R小于乘客可接受的危险等级

根据该危险性约束，即可将三维决策场约束成一个二维平面；具体求解如下：Dangerous constraints:

That is to ensure that the risk R corresponding to the optimal trajectory is less than the acceptable risk level for passengers

According to the risk constraint, the three-dimensional decision field can be constrained to a two-dimensional plane; the specific solution is as follows:

In the formula, γ is the weight factor; s _t represents the state parameters corresponding to the given trajectory at time t, including the horizontal and vertical coordinates, speed, and yaw angle information; p _t represents the state parameters corresponding to the surrounding vehicles at time t, including the horizontal and vertical coordinates. Coordinate, speed, yaw angle information; F is the risk assessment function;

将上述二维平面约束成一条曲线；其中，v_final为给定轨迹若干个周期后对应的速度，

为当前交通状况下对应的车辆最佳车速；Efficiency constraints:

Constrain the above two-dimensional plane into a curve; where v _final is the velocity corresponding to a given trajectory after several cycles,

is the best speed of the vehicle corresponding to the current traffic condition;

Stationarity constraint: minΔy, which constrains the above curve into the optimal decision point, and determines the optimal driving trajectory of the autonomous vehicle at the next moment through this decision point; where Δy is the longitudinal deviation between the decided trajectory and the current road .

The control unit includes an electronic control unit (ECU) and an active steering motor, a brake and an accelerator pedal displacement motor electrically connected to it; the electronic control unit generates an optimal trajectory for the active steering motor, braking and accelerator pedals according to the optimal trajectory planned by the trajectory planning unit. The control commands of the motor and the accelerator pedal displacement motor are used to control the driving state of the vehicle.

When working, the environmental perception unit first uses various sensors to obtain motion information around the autonomous vehicle, and transmits this information to the on-board computer for real-time decision-making. Carry out trajectory planning, the trajectory contains both the path information of the autonomous vehicle and the speed information, so it is well adapted to the decision-making planning under the actual complex working conditions. After obtaining the trajectory information, the control unit of the vehicle will use the corresponding control algorithm to convert the trajectory information into the control quantity information directly input by the controller, and input these control quantities to the active steering motor, brake and accelerator pedal displacement motor, thereby Realize the automatic driving of the vehicle.

The invention also discloses a trajectory planning method for an automatic driving vehicle decision-making system under complex working conditions, based on the above system, comprising the following steps:

1) Obtain the traversal trajectory: first, the target position points that the vehicle may reach after a number of cycles are given, and each target position point represents a trajectory, that is, the traversal trajectory;

2) Carry out an optimization search according to the above traversal trajectory, and optimize an optimal trajectory of the vehicle at the current moment through the constraints of danger, efficiency and stability faced by the vehicle.

The method for obtaining the traversal track in the step 1) specifically includes the following steps:

11) According to the current position of the vehicle and the given target position point, a polynomial is used to fit the path corresponding to the future traversal trajectory of the vehicle, and four constraints are used to fit a third-order polynomial, as follows:

y=a ₀ +a ₁ x+a ₂ x ² +a ₃ x ³

为当前时刻车辆对应的横摆角，(x_k,y_k)为当前状态自动驾驶车辆对应的位置坐标，(x_p,y_p)为给定的若干个周期之后自动驾驶车辆到达的目标点；Among them, a0, a1, a2, a3 are the fitting parameters corresponding to the polynomial path, respectively,

is the yaw angle corresponding to the vehicle at the current moment, (x _k , y _k ) is the position coordinate corresponding to the current state of the autonomous vehicle, (x _p , y _p ) is the target point that the autonomous vehicle will reach after a given number of cycles ;

12) Use the integral to find the length corresponding to the above path, and regard the process as a uniform acceleration motion process to obtain the speed corresponding to the traversing track;

The length S of each decision path:

where y' is the slope of the polynomial path;

Consider the process as a uniformly accelerated motion; thus, the acceleration corresponding to each decision point is obtained:

Among them, T is the time corresponding to each cycle, v _k is the current speed of the vehicle, and a is the acceleration corresponding to the process;

The speed corresponding to this process is expressed as follows:

v _t =v _k +a*(tk)

Among them, v _k is the speed corresponding to the vehicle at the current moment, and v _t represents the speed corresponding to the vehicle after t cycles;

13) According to the path fitted in step 11) and the speed on the path obtained in step 12), the parameter information (path + speed) of the traversing trajectory of the vehicle is obtained.

Referring to Figure 2, the optimal trajectory search method in step 2) specifically includes the following steps:

21) Obtain the risk degree corresponding to each trajectory, and the risk degree can form a three-dimensional danger field of a vehicle in the future, where the risk degree evaluation function F is established as follows:

Among them, S _r is the road safety factor; D _sf is the standard safety distance; b is the limit coefficient; _{De es} is the actual distance between the vehicle and the surrounding vehicles, t is the time for the surrounding vehicles to reach the front of the vehicle, and t _b is the braking time;

22) Constrain the above three-dimensional hazard field to obtain an optimal trajectory.

Wherein, the restriction on the three-dimensional hazardous field in the step 22) specifically includes:

即保证最优轨迹对应的危险度R小于乘客可接受的危险等级

根据该约束，即可将三维决策场约束成一个二维平面；具体求解如下：221) Dangerous restraint:

That is to ensure that the risk R corresponding to the optimal trajectory is less than the acceptable risk level for passengers

According to this constraint, the three-dimensional decision field can be constrained to a two-dimensional plane; the specific solution is as follows:

Among them, γ is the weight factor; s _t represents the state parameters corresponding to a given trajectory at time t, including the horizontal and vertical coordinates, speed, and yaw angle information; p _t represents the state parameters corresponding to the surrounding vehicles at time t, including the horizontal and vertical coordinates. , speed, yaw angle information; F is the risk assessment function;

该约束保证车辆能沿着交通道路提供的最佳车速行驶，根据该高效性约束，将上述二维平面约束成一条曲线；其中，v_final为给定轨迹若干个周期后对应的速度，

为当前交通状况下对应的车辆最佳车速；222) Efficiency constraints:

This constraint ensures that the vehicle can travel along the best speed provided by the traffic road. According to the efficiency constraint, the above-mentioned two-dimensional plane is constrained into a curve; where v _final is the speed corresponding to a given trajectory after several cycles,

is the best speed of the vehicle corresponding to the current traffic condition;

223) Stationarity constraint: minΔy, the stationarity constraint can ensure that the vehicle changes lanes less, thereby improving the ride comfort; according to this constraint, the above curve is constrained to an optimal decision point, and the autonomous vehicle is determined by this decision point The optimal driving trajectory at time t+1; among them, Δy is the longitudinal deviation between the decided trajectory and the current road.

3) The optimal trajectory of the vehicle in the current state is obtained above. Next, the vehicle needs to be controlled to track the trajectory, and the following vehicle dynamics model is established based on the linearization assumption under the small angle of the tire for tracking.

Wherein, the tracking method based on vehicle dynamics used in step 3) includes the following steps:

31) The vehicle state equation based on dynamics is obtained:

时，When the vehicle control quantity _udyn is the front wheel angle σ _f and the vehicle speed v, that is, _udyn = [σ _f ,v], the state quantity is the vehicle motion trajectory sequence

hour,

为车辆纵向速度，

为车辆侧向速度时，

为车辆横摆角，

为横摆角速度，Y,X为地球坐标系下的纵横坐标；in,

is the longitudinal speed of the vehicle,

is the lateral speed of the vehicle,

is the vehicle yaw angle,

is the yaw angular velocity, Y and X are the vertical and horizontal coordinates in the earth coordinate system;

The following discretized equation of state can be established:

Among them, k is the current moment, T is the sampling time of each discretization cycle, I is the identity matrix, f is the dynamic equation, and (u ₀ , ξ ₀ ) is the reference state point.

32) Track the establishment of the objective function:

With the above prediction equation based on dynamics, it can be further tracked according to the deviation between the predicted trajectory and the expected trajectory, so as to control the safe driving of the vehicle. Specifically, the following objective function J(k) is used:

Among them, η is the predicted actual state quantity, η _ref is the reference state quantity obtained from the planned trajectory, and ΔU is the control quantity increment; the first item of the objective function is the deviation between the predicted trajectory and the reference trajectory, reflecting the trajectory followability; the The second term of the objective function is the deviation of the control quantity, which reflects the stability.

33) For the above objective function, obtain the final trajectory tracking sequence through the following two constraints;

321) Control quantity constraint: The control quantity is defined as follows:

u _min (t+k)≤u(t+k)≤u _max (t+k),k=0,1,L,20

322) Control incremental constraints:

Δu _min (t+k)≤Δu(t+k)≤Δu _max (t+k),k=0,1,L,20

With the above constraints, the optimal tracking control sequence of the autonomous vehicle can be solved at each moment, so as to ensure that the vehicle travels along the safest trajectory.

There are many specific application ways of the present invention, and the above are only the preferred embodiments of the present invention. It should be pointed out that for those skilled in the art, without departing from the principle of the present invention, several improvements can be made. These Improvements should also be considered as the protection scope of the present invention.

Claims (1)

1. A trajectory planning method of an automatic driving vehicle decision-making system under a complex working condition is based on the automatic driving vehicle decision-making system under the complex working condition, and is characterized in that the system comprises the following steps: the system comprises an environment sensing unit, a real-time decision unit, a track planning unit and a control unit;

the environment sensing unit is used for sensing the motion information of the automatic driving vehicle and the surrounding vehicles in real time;

the real-time decision unit comprises an on-board computer on the automatic driving vehicle and a CAN communication module connected with the on-board computer; the CAN communication module is connected with the environment sensing unit and receives the motion information; the vehicle-mounted computer decides the optimal driving behavior of the automatic driving vehicle in the current state according to the motion information;

the track planning unit is connected with the real-time decision unit and is used for carrying out double planning on the path and the speed of the vehicle according to the optimal driving behavior of the automatic driving vehicle decided by the real-time decision unit to obtain an optimal track;

the control unit comprises an electronic control unit, and an active steering motor, a brake and accelerator pedal displacement motor which are electrically connected with the electronic control unit; the electronic control unit generates control instructions for an active steering motor, a brake and accelerator pedal displacement motor according to the optimal track planned by the track planning unit, and further controls the running state of the vehicle;

the method comprises the following steps:

1) obtaining a traversal track: firstly, target position points which are possibly reached by the vehicle after a plurality of periods are given, wherein each target position point represents a track, namely a traversal track;

2) carrying out optimization search according to the traversal track, and optimizing an optimal track of the vehicle at the current moment through the danger, high efficiency and stability constraints faced by the vehicle;

the method for obtaining the traversal trajectory in the step 1) specifically comprises the following steps:

11) according to the current position of the vehicle and a given target position point, fitting a path corresponding to a future traversal track of the vehicle by using a polynomial, fitting by using 4 constraints and using a 3-degree polynomial, and specifically:

y＝a₀+a₁x+a₂x²+a₃x³

wherein, a₀,a₁,a₂,a₃Respectively, the fitting parameters corresponding to the polynomial path,

the yaw angle corresponding to the vehicle at the present moment, (x)_k,y_k) Position coordinates corresponding to the autonomous vehicle for the current state, (x)_p,y_p) A target point reached by the autonomous vehicle after a given number of cycles;

12) calculating the length corresponding to the path by utilizing integral, and regarding the process as a uniform acceleration motion process to obtain the speed corresponding to the traversal track;

length of each decision path S:

wherein y' is the slope of the polynomial path;

considering the process as uniform acceleration motion; thereby obtaining the acceleration corresponding to each decision point:

wherein T is the time corresponding to each period, v_kThe current speed of the vehicle is taken as a, and the acceleration corresponding to the process is taken as a;

the corresponding speeds of the process are expressed as follows:

v_t＝v_k+a*(t-k)

wherein v is_kFor the speed, v, corresponding to the vehicle at the present moment_tRepresenting the corresponding speed of the vehicle after t periods;

13) obtaining parameter information of the vehicle traversing track according to the path fitted in the step 11) and the speed on the path obtained in the step 12);

the optimal track searching method in the step 2) specifically comprises the following steps:

21) acquiring the risk degree corresponding to each track, wherein the risk degree can form a three-dimensional risk field of the vehicle at a future moment, and a risk degree evaluation function F is established as follows:

wherein S is_rThe road safety factor; d_sfIs a standard safe distance; b is a clipping coefficient; d_esIs the actual distance between the vehicle and the surrounding vehicles, t is the time when the surrounding vehicles reach the front of the vehicle, t_bThe braking time is;

22) constraining the three-dimensional dangerous field to obtain an optimal track;

the step 22) of constraining the three-dimensional danger field specifically includes:

221) risk constraint:

namely, the danger degree R corresponding to the optimal track is ensured to be less than the acceptable danger level of the passenger

According to the constraint, the three-dimensional decision field can be constrained into a two-dimensional plane; the specific solution is as follows:

wherein γ is a weighting factor; s_tRepresenting state parameters corresponding to the given track at the moment t, wherein the state parameters specifically comprise horizontal and vertical coordinates, speed and yaw angle information; p is a radical of_tRepresenting corresponding state parameters of vehicles around the t moment, wherein the state parameters comprise horizontal and vertical coordinates, speed and yaw angle information; f is a risk assessment function;

222) and (3) high-efficiency constraint:

constraining the two-dimensional plane into a curve; wherein v is_finalFor a given trajectory a corresponding speed after a number of cycles,

for the pair under the current traffic conditionThe optimal vehicle speed;

223) and (3) stability constraint: min delta y, constraining the curve into an optimal decision point, and determining the optimal running track of the automatic driving vehicle at the moment t +1 through the decision point; and Δ y is the longitudinal deviation of the determined track and the current road.

Images