CN105974917B - A kind of vehicle obstacle-avoidance path planning research method based on novel artificial potential field method - Google Patents

Abstract

The invention discloses a research method for vehicle obstacle avoidance path planning based on a novel artificial potential field method. After obtaining the information required for obstacle path planning, the road boundary repulsion potential field and obstacle repulsion potential field models based on the artificial potential field method are established, and the main vehicle is subjected to The balance equation is established based on the action of the force, and the location points that the main vehicle will pass through during the obstacle avoidance process are obtained by solving the solution, so as to obtain the obstacle avoidance path. At the same time, the speed of the main vehicle during the obstacle avoidance process is controlled to improve safety and comfort. The method used in the invention has a small calculation amount and is convenient for realizing real-time control, and the planned obstacle avoidance path is safer and more reliable than the traditional method.

Description

A Research Method for Vehicle Obstacle Avoidance Path Planning Based on Novel Artificial Potential Field Method

technical field

The invention belongs to the field of motor vehicle driving safety, and in particular relates to a research method for vehicle obstacle avoidance path planning based on a novel artificial potential field method.

Background technique

Road traffic accidents are mostly caused by collisions between vehicles and obstacles and secondary accidents after collisions. According to the statistical data of traffic accidents in my country in 2010 released by the Traffic Management Science Research Institute of the Ministry of Public Security, the analysis shows that the number of traffic accidents caused by driver errors (such as: misjudgment, wrong decision, etc.) accounts for about 90%. If the driver can be helped to take corresponding safety measures in an emergency traffic situation, the probability of traffic accidents will be greatly reduced, and the vehicle's local obstacle avoidance path planning is an important means to achieve this goal. This method plans a safe path for the vehicle before the collision, so that the vehicle can bypass the obstacle without collision, which is of great significance to reduce the occurrence of road traffic accidents.

Vehicle local path planning is a relatively complicated process. Drivers only rely on their senses and experience to make obstacle avoidance judgments during driving, which is prone to accidents, especially when driving at high speeds. Local path planning is mainly divided into two types: known environment information and unknown environment information. Since the scope of the former is very limited, the present invention is mainly aimed at vehicle local path planning in the case of unknown environment information. Vehicles obtain road information through on-board equipment (millimeter wave radar, CCD camera, various sensors, etc.), such as road width, number of lanes, position and size of obstacles, etc. Based on this information, a collision-free optimal path from the starting point to the goal point is planned.

Chinese patent CN 102520718 A discloses a robot obstacle avoidance path planning method based on physical modeling. The method establishes a robot dual grid information map by setting up a gravitational field grid and a distance information grid in the robot working area. Based on the above dual The raster information map uses the directed traversal method to search for all feasible paths for planning. This method is aimed at planning obstacle-avoiding paths for robots under the condition of existing environmental information, and when the grid is obtained very small, there are problems such as large amount of calculation. Chinese patent CN104317291A discloses a research method for robot collision avoidance path planning based on artificial potential field method, and provides a collision avoidance path planning method for mobile robots with complex shapes in an unknown environment. This method is only suitable for static obstacles, and cannot overcome the local minimum problem of the traditional artificial potential field method.

Contents of the invention

Aiming at the deficiencies of the prior art, the present invention provides a vehicle obstacle avoidance path planning research method based on a novel artificial potential field method, which solves the problem of large calculation and local minimum value of the traditional artificial potential field method.

The present invention adopts the following technical solutions to achieve the above-mentioned technical purpose.

A research method for vehicle obstacle avoidance path planning based on a novel artificial potential field method, comprising the following steps:

S1. Use CCD cameras, millimeter wave radars, and on-board equipment to collect road information, obstacle information, and main vehicle information required for vehicle obstacle avoidance path planning in real time;

S2. After obtaining the information required for vehicle obstacle avoidance path planning, establish a road coordinate system within the detection range of the millimeter-wave radar, and use vectors to represent the position of road boundary points, obstacles, and the main vehicle. The car information establishes the road boundary repulsion potential field and obstacle repulsion potential field model based on the artificial potential field method; the details are as follows:

S2.1 Establishment of road coordinate system

On a straight or nearly straight multi-lane road with a width of B, according to the performance of the millimeter-wave radar, within the detectable distance L of the millimeter-wave radar, divide the road boundary into n equal parts, and the distance between each equal part L ₀ = L/n; take the centerline of the lane where the main vehicle is located as the x-axis, and the projection point of the main vehicle's center of mass on the road surface as the origin to establish a road coordinate system, assuming that the vehicle's center of mass is located at the road boundary at each moment in the future, corresponding to On the connecting line of the dividing points, the position of each dividing point, obstacle, and main vehicle on the left and right boundaries of the road can be represented by vectors;

S2.2 Establishment of road boundary repulsion potential field

Identify the front road boundary line through the CCD camera and extract the road boundary line data, analyze and process the boundary line data to extract road information, and then establish the road boundary repulsion potential field;

S2.3 Establishment of obstacle repulsion potential field

The millimeter-wave radar detects the obstacle information in front of the main vehicle, and the on-board sensor obtains the speed information of the main vehicle, and then establishes the obstacle repulsion potential field;

S3. Establish a balance equation based on the force that the main vehicle receives in the composite field composed of the road boundary repulsion potential field and the obstacle repulsion potential field, and use the mathematical software matlab to solve it to obtain the main vehicle's obstacles during obstacle avoidance. The location point of , so as to obtain the obstacle avoidance path;

S4. Control the speed of the main vehicle during the obstacle avoidance process to improve safety, so that the main vehicle reduces the vehicle speed to an appropriate value during obstacle avoidance, and returns to normal speed after avoiding the obstacle.

Further, in the S1, the road information includes road width and the number of lanes; obstacle information includes the number, size, position and speed of obstacles; the host vehicle information includes the speed of the host vehicle, the distance between the host vehicle and the obstacle, the The distance between the car and the road boundary and the angle of the host car relative to the obstacle.

Further, in the establishment process of the S2.3 obstacle repulsion potential field, the main vehicle is equivalent to a mass point, and a safety circle with a diameter D is used to wrap the obstacle. At the same time, in order to enable the main vehicle to start obstacle avoidance in advance , giving the obstacle an influence range ρ ₀ , when the vehicle enters the obstacle influence range ρ ₀ , it will only be affected by the obstacle repulsion potential field distributed along the y-direction of the road coordinate system. At the same time, for the obstacle moving in front of the main vehicle , if the velocity of the obstacle has a velocity component in the velocity direction of the host vehicle, the host vehicle will also be affected by the repulsive force of the velocity potential field of the obstacle.

Further, in the above S3, with the help of matlab to solve the established balance equation, what is actually obtained is the ordinate of the point where the main vehicle will drive to at a certain time in the future, so as to obtain the points that the main vehicle will pass through during the obstacle avoidance process, and then Curve fitting is performed on these points to obtain an obstacle avoidance path that enables the main vehicle to bypass obstacles safely; at the same time, since the obstacle may be moving, the path is performed again according to the newly collected information at intervals Δt planning to ensure real-time performance.

Further, in the S4, during the obstacle avoidance process of the main vehicle, after the main vehicle enters the influence range of the obstacle, the speed of the main vehicle is controlled so that the speed of the main vehicle can decrease with the decrease of the distance between the main vehicle and the obstacle. After bypassing the obstacle, the speed of the main vehicle can increase with the increase of the distance between the main vehicle and the obstacle. When the main vehicle drives out of the influence range of the obstacle, the speed of the main vehicle will no longer be controlled by the model.

Beneficial effects: the improved artificial potential field method is used to plan a safe path for the vehicle's autonomous obstacle avoidance, and the speed of the main vehicle is controlled during the obstacle avoidance process to improve the safety and comfort of the obstacle avoidance process. For moving obstacles and stationary obstacles, this method can plan a safe and collision-free path for the vehicle to avoid obstacles before the collision occurs, which can greatly reduce traffic accidents caused by obstacle avoidance errors, and the used The calculation amount of the method is small, and it is convenient to realize real-time control.

Description of drawings

Fig. 1 is a kind of flow chart of the vehicle obstacle avoidance path planning research method based on novel artificial potential field method of the present invention;

Fig. 2 is a road coordinate system diagram described in a vehicle obstacle avoidance path planning research method based on the novel artificial potential field method of the present invention;

Fig. 3 is a schematic diagram of road boundary repulsion described in a method of vehicle obstacle avoidance path planning research method based on the novel artificial potential field method of the present invention;

Fig. 4 is a distribution diagram of the road boundary repulsion potential field described in the vehicle obstacle avoidance path planning research method based on the novel artificial potential field method of the present invention;

Fig. 5 is a schematic diagram of the speed direction described in a vehicle obstacle avoidance path planning research method based on the novel artificial potential field method of the present invention;

Fig. 6 is a diagram of the resultant force suffered by the main vehicle described in the research method for vehicle obstacle avoidance path planning based on the novel artificial potential field method of the present invention;

Fig. 7 is the obstacle avoidance path diagram described in a kind of vehicle obstacle avoidance path planning research method based on the novel artificial potential field method of the present invention;

Fig. 8 is the non-introduced speed obstacle avoidance path diagram described in the vehicle obstacle avoidance path planning research method based on the novel artificial potential field method of the present invention;

Fig. 9 is a path following diagram described in a research method for vehicle obstacle avoidance path planning based on the novel artificial potential field method of the present invention;

Fig. 10 is a yaw rate diagram described in a research method for vehicle obstacle avoidance path planning based on the novel artificial potential field method of the present invention;

FIG. 11 is a diagram of lateral acceleration described in a research method for vehicle obstacle avoidance path planning based on a novel artificial potential field method according to the present invention.

Detailed ways

The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments, but the protection scope of the present invention is not limited thereto.

As shown in Figure 1, a flow chart of a research method for vehicle obstacle avoidance path planning based on the improved artificial potential field method and speed control, including steps:

S1. Use CCD camera, millimeter-wave radar, and vehicle-mounted equipment (vehicle sensor, global positioning system GPS) to collect in real time the road information, obstacle information, and main vehicle information required for vehicle obstacle avoidance path planning; the CCD camera is installed in front of the main vehicle On the windshield, it is necessary to ensure that the camera can "look straight ahead"; the millimeter-wave radar is installed on the front of the car and on the longitudinal axis of the vehicle, and the distance from the ground is at least 35cm and the maximum is 65cm; the vehicle speed sensor is installed in the transmission case. The main vehicle has built-in GPS.

The road information includes the road width and the number of lanes; the obstacle information includes the number, size, position and speed of obstacles; the main vehicle information includes the speed of the main vehicle, the distance between the main vehicle and obstacles, and the distance between the main vehicle and the road boundary And the angle of the main vehicle relative to the obstacle.

S2. After obtaining the information required for vehicle obstacle avoidance path planning, establish a road coordinate system within the detection range of the millimeter-wave radar, and use vectors to represent the position of road boundary points, obstacles, and the main vehicle. The car information establishes the road boundary repulsion potential field and obstacle repulsion potential field model based on the artificial potential field method; the details are as follows:

S2.1 Establishment of road coordinate system

On a straight or nearly straight multi-lane road with a width of B, according to the performance of the millimeter-wave radar, within the detectable distance L of the millimeter-wave radar, divide the road boundary into n equal parts, and the distance between each equal part L ₀ =L/n, as shown in Figure 2; take the center line of the lane where the main vehicle is located as the x-axis, and the projection point of the main vehicle’s center of mass on the road surface as the origin to establish a road coordinate system, assuming that the vehicle’s The center of mass is located on the connection line corresponding to the bisection points of the road boundary, then the position of each bisection point, obstacle, and main vehicle on the left and right boundaries of the road can be represented by a vector.

S2.2 Establishment of road boundary repulsion potential field

Identify the front road boundary line through the CCD camera and extract the road boundary line data, analyze and process the boundary line data to extract road information, and then establish the road boundary repulsion potential field; Generate a repulsive force, as shown in Figure 3, to limit the driving area of the vehicle.

According to the experience of using the artificial potential field model in the field of robots, the mathematical model of the repulsion potential field at the road boundary is established as shown in the following formula:

In the formula, U _road,L , U _road,R are the repulsive force potential fields on the left and right boundaries of the road, respectively, k _roadL , k _roadR are the proportional constants of the repulsive force applied by the dangerous repulsive force field on the left and right boundaries of the road, respectively, are the coordinate vectors of the center of mass of the car and the corresponding points on the left and right boundaries of the road, and Wcar is the width of the _car .

From the mathematical models (1), (2) and Figure 4, it can be seen that the smaller the distance between the vehicle and the road boundary, the greater its potential energy value, and the greater the repulsion force on the vehicle. When the distance between the vehicle and the road boundary tends to zero When , the road boundary repulsion will tend to infinity, so as to limit the driving area of the vehicle. The repulsion can be obtained by gradient calculation of the potential field model.

In order to enable the vehicle to drive along the lane when there are no obstacles in the road or without taking obstacle avoidance measures, that is, to realize the lane keeping function, we adjust the proportional constants k _road,L and k _road,R of the potential field to make the vehicle in Under the action of the repulsive potential field at the road boundary, its force balance point is always kept in the middle of the lane. However, considering the traffic rules and the driver's driving habits, we will try our best to make the main vehicle be able to drive along the right side without avoiding obstacles. The centerline of the lane travels, and the present invention takes the driving lane of the main vehicle as a two-lane lane, as can be known from the potential field mathematical model:

U _{road, L} = U _{road, R} (3)

When there is no obstacle, the distance between the main vehicle and the right boundary of the lane is The distance between the main vehicle and the left boundary of the lane is

which is

Thus the following relationship is obtained:

S2.3 Establishment of obstacle repulsion potential field

The millimeter-wave radar detects the obstacle information in front of the main vehicle, and the on-board sensor obtains the speed information of the main vehicle, and then establishes the obstacle repulsion potential field.

The obstacle repulsion potential field produces a repulsion effect on the moving vehicle, keeping the vehicle away from the obstacle. During the driving process of the car, the road traffic conditions ahead may change at any time, there may be no obstacles, obstacles may appear suddenly, obstacles may be stationary or moving; therefore, the vehicle radar must constantly Detect the road conditions ahead, including the number, size, position and speed of obstacles. The factors affecting the size of the obstacle repulsion mainly include: the position and speed of the obstacle relative to the vehicle, and the size of the obstacle (according to the standard vehicle).

In the process of path planning, the main vehicle is equivalent to a particle, which is inconsistent with the actual situation. Therefore, a safety circle with a diameter of D is used to wrap the obstacle. The size of this safety circle must be the size of the main vehicle and the obstacle. All take into account, the tentative diameter D of the present invention is twice the vehicle width for this reason. At the same time, in order for the main vehicle to start avoiding obstacles in advance, we give the obstacle an influence range ρ ₀ , and the value of ρ ₀ is the braking safety distance of the vehicle. When the vehicle enters the obstacle influence range ρ ₀ , it will be repulsed by the obstacle The effect of the potential field, and the repulsive potential field is only distributed along the y direction. At the same time, for the obstacle moving in front of the main vehicle, the speed direction of the obstacle is defined as β, and the speed direction of the main vehicle is θ. As shown in Figure 5, the angle between the speed direction of the main vehicle and the obstacle speed direction α = θ-β; if That is, the speed of the obstacle has a component v ₀ cosα in the speed of the main vehicle, and the main vehicle will also be affected by the repulsive force of the velocity potential field of the obstacle; if That is to say, the speed of the obstacle has no velocity component in the direction of the speed of the main vehicle, so the main vehicle is not affected by the potential field of velocity repulsion. The obstacle avoidance process only considers the obstacles in front of the main vehicle, so α∈(0,π).

Case 1, when When , the repulsion potential field of the obstacle is:

Case 2, when When , the repulsion potential field of the obstacle is:

Case three, when At this time, the main vehicle is not affected by the repulsive potential field of obstacles, that is,

U _req = 0 (8)

In summary, the obstacle repulsion potential field is

where k _ob is the proportional coefficient of the obstacle repulsion potential field, is the coordinate vector of the point corresponding to the center of mass of the _car , Wcar is the width of the car, is the position vector of the obstacle, D is the diameter of the safety circle, ρ ₀ is the influence range of the obstacle, v is the current velocity of the main vehicle, v ₀ is the current velocity of the dynamic obstacle, θ is the current velocity of the moving vehicle Movement direction; φ is the current movement direction of the dynamic obstacle.

From the mathematical model (9) and the potential energy value distribution diagram in Figure 4, it can be seen that after the main vehicle enters the influence range of the obstacle, as the distance between the main vehicle and the obstacle decreases, the repulsion force received by the main vehicle increases. When the distance of the object approaches zero, the repulsive force of the obstacle will expand to an infinite area, so as to prevent the main vehicle from colliding with the obstacle. At the same time, for a moving obstacle, the greater the component of the obstacle's speed in the direction of the vehicle's speed, the greater the repulsion force received by the vehicle.

S3. Establish a balance equation based on the force that the main vehicle receives in the composite field composed of the road boundary repulsion potential field and the obstacle repulsion potential field, and use matlab to solve it to obtain the position that the main vehicle will pass through during the obstacle avoidance process point, so as to obtain the obstacle avoidance path;

In the composite field composed of the road boundary repulsion potential field and the obstacle repulsion potential field, the main vehicle is affected by the composite field force and finally reaches a balanced state, as shown in Figure 6, namely:

Solve it with the help of the mathematical software matlab, since it is assumed that the abscissa of the main vehicle at any time in the future corresponds to a certain bisection point of the road boundary, that is, the abscissa of the main vehicle is known ( _xi = (i-1)L ₀ ), Solving the balance equation, what is actually obtained is the ordinate of the point that the main vehicle will drive to at a certain time in the future, so as to obtain the points that the main vehicle will pass through during the obstacle avoidance process, and then connect these points with a smooth curve, An obstacle avoidance path that enables the main vehicle to bypass obstacles safely is obtained. At the same time, because the obstacle may be moving, the path planning is carried out again according to the newly collected information at intervals Δt to ensure real-time performance.

The main program is as follows:

Through the operation of matlab, the coordinates of the obstacle avoidance path can be obtained. According to the value of l, there are 120 sets of data in total. Due to space limitations, only 20 sets are listed here, as shown in Table 1:

Table 1 20 sets of coordinates in the obstacle avoidance process

From the data in Table 1 and Figure 7, it can be seen that the distance between the main vehicle and the obstacle in the path planned by the improved method is greater than the distance before the improvement by at least 20cm, which can effectively improve the safety of obstacle avoidance , to avoid the phenomenon of "passing by" with obstacles. It can be seen from Figure 8 that for moving obstacles, the path planned by the method before the improvement overlaps with the obstacle, which means that the main vehicle will collide with the obstacle when driving on this path, but the improved method can Good for avoiding moving obstacles.

S4. Control the speed of the main vehicle during the obstacle avoidance process to improve safety, so that the main vehicle reduces the vehicle speed to an appropriate value during obstacle avoidance, and returns to normal speed after avoiding the obstacle.

In order to ensure safety during the obstacle avoidance process, the vehicle must keep a certain distance from the obstacle, and if it is still driving at the previous speed (usually >40km/h) during the obstacle avoidance steering, the safety of obstacle avoidance will be seriously affected and riding comfort, especially when driving at high speed, this paper proposes a control method for the vehicle speed in the obstacle avoidance process, so that the vehicle can reduce the vehicle speed to a suitable value when avoiding obstacles, and return to normal after avoiding obstacles Drive at speed. The speed control model is:

In the formula, d _co represents the distance between the main vehicle and the obstacle, d ₀ is the reserved safety distance, v _c is the speed of the main vehicle before avoiding obstacles, a _max is the maximum deceleration, λ is the amplification factor, and λ=0.6 ～0.7, ρ ₀ represents the influence distance of obstacles, and t _d is the time from the start of braking to the stop of the vehicle.

From the speed control model, it can be seen that after the main vehicle enters the range affected by the obstacle, the speed can decrease with the decrease of the distance from the obstacle. Larger and larger, when the master vehicle drives out of the influence range of the obstacle, the vehicle speed will no longer be controlled by the slave model.

Import the obstacle avoidance path calculated by matlab into the vehicle dynamics simulation software carsim, and the simulation curves shown in Figure 9 and Figure 10 can be obtained; Figure 9 is the path following curve, and the circled curve in the figure is the main vehicle in the simulation software The real driving path of , the curve without circles is the target path, which is the path obtained from the solution; it can be seen from the figure that the two curves are basically consistent, indicating that in the carsim simulation software, the main vehicle is driving along the calculated obstacle avoidance path , at the same time, it can also show that the various dynamic information of the main vehicle in the simulation process is consistent with the state information of the main vehicle in the obstacle avoidance process in reality. The model parameters in the simulation process are shown in Table 2.

Table 2 Simulation model parameters

variable value unit K _L 900 -- K _R 100 -- K _oj 1500 -- lambda 2.5 -- l ₀ 1.25 m ρ ₀ 10 m L 180 m B 7 m D. 4 m

Figure 10 and Figure 11 are diagrams of the yaw rate and lateral acceleration of the main vehicle during obstacle avoidance. It can be seen that the change trends of the two figures are roughly the same, which means that the yaw rate and lateral acceleration of the main vehicle change with the obstacle avoidance process of the main vehicle. pendulum speed.

The change trend of the two graphs reflects the entire obstacle avoidance process of the main vehicle. At the beginning, the main vehicle accelerates to the preset speed in a very short time, and both the yaw rate and the lateral acceleration have large values. Increase to the preset value, the yaw rate and lateral acceleration only change in a small range, until about 6 seconds, the main car approaches the obstacle in front and starts to turn slowly, at about 8.4 seconds, the main car yaw rate and The lateral acceleration has reached the maximum value, indicating that the main vehicle has reached the front side of the obstacle and is about to bypass the obstacle. After that, the values of yaw rate and lateral acceleration become smaller, and the main vehicle gradually bypasses the obstacle and Return to original lane.

In Figure 10 and Figure 11, the dotted line is the yaw rate and lateral acceleration diagram of the main vehicle obtained after the speed is controlled during the obstacle avoidance process, and the solid line is the yaw rate and lateral acceleration of the main vehicle obtained without speed control picture. When the main vehicle does not enter the influence range of the obstacle, the two curves in the figure basically coincide. After entering the influence range of the obstacle, it can be clearly seen that after the obstacle avoidance process controls the vehicle speed, its yaw rate and The values of the lateral acceleration are all smaller than the value without controlling the vehicle speed, and the value of the lateral acceleration is less than 0.4g, which shows that controlling the vehicle speed during the obstacle avoidance process can effectively improve the comfort.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. It should be understood that the present invention is not limited to the implementation solutions described here. The purpose of these implementation solutions descriptions is to help those skilled in the art Those skilled in the art practice the present invention. Any person skilled in the art can easily carry out further improvement and perfection without departing from the spirit and scope of the present invention, so the present invention is only limited by the content and scope of the claims of the present invention, and it is intended to cover all Alternatives and equivalents within the spirit and scope of the invention as defined by the appended claims.

Claims (5)

1. A vehicle obstacle avoidance path planning research method based on novel artificial potential field method, is characterized in that, comprises the following steps: S1. Use CCD cameras, millimeter wave radars, and on-board equipment to collect road information, obstacle information, and main vehicle information required for vehicle obstacle avoidance path planning in real time; S2. After obtaining the information required for vehicle obstacle avoidance path planning, establish a road coordinate system within the detection range of the millimeter-wave radar, and use vectors to represent the position of road boundary points, obstacles, and the main vehicle. The car information establishes the road boundary repulsion potential field and obstacle repulsion potential field model based on the artificial potential field method; the details are as follows: S2.1 Establishment of road coordinate system On a straight or nearly straight multi-lane road with a width of B, according to the performance of the millimeter-wave radar, within the detectable distance L of the millimeter-wave radar, divide the road boundary into n equal parts, and the distance between each equal part L ₀ = L/n; take the centerline of the lane where the main vehicle is located as the x-axis, and the projection point of the main vehicle's center of mass on the road surface as the origin to establish a road coordinate system, assuming that the vehicle's center of mass is located at the road boundary at each moment in the future, corresponding to On the connecting line of the dividing points, the position of each dividing point, obstacle, and main vehicle on the left and right boundaries of the road can be represented by vectors; S2.2 Establishment of road boundary repulsion potential field Identify the front road boundary line through the CCD camera and extract the road boundary line data, analyze and process the boundary line data to extract road information, and then establish the road boundary repulsion potential field; S2.3 Establishment of obstacle repulsion potential field The millimeter-wave radar detects the obstacle information in front of the main vehicle, and the on-board sensor obtains the speed information of the main vehicle, and then establishes the obstacle repulsion potential field; S3. Establish a balance equation based on the force that the main vehicle receives in the composite field composed of the road boundary repulsion potential field and the obstacle repulsion potential field, and use the mathematical software matlab to solve it to obtain the main vehicle's obstacles during obstacle avoidance. The location point of , so as to obtain the obstacle avoidance path; S4. Control the speed of the main vehicle during the obstacle avoidance process to improve safety, so that the main vehicle reduces the vehicle speed to an appropriate value during obstacle avoidance, and returns to normal speed after avoiding the obstacle. 2. A kind of vehicle obstacle avoidance path planning research method based on novel artificial potential field method according to claim 1, is characterized in that, in described S1, road information comprises road width and lane quantity; Obstacle information comprises obstacle The number, size, position and speed of the main vehicle; the information of the main vehicle includes the speed of the main vehicle, the distance between the main vehicle and the obstacle, the distance between the main vehicle and the road boundary, and the angle of the main vehicle relative to the obstacle. 3. A kind of vehicle obstacle avoidance path planning research method based on the novel artificial potential field method according to claim 1, is characterized in that, in the establishment process of described S2.3 obstacle repulsion force potential field, the main vehicle equivalent is a mass point, and wraps the obstacle with a safety circle with a diameter of D. At the same time, in order to enable the main vehicle to start avoiding obstacles in advance, an influence range ρ ₀ is given to the obstacle. When the vehicle enters the obstacle influence range ρ ₀ , it will It is only affected by the obstacle repulsion potential field distributed along the y direction of the road coordinate system. At the same time, for the obstacle moving in front of the main vehicle, if the velocity of the obstacle has a velocity component in the direction of the main vehicle speed, the main vehicle will also be affected by The repulsion effect of the obstacle velocity potential field. 4. a kind of vehicle obstacle avoidance path planning research method based on novel artificial potential field method according to claim 1, is characterized in that, in described S3, by means of matlab solution to the equilibrium equation of establishment, what actually obtains is the main vehicle The ordinate of the point that will be driven at a certain time in the future, so as to obtain the points that the main vehicle will pass through during the obstacle avoidance process, and then perform curve fitting on these points, so as to obtain an obstacle avoidance system that can enable the main vehicle to safely bypass obstacles At the same time, because the obstacle may be moving, so at intervals Δt, the path planning is carried out again according to the newly collected information to ensure real-time performance. 5. A kind of vehicle obstacle avoidance path planning research method based on the novel artificial potential field method according to claim 1, it is characterized in that, described S4 is in the obstacle avoidance process of the main vehicle, after the main vehicle enters the range of influence of obstacles, Control the speed of the main vehicle so that the speed of the main vehicle can decrease with the decrease of the distance between the main vehicle and the obstacle. When the vehicle bypasses the obstacle, the speed of the main vehicle can increase with the increase of the distance between the main vehicle and the obstacle. When the main vehicle is out of the influence range of the obstacle, the speed of the main vehicle will no longer be controlled by the model.