CN114442637B - Unmanned vehicle local dynamic obstacle avoidance path planning method - Google Patents
Unmanned vehicle local dynamic obstacle avoidance path planning method Download PDFInfo
- Publication number
- CN114442637B CN114442637B CN202210126582.2A CN202210126582A CN114442637B CN 114442637 B CN114442637 B CN 114442637B CN 202210126582 A CN202210126582 A CN 202210126582A CN 114442637 B CN114442637 B CN 114442637B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- obstacle
- target point
- obs
- force
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000014509 gene expression Effects 0.000 claims description 27
- 230000004888 barrier function Effects 0.000 claims description 16
- 230000005484 gravity Effects 0.000 claims description 12
- 230000001133 acceleration Effects 0.000 claims description 8
- 238000009499 grossing Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 5
- 238000005096 rolling process Methods 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 abstract description 13
- 230000008569 process Effects 0.000 abstract description 8
- 230000010355 oscillation Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 9
- 230000009471 action Effects 0.000 description 5
- 238000013459 approach Methods 0.000 description 4
- 238000005381 potential energy Methods 0.000 description 4
- 238000012216 screening Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention provides a planning method for a local dynamic obstacle avoidance path of an unmanned vehicle, which solves the problems that the target of the traditional artificial potential field method is unreachable and the local is optimal under partial working conditions by improving the artificial potential field method, so that the unmanned vehicle overcomes local oscillation, and a planned local planning path meeting the obstacle avoidance requirement can be planned; in the method, the requirements of vehicle kinematics and dynamics performance are added in the path planning process, the collision safety priority is set, the smoothness of the planned path is ensured, and the tracking requirement of a lower-layer vehicle tracker is met; by analyzing the working conditions of complex dynamic obstacles in the road environment, the invention can respectively carry out obstacle avoidance planning for the lateral dynamic obstacles and the homodromous obstacles, and combine the two working conditions, so that the planning algorithm meets the obstacle avoidance of the working conditions of multiple dynamic obstacles, and the applicability and the effectiveness of the planning algorithm are improved.
Description
Technical Field
The invention belongs to the technical field of automatic driving of unmanned vehicles, and particularly relates to a method for planning a local dynamic obstacle avoidance path of an unmanned vehicle.
Background
The path planning is used as one of key technologies in the unmanned vehicle field, determines whether the unmanned vehicle can stably and safely run, and plays a role in bridging between the vehicle environment information sensing and the vehicle intelligent control function. The path planning algorithm adopted on the unmanned vehicle at present mainly comprises A * 、D * Algorithms such as a fast random tree and the like are initially applied to a plurality of real vehicle platforms, but are limited by the defect of high calculation amount, and can only be used for static planning at present. The artificial potential field method has the advantages of simple structure, good instantaneity, smooth generated path and the like, and is beneficial to being applied to dynamic programming aspects such as real-time obstacle avoidance and smooth track control, and the like, because the model structure is simple, the obstacle avoidance and planning task can be completed in real time without great calculated amount. However, the existing artificial potential field method has the following problems:
1. problems of unreachable targets, local optimum and the like exist in a complex environment, so that the unmanned vehicle locally oscillates or is not stopped before stopping, and the requirement of local obstacle avoidance planning is not met;
2. most potential field method path planning does not consider the kinematic and dynamic properties of the vehicle, so that the planned path does not meet the vehicle tracking requirement;
3. most potential field method planning algorithms are applicable to static scenes or simple dynamic scenes, and when complex dynamic obstacles exist in a road environment, the planning algorithm cannot effectively plan an obstacle avoidance path in real time.
Disclosure of Invention
In order to overcome the technical problems in the prior art, the invention provides a method for planning a local dynamic obstacle avoidance path of an unmanned vehicle, which specifically comprises the following steps:
step one, respectively establishing a gravity potential field and a repulsive potential field function model of a driving target point and an obstacle in the environment for the unmanned vehicle aiming at the local obstacle avoidance driving environment where the unmanned vehicle is located, wherein the gravity potential field and the repulsive potential field function model are used for reflecting the relation between the gravity of the target point to the unmanned vehicle and the position of the unmanned vehicle and the relation between the repulsive force of the obstacle to the unmanned vehicle and the position of the unmanned vehicle, and constructing a driving environment risk field potential force function model by the gravity and the repulsive force;
step two, when the constructed driving environment risk field potential force function model reaches the resultant force borne by the local minimum value vehicle to enable the vehicle to be far away from the target point, determining the corresponding specific stressed working condition of the vehicle which leads the unmanned vehicle to be unable to run to the target point;
step three, respectively providing corresponding path planning solutions aiming at different specific stress working conditions of the vehicle: (1) temporarily changing the attractive force using the set virtual target point; (2) removing the repulsive force of the obstacle which is positioned in the driving direction and far away from the target point; (3) improving the gravitation potential field function model according to the number of the barriers; (4) decomposing the repulsive force and canceling the repulsive force component in a certain direction to ensure that the resultant force of the residual repulsive force component and the attractive force is in a direction approaching to the target point;
step four, setting a dynamic path planning period, a safe distance threshold value and collision risk constraint conditions based on the solution provided in the step three in combination with the movement speed and the direction of the obstacle so as to carry out obstacle avoidance path planning and obtain the position and speed control quantity of the vehicle in real time in a rolling way;
and fifthly, performing smoothing treatment on the vehicle positions in the planned obstacle avoidance path by utilizing the Bezier curve, so as to obtain a complete unmanned vehicle local obstacle avoidance planning path.
Further, in the first step, the driving environment risk potential force function model is built, and the method specifically comprises the following steps:
the attraction potential field function model of the target point to the unmanned vehicle is adopted as follows:
wherein eta is the direct proportionality coefficient of the gravitational potential field, d (x, x goal ) For the current position coordinate x and the target point position coordinate x of the vehicle goal A distance vector therebetween in a direction from the vehicle to the target point;
deriving the gravitational potential field function to obtain gravitational function F att ，F att The direction of (2) is the direction in which the gravitational potential energy drops most rapidly, namely the negative gradient of the gravitational potential field, and the expression is:
wherein,representing the gradient function. The above equation shows that the magnitude of the attractive force value is proportional to the distance between the vehicle and the target point, and the farther the vehicle is from the target point, the larger the attractive force is, and the smaller the attractive force is. The gravitational force F can be regulated by the gravitational force potential field positive proportion coefficient eta att Is a value of (2).
The repulsive potential field function model of the barrier to the unmanned vehicle adopts the following specific forms:
wherein k is the direct proportionality coefficient of repulsive force potential field, d 0 Maximum range of influence of repulsive force to vehicle for obstacle, only when vehicle moves to d 0 When the range is in the range, the repulsive force field generated by the obstacle acts, and the acting force of the repulsive force potential field on the vehicle is larger along with the approach of the distance between the repulsive force field and the vehicle; when the distance between the two is greater than d 0 At the time of repulsive force field U rep ＝0；x obs Is the position coordinate of the obstacle, d (x, x obs ) Is the distance between the vehicle and the obstacle;
the repulsive force potential field function is derived to obtain a repulsive force function F rep ，F rep The direction of the potential energy of the repulsive force is the direction of the fastest decrease, namely the negative gradient of the potential field of the attractive force, and the expression is as follows:
the driving environment risk field function is formed by superposing a target point gravitation potential field function model and an obstacle repulsive potential field function model, and the expression is as follows:
wherein n is the number of obstacles influencing the repulsive force of the vehicle;
and deriving the driving environment risk field function to obtain the driving risk field potential force function model, wherein the expression is as follows:
further, the specific stress working conditions of the vehicle, which result in the unmanned vehicle not being able to travel to the target point, in the second step include:
working condition one: the obstacle is positioned between the vehicle and the target point, the attractive force of the target point to the vehicle is equal to the repulsive force of the obstacle to the vehicle in opposite directions, so that the stress of the vehicle is balanced, and the vehicle cannot continuously move to the target point;
working condition II: the obstacle is positioned in the driving direction but far from the target point, the attraction force of the target point to the vehicle is equal to the repulsive force of the obstacle to the vehicle, and the directions are opposite, so that the stress of the vehicle is balanced, and the vehicle cannot continuously move to the target point;
and (3) working condition III: more than two barriers exist on two sides of the direction of the vehicle towards the target point, and the resultant force of the repulsive force of the barriers and the attractive force of the target point enables the vehicle to be stressed in balance and can not move towards the target point continuously;
and (4) working condition four: more than two barriers exist on two sides of the direction of the vehicle towards the target point, and the resultant force of the repulsive force of the barriers and the attractive force of the target point enables the vehicle to be far away from the target point.
Further, the path planning solution provided in the third step specifically performs the following operations for the various working conditions:
aiming at the first working condition, a solution (1) is provided, and a virtual target point positioned near the target point is provided, so that the vehicle temporarily escapes from a local minimum trap under the attraction of the virtual target point, and the virtual target point is withdrawn at a proper time;
aiming at the second working condition, a solution (2) is provided, and when an obstacle is positioned in the running direction but far from a target point, the repulsive force of the obstacle is directly withdrawn, so that the running risk field potential force function escapes from a local minimum trap;
for the third working condition, firstly judging whether the influence-free distance between the obstacles meets the lateral safety passing distance S of the vehicle according to the influence range of the obstacles safe Providing a solution (3) if the vehicle is satisfied, improving the gravitational potential field function according to the number n of obstacles by the following way to increase the gravitational magnitude:
if the lateral safety passing distance S is not satisfied safe Providing a solution (1) to make the travelling risk field potential force function temporarily escape from a local minimum trap;
and (4) aiming at the fourth working condition, decomposing the repulsive force and canceling the repulsive force component in a certain direction, so that the resultant force of the residual repulsive force component and the attractive force is changed into a direction approaching to the target point.
Further, in the fourth step, the following process is specifically executed to perform obstacle avoidance path planning:
in order to improve the efficiency and accuracy of a planning algorithm, first screening obstacles in a local obstacle avoidance environment of a driving car. Firstly, establishing a virtual straight line from a self vehicle to a target point, wherein the expression is as follows:
L ST :y＝k ST x+b ST ，x∈(x eg o,x target )
wherein,is a straight line L ST Slope of>Is a straight line L ST The intercept of (x) ego ,y ego )、(x target ,y target ) The position coordinates of the vehicle and the target point are respectively;
let the distance from the obstacle to the vehicle be d obs-ego Obstacle to straight line L ST Distance d of (2) obs-ST When d obs-ego Or d obs-ST When any one of the obstacles is smaller than the respective safety threshold, the corresponding obstacle is judged to influence the subsequent path planning of the vehicle, so that the obstacles which possibly influence the path planning are screened out for subsequent planning calculation. The obstacle pre-screening method ignores the influence of the obstacle with a longer distance on the expected track, can effectively shorten the time of a path planning algorithm, and greatly improves the path planning efficiency. d, d obs-ego Or d obs-ST The expression of (2) is as follows:
wherein d obs-ego And d obs-ST The corresponding safety threshold values are d respectively obs-ego * And d obs-ST * ；
Aiming at the lateral dynamic obstacle, a ray pointing to the movement direction of the obstacle by taking the current position coordinate of the obstacle as a starting point is established according to the movement direction of the obstacle and is marked as L obs ，L obs The moment changes along with the change of the coordinates and the movement direction of the obstacle, so that the movement track of the obstacle can be roughly predicted in a short time domain, and whether the obstacle is likely to collide with a self-vehicle or not can be judged according to the movement intention of the obstacle. Ray L obs The expression of (2) is as follows:
wherein θ obs Is the included angle between the moving direction of the obstacle and the horizontal axis, is a dynamic variable, and the position coordinate (x obs ,y obs ) Updated time by time with the movement of the obstacle;
setting ray L obs And the straight line L ST Is P (x) P ,y P ) The virtual intersection point P (x) can be obtained by combining two straight lines P ,y P ) Position coordinates of (c); the abscissa and ordinate expressions are as follows:
based on the virtual collision point P, respectively calculating the time required for the vehicle and the obstacle to reach the virtual collision point P from the current position; let the current speed of the vehicle be v ego Acceleration a ego The current speed of the obstacle is v obs Acceleration a obs The time consumption of the two driving points to the point P respectively in the current motion state is t respectively ego-P 、t obs-P The expression is as follows:
wherein S is ego-P For the distance from the current position of the own vehicle to the virtual intersection point P, S obs-P Distance from the current position of the obstacle vehicle to the virtual intersection point P;
by comparing t obs-P And t ego-P The size of the obstacle is combined with the distance between the vehicle and the obstacle, the risk of collision between the vehicle and the lateral obstacle is judged, and the running state of the vehicle is maintained or adjusted;
aiming at the same-direction dynamic obstacle, judging the risk of collision between the vehicle and the lateral obstacle according to the current speed of the unmanned vehicle, the speed of the obstacle and the distance between the unmanned vehicle and the obstacle, and maintaining or adjusting the running state of the vehicle.
Further, in the fifth step, a bezier curve of the following form is adopted to smooth the vehicle position in the planned obstacle avoidance path:
wherein P(s) is a control point, s is a variable, P (i) represents a position point coordinate, B i,n (s) is an n-degree Bernstan polynomial, which can be expressed as:
wherein n represents the order of the Bezier curve, the number of the position points is n+1, and the number of the control points is n-1.
And (3) preferably selecting a third-order Bezier curve to carry out the smoothing process, so as to obtain a complete unmanned vehicle local obstacle avoidance planning path.
Compared with the prior art, the unmanned vehicle local dynamic obstacle avoidance path planning method provided by the invention has at least the following beneficial effects:
(1) According to the invention, through improving the artificial potential field method, the problems that the target of the traditional artificial potential field method is unreachable and the local is optimal under partial working conditions are solved, so that the unmanned vehicle overcomes local oscillation, and a planned local planning path meeting the obstacle avoidance requirement can be planned;
(2) In the path planning process, the requirements of vehicle kinematics and dynamics performance are added, the collision safety priority is set, the smoothness of the planned path is ensured, and the tracking requirement of a lower-layer vehicle tracker is met;
(3) According to the invention, through analyzing the working conditions of complex dynamic obstacles in the road environment, obstacle avoidance planning is respectively carried out aiming at the lateral dynamic obstacles and the homodromous obstacles, and the two working conditions are combined, so that the planning algorithm meets the obstacle avoidance of the working conditions of multiple dynamic obstacles, and the applicability and the effectiveness of the planning algorithm are improved.
Drawings
FIG. 1 is a block flow diagram of a method provided by the present invention;
FIG. 2 is a schematic diagram and a solution diagram for a local minimum operating mode according to the present invention;
FIG. 3 is a diagram of a second schematic view and a solution for a local minimum condition according to the present invention;
FIG. 4 is a diagram of the present invention for a local minimum operating mode;
FIG. 5 is a schematic diagram and solution diagram of the present invention for target unreachable conditions;
FIG. 6 is a schematic diagram of a lateral dynamic obstacle avoidance plan in accordance with aspects of the present invention;
fig. 7 is a schematic diagram of a co-directional dynamic obstacle avoidance plan in the scheme of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made apparent and fully in view of the accompanying drawings, in which some, but not all embodiments of the invention are shown. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The invention provides a method for planning a local dynamic obstacle avoidance path of an unmanned vehicle, which is shown in fig. 1, and specifically comprises the following steps:
step one, respectively establishing a gravity potential field and a repulsive potential field function model of a driving target point and an obstacle in the environment for the unmanned vehicle aiming at the local obstacle avoidance driving environment where the unmanned vehicle is located, wherein the gravity potential field and the repulsive potential field function model are used for reflecting the relation between the gravity of the target point to the unmanned vehicle and the position of the unmanned vehicle and the relation between the repulsive force of the obstacle to the unmanned vehicle and the position of the unmanned vehicle, and constructing a driving environment risk field potential force function model by the gravity and the repulsive force;
step two, when the constructed driving environment risk field potential force function model reaches the resultant force borne by the local minimum value vehicle to enable the vehicle to be far away from the target point, determining the corresponding specific stressed working condition of the vehicle which leads the unmanned vehicle to be unable to run to the target point;
step three, respectively providing corresponding path planning solutions aiming at different specific stress working conditions of the vehicle: (1) temporarily changing the attractive force using the set virtual target point; (2) removing the repulsive force of the obstacle which is positioned in the driving direction and far away from the target point; (3) improving the gravitation potential field function model according to the number of the barriers; (4) decomposing the repulsive force and canceling the repulsive force component in a certain direction to ensure that the resultant force of the residual repulsive force component and the attractive force is in a direction approaching to the target point;
step four, setting a dynamic path planning period, a safe distance threshold value and collision risk constraint conditions based on the solution provided in the step three in combination with the movement speed and the direction of the obstacle so as to carry out obstacle avoidance path planning and obtain the position and speed control quantity of the vehicle in real time in a rolling way;
and fifthly, performing smoothing treatment on the vehicle positions in the planned obstacle avoidance path by utilizing the Bezier curve, so as to obtain a complete unmanned vehicle local obstacle avoidance planning path.
In a preferred embodiment of the present invention, the step one of establishing the driving environment risk potential function model specifically includes the following steps:
the attraction potential field function model of the target point to the unmanned vehicle is adopted as follows:
wherein eta is the direct proportionality coefficient of the gravitational potential field, d (x, x goal ) For the current position coordinate x and the target point position coordinate x of the vehicle goal A distance vector therebetween in a direction from the vehicle to the target point;
deriving the gravitational potential field function to obtain gravitational function F att ，F att The direction of (2) is the direction in which the gravitational potential energy drops most rapidly, namely the negative gradient of gravitational potential field, the expression is thatThe method comprises the following steps:
wherein,representing the gradient function. The above equation shows that the magnitude of the attractive force value is proportional to the distance between the vehicle and the target point, and the farther the vehicle is from the target point, the larger the attractive force is, and the smaller the attractive force is. The gravitational force F can be regulated by the gravitational force potential field positive proportion coefficient eta att Is a value of (2).
The repulsive potential field function model of the barrier to the unmanned vehicle adopts the following specific forms:
wherein k is the direct proportionality coefficient of repulsive force potential field, d 0 Maximum range of influence of repulsive force to vehicle for obstacle, only when vehicle moves to d 0 When the range is in the range, the repulsive force field generated by the obstacle acts, and the acting force of the repulsive force potential field on the vehicle is larger along with the approach of the distance between the repulsive force field and the vehicle; when the distance between the two is greater than d 0 At the time of repulsive force field U rep ＝0；x obs Is the position coordinate of the obstacle, d (x, x obs ) Is the distance between the vehicle and the obstacle;
the repulsive force potential field function is derived to obtain a repulsive force function F rep ，F rep The direction of the potential energy of the repulsive force is the direction of the fastest decrease, namely the negative gradient of the potential field of the attractive force, and the expression is as follows:
the driving environment risk field function is formed by superposing a target point gravitation potential field function model and an obstacle repulsive potential field function model, and the expression is as follows:
wherein n is the number of obstacles influencing the repulsive force of the vehicle;
and deriving the driving environment risk field function to obtain the driving risk field potential force function model, wherein the expression is as follows:
in a preferred embodiment of the present invention, the specific stress conditions of the vehicle in the second step, which result in the unmanned vehicle not being able to travel to the target point, specifically include, as shown in fig. 2-5:
working condition one: the obstacle is located between the vehicle and the target point, as shown in fig. 2 (a), the attraction force of the target point to the vehicle is equal to the repulsive force of the obstacle to the vehicle in opposite directions, so that the vehicle is stressed in a balanced manner, and cannot move to the target point continuously;
working condition II: the obstacle is positioned in the driving direction but far from the target point, as shown in fig. 3, the attraction force of the target point to the vehicle is equal to the repulsive force of the obstacle to the vehicle in opposite directions, so that the stress of the vehicle is balanced, and the vehicle cannot move to the target point continuously;
and (3) working condition III: more than two barriers exist on two sides of the direction of the vehicle towards the target point, as shown in fig. 4 (a), the resultant force of the repulsive force of the barriers and the attractive force of the target point balances the stress of the vehicle, and the vehicle cannot move towards the target point continuously;
and (4) working condition four: more than two obstacles exist on two sides of the direction of the vehicle towards the target point, and as shown in fig. 5 (a), the resultant force of the repulsive force of the obstacle and the attractive force of the target point makes the vehicle far away from the target point.
In a preferred embodiment of the present invention, the path planning solution provided in step three specifically performs the following operations for the various operating conditions:
providing a solution (1) aiming at the first working condition, and by providing a virtual target point which is positioned near the target point, as shown in fig. 2 (b), enabling the vehicle to temporarily escape from a local minimum trap under the attraction of the virtual target point, and then withdrawing the virtual target point at a proper time;
providing a solution (2) aiming at a second working condition, and directly canceling the repulsive force of the obstacle when the obstacle is positioned in the running direction but far from the target point as shown in fig. 3, so that the running risk field potential function escapes from a local minimum trap;
for the third working condition, when the vehicle falls into a local minimum under the combined action of a plurality of obstacles and target points, as shown in fig. 4 (b), firstly, judging whether the influence-free distance between the obstacles meets the lateral safety passing distance S of the vehicle according to the influence range of the obstacles safe If the vehicle is satisfied, a solution (3) is provided, which is based on the number n of obstacles and improves the gravitational potential field function in such a way that the vehicle continues to advance in the current driving direction until the target point is reached, as shown in fig. 3. The improved potential field function is:
if the lateral safety passing distance S is not satisfied safe Providing a solution (1) to make the travelling risk field potential force function temporarily escape from a local minimum trap;
providing a solution (4) aiming at the fourth working condition, dividing the repulsive force into two vectors of a gravitational direction and a vertical gravitational direction, and judging the magnitudes of two repulsive force component forces as shown in fig. 5 (b):
if the absolute value of the repulsive force component along the attractive force direction is smaller than the attractive force, the vertical repulsive force is zero, namely:
F repy ＝0
F closing device ＝F att +F repx
If the absolute value of the repulsive force component along the attractive force direction is larger than the attractive force, the repulsive force component along the attractive force direction is zero, namely:
F repx ＝0
F closing device ＝F att +F repy
Therefore, the improved potential field method can eliminate the influence of the obstacle on the vehicles nearby the target point, so that the vehicles can smoothly reach the target point.
In a preferred embodiment of the present invention, the following procedure is specifically executed in the fourth step to perform obstacle avoidance path planning:
in order to improve the efficiency and accuracy of a planning algorithm, first screening obstacles in a local obstacle avoidance environment of a driving car. Firstly, establishing a virtual straight line from a self vehicle to a target point, wherein the expression is as follows:
L ST :y＝k ST x+b ST ，x∈(x ego ,x target )
wherein,is a straight line L ST Slope of>Is a straight line L ST The intercept of (x) ego ,y ego )、(x target ,y target ) The position coordinates of the vehicle and the target point are respectively;
let the distance from the obstacle to the vehicle be d obs-ego Obstacle to straight line L ST Distance d of (2) obs-ST When d obs-ego Or d obs-ST When any one of the obstacles is smaller than the respective safety threshold, the corresponding obstacle is judged to influence the subsequent path planning of the vehicle, so that the obstacles which possibly influence the path planning are screened out for subsequent planning calculation. The obstacle pre-screening method ignores the influence of the obstacle with a longer distance on the expected track, can effectively shorten the time of a path planning algorithm, and greatly improves the path planning efficiency. d, d obs-ego Or d obs-ST The expression of (2) is as follows:
wherein d obs-ego And d obs-ST The corresponding safety threshold values are d respectively obs-ego * And d obs-ST * ；
For the lateral dynamic obstacle, as shown in fig. 6, a ray pointing to the moving direction of the obstacle is established by taking the current position coordinate of the obstacle as a starting point according to the moving direction of the obstacle and is marked as L obs ，L obs The moment changes along with the change of the coordinates and the movement direction of the obstacle, so that the movement track of the obstacle can be roughly predicted in a short time domain, and whether the obstacle is likely to collide with a self-vehicle or not can be judged according to the movement intention of the obstacle. Ray L obs The expression of (2) is as follows:
wherein θ obs Is the included angle between the moving direction of the obstacle and the horizontal axis, is a dynamic variable, and the position coordinate (x obs ,y obs ) Updated time by time with the movement of the obstacle;
setting ray L obs And the straight line L ST Is P (x) P ,y P ) The virtual intersection point P (x) can be obtained by combining two straight lines P ,y P ) Position coordinates of (c); the abscissa and ordinate expressions are as follows:
based on the virtual collision point P, respectively calculating the time required for the vehicle and the obstacle to reach the virtual collision point P from the current position; let the current speed of the vehicle be v ego Acceleration a ego The current speed of the obstacle isv obs Acceleration a obs The time consumption of the two driving points to the point P respectively in the current motion state is t respectively ego-P 、t obs-P The expression is as follows:
wherein S is ego-P For the distance from the current position of the own vehicle to the virtual intersection point P, S obs-P Distance from the current position of the obstacle vehicle to the virtual intersection point P;
comparing the time of the self-vehicle and the obstacle vehicle to the point P, if t obs-P <t ego-P It is described that the obstacle vehicle reaches the virtual intersection faster, and in this case, it is necessary to determine in advance whether or not the position of the obstacle vehicle affects the own vehicle. When the obstacle vehicle is located in a certain fixed range of the intersection point P, if the distance from the obstacle to the self-vehicle is larger than the safety distance, the obstacle has no influence on the movement of the self-vehicle, and the self-vehicle keeps running in an original state under the action of the attraction of the target point. If the distance from the obstacle to the own vehicle is smaller than the safety distance, the collision risk increases, and then the own vehicle needs to be decelerated or braked in advance so as to avoid collision. When the obstacle vehicle leaves the point P, the collision risk is reduced, the self-vehicle returns to the original speed, and the obstacle vehicle runs to the target point under the action of the attraction potential field.
If t obs-P ＝t ego-P Description of self-vehicle and obstacle vehicleThe vehicles arrive at the virtual intersection at the same time, and the motion condition of the obstacle is uncontrollable, so that the method needs to judge what measures to avoid the collision according to the motion and dynamics constraint of the self-vehicle. Measures for avoiding collisions mainly include braking, deceleration, acceleration and steering. And setting collision decision priority on the premise of ensuring driving safety, wherein the priority of the deceleration and braking working conditions is higher than that of the acceleration and steering working conditions. According to the arrangement of the decision priority, when collision risk exists, on the premise of ensuring the safety distance, the self-vehicle firstly takes a deceleration measure, and if the collision risk still fails to be reduced after deceleration, takes a braking measure to avoid the obstacle vehicle. After the obstacle vehicle gradually gets far away from the self-vehicle and the collision risk is reduced, the self-vehicle starts to accelerate slowly until the given vehicle speed is recovered.
If t obs-P >t ego-P When the self-vehicle approaches the virtual intersection point P, if the distance from the obstacle to the self-vehicle is smaller than the safety distance, the collision risk is increased, and the self-vehicle deviates from the initial track under the action of the repulsive force of the obstacle, namely, deviates from the linear track to avoid the dynamic obstacle; secondly, after the collision risk is perceived to be increased by the self-vehicle, the vehicle speed can be increased while avoiding, so that the influence range of the obstacle is quickly separated, and the safety of path planning is further ensured. When the self-vehicle approaches the virtual intersection point P, if the distance from the obstacle to the self-vehicle is greater than the safety distance, no collision risk exists, and the self-vehicle keeps running in an original state under the action of the potential field until reaching the target point.
For the same-direction dynamic obstacle, as shown in fig. 7, the unmanned vehicle needs to judge the running state of the front vehicle in time and make a decision: following, braking or steering.
Following vehicle working conditions: and the unmanned vehicle and the front vehicle have moderate running speed, and the distance between the unmanned vehicle and the front vehicle meets the requirement of a safe distance, so that the unmanned vehicle keeps the current speed for following the vehicle.
Braking condition: the speed of the unmanned aerial vehicle is greater than that of the front vehicle, the distance between vehicles is smaller than the safety distance, meanwhile, the side of the unmanned aerial vehicle is provided with an obstacle and the steering requirement is not met, and then the unmanned aerial vehicle performs braking operation.
Steering conditions: the speed of the unmanned vehicle is greater than that of the front vehicle, the vehicle distance meets the lane changing distance, and meanwhile, the lane changing condition is met by the side road environment of the unmanned vehicle, so that the unmanned vehicle performs lane changing operation.
And the corresponding planning control algorithm is selected in real time by analyzing the motion state of the dynamic obstacle, so that real-time obstacle avoidance planning is realized.
In a preferred embodiment of the present invention, in the fifth step, the vehicle position in the planned obstacle avoidance path is smoothed using a bezier curve of the following form:
wherein P(s) is a control point, s is a variable, P (i) represents a position point coordinate, B i,n (s) is an n-degree Bernstan polynomial, which can be expressed as:
wherein n represents the order of the Bezier curve, the number of the position points is n+1, and the number of the control points is n-1.
In this embodiment, a third-order bezier curve is preferably selected to perform the smoothing process, so as to obtain a complete unmanned vehicle local obstacle avoidance planning path.
It should be understood that, the sequence number of each step in the embodiment of the present invention does not mean that the execution sequence of each process should be determined by the function and the internal logic of each process, and should not limit the implementation process of the embodiment of the present invention.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (5)
1. A method for planning a local dynamic obstacle avoidance path of an unmanned vehicle is characterized by comprising the following steps of: the method specifically comprises the following steps:
step one, respectively establishing a gravity potential field and a repulsive potential field function model of a driving target point and an obstacle in the environment for the unmanned vehicle aiming at the local obstacle avoidance driving environment where the unmanned vehicle is located, wherein the gravity potential field and the repulsive potential field function model are used for reflecting the relation between the gravity of the target point to the unmanned vehicle and the position of the unmanned vehicle and the relation between the repulsive force of the obstacle to the unmanned vehicle and the position of the unmanned vehicle, and constructing a driving environment risk field potential force function model by the gravity and the repulsive force;
step two, when the constructed running environment risk field potential function model reaches a local minimum value and the resultant force borne by the vehicle makes the vehicle far away from the target point, determining a corresponding specific stressed working condition of the vehicle which leads the unmanned vehicle to be unable to run to the target point;
step three, respectively providing corresponding path planning solutions aiming at different specific stress working conditions of the vehicle: (1) temporarily changing the attractive force using the set virtual target point; (2) removing the repulsive force of the obstacle which is positioned in the driving direction and far away from the target point; (3) improving the gravitation potential field function model according to the number of the barriers; (4) decomposing the repulsive force and canceling the repulsive force component in a certain direction to ensure that the resultant force of the residual repulsive force component and the attractive force is in a direction approaching to the target point;
step four, setting a dynamic path planning period, a safe distance threshold value and collision risk constraint conditions based on the solution provided in the step three in combination with the movement speed and the direction of the obstacle so as to carry out obstacle avoidance path planning and obtain the vehicle position and speed control quantity in a real-time rolling manner, wherein the method comprises the following steps:
firstly, establishing a virtual straight line from a self vehicle to a target point, wherein the expression is as follows:
L ST :y＝k ST x+b ST ，x∈(x ego ,x target )
wherein,is a straight line L ST Slope of>Is a straight line L ST The intercept of (x) ego ,y ego )、(x target ,y target ) The position coordinates of the vehicle and the target point are respectively;
let the distance from the obstacle to the vehicle be d obs-ego Obstacle to straight line L ST Distance d of (2) obs-ST ，d obs-ego Or d obs-ST The expression of (2) is as follows:
wherein d obs-ego And d obs-ST The corresponding safety threshold values are d respectively obs-ego * And d obs-ST * ，x obs Position coordinates of the obstacle;
aiming at the lateral dynamic obstacle, a ray pointing to the movement direction of the obstacle by taking the current position coordinate of the obstacle as a starting point is established according to the movement direction of the obstacle and is marked as L obs The expression is as follows:
wherein θ obs Is the included angle between the moving direction of the obstacle and the horizontal axis;
setting ray L obs And the straight line L ST Is P (x) P ,y P ) The virtual intersection point P (x) can be obtained by combining two straight lines P ,y P ) Position coordinates of (c); the abscissa and ordinate expressions are as follows:
based on the virtual intersection point P, respectively calculating the time required for the vehicle and the obstacle to reach the virtual intersection point P from the current position; let the current speed of the vehicle be v ego Acceleration a ego The current speed of the obstacle is v obs Acceleration a obs The time consumption of the two driving to the virtual intersection point P in the current motion state is t respectively ego-P 、t obs-P The expression is as follows:
wherein S is ego-P For the distance from the current position of the own vehicle to the virtual intersection point P, S obs-P Distance from the current position of the obstacle vehicle to the virtual intersection point P;
by comparing t obs-P And t ego-P The size of the obstacle is combined with the distance between the vehicle and the obstacle, the risk of collision between the vehicle and the lateral obstacle is judged, and the running state of the vehicle is maintained or adjusted;
aiming at the same-direction dynamic obstacle, judging the risk of collision between the vehicle and the lateral obstacle according to the current speed of the unmanned vehicle, the speed of the obstacle and the distance between the unmanned vehicle and the obstacle, and maintaining or adjusting the running state of the vehicle;
and fifthly, performing smoothing treatment on the vehicle positions in the planned obstacle avoidance path by utilizing the Bezier curve, so as to obtain a complete unmanned vehicle local obstacle avoidance planning path.
2. The method of claim 1, wherein: the driving environment risk field potential force function model established in the first step specifically comprises the following steps:
the attraction potential field function model of the target point to the unmanned vehicle is adopted as follows:
wherein eta is the direct proportionality coefficient of the gravitational potential field, d (x, x goal ) For the current position coordinate x and the target point position coordinate x of the vehicle goal A distance vector therebetween in a direction from the vehicle to the target point;
deriving the gravitation potential field function model to obtain gravitation function F att The expression is:
wherein,representing a gradient function;
the repulsive potential field function model of the barrier to the unmanned vehicle adopts the following specific forms:
wherein k is the direct proportionality coefficient of repulsive force potential field, d 0 Maximum range of influence, x, of repulsive force generated by obstacles on vehicle obs Is the position coordinate of the obstacle, d (x, x obs ) Between a vehicle and an obstacleA distance;
deriving a repulsive potential field function model to obtain a repulsive function F rep The expression is:
the driving environment risk field function model is formed by superposing an attractive force potential field function model of an unmanned vehicle by a target point and a repulsive force potential field function model of the unmanned vehicle by an obstacle, and the expression is as follows:
wherein n is the number of obstacles influencing the repulsive force of the vehicle;
and deriving the driving environment risk field function model to obtain the driving environment risk field potential force function model, wherein the expression is as follows:
3. the method of claim 1, wherein: in the second step, the specific stress working conditions of the vehicle, which lead to the unmanned vehicle not being able to travel to the target point, specifically include:
working condition one: the obstacle is positioned between the vehicle and the target point, the attractive force of the target point to the vehicle is equal to the repulsive force of the obstacle to the vehicle in opposite directions, so that the stress of the vehicle is balanced, and the vehicle cannot continuously move to the target point;
working condition II: the obstacle is positioned in the driving direction but far from the target point, the attraction force of the target point to the vehicle is equal to the repulsive force of the obstacle to the vehicle, and the directions are opposite, so that the stress of the vehicle is balanced, and the vehicle cannot continuously move to the target point;
and (3) working condition III: more than two barriers exist on two sides of the direction of the vehicle towards the target point, and the resultant force of the repulsive force of the barriers and the attractive force of the target point enables the vehicle to be stressed in balance and can not move towards the target point continuously;
and (4) working condition four: more than two barriers exist on two sides of the direction of the vehicle towards the target point, and the resultant force of the repulsive force of the barriers and the attractive force of the target point enables the vehicle to be far away from the target point.
4. A method as claimed in claim 3, wherein: the path planning solution provided in the third step specifically performs the following operations for various working conditions:
aiming at the first working condition, a solution (1) is provided, and a virtual target point positioned near the target point is provided, so that a vehicle temporarily escapes from a local minimum trap under the attraction of the virtual target point, and the virtual target point is withdrawn at a proper time;
aiming at the second working condition, a solution (2) is provided, and when an obstacle is positioned in the running direction but far from a target point, the repulsive force of the obstacle is directly withdrawn, so that a running environment risk field potential force function model escapes from a local minimum trap;
for the third working condition, firstly judging whether the influence-free distance between the obstacles meets the lateral safety passing distance S of the vehicle according to the influence range of the obstacles safe Providing a solution (3) if the vehicle is satisfied, improving the gravitational potential field function according to the number n of obstacles by the following way to increase the gravitational magnitude:
eta is the direct proportionality coefficient of the gravitation potential field, d (x, x) goal ) For the current position coordinate x and the target point position coordinate x of the vehicle goa l is a distance vector between the two points, the direction is from the vehicle to the target point, n is the number of obstacles influencing the repulsive force of the vehicle;
if the lateral safety passing distance S is not satisfied safe Providing a solution (1) to make the driving environment risk field potential force function model temporarily escape from the local poleA small value trap;
and (4) aiming at the fourth working condition, decomposing the repulsive force and canceling the repulsive force component in a certain direction, so that the resultant force of the residual repulsive force component and the attractive force is changed into a direction approaching to the target point.
5. The method of claim 1, wherein: in the fifth step, the following Bezier curve is adopted to carry out smoothing treatment on the vehicle position in the planned obstacle avoidance path:
wherein P(s) is a control point, s is a variable, P (i) represents a position point coordinate, B i,n (s) is an n-degree Bernstan polynomial, which can be expressed as:
wherein n represents the order of the Bezier curve, the number of the position points is n+1, and the number of the control points is n-1.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210126582.2A CN114442637B (en) | 2022-02-10 | 2022-02-10 | Unmanned vehicle local dynamic obstacle avoidance path planning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210126582.2A CN114442637B (en) | 2022-02-10 | 2022-02-10 | Unmanned vehicle local dynamic obstacle avoidance path planning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114442637A CN114442637A (en) | 2022-05-06 |
| CN114442637B true CN114442637B (en) | 2023-11-10 |
Family
ID=81371022
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210126582.2A Active CN114442637B (en) | 2022-02-10 | 2022-02-10 | Unmanned vehicle local dynamic obstacle avoidance path planning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114442637B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115167470B (en) * | 2022-08-18 | 2023-11-28 | 深圳市欧铠智能机器人股份有限公司 | Automatic cargo delivery distribution system and method for delivery robot |
| CN115328152B (en) * | 2022-09-05 | 2023-06-30 | 北京理工大学 | Unmanned vehicle local real-time obstacle avoidance path planning method based on improved artificial potential field method |
| CN115469665B (en) * | 2022-09-16 | 2023-07-04 | 广东工业大学 | Intelligent wheelchair target tracking control method and system suitable for dynamic environment |
| CN115480591B (en) * | 2022-10-20 | 2023-09-12 | 广东电网有限责任公司云浮供电局 | Safety obstacle avoidance method for unmanned aerial vehicle in power distribution network equipment environment inspection |
| CN116339347B (en) * | 2023-04-24 | 2023-10-31 | 广东工业大学 | Unmanned vehicle running path planning method, device and equipment |
| CN116202550B (en) * | 2023-05-06 | 2023-07-11 | 华东交通大学 | Automobile path planning method integrating improved potential field and dynamic window |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010076488A (en) * | 2008-09-24 | 2010-04-08 | Equos Research Co Ltd | Vehicle |
| KR20150086065A (en) * | 2014-01-17 | 2015-07-27 | 전남대학교산학협력단 | System and method for path planning for autonomous navigation of driverless ground vehicle |
| CN106843235A (en) * | 2017-03-31 | 2017-06-13 | 深圳市靖洲科技有限公司 | It is a kind of towards the Artificial Potential Field path planning without person bicycle |
| CN110567478A (en) * | 2019-09-30 | 2019-12-13 | 广西科技大学 | unmanned vehicle path planning method based on artificial potential field method |
| CN110908373A (en) * | 2019-11-11 | 2020-03-24 | 南京航空航天大学 | Intelligent vehicle track planning method based on improved artificial potential field |
| CN111665846A (en) * | 2020-06-24 | 2020-09-15 | 哈尔滨工程大学 | Water surface unmanned ship path planning method based on rapid scanning method |
| CN112099493A (en) * | 2020-08-31 | 2020-12-18 | 西安交通大学 | Autonomous mobile robot trajectory planning method, system and equipment |
| CN112577491A (en) * | 2020-12-14 | 2021-03-30 | 上海应用技术大学 | Robot path planning method based on improved artificial potential field method |
| CN113190004A (en) * | 2021-05-07 | 2021-07-30 | 河南科技大学 | Unmanned vehicle collision avoidance path planning method based on algorithm fusion |
| CN113467472A (en) * | 2021-07-27 | 2021-10-01 | 山东科技大学 | Robot path planning method in complex environment |
| CN113515125A (en) * | 2021-07-05 | 2021-10-19 | 中国石油大学(华东) | Unmanned vehicle full-working-condition obstacle avoidance control method and performance evaluation method |
| CN113720346A (en) * | 2021-09-02 | 2021-11-30 | 重庆邮电大学 | Vehicle path planning method and system based on potential energy field and hidden Markov model |
| CN113848914A (en) * | 2021-09-28 | 2021-12-28 | 福州大学 | Collision coefficient artificial potential field method local path planning method in dynamic environment |
-
2022
- 2022-02-10 CN CN202210126582.2A patent/CN114442637B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2010076488A (en) * | 2008-09-24 | 2010-04-08 | Equos Research Co Ltd | Vehicle |
| KR20150086065A (en) * | 2014-01-17 | 2015-07-27 | 전남대학교산학협력단 | System and method for path planning for autonomous navigation of driverless ground vehicle |
| CN106843235A (en) * | 2017-03-31 | 2017-06-13 | 深圳市靖洲科技有限公司 | It is a kind of towards the Artificial Potential Field path planning without person bicycle |
| CN110567478A (en) * | 2019-09-30 | 2019-12-13 | 广西科技大学 | unmanned vehicle path planning method based on artificial potential field method |
| CN110908373A (en) * | 2019-11-11 | 2020-03-24 | 南京航空航天大学 | Intelligent vehicle track planning method based on improved artificial potential field |
| CN111665846A (en) * | 2020-06-24 | 2020-09-15 | 哈尔滨工程大学 | Water surface unmanned ship path planning method based on rapid scanning method |
| CN112099493A (en) * | 2020-08-31 | 2020-12-18 | 西安交通大学 | Autonomous mobile robot trajectory planning method, system and equipment |
| CN112577491A (en) * | 2020-12-14 | 2021-03-30 | 上海应用技术大学 | Robot path planning method based on improved artificial potential field method |
| CN113190004A (en) * | 2021-05-07 | 2021-07-30 | 河南科技大学 | Unmanned vehicle collision avoidance path planning method based on algorithm fusion |
| CN113515125A (en) * | 2021-07-05 | 2021-10-19 | 中国石油大学(华东) | Unmanned vehicle full-working-condition obstacle avoidance control method and performance evaluation method |
| CN113467472A (en) * | 2021-07-27 | 2021-10-01 | 山东科技大学 | Robot path planning method in complex environment |
| CN113720346A (en) * | 2021-09-02 | 2021-11-30 | 重庆邮电大学 | Vehicle path planning method and system based on potential energy field and hidden Markov model |
| CN113848914A (en) * | 2021-09-28 | 2021-12-28 | 福州大学 | Collision coefficient artificial potential field method local path planning method in dynamic environment |
Non-Patent Citations (4)
| Title |
|---|
| An RRT based navigation approach for mobile robot sand automated vehicles;Luis Garrote 等;2014 12th IEEE International Conference on Industrial Informatics (INDIN);全文 * |
| 基于双重A* 算法的移动机器人动态环境路径规划;陈伟华 等;组合机床与自动化加工技术(第4期);全文 * |
| 基于模糊神经网络的移动机器人路径规划技术研究;熊博;中国优秀博硕士学位论文全文数据库(硕士)信息科技辑(第01期);全文 * |
| 改进人工势场法的移动机器人局部路径规划;王迪 等;山东理工大学学报（自然科学版）;第35卷(第3期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114442637A (en) | 2022-05-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114442637B (en) | Unmanned vehicle local dynamic obstacle avoidance path planning method | |
| CN111338340B (en) | Model prediction-based local path planning method for unmanned vehicle | |
| CN112631294B (en) | Intelligent path planning method for mobile robot | |
| CN110298131B (en) | Method for establishing automatic driving lane change decision model in hybrid driving environment | |
| CN109976340B (en) | Man-machine cooperation dynamic obstacle avoidance method and system based on deep reinforcement learning | |
| CN109375632B (en) | Real-time trajectory planning method for automatic driving vehicle | |
| CN112389436B (en) | Safety automatic driving track changing planning method based on improved LSTM neural network | |
| CN112810630B (en) | Method and system for planning track of automatic driving vehicle | |
| CN111413966A (en) | Progressive model prediction unmanned planning tracking cooperative control method | |
| CN111781948A (en) | Unmanned aerial vehicle formation shape transformation and online dynamic obstacle avoidance method | |
| CN110377039A (en) | A kind of vehicle obstacle-avoidance trajectory planning and tracking and controlling method | |
| Hongyu et al. | An improved artificial potential field model considering vehicle velocity for autonomous driving | |
| CN112965476B (en) | High-speed unmanned vehicle trajectory planning system and method based on multi-window model | |
| CN113050646B (en) | Dynamic environment path planning method for indoor mobile robot | |
| CN113721637B (en) | Intelligent vehicle dynamic obstacle avoidance path continuous planning method and system and storage medium | |
| CN115328152B (en) | Unmanned vehicle local real-time obstacle avoidance path planning method based on improved artificial potential field method | |
| CN113505545B (en) | Rail transit vehicle pneumatic multi-objective optimization method based on improved point adding criterion | |
| CN115683145A (en) | Automatic driving safety obstacle avoidance method based on track prediction | |
| CN113515125A (en) | Unmanned vehicle full-working-condition obstacle avoidance control method and performance evaluation method | |
| CN116643572A (en) | Local path planning method, electronic equipment and medium for indoor complex environment | |
| Lattarulo et al. | A speed planner approach based on Bézier curves using vehicle dynamic constrains and passengers comfort | |
| Xiong et al. | Surrounding vehicle trajectory prediction and dynamic speed planning for autonomous vehicle in cut-in scenarios | |
| CN116465427A (en) | Intelligent vehicle lane changing obstacle avoidance path planning method based on space-time risk quantification | |
| CN115963855A (en) | Unpowered reentry aircraft landing area prediction method based on deep learning | |
| Liu et al. | Research on local real-time obstacle avoidance path planning of unmanned vehicle based on improved artificial potential field method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |