CN108536149B - Unmanned vehicle obstacle avoidance control method based on Dubins path - Google Patents
Unmanned vehicle obstacle avoidance control method based on Dubins path Download PDFInfo
- Publication number
- CN108536149B CN108536149B CN201810375570.7A CN201810375570A CN108536149B CN 108536149 B CN108536149 B CN 108536149B CN 201810375570 A CN201810375570 A CN 201810375570A CN 108536149 B CN108536149 B CN 108536149B
- Authority
- CN
- China
- Prior art keywords
- obstacle
- unmanned vehicle
- circle
- moment
- path
- 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 32
- 238000012544 monitoring process Methods 0.000 claims abstract description 11
- 238000012360 testing method Methods 0.000 claims abstract description 4
- 230000003068 static effect Effects 0.000 claims description 40
- 238000005259 measurement Methods 0.000 claims description 9
- 230000004888 barrier function Effects 0.000 claims description 7
- 239000013598 vector Substances 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 4
- 239000004973 liquid crystal related substance Substances 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 7
- 206010039203 Road traffic accident Diseases 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000001149 cognitive effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000000007 visual effect Effects 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 or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
- G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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 or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- 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
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention provides an unmanned vehicle obstacle avoidance control device and a control method based on a Dubin path, wherein the device comprises a camera arranged outside an A column on the left side of an unmanned vehicle, a camera arranged outside an A column on the right side of the unmanned vehicle and a laser radar arranged on the roof of the unmanned vehicle; the method comprises the following steps: the radar locates and tests the speed of the obstacle entering the monitoring range of the camera; determining an obstacle sequence to be collided with the intelligent vehicle based on an obstacle avoidance algorithm; the intelligent vehicle re-plans the current obstacle avoidance path according to the new obstacle sequence so as to complete the obstacle avoidance operation; according to the invention, the cameras are arranged in the middle of the two A columns of the unmanned vehicle, so that the problem of blind areas of the field of view of the unmanned vehicle is effectively solved, and meanwhile, the perfection and accuracy of the acquired information are improved; different obstacle avoidance judging algorithms are adopted for different obstacles in the unmanned vehicle, so that the accuracy and precision of obstacle avoidance of the unmanned vehicle are improved.
Description
Technical Field
The invention belongs to the field of automobiles, and relates to an unmanned vehicle obstacle avoidance control device and method based on a Dubin path.
Background
With the continuous development and perfection of automobile technology, unmanned technology should take place, and unmanned relies on artificial intelligence, visual computing, radar, monitoring device and global positioning system to cooperate, so that the computer can operate the motor vehicle automatically and safely without any human initiative. The main principle is that a vehicle-mounted sensing system senses the road environment, automatically plans a driving route and controls the vehicle to reach a preset target; and meanwhile, the vehicle-mounted sensor senses the surrounding environment, and controls the steering and the speed of the vehicle according to the road, the vehicle position and the obstacle information obtained by sensing, so that the vehicle can safely and reliably run on the road.
However, the existing unmanned technology mainly has the following two problems: 1. the sensor has recognition obstacle, the radar and the camera have great influence on the surrounding environment due to weather and environment, the sensor technology is imperfect and a monitoring dead angle often exists, and the information of the nearby obstacle can not be accurately obtained; 2. the intelligent vehicle processor can not correctly recognize the behaviors of vehicles and pedestrians like the human brain, and has cognitive defects; 3. people are not trusted of unmanned technology.
Both the first two main problems lead to the fact that the unmanned vehicle cannot accurately avoid the obstacle, and the third problem is aggravated, but many patents at present do not well solve the problem of avoiding the obstacle of the unmanned vehicle.
The invention discloses a laser obstacle avoidance method and a system for an unmanned automobile, wherein the system comprises a driving control module, a laser component and an autonomous obstacle avoidance module, wherein the driving control module controls the unmanned automobile to run through an instruction of the autonomous obstacle avoidance module, a laser emitter sends laser to the outside and receives the laser reflected by an external obstacle, and a laser signal is sent to the autonomous obstacle avoidance module of the unmanned automobile for obstacle avoidance; the patent with the application number of 201610749321.0 discloses an obstacle avoidance method and system for an unmanned automobile, wherein the system comprises an information acquisition module, an information processing module and a driving control module, wherein the information acquisition module acquires three-dimensional scene information in the advancing direction of the unmanned automobile by adopting a laser ranging array, and the information processing module detects obstacle points in front of the unmanned automobile according to the acquired three-dimensional scene information to determine an obstacle avoidance path and controls the unmanned automobile to drive according to the obstacle avoidance path; however, although the above two patents can accurately avoid static obstacles, they cannot play a good role in avoiding dynamic obstacles.
Disclosure of Invention
The invention aims to solve the technical problem of overcoming the problems existing in the prior art and providing an unmanned vehicle obstacle avoidance control device and method based on a Dubins path.
The device can predict the running paths of other vehicles and pedestrians, and control the running state of the self-vehicle according to the running paths, and the invention can improve the running safety of the unmanned vehicle, and specifically aims to:
1. the recognition of the obstacle is facilitated for the unmanned vehicle, the perfection of the unmanned technology is improved, and a series of problems caused by imperfect sensor technology in the current stage are solved;
2. the problem of cognitive defect of an unmanned vehicle processor is solved, and the path pre-judgment of the movement obstacle is facilitated, so that the occurrence of unmanned traffic accidents is reduced.
The invention is realized by adopting the following technical scheme:
the invention provides an unmanned vehicle obstacle avoidance control device based on a Dubin path, which is characterized by comprising a camera arranged outside an A column on the left side of an unmanned vehicle, a camera arranged outside an A column on the right side of the unmanned vehicle and a laser radar arranged on the roof of the unmanned vehicle, wherein the two cameras are positioned in the middle of the A column and on the same horizontal line, the center of mass of the laser radar and the center of mass of the unmanned vehicle are on the same straight line, the straight line is perpendicular to the horizontal plane, and the two cameras and the laser radar are connected with an ECU of the unmanned vehicle.
The invention also provides a unmanned vehicle obstacle avoidance control method based on the Dubin path, which is characterized by comprising the following specific steps:
the radar locates and tests the speed of the obstacle entering the monitoring range of the camera;
step two, determining an obstacle sequence to be collided with the intelligent vehicle based on an obstacle avoidance algorithm;
the intelligent vehicle re-plans the current obstacle avoidance path according to the new obstacle sequence to finish obstacle avoidance operation;
wherein, the liquid crystal display device comprises a liquid crystal display device,
the specific process of the step (I) is as follows:
the unmanned vehicle detects the obstacle information under the multi-obstacle environment through two cameras positioned in the middle of the A column on the left side and the right side and the laser radar on the roof;
establishing an unmanned vehicle search model, and assuming that a search area of the unmanned vehicle is an area with a radius of R and an opening angle of 2 theta, wherein theta is determined by a camera visible angle, and R is determined by a camera monitoring distance;
the laser radar detects the number of obstacles in a search area of the unmanned vehicle, the running speed of the obstacles, the positions of the obstacles and the distance between the mass center of the unmanned vehicle and the observation points of the obstacles, and transmits motion data to a central processor of the unmanned vehicle;
the specific process of the step (II) is as follows:
defining a range circle to take the mass center of the unmanned vehicle as the circle center and R as 1 Is a circle of radius, and the range circle should enclose the unmanned vehicle contour line and let l '. Gtoreq.l, l' be the shortest distance between the range circle and the unmanned vehicle contour line, l be the shortest safe distance between the two vehicles;
when the obstacle enters the search area, starting to perform obstacle avoidance judgment;
in order to more accurately execute obstacle avoidance operation, the unmanned vehicle is generally in a multi-obstacle environment during running, and obstacles encountered by the unmanned vehicle are divided into two types: a stationary obstacle and a movement obstacle;
the judging method comprises the following steps: the laser radar acquires the speed and position information of the obstacle in the radar monitoring range every 0.05s, if the speed of the obstacle at each moment is 0, the obstacle is a static obstacle, and if the speed of the obstacle at a certain moment is not 0, the obstacle is a movement obstacle;
assuming that the unmanned vehicle does linear motion, constructing a two-dimensional plane xoy, taking the mass center of the unmanned vehicle as an origin, taking the advancing direction of the unmanned vehicle as a y axis, and rotating the y axis by 90 degrees along the clockwise direction as the positive direction of an x axis;
(1) Obstacle avoidance judgment is carried out on static obstacles:
because the speed of the static obstacle is 0, namely the observation point of the static obstacleThe coordinates are unchanged, and the coordinates of the observation points of the static obstacle are set as (x 0 ,y 0 ) Therefore, the shortest distance between the unmanned vehicle doing linear motion and the static obstacle is the length of the perpendicular line from the observation point of the static obstacle to the y axis; the length of the vertical line is the absolute value of the abscissa of the observation point of the static obstacle, i.e. |x 0 I (I); when |x 0 I is larger than the radius R of the circle 1 When the vehicle is in a driving state, the static obstacle can be judged not to collide with the unmanned vehicle; when |x 0 I is less than or equal to the radius R of the range circle 1 When the static obstacle is judged to collide with the unmanned vehicle, the static obstacle which is judged to collide is added into the obstacle sequence;
(2) Obstacle avoidance judgment is carried out on the movement obstacle:
firstly, carrying out track prediction on the track of the observation point of the movement obstacle by adopting a Kalman filtering algorithm, wherein the specific operation is as follows:
a. constructing a system prediction equation
The current moment is represented by k-1, and the position of the movement obstacle observation point at the moment k-1 measured by the laser radar in the two-dimensional plane xoy is set as (x (k-1), y (k-1)); let the speed of the observed point of the moving obstacle at the moment k-1 measured by the laser radar in the two-dimensional plane xoy be (v) x (k-1),v y (k-1)); setting the time interval of each moment as sampling interval time t, taking t=0.15 s; set Q x (k-1),Q y (k-1) is zero in mean and sigma in variance 0 2 2 orthogonal vectors of Gaussian white noise Q (k-1) at time k-1, Q x (k-1),Q y And (4) at any moment (k-1) mutually independent, wherein e is a natural constant and is also called Euler number, and the position and the speed equation of the observation point of the movement obstacle at the moment k in the two-dimensional plane xoy are obtained according to a physical movement formula as follows:
in the method, in the process of the invention,the predicted value of the position of the motion obstacle observation point in the two-dimensional plane xoy at the moment k,the predicted value of the speed of the motion obstacle observation point at the moment k in the two-dimensional plane xoy is used as the predicted value;
the system prediction equation is obtained by arrangement:
wherein, let the
X(k-1)＝(x(k-1)v x (k-1)y(k-1)v y (k-1)) T
X (k-1) is a laser radar measured value of the movement obstacle observation point at the moment k-1 in the two-dimensional plane xoy, wherein the predicted value of the movement obstacle observation point at the moment k in the two-dimensional plane xoy;
order the
A simplified system prediction equation is then obtained:
b. constructing a system measurement equation
Similarly, the position of the movement obstacle observation point at the moment k measured by the laser radar on the two-dimensional plane xoy is set as (x (k), y (k)); let the velocity of the movement obstacle observation point at the k moment measured by the laser radar in the two-dimensional plane xoy be (v x (k),v y (k) A) is provided; let R be x (k),R y (k) Is zero mean and sigma variance 1 2 2 orthogonal vectors of Gaussian white noise R (k) at time k, R x (k),R y (k) The coordinate and the speed of the observation point of the moving obstacle at the moment k in the two-dimensional plane xoy are measured according to the following equation:
wherein, let the
X(k)＝(x(k)v x (k)y(k)v y (k)) T
X (k) is a laser radar measured value of a motion obstacle observation point at the moment k in a two-dimensional plane xoy;
a simplified system measurement equation is obtained:
Y(k)＝HX(k)+IR(k)
c. calculating the error covariance P at time k k
d. Calculation of Kalman gain K k Obtaining the predicted value of the observation point of the movement obstacle at the moment k+1 in the two-dimensional plane
K k ＝P k H T (HP k H T +R(k)) -1
e. Calculating predicted value of motion obstacle observation point at time k+1 in two-dimensional plane xoyAnd a covariance matrix P between lidar measurements X (k+1) k+1 Prepare for the next recursion
P k+1 ＝(I-K k H)P k
Therefore, the predicted position of the motion obstacle observation point at each moment under the two-dimensional plane xoy can be obtained, and the position prediction track of the obstacle observation point can be obtained by connecting each predicted position.
Secondly, calculating the distance L between the observation point of the movement obstacle and the mass center of the unmanned vehicle at the same moment according to a formula between two points in the two-dimensional plane xoy, and if L is less than or equal to R 1 The movement obstacle is proved to collide with the unmanned vehicle at the moment, and the movement obstacle which is judged to collide is added to the obstacle sequence;
the specific process of the step (III) is as follows:
(1) When a plurality of obstacles exist in the unmanned vehicle obstacle sequence, the obstacles are sequentially avoided according to the distance between the unmanned vehicle and the unmanned vehicle, firstly, the obstacle closest to the unmanned vehicle is avoided, and then, the static obstacle and the moving obstacle are subjected to obstacle avoidance processing according to respective obstacle avoidance algorithms;
(2) The obstacle avoidance algorithm for the static obstacle is as follows:
the static obstacle position in the obstacle sequence is unchanged, so that the direction of the running speed of the unmanned vehicle is directly adjusted according to the monitored condition, and the obstacle can be effectively avoided;
the steering wheel of the unmanned vehicle can effectively avoid the obstacle by turning a certain angle theta to the opposite direction of the static obstacle, and the theta satisfies the following conditions:
(3) The obstacle avoidance algorithm for the movement obstacle is as follows:
defining an obstacle circle as a center of circle with a movement obstacle mass center R 2 A circle of radius, and the obstacle circle should enclose a movement obstacle contour;
a. the positions of the start circle Cs, the fault circle D, and the target circle Cf are determined:
on the two-dimensional plane track diagram, T is taken 1 ＝T t Taking the range circle at the moment-nt as a starting circle Cs and taking T t Taking the obstacle circle at the moment as a fault circle D and taking T 1 ＝T t The range circle when successfully avoiding the obstacle circle D and returning to the original path at the moment +nt is the target circle Cf;
T t ＝L/v x
v x ＝|v-v z |
wherein T is t V is the corresponding time when the movement obstacle collides with the unmanned vehicle x For the relative speed between the movement obstacle and the unmanned vehicle, v is the speed of the unmanned vehicle, v z Taking n as a positive integer which is more than or equal to 3 for the speed of a movement barrier so that the unmanned vehicle has enough reflecting time;
b. determining Dubin path between start circle Cs and fail circle D
According to the running direction of the fault circle D, two effective Dubin paths can be obtained, namely, two unmanned vehicle range circles run from the starting circle Cs to the Dubin paths tangential to the fault circle D, namely SD-1 and SD-2;
c. determining Dubin path between fault circle D and target circle Cf
The Dubin paths are carried out on the fault circle D and the target circle Cf, and 2 effective Dubin paths can be obtained in the same way, namely, the Dubin paths of two unmanned vehicle range circles which run from the tangential position of the two unmanned vehicle range circles to the position of the target circle Cf are respectively Df-1 and Df-2;
the path formed by path SD-1 and path Df-1 is called path SD 1 f，
Path SD-2 and path DfThe path formed by-2 is called path SD 2 f；
d. Determining Dubin path between start circle Cs and target circle Cf
From the travel direction analysis of the obstacle circle D, the path SD is known 2 f and obstacle circle D
Is interfered, i.e. a path SD close to the travelling direction of the obstacle circle D 2 f, path SD 1 f does not interfere with the traveling direction of the obstacle circle D, i.e., the path SD away from the traveling direction of the obstacle circle D 1 f, the effective obstacle avoidance path is SD 1 f。
Compared with the prior art, the invention has the beneficial effects that:
according to the unmanned vehicle obstacle avoidance control method based on the Dubin path, the obstacle is classified, whether the obstacle interferes with the movement of the unmanned vehicle or not is judged by adopting an obstacle avoidance algorithm, the obstacle which generates interference is added into an obstacle sequence, and the driving path is planned again. The following beneficial effects can be achieved:
1. the acquisition cameras are arranged in the middle of the two A columns of the unmanned vehicle, so that the problem of blind areas of the field of view of the unmanned vehicle is effectively solved, and meanwhile, the perfection and accuracy of the acquired information are improved;
2. classifying obstacles encountered in the unmanned aerial vehicle, adopting different obstacle avoidance judging algorithms for different obstacles, collecting obstacle information in the obstacle environment in real time, updating an obstacle sequence in real time, and improving the accuracy and precision of obstacle avoidance of the unmanned aerial vehicle;
3. the control system adopts a Kalman filtering algorithm to pre-judge the motion trail of the observation point of the movement obstacle, and adopts a Dubin path to carry out path planning, so that compared with the prior art, the accuracy of pre-judging the behavior of the obstacle through a vehicle-mounted processor is higher, the driving safety of the unmanned vehicle is improved, and meanwhile, the traffic accident caused by the recognition of the obstacle by the processor of the unmanned vehicle can be effectively avoided;
drawings
The invention is further described below with reference to the accompanying drawings:
FIG. 1 is a schematic diagram of a Dubin path-based unmanned vehicle obstacle avoidance control device according to the present invention;
FIG. 2 is a flow chart of a Dubin path-based unmanned vehicle obstacle avoidance control method according to the present invention;
FIG. 3 is an unmanned vehicle search model;
FIG. 4 is a diagram of a Dubin path;
in the figure: 1. the unmanned vehicle roof, 2, laser radar, 3, A post, 4, camera.
Detailed Description
The invention is described in detail below with reference to the attached drawing figures:
the utility model provides an unmanned vehicle keeps away barrier controlling means based on Dubins route, a serial communication port, including one set up at unmanned vehicle left side A outside camera 4 of post 3, one set up at unmanned vehicle right side A outside camera 4 of post 3 and one locate unmanned vehicle roof 1's laser radar 2, two cameras 4 all are in the middle part of being located A post 3 and lie in same horizontal line, laser radar 2 is in same straight line with unmanned vehicle's barycenter, and this straight line is perpendicular with the horizontal plane. As shown in fig. 1;
the cameras 4 are arranged on the left and right A columns 3 outside the unmanned vehicle, so that the problem of vision blind areas of the unmanned vehicle can be solved;
the unmanned vehicle obstacle avoidance control method based on the Dubin path is characterized by comprising the following specific steps of:
the radar locates and tests the speed of the obstacle entering the monitoring range of the camera;
step two, determining an obstacle sequence to be collided with the intelligent vehicle based on an obstacle avoidance algorithm;
the intelligent vehicle re-plans the current obstacle avoidance path according to the new obstacle sequence to finish obstacle avoidance operation;
the flow chart of the obstacle avoidance control method is shown in fig. 2.
Wherein, the specific process of the step (one) is as follows:
the unmanned vehicle detects the obstacle information in the multi-obstacle environment through two cameras 4 positioned in the middle of the A column 3 at the left side and the right side and the laser radar 2 of the roof 1;
and establishing an unmanned vehicle search model, and assuming that a search area of the unmanned vehicle is an area with a radius of R and an opening angle of 2 theta, wherein theta is determined by a camera visible angle, and R is determined by a camera monitoring distance. The unmanned vehicle search model is shown in fig. 3;
the laser radar 2 detects the number of obstacles in the search area of the unmanned vehicle, the running speed of the obstacles, the positions of the obstacles and the distance between the mass center of the unmanned vehicle and the observation points of the obstacles, and transmits motion data to the central processor of the unmanned vehicle;
the specific process of the step (II) is as follows:
defining a range circle to take the mass center of the unmanned vehicle as the circle center and R as 1 Is a circle of radius, and the range circle should enclose the unmanned vehicle contour line and let l '. Gtoreq.l, l' be the shortest distance between the range circle and the unmanned vehicle contour line, l be the shortest safe distance between the two vehicles;
when the obstacle enters the search area, starting to perform obstacle avoidance judgment;
in order to more accurately execute obstacle avoidance operation, the unmanned vehicle is generally in a multi-obstacle environment during running, and obstacles encountered by the unmanned vehicle are divided into two types: a stationary obstacle and a movement obstacle;
the judging method comprises the following steps: the laser radar acquires the speed and position information of the obstacle in the radar monitoring range every 0.05s, if the speed of the obstacle at each moment is 0, the obstacle is a static obstacle, and if the speed of the obstacle at a certain moment is not 0, the obstacle is a movement obstacle;
assuming that the unmanned vehicle does linear motion, constructing a two-dimensional plane xoy, taking the mass center of the unmanned vehicle as an origin, taking the advancing direction of the unmanned vehicle as a y axis, and rotating the y axis by 90 degrees along the clockwise direction as the positive direction of an x axis;
(1) Obstacle avoidance judgment is carried out on static obstacles:
since the speed of the stationary obstacle is 0, that is, the coordinates of the stationary obstacle observation point are unchanged, the coordinates of the stationary obstacle observation point are set as (x 0 ,y 0 ) Therefore, the shortest distance between the unmanned vehicle doing linear motion and the static obstacle is the length of the perpendicular line from the observation point of the static obstacle to the y axis; the length of the vertical line is the absolute value of the abscissa of the observation point of the static obstacle, i.e. |x 0 I (I); when |x 0 I is larger than the radius R of the circle 1 When the vehicle is in a driving state, the static obstacle can be judged not to collide with the unmanned vehicle; when |x 0 I is less than or equal to the radius R of the range circle 1 When the static obstacle is judged to collide with the unmanned vehicle, the static obstacle which is judged to collide is added into the obstacle sequence;
(2) Obstacle avoidance judgment is carried out on the movement obstacle:
firstly, carrying out track prediction on the track of the observation point of the movement obstacle by adopting a Kalman filtering algorithm, wherein the specific operation is as follows:
a. constructing a system prediction equation
The current moment is represented by k-1, and the position of the movement obstacle observation point at the moment k-1 measured by the laser radar in the two-dimensional plane xoy is set as (x (k-1), y (k-1)); let the speed of the observed point of the moving obstacle at the moment k-1 measured by the laser radar in the two-dimensional plane xoy be (v) x (k-1),v y (k-1)); setting the time interval of each moment as sampling interval time t, taking t=0.15 s; set Q x (k-1),Q y (k-1) is zero in mean and sigma in variance 0 2 2 orthogonal vectors of Gaussian white noise Q (k-1) at time k-1, Q x (k-1),Q y And (4) at any moment (k-1) mutually independent, wherein e is a natural constant and is also called Euler number, and the position and the speed equation of the observation point of the movement obstacle at the moment k in the two-dimensional plane xoy are obtained according to a physical movement formula as follows:
in the method, in the process of the invention,the predicted value of the position of the motion obstacle observation point in the two-dimensional plane xoy at the moment k,the predicted value of the speed of the motion obstacle observation point at the moment k in the two-dimensional plane xoy is used as the predicted value;
the system prediction equation is obtained by arrangement:
wherein, let the
X(k-1)＝(x(k-1)v x (k-1)y(k-1)v y (k-1)) T
X (k-1) is a laser radar measured value of the movement obstacle observation point at the moment k-1 in the two-dimensional plane xoy, wherein the predicted value of the movement obstacle observation point at the moment k in the two-dimensional plane xoy;
order the
A simplified system prediction equation is then obtained:
b. constructing a system measurement equation
Similarly, the position of the movement obstacle observation point at the moment k measured by the laser radar on the two-dimensional plane xoy is set as (x (k), y (k)); let the velocity of the movement obstacle observation point at the k moment measured by the laser radar in the two-dimensional plane xoy be (v x (k),v y (k) A) is provided; let R be x (k),R y (k) Is zero mean and sigma variance 1 2 2 orthogonal vectors of Gaussian white noise R (k) at time k, R x (k),R y (k) The coordinate and the speed of the observation point of the moving obstacle at the moment k in the two-dimensional plane xoy are measured according to the following equation:
wherein, let the
X(k)＝(x(k)v x (k)y(k)v y (k)) T
X (k) is a laser radar measured value of a motion obstacle observation point at the moment k in a two-dimensional plane xoy;
a simplified system measurement equation is obtained:
Y(k)＝HX(k)+IR(k)
c. calculating the error covariance P at time k k
d. Calculation of Kalman gain K k Obtaining the predicted value of the observation point of the movement obstacle at the moment k+1 in the two-dimensional plane
K k ＝P k H T (HP k H T +R(k)) -1
e. Calculating predicted value of motion obstacle observation point at time k+1 in two-dimensional plane xoyAnd a covariance matrix P between lidar measurements X (k+1) k+1 Prepare for the next recursion
P k+1 ＝(I-K k H)P k
Therefore, the predicted position of the motion obstacle observation point at each moment under the two-dimensional plane xoy can be obtained, and the position prediction track of the obstacle observation point can be obtained by connecting each predicted position.
Secondly, calculating the distance L between the observation point of the movement obstacle and the mass center of the unmanned vehicle at the same moment according to a formula between two points in the two-dimensional plane xoy, and if L is less than or equal to R 1 The movement obstacle is proved to collide with the unmanned vehicle at the moment, and the movement obstacle which is judged to collide is added to the obstacle sequence;
the specific process of the step (III) is as follows:
(1) When a plurality of obstacles exist in the unmanned vehicle obstacle sequence, the obstacles are sequentially avoided according to the distance between the unmanned vehicle and the unmanned vehicle, firstly, the obstacle closest to the unmanned vehicle is avoided, and then, the static obstacle and the moving obstacle are subjected to obstacle avoidance processing according to respective obstacle avoidance algorithms;
(2) The obstacle avoidance algorithm for the static obstacle is as follows:
the static obstacle position in the obstacle sequence is unchanged, so that the direction of the running speed of the unmanned vehicle is directly adjusted according to the monitored condition, and the obstacle can be effectively avoided;
the steering wheel of the unmanned vehicle can effectively avoid the obstacle by turning a certain angle theta to the opposite direction of the static obstacle, and the theta satisfies the following conditions:
(3) The obstacle avoidance algorithm for the movement obstacle is as follows:
defining an obstacle circle as a center of circle with a movement obstacle mass center R 2 A circle of radius, and the obstacle circle should enclose a movement obstacle contour;
a. the positions of the start circle Cs, the fault circle D, and the target circle Cf are determined:
on the two-dimensional plane track diagram, T is taken 1 ＝T t Taking the range circle at the moment-nt as a starting circle Cs and taking T t Taking the obstacle circle at the moment as a fault circle D and taking T 1 ＝T t The range circle when successfully avoiding the obstacle circle D and returning to the original path at the moment +nt is the target circle Cf;
T t ＝L/v x
v x ＝|v-v z |
wherein T is t V is the corresponding time when the movement obstacle collides with the unmanned vehicle x For the relative speed between the movement obstacle and the unmanned vehicle, v is the speed of the unmanned vehicle, v z Taking n as a positive integer which is more than or equal to 3 for the speed of a movement barrier so that the unmanned vehicle has enough reflecting time;
b. determining Dubin path between start circle Cs and fail circle D
According to the running direction of the fault circle D, two effective Dubins paths can be obtained, namely, two unmanned vehicle range circles run from the starting circle Cs to the Dubins paths tangential to the fault circle D, namely SD-1 and SD-2.
c. Determining Dubin path between fault circle D and target circle Cf
The Dubin paths are carried out on the fault circle D and the target circle Cf, and 2 effective Dubin paths can be obtained in the same way, namely, the Dubin paths of two unmanned vehicle range circles which run from the tangential position of the two unmanned vehicle range circles to the position of the target circle Cf are respectively Df-1 and Df-2;
the path formed by path SD-1 and path Df-1 is called path SD 1 f，
The path formed by path SD-2 and path Df-2 is called path SD 2 f；
d. Determining Dubin path between start circle Cs and target circle Cf
From the travel direction analysis of the obstacle circle D, the path SD is known 2 f interfere with the traveling direction of the obstacle circle D, i.e., the path SD approaching the traveling direction of the obstacle circle D 2 f, path SD 1 f does not interfere with the traveling direction of the obstacle circle D, i.e., the path SD away from the traveling direction of the obstacle circle D 1 f, the effective obstacle avoidance path is SD 1 f；
The dubin path is shown in fig. 4.
Claims (1)
1. The utility model provides an unmanned vehicle keeps away barrier control method based on Dubins route, use an unmanned vehicle keeps away barrier control device based on Dubins route, including one set up camera (4) outside unmanned vehicle left side A post (3), one set up camera (4) outside unmanned vehicle right side A post (3) and one locate laser radar (2) of unmanned vehicle roof (1), two cameras (4) are all in the middle part of A post (3) and lie in same horizontal line, laser radar (2) are in same straight line with unmanned vehicle's barycenter, and this straight line is perpendicular with the horizontal plane, two cameras (4) and laser radar (2) are all connected with unmanned vehicle's ECU, its characterized in that, concretely steps are as follows:
the radar locates and tests the speed of the obstacle entering the monitoring range of the camera;
step two, determining an obstacle sequence to be collided with the intelligent vehicle based on an obstacle avoidance algorithm;
the intelligent vehicle re-plans the current obstacle avoidance path according to the new obstacle sequence to finish obstacle avoidance operation;
wherein, the liquid crystal display device comprises a liquid crystal display device,
the specific process of the step (I) is as follows:
the unmanned vehicle detects obstacle information in a multi-obstacle environment through two cameras (4) positioned in the middle of a column A (3) at the left side and the right side and a laser radar (2) positioned on a roof (1);
establishing an unmanned vehicle search model, and assuming that a search area of the unmanned vehicle is an area with a radius of R and an opening angle of 2 theta, wherein theta is determined by a camera visible angle, and R is determined by a camera monitoring distance;
the laser radar (2) detects the number of obstacles in a search area of the unmanned vehicle, the running speed of the obstacles, the positions of the obstacles and the distance between the mass center of the unmanned vehicle and the observation points of the obstacles, and transmits motion data to the central processor of the unmanned vehicle;
the specific process of the step (II) is as follows:
defining a range circle to take the mass center of the unmanned vehicle as the circle center and R as 1 Is a circle of radius, and the range circle should enclose the unmanned vehicle contour line and let l '. Gtoreq.l, l' be the shortest distance between the range circle and the unmanned vehicle contour line, l be the shortest safe distance between the two vehicles;
when the obstacle enters the search area, starting to perform obstacle avoidance judgment;
in order to more accurately execute obstacle avoidance operation, the unmanned vehicle is generally in a multi-obstacle environment during running, and obstacles encountered by the unmanned vehicle are divided into two types: a stationary obstacle and a movement obstacle;
the judging method comprises the following steps: the laser radar acquires the speed and position information of the obstacle in the radar monitoring range every 0.05s, if the speed of the obstacle at each moment is 0, the obstacle is a static obstacle, and if the speed of the obstacle at a certain moment is not 0, the obstacle is a movement obstacle;
assuming that the unmanned vehicle does linear motion, constructing a two-dimensional plane xoy, taking the mass center of the unmanned vehicle as an origin, taking the advancing direction of the unmanned vehicle as a y axis, and rotating the y axis by 90 degrees along the clockwise direction as the positive direction of an x axis;
(1) Obstacle avoidance judgment is carried out on static obstacles:
because the speed of the stationary barrier is 0That is, the coordinates of the observation point of the stationary obstacle are unchanged, and the coordinates of the observation point of the stationary obstacle are set as (x 0 ,y 0 ) Therefore, the shortest distance between the unmanned vehicle doing linear motion and the static obstacle is the length of the perpendicular line from the observation point of the static obstacle to the y axis; the length of the vertical line is the absolute value of the abscissa of the observation point of the static obstacle, i.e. |x 0 I (I); when |x 0 I is larger than the radius R of the circle 1 When the vehicle is in a driving state, the static obstacle can be judged not to collide with the unmanned vehicle; when |x 0 I is less than or equal to the radius R of the range circle 1 When the static obstacle is judged to collide with the unmanned vehicle, the static obstacle which is judged to collide is added into the obstacle sequence;
(2) Obstacle avoidance judgment is carried out on the movement obstacle:
firstly, carrying out track prediction on the track of the observation point of the movement obstacle by adopting a Kalman filtering algorithm, wherein the specific operation is as follows:
a. constructing a system prediction equation
The current moment is represented by k-1, and the position of the movement obstacle observation point at the moment k-1 measured by the laser radar in the two-dimensional plane xoy is set as (x (k-1), y (k-1)); let the speed of the observed point of the moving obstacle at the moment k-1 measured by the laser radar in the two-dimensional plane xoy be (v) x (k-1),v y (k-1)); setting the time interval of each moment as sampling interval time t, taking t=0.15 s; set Q x (k-1),Q y (k-1) is zero in mean and sigma in variance 0 2 2 orthogonal vectors of Gaussian white noise Q (k-1) at time k-1, Q x (k-1),Q y And (4) at any moment (k-1) mutually independent, wherein e is a natural constant and is also called Euler number, and the position and the speed equation of the observation point of the movement obstacle at the moment k in the two-dimensional plane xoy are obtained according to a physical movement formula as follows:
in the method, in the process of the invention,the predicted value of the position of the motion obstacle observation point in the two-dimensional plane xoy at the moment k,the predicted value of the speed of the motion obstacle observation point at the moment k in the two-dimensional plane xoy is used as the predicted value;
the system prediction equation is obtained by arrangement:
wherein, let the
X(k-1)＝(x(k-1)v x (k-1)y(k-1)v y (k-1)) T
X (k-1) is a laser radar measured value of the movement obstacle observation point at the moment k-1 in the two-dimensional plane xoy, wherein the predicted value of the movement obstacle observation point at the moment k in the two-dimensional plane xoy;
order the
A simplified system prediction equation is then obtained:
b. constructing a system measurement equation
Similarly, the position of the movement obstacle observation point at the moment k measured by the laser radar on the two-dimensional plane xoy is set as (x (k), y (k)); let the velocity of the movement obstacle observation point at the k moment measured by the laser radar in the two-dimensional plane xoy be (v x (k),v y (k) A) is provided; let R be x (k),R y (k) Is zero mean and sigma variance 1 2 2 orthogonal vectors of Gaussian white noise R (k) at time k, R x (k),R y (k) The coordinate and the speed of the observation point of the moving obstacle at the moment k in the two-dimensional plane xoy are measured according to the following equation:
wherein, let the
X(k)＝(x(k)v x (k)y(k)v y (k)) T
X (k) is a laser radar measured value of a motion obstacle observation point at the moment k in a two-dimensional plane xoy;
a simplified system measurement equation is obtained:
Y(k)＝HX(k)+IR(k)
c. calculating the error covariance P at time k k
d. Calculation of Kalman gain K k Obtaining the predicted value of the observation point of the movement obstacle at the moment k+1 in the two-dimensional plane
K k ＝P k H T (HP k H T +R(k)) -1
e. Calculating predicted value of motion obstacle observation point at time k+1 in two-dimensional plane xoyAnd a covariance matrix P between lidar measurements X (k+1) k+1 Prepare for the next recursion
P k+1 ＝(I-K k H)P k
Therefore, the predicted position of the motion obstacle observation point at each moment under the two-dimensional plane xoy can be obtained, and the position prediction track of the obstacle observation point can be obtained by connecting each predicted position;
secondly, calculating the distance L between the observation point of the movement obstacle and the mass center of the unmanned vehicle at the same moment according to a formula between two points in the two-dimensional plane xoy, and if L is less than or equal to R 1 The movement obstacle is proved to collide with the unmanned vehicle at the moment, and the movement obstacle which is judged to collide is added to the obstacle sequence;
the specific process of the step (III) is as follows:
(1) When a plurality of obstacles exist in the unmanned vehicle obstacle sequence, the obstacles are sequentially avoided according to the distance between the unmanned vehicle and the unmanned vehicle, firstly, the obstacle closest to the unmanned vehicle is avoided, and then, the static obstacle and the moving obstacle are subjected to obstacle avoidance processing according to respective obstacle avoidance algorithms;
(2) The obstacle avoidance algorithm for the static obstacle is as follows:
the static obstacle position in the obstacle sequence is unchanged, so that the direction of the running speed of the unmanned vehicle is directly adjusted according to the monitored condition, and the obstacle can be effectively avoided;
the steering wheel of the unmanned vehicle can effectively avoid the obstacle by turning a certain angle theta to the opposite direction of the static obstacle, and the theta satisfies the following conditions:
(3) The obstacle avoidance algorithm for the movement obstacle is as follows:
defining an obstacle circle as a center of circle with a movement obstacle mass center R 2 A circle of radius, and the obstacle circle should enclose a movement obstacle contour;
a. the positions of the start circle Cs, the fault circle D, and the target circle Cf are determined:
on the two-dimensional plane track diagram, T is taken 1 ＝T t Taking the range circle at the moment-nt as a starting circle Cs and taking T t Taking the obstacle circle at the moment as a fault circle D and taking T 1 ＝T t The range circle when successfully avoiding the obstacle circle D and returning to the original path at the moment +nt is the target circle Cf;
T t ＝L/v x
v x ＝|v-v z |
wherein T is t V is the corresponding time when the movement obstacle collides with the unmanned vehicle x For the relative speed between the movement obstacle and the unmanned vehicle, v is the speed of the unmanned vehicle, v z Taking n as a positive integer which is more than or equal to 3 for the speed of a movement barrier so that the unmanned vehicle has enough reflecting time;
b. determining Dubin path between start circle Cs and fail circle D
According to the running direction of the fault circle D, two effective Dubin paths can be obtained, namely, two unmanned vehicle range circles run from the starting circle Cs to the Dubin paths tangential to the fault circle D, namely SD-1 and SD-2;
c. determining Dubin path between fault circle D and target circle Cf
The Dubin paths are carried out on the fault circle D and the target circle Cf, and 2 effective Dubin paths can be obtained in the same way, namely, the Dubin paths of two unmanned vehicle range circles which run from the tangential position of the two unmanned vehicle range circles to the position of the target circle Cf are respectively Df-1 and Df-2;
the path formed by path SD-1 and path Df-1 is called path SD 1 f，
The path formed by path SD-2 and path Df-2 is called path SD 2 f；
d. Determining Dubin path between start circle Cs and target circle Cf
From the travel direction analysis of the obstacle circle D, the path SD is known 2 f interfere with the traveling direction of the obstacle circle D, i.e., the path SD approaching the traveling direction of the obstacle circle D 2 f, path SD 1 f does not interfere with the traveling direction of the obstacle circle D, i.e., the path SD away from the traveling direction of the obstacle circle D 1 f, the effective obstacle avoidance path is SD 1 f。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810375570.7A CN108536149B (en) | 2018-04-25 | 2018-04-25 | Unmanned vehicle obstacle avoidance control method based on Dubins path |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810375570.7A CN108536149B (en) | 2018-04-25 | 2018-04-25 | Unmanned vehicle obstacle avoidance control method based on Dubins path |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108536149A CN108536149A (en) | 2018-09-14 |
| CN108536149B true CN108536149B (en) | 2023-07-28 |
Family
ID=63477606
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810375570.7A Active CN108536149B (en) | 2018-04-25 | 2018-04-25 | Unmanned vehicle obstacle avoidance control method based on Dubins path |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108536149B (en) |
Families Citing this family (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109270933B (en) * | 2018-10-11 | 2021-06-22 | 中国科学院深圳先进技术研究院 | Unmanned obstacle avoidance method, device, equipment and medium based on conic curve |
| CN109683606A (en) * | 2018-11-21 | 2019-04-26 | 江苏科技大学 | A kind of pilotless automobile automatic obstacle avoiding method |
| CN109901194A (en) * | 2019-03-18 | 2019-06-18 | 爱驰汽车有限公司 | Onboard system, method, equipment and the storage medium of anticollision |
| CN109883427B (en) * | 2019-03-25 | 2023-04-07 | 江苏科技大学 | Obstacle avoidance method of unmanned ship based on Dubins path and probability threat map |
| CN109901618A (en) * | 2019-03-29 | 2019-06-18 | 国网山东省电力公司梁山县供电公司 | Power-line patrolling system and method |
| CN109917792B (en) * | 2019-04-10 | 2023-10-13 | 湖南汽车工程职业学院 | Autonomous anti-collision system based on unmanned sightseeing electric vehicle |
| CN112130551A (en) * | 2019-06-25 | 2020-12-25 | 北京百度网讯科技有限公司 | Decision planning method and device for travel path and speed of unmanned vehicle |
| CN110275168B (en) * | 2019-07-09 | 2021-05-04 | 厦门金龙联合汽车工业有限公司 | Multi-target identification and anti-collision early warning method and system |
| CN113119964B (en) * | 2019-12-30 | 2022-08-02 | 宇通客车股份有限公司 | Collision prediction judgment method and device for automatic driving vehicle |
| CN111473795B (en) * | 2020-04-08 | 2022-05-17 | 江苏盛海智能科技有限公司 | Obstacle avoidance method and terminal for unmanned vehicle |
| CN111966088B (en) * | 2020-07-14 | 2022-04-05 | 合肥工业大学 | Control system and control method for automatically-driven toy car for children |
| CN112230242B (en) * | 2020-09-30 | 2023-04-25 | 深兰人工智能(深圳)有限公司 | Pose estimation system and method |
| CN112050809B (en) * | 2020-10-08 | 2022-06-17 | 吉林大学 | Wheel type odometer and gyroscope information fusion unmanned vehicle directional positioning method |
| CN112255628A (en) * | 2020-10-09 | 2021-01-22 | 新石器慧义知行智驰(北京)科技有限公司 | Obstacle trajectory prediction method, apparatus, device, and medium |
| CN112596074B (en) * | 2020-12-09 | 2022-04-12 | 南京农业大学 | Navigation vehicle obstacle detection method based on laser radar |
| CN112506222A (en) * | 2020-12-10 | 2021-03-16 | 中国南方电网有限责任公司超高压输电公司天生桥局 | Unmanned aerial vehicle intelligent obstacle avoidance method and device |
| CN112729320B (en) * | 2020-12-22 | 2022-05-17 | 中国第一汽车股份有限公司 | Method, device and equipment for constructing obstacle map and storage medium |
| CN113643568B (en) * | 2021-07-22 | 2022-11-15 | 吉林大学 | Vehicle intersection collision avoidance system and method based on unmanned aerial vehicle |
| CN113589830B (en) * | 2021-10-08 | 2022-01-07 | 创泽智能机器人集团股份有限公司 | Robot walking direction prediction method and equipment |
| CN114103893A (en) * | 2021-11-26 | 2022-03-01 | 河北春玖智能科技有限公司 | Unmanned vehicle trajectory prediction anti-collision method |
| CN114428504A (en) * | 2022-01-18 | 2022-05-03 | 上汽通用五菱汽车股份有限公司 | Unmanned vehicle obstacle avoidance method, system, electronic device and storage medium |
| CN114489087B (en) * | 2022-04-18 | 2022-07-05 | 北京理工大学 | Multi-unmanned vehicle path collaborative planning method and system |
| CN117148848B (en) * | 2023-10-27 | 2024-01-26 | 上海伯镭智能科技有限公司 | Intelligent obstacle avoidance method and system for unmanned vehicle |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1961613A2 (en) * | 2007-02-23 | 2008-08-27 | Aisin AW Co., Ltd. | Driving support method and driving support device |
| CN101277432A (en) * | 2007-03-26 | 2008-10-01 | 爱信艾达株式会社 | Driving support method and driving support apparatus |
| CN103176185A (en) * | 2011-12-26 | 2013-06-26 | 上海汽车集团股份有限公司 | Method and system for detecting road barrier |
| DE102016106298A1 (en) * | 2015-04-06 | 2016-10-06 | GM Global Technology Operations LLC | Fusion method for a cross traffic application using radar devices and a camera |
| CN107957583A (en) * | 2017-11-29 | 2018-04-24 | 江苏若博机器人科技有限公司 | A kind of round-the-clock quick unmanned vehicle detection obstacle avoidance system of Multi-sensor Fusion |
| CN208061025U (en) * | 2018-04-25 | 2018-11-06 | 吉林大学 | A kind of automatic driving vehicle avoidance obstacle device based on the paths Dubins |
-
2018
- 2018-04-25 CN CN201810375570.7A patent/CN108536149B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1961613A2 (en) * | 2007-02-23 | 2008-08-27 | Aisin AW Co., Ltd. | Driving support method and driving support device |
| CN101277432A (en) * | 2007-03-26 | 2008-10-01 | 爱信艾达株式会社 | Driving support method and driving support apparatus |
| CN103176185A (en) * | 2011-12-26 | 2013-06-26 | 上海汽车集团股份有限公司 | Method and system for detecting road barrier |
| DE102016106298A1 (en) * | 2015-04-06 | 2016-10-06 | GM Global Technology Operations LLC | Fusion method for a cross traffic application using radar devices and a camera |
| CN107957583A (en) * | 2017-11-29 | 2018-04-24 | 江苏若博机器人科技有限公司 | A kind of round-the-clock quick unmanned vehicle detection obstacle avoidance system of Multi-sensor Fusion |
| CN208061025U (en) * | 2018-04-25 | 2018-11-06 | 吉林大学 | A kind of automatic driving vehicle avoidance obstacle device based on the paths Dubins |
Non-Patent Citations (3)
| Title |
|---|
| Hongfeng Wang.Detection and Tracking Algorithm of Front Vehicle Based on Laser Radar.SAE Technical Paper Series.2015,1-7. * |
| 关震宇.基于Dubins路径的无人机避障规划算法.北京理工大学学报.2014,第34卷(第6期),571-573. * |
| 李龙杰.基于四线激光雷达的道路信息提取技术研究.硕士学位论文.2017,第2017年(第03期),68-70页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108536149A (en) | 2018-09-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108536149B (en) | Unmanned vehicle obstacle avoidance control method based on Dubins path | |
| US11783707B2 (en) | Vehicle path planning | |
| CN107646114B (en) | Method for estimating lane | |
| US11313976B2 (en) | Host vehicle position estimation device | |
| Tsugawa et al. | An architecture for cooperative driving of automated vehicles | |
| CN111071249B (en) | Unmanned vehicle emergency steering obstacle avoidance method based on obstacle motion prediction | |
| CN109085829B (en) | Dynamic and static target identification method | |
| US20190031198A1 (en) | Vehicle Travel Control Method and Vehicle Travel Control Device | |
| US11275173B2 (en) | Yaw rate from radar data | |
| Kim et al. | Automated complex urban driving based on enhanced environment representation with GPS/map, radar, lidar and vision | |
| CN110060467A (en) | Prediction meanss, prediction technique and storage medium | |
| CN112068574A (en) | Control method and system for unmanned vehicle in dynamic complex environment | |
| CN114442101B (en) | Vehicle navigation method, device, equipment and medium based on imaging millimeter wave radar | |
| CN110816540A (en) | Traffic jam determining method, device and system and vehicle | |
| WO2021056499A1 (en) | Data processing method and device, and movable platform | |
| CN114200945B (en) | Safety control method of mobile robot | |
| JP2021082286A (en) | System and method for improving lane change detection, and non-temporary computer-readable medium | |
| CN111596666A (en) | Detection method for obstacle collision threat based on AGV motion prediction | |
| CN208061025U (en) | A kind of automatic driving vehicle avoidance obstacle device based on the paths Dubins | |
| US10839678B2 (en) | Vehicle identifying device | |
| CN111857121A (en) | Patrol robot walking obstacle avoidance method and system based on inertial navigation and laser radar | |
| CN111186438B (en) | Filtering method for curve obstacle vehicle | |
| CN110979320B (en) | Pedestrian emergency avoidance control method with irregular traveling path | |
| CN112002032A (en) | Method, device, equipment and computer readable storage medium for guiding vehicle driving | |
| CN112154455B (en) | Data processing method, equipment and movable platform |
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 |