CN111650945A - Dynamic barrier anti-collision method - Google Patents
Dynamic barrier anti-collision method Download PDFInfo
- Publication number
- CN111650945A CN111650945A CN202010598009.2A CN202010598009A CN111650945A CN 111650945 A CN111650945 A CN 111650945A CN 202010598009 A CN202010598009 A CN 202010598009A CN 111650945 A CN111650945 A CN 111650945A
- Authority
- CN
- China
- Prior art keywords
- obstacle
- dynamic
- straight line
- speed
- vehicle
- 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.)
- Granted
Links
- 230000004888 barrier function Effects 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 34
- 230000001133 acceleration Effects 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 description 10
- 230000004927 fusion Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000008447 perception Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
Images
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
- G05D1/0257—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, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/0088—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours
-
- 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
- G05D1/0223—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, 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
- G05D1/0231—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
- G05D1/0248—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 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, 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
- G05D1/0255—Control of position or course in two dimensions specially adapted to land vehicles using acoustic signals, e.g. ultra-sonic singals
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Optics & Photonics (AREA)
- Acoustics & Sound (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Medical Informatics (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The invention provides a dynamic barrier anti-collision method, which comprises the following steps: predicting to obtain linear predicted track information of the dynamic barrier within a preset time length according to the instantaneous speed and the current position information of the dynamic barrier; when the straight line prediction track is intersected with the planned path and when the straight line prediction track and the planned path are not in opposite directions, determining the area attribute of the dynamic barrier according to the current position information of the vehicle and the current position information of the dynamic barrier; performing speed planning through a trapezoidal speed planning algorithm according to the region attribute of the dynamic obstacle and the age of the dynamic obstacle; the age of the dynamic obstacle is the time length counted from the moment of acquiring the obstacle information; and generating a control signal according to the planned speed, and sending the control signal to an actuator for execution. Therefore, the safety of the vehicle is ensured.
Description
Technical Field
The invention relates to the field of data processing, in particular to a dynamic barrier collision avoidance method.
Background
In recent years, the unmanned technology is becoming more and more mature depending on the rapid development of the artificial intelligence technology, and the daily life of people is gradually changed from the aspects of travel modes, unmanned logistics, special operations and the like. How to ensure the safety of the unmanned vehicle in the environment with dynamic obstacles such as pedestrians or vehicles is a difficult problem. In order to improve the safety of the unmanned vehicle, a dynamic barrier collision avoidance method with strong robustness and high operation efficiency needs to be developed, so that the unmanned vehicle can avoid dynamic pedestrians or vehicles more safely.
The existing dynamic obstacle anti-collision method firstly obtains the predicted track of an obstacle in a future period of time through a probability track model method, and the method considers the uncertainty of the yaw velocity and the velocity of the obstacle in the track prediction and predicts the possible future driving track of the obstacle. And then, judging the future running track of the vehicle to be intersected with the predicted track in the motion planning, and planning to reduce the speed or stop the vehicle according to the collision time during intersection so as to realize collision avoidance.
The existing dynamic barrier collision avoidance method is generally limited by perception accuracy, calculation performance and planning strategy, and has three main problems: (1) when the sensed obstacle data has large jitter, the problem that the planned own track has poor consistency due to the fact that the jitter of the tail section of the predicted track is large exists, and safety collision avoidance cannot be guaranteed; (2) the algorithm has high complexity, long calculation time consumption and is not suitable for a vehicle-mounted calculation platform with limited calculation resources; (3) the method of planning according to the collision time may plan a more aggressive result and occupy the original driving trajectory of the pedestrian or vehicle, which may cause an unsafe feeling of the pedestrian or vehicle.
Disclosure of Invention
The embodiment of the invention aims to provide a dynamic barrier collision avoidance method, and aims to solve the problems that in the prior art, safety collision avoidance cannot be ensured, the algorithm complexity is high, the calculation time consumption is long, and the method is not suitable for a vehicle-mounted calculation platform with limited calculation resources and causes unsafe feeling of people or vehicles.
In order to solve the above problem, in a first aspect, the present invention provides a dynamic obstacle collision avoidance method, including:
acquiring obstacle information; the obstacle information includes dynamic obstacle information including instantaneous speed and current position information of a dynamic obstacle;
predicting to obtain linear predicted track information of the dynamic barrier within a preset time length according to the instantaneous speed and the current position information of the dynamic barrier; the straight line prediction track information comprises the direction and the length of the straight line prediction track;
judging whether the straight line prediction track is intersected with the planned path or not according to the direction of the straight line prediction track, the length of the straight line prediction track and the planned path;
when the straight line prediction track intersects with the planned path, judging whether the straight line prediction track and the planned path are in opposite directions or not according to the direction of the straight line prediction track and the planned path;
when the straight line prediction track and the planned path are not in opposite directions, determining the area attribute of the dynamic obstacle according to the current position information of the vehicle and the current position information of the dynamic obstacle;
performing speed planning through a trapezoidal speed planning algorithm according to the region attribute of the dynamic obstacle and the age of the dynamic obstacle; the age of the dynamic barrier is the time length from the clustering moment to time;
and generating a control signal according to the planned speed, and sending the control signal to an actuator for execution.
In a possible implementation manner, the predicting to obtain the straight line predicted trajectory information of the dynamic obstacle within the preset time length according to the instantaneous speed and the current position information of the dynamic obstacle specifically includes:
determining the origin of the straight line prediction track according to the current position information of the dynamic barrier;
determining the direction of the straight line predicted track according to the direction of the instantaneous speed of the dynamic obstacle;
and determining the length of the straight line prediction track according to the product of the instantaneous speed of the dynamic obstacle and the prediction duration.
In one possible implementation, the method further includes:
when the straight line prediction track and the local planning path are in non-opposite directions, determining a collision point according to the straight line prediction track information and the planning path;
determining a deceleration distance according to the current position information of the vehicle and a preset first acceleration threshold; the deceleration distance is a distance for the vehicle to decelerate from the current position by a preset first acceleration threshold value;
and planning the distance between the deceleration distance and the collision point by a trapezoidal speed planning algorithm.
In a possible implementation manner, the performing speed planning according to the attribute of the area where the dynamic obstacle is located and the age of the dynamic obstacle specifically includes:
when the area attribute of the dynamic barrier is a first area, judging whether the age of the dynamic barrier is greater than a preset time length, and when the age of the dynamic barrier is greater than the preset time length, calling a trapezoidal speed planning algorithm to plan parking;
and when the area attribute of the dynamic barrier is a second area, judging whether the age of the dynamic barrier is greater than a preset time length, and calling a trapezoidal speed planning algorithm to plan deceleration when the age of the dynamic barrier is greater than the preset time length.
In a possible implementation manner, after the linear predicted trajectory information of the dynamic obstacle within a preset time length is obtained through prediction according to the instantaneous speed and the current position information of the dynamic obstacle, the method further includes:
discretizing the straight line prediction track to obtain cell points of a plurality of virtual obstacles; the cell point of the virtual obstacle is a contour point of the dynamic obstacle on the straight line prediction track.
In a possible implementation manner, the trapezoidal velocity planning algorithm specifically includes:
calculating a pre-aiming distance according to the speed information of the vehicle, a preset second acceleration threshold, a safety distance and a preset distance constant;
judging whether the pre-aiming distance is intersected with the cell point of the virtual obstacle;
when the pre-aiming distance is intersected with the cell point of the virtual obstacle, the cell point of the intersected virtual obstacle is determined, and the speed of a road point between a road point in a safety distance before the intersected cell point of the virtual obstacle and the end point of a planned path of the intersected cell point of the virtual obstacle is set to be 0.
In a possible implementation manner, the calculating the pre-aiming distance according to the speed information of the vehicle, a preset second acceleration threshold, the safe distance, and a preset distance constant specifically includes:
and dividing the square of the speed information of the vehicle by a preset second acceleration threshold value, and adding the safety distance and a preset distance constant to obtain the pre-aiming distance.
In a second aspect, the invention provides an apparatus comprising a memory for storing a program and a processor for performing the method of any of the first aspects.
In a third aspect, the present invention provides a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method according to any one of the first aspect.
In a fourth aspect, the invention provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the method of any of the first aspects.
The dynamic barrier anti-collision method provided by the embodiment of the invention has the following technical effects:
(1) according to the method, the trajectory of the dynamic barrier is predicted by using the linear prediction model, the predicted trajectory is discretized into trajectory points which serve as cell points of the virtual barrier, the barrier prediction model is simplified, the time domain solving problem is simplified into a space anti-collision problem, and the safety problem of anti-collision failure caused by the jitter of collision time does not exist.
(2) The linear prediction model is low in algorithm complexity and suitable for the vehicle-mounted computing platform with limited computing resources.
(3) The area division method and the obstacle age size method effectively filter the dynamic obstacles in the non-dangerous area, and reduce the false triggering of the anti-collision function.
(4) In this application, when taking place to interfere the orbit of traveling of dynamic barriers such as pedestrian or vehicle from the track of car, can park and wait until the barrier is kept away from to just not continuing to travel at the risk of not colliding, effectively guarantee the security.
Drawings
Fig. 1 is a schematic structural diagram of a software system according to an embodiment of the present invention;
fig. 2 is a scene diagram of collision avoidance of a dynamic obstacle according to a first embodiment of the present invention;
fig. 3 is a schematic view of a dynamic obstacle collision avoidance process according to an embodiment of the present invention;
FIG. 4 is a diagram illustrating an effect of a trapezoidal velocity planning algorithm according to an embodiment of the present invention;
fig. 5 shows an embodiment of the present invention.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant invention and not restrictive of the invention. It should be further noted that, for the convenience of description, only the portions related to the related invention are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
Fig. 1 is a schematic structural diagram of a software system according to an embodiment of the present invention. The system consists of a vehicle-mounted sensor, a vehicle-mounted arithmetic unit and an actuator, and the dynamic barrier collision avoidance function is integrated in the vehicle-mounted arithmetic unit. The dynamic obstacle collision avoidance function relates to a plurality of key technologies such as environment perception, behavior prediction and speed planning in motion planning, and a specific implementation scheme will be described in detail below.
Firstly, the fusion positioning obtains the state of the vehicle from the vehicle-mounted sensor, and the sensing fusion obtains the environmental information around the vehicle from the vehicle-mounted sensor, wherein the environmental information mainly comprises the speed of the vehicle, the position of a peripheral obstacle and the speed information. Second, the behavior prediction predicts a straight-line predicted trajectory of the dynamic obstacle for a future period of time based on the position and instantaneous speed of the dynamic obstacle. Thirdly, judging whether the motion planning is intersected with the straight line prediction track of the dynamic barrier or not on the basis of the planned path, if so, planning deceleration or stopping near the intersection point, and correspondingly generating acceleration and deceleration requirements by the control module. And finally, the actuator receives the acceleration and deceleration requirement and then actively controls the accelerator and the braking system of the vehicle to adjust the speed of the vehicle, so that the vehicle is prevented from colliding with a dynamic barrier.
Fig. 2 is a dynamic obstacle anti-collision scene diagram according to an embodiment of the present invention, in order to avoid a problem of large jitter at a predicted track end section in the prior art, the present application converts a linear predicted track of a dynamic obstacle in a time domain into an obstacle anti-collision problem in a two-dimensional space by using a linear prediction method, so as to reduce a collision risk caused by jitter of collision time. The method comprises the steps of obtaining linear prediction track information of the dynamic obstacle through the instantaneous speed and age of the dynamic obstacle, sampling the linear prediction track according to a fixed time interval to obtain discrete track points (dotted lines in fig. 2), and using the track points as cell points of the virtual obstacle to represent the outline of the virtual obstacle.
In addition, the speed calculation of the perception fusion on the low-speed obstacle is not accurate enough, and particularly the course of the low-speed target is changed greatly, so that the swing of the predicted output track is obvious. In order to reduce the predictive jitter problem, when the speed of the obstacle exceeds 0.2m/s, the obstacle is considered as a dynamic obstacle, and the dynamic obstacle is tracked, endowed with an age attribute and provided for a downstream algorithm. Here, the age attribute is a time length counted from the clustering timing. Clustering is a processing method for the acquired laser point cloud by perception fusion, and for example, laser point cloud clustering can be performed by a point cloud Euclidean clustering algorithm.
Fig. 3 is a schematic view of a dynamic obstacle collision avoidance process according to an embodiment of the present invention. The execution main body of the application is an on-board arithmetic unit, the application is applied to an unmanned vehicle, and as shown in figure 3, the application comprises the following steps:
Specifically, various vehicle-mounted sensors such as a laser radar, an ultrasonic radar, a camera and a vision module are mounted on a vehicle, sensing fusion is performed on various environmental information acquired by the vehicle-mounted sensors, for example, after point cloud data is removed from the ground, a point cloud on the ground presents a real obstacle, and after clustering is performed, static obstacle information and dynamic obstacle information are determined. Here, in order to reduce the jitter of the straight line predicted trajectory orientation information, the obstacle speed exceeding a preset speed threshold, such as 0.2m/s, is determined as a dynamic obstacle, otherwise, as a static obstacle.
The method is limited by sensor characteristics and algorithm boundaries, the position, speed and yaw rate information of the obstacle output by sensing fusion have certain deviation, if a probability track model is adopted to predict the obstacle track, large jitter occurs at the tail section of the predicted track, the consistency of downstream decision and motion planning is poor, and the safety cannot be guaranteed. In addition, the algorithm for predicting the obstacle trajectory by the probability trajectory model is high in complexity, long in calculation time consumption and not suitable for a vehicle-mounted platform with limited calculation resources.
The linear model prediction algorithm is low in complexity, the jitter of the tail section of the predicted track is small, and when high-frequency real-time prediction is conducted and the prediction duration is short, the real motion track of the obstacle can be basically met. Therefore, the method and the device adopt the linear model prediction, namely predicting the linear track of the dynamic obstacle in a future period of time according to the instantaneous speed of the dynamic obstacle.
Wherein step 120 comprises: firstly, determining the origin of a straight line prediction track according to the current position information of the dynamic barrier; secondly, determining the direction of a straight line predicted track according to the direction of the instantaneous speed of the dynamic barrier; and finally, determining the length of the straight line prediction track according to the product of the instantaneous speed of the dynamic obstacle and the prediction duration. That is, the direction of the linear track is the current speed direction, and the length S is the instantaneous speed V of the obstacleobjDetermined by the predicted time period t, i.e. S ═ Vobj×t。
And step 130, judging whether the straight line prediction track is intersected with the planned path or not according to the direction of the straight line prediction track, the length of the straight line prediction track and the planned path.
Specifically, in the driving process of the vehicle, the motion planning can plan a path in advance according to fusion positioning and perception fusion data, intersection judgment can be carried out according to the direction and the length of the linear prediction track and the planned path, and whether the linear prediction track intersects with the path or not is judged. When the intersections, step 140 is performed.
And 140, when the straight line prediction track intersects with the planned path, judging whether the straight line prediction track and the local planned path are in opposite directions or not according to the direction of the straight line prediction track and the local planned path.
Specifically, when the straight line predicted track intersects with the planned path, it is determined whether the straight line predicted track and the planned path are in the same direction or in the opposite direction, where the straight line predicted track and the planned path intersect with each other.
And 150, when the straight line predicted track and the planned path are not in opposite directions, determining the area attribute of the dynamic obstacle according to the current position information of the vehicle and the current position information of the dynamic obstacle.
Specifically, when the straight line predicted trajectory is in the same direction as the planned path, it may be determined in which region of the vehicle the dynamic obstacle is located, that is, the region attribute, where the region attribute includes the first region, the second region, and the third region, and then step 160 is performed. Referring to fig. 2, a vehicle coordinate system uses a midpoint position of a rear axle of a vehicle as an origin, a longitudinal direction of the vehicle is an x-axis direction, a transverse direction of the vehicle is a y-axis direction, and a vertical upward direction is a z-axis direction. The parking area and the deceleration area are divided according to the threat degree of the obstacles in different directions, for example, the obstacle in the parking area threatens the most in the areas except the deceleration area in the front and the rear, so that the vehicle needs to be parked; obstacles in the rear blind area should not be taken into consideration; a deceleration area is needed to be arranged between the blind area and the parking area for transition, and the shaking of the decision of whether to park or not caused by the shaking of the position of the obstacle is avoided. Thus, three areas around the vehicle are determined, which facilitates subsequent different speed planning of dynamic obstacles in different zones.
Further, when the straight line predicted track and the planned path are in opposite directions, collision points need to be determined according to the straight line predicted track information and the planned path; then determining a deceleration distance according to the current position information of the vehicle and a preset first acceleration threshold; and planning the distance between the deceleration distance and the collision point by a trapezoidal speed planning algorithm. The deceleration distance is a distance for the vehicle to travel in a deceleration manner starting from the current position by a preset first deceleration threshold. The preset first deceleration threshold is related to the type of the vehicle and the current speed information of the vehicle, for example, when the vehicle is a medium-sized vehicle, if the current speed information of the vehicle is 60km/h, the preset first acceleration threshold is-0.5 m/s, after each specific type of vehicle, a corresponding first acceleration threshold is preset, the corresponding relationship between the speed information and the first acceleration information can be stored in the motion plan in the form of a first comparison table, and when the planning is performed by a trapezoidal speed planning algorithm, after the current speed information of the vehicle is determined, the first acceleration threshold can be determined by searching the first comparison table.
Therefore, if the vehicle is a dynamic obstacle opposite to the planned path of the vehicle, the vehicle can be planned to reduce the speed to a lower speed in advance by a certain distance, and the vehicle can run at the lower speed at a constant speed, so that the collision is avoided.
Specifically, when the area attribute where the dynamic barrier is located is a first area, whether the age of the dynamic barrier is greater than a preset duration is judged, and when the age of the dynamic barrier is greater than the preset duration, a trapezoidal speed planning algorithm is called to plan parking; and when the area attribute of the dynamic barrier is a second area, judging whether the age of the dynamic barrier is greater than the preset duration, and calling a trapezoidal speed planning algorithm to plan the deceleration when the age of the dynamic barrier is greater than the preset duration.
Further, after step 120, the present application may further include: discretizing the straight line prediction track to obtain cell points of a plurality of virtual obstacles. Subsequently, the speed planning can be performed in the trapezoidal speed planning algorithm through the cell point of the virtual obstacle.
Referring to fig. 4, V represents the speed planned by the trapezoidal speed planning algorithm, and S represents the accumulated distance corresponding to the planned speed. The ladder planning algorithm is described below:
specifically, firstly, a pre-aiming distance is calculated according to speed information of the vehicle, a preset second acceleration threshold, a safety distance and a preset distance constant; secondly, judging whether the pre-aiming distance is intersected with the cell point of the virtual obstacle; and finally, when the pre-aiming distance is intersected with the cell point of the virtual obstacle, determining the cell point of the intersected virtual obstacle, and setting the speed of a waypoint in a safety distance before the cell point of the intersected virtual obstacle and a waypoint between the cell point of the intersected virtual obstacle and the end point of the planned path as 0. Then, smoothing processing can be carried out on the road points between the current position information of the vehicle and the safe distance of the cell points of the intersected virtual obstacles, so that a new planned path can be obtained by the motion planning and is output to the control.
Therefore, by the trapezoidal speed planning algorithm, when the cell point of the virtual obstacle is within the pre-aiming distance, the path of the waypoint between the waypoint before the safety distance of the cell point of the intersected virtual obstacle and the current position information of the vehicle can be planned, so that the vehicle can be planned to stop before reaching the safety distance of the cell point of the virtual obstacle.
The square of the speed information of the vehicle is divided by a preset second acceleration threshold value, and the safety distance and a preset distance constant are added to obtain the pre-aiming distance. The specific formula is as follows:
where Dist is the distance to aim in advance, v is the speed information of the vehicle, which can be obtained in real time by the vehicle-mounted sensor, a is the preset second, Safe is the Safe distance, and Offset is the set distance constant. The preset second acceleration is generally-0.2 to-1 m/s2The distance constant is usually the distance from the rear axle of the vehicle to the blind area part of the front suspension of the vehicle body, and is a set value related to the type of the vehicle.
When the cell point of the virtual barrier occupies the road in front of the vehicle in the parking area, the vehicle can be parked and waited in a safe distance, the vehicle can continue to run until the dynamic barrier is far away from the road and no collision risk exists, the original track of the dynamic barrier can not be interfered by the vehicle, the situation that the vehicle accelerates to rush through the original collision point can not occur, and the safety is effectively guaranteed.
Specifically, a control module in the vehicle-mounted computing unit generates control signals according to the planned speed, and sends the control signals, wherein the control signals comprise steering control signals and torque control signals, the steering of the vehicle is controlled through the steering control signals, the speed of the vehicle is controlled through the torque control signals, and the control signals are sent to the actuator, so that the actuator controls the steering of the vehicle according to the steering control signals, and controls the speed of the vehicle according to the torque control signals.
The present application is further described below in conjunction with fig. 3 and 5.
After the vehicle is electrified, the vehicle-mounted sensor, the vehicle-mounted arithmetic unit and the actuator are started to start working.
Referring to the detailed description in step 120, the information of the predicted straight line trajectory may be obtained through the straight line prediction model, and whether the predicted straight line trajectory intersects with the planned route of the own vehicle is determined, and different steps are respectively performed for intersection or non-intersection.
And step 204, planning deceleration in advance within the deceleration distance.
When the deceleration is planned within the deceleration distance in advance, planning can be performed according to a trapezoidal speed planning algorithm.
The regional attributes comprise a parking area, a deceleration area and a blind area. When the dynamic obstacle is in the parking area, step 206 is executed, when the dynamic obstacle is in the deceleration area, step 207 is executed, and when the dynamic obstacle is in the blind area, step 210 is executed.
And step 206, judging whether the age of the dynamic obstacle is more than t seconds when the dynamic obstacle is in the parking area.
Wherein t seconds is a preset duration, when the vehicle is in a parking area and the age of the obstacle is greater than t seconds, step 208 is executed, and when the age of the obstacle is not greater than t seconds, step 210 is executed.
And step 208, planning parking.
And step 211, planning a path according to a trapezoidal speed planning algorithm when planning parking or planning deceleration.
And step 212, ending.
By applying the dynamic barrier anti-collision method provided by the first embodiment of the invention, the following technical effects are achieved:
(1) according to the method, the trajectory of the dynamic barrier is predicted by using the linear prediction model, the predicted trajectory is discretized into trajectory points which serve as cell points of the virtual barrier, the barrier prediction model is simplified, the time domain solving problem is simplified into a space anti-collision problem, and the safety problem of anti-collision failure caused by the jitter of collision time does not exist.
(2) The linear prediction model is low in algorithm complexity and suitable for the vehicle-mounted computing platform with limited computing resources.
(3) The area division method and the obstacle age size method effectively filter the dynamic obstacles in the non-dangerous area, and reduce the false triggering of the anti-collision function.
(4) In this application, when taking place to interfere the orbit of traveling of dynamic barriers such as pedestrian or vehicle from the track of car, can park and wait until the barrier is kept away from to just not continuing to travel at the risk of not colliding, effectively guarantee the security.
The second embodiment of the invention provides equipment which comprises a memory and a processor, wherein the memory is used for storing programs, and the memory can be connected with the processor through a bus. The memory may be a non-volatile memory such as a hard disk drive and a flash memory, in which a software program and a device driver are stored. The software program is capable of performing various functions of the above-described methods provided by embodiments of the present invention; the device drivers may be network and interface drivers. The processor is used for executing a software program, and the software program can realize the method provided by the first embodiment of the invention when being executed.
A third embodiment of the present invention provides a computer program product including instructions, which, when the computer program product runs on a computer, causes the computer to execute the method provided in the first embodiment of the present invention.
The fourth embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the method provided in the first embodiment of the present invention is implemented.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied in hardware, a software module executed by a processor, or a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
The above embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, it should be understood that the above embodiments are merely exemplary embodiments of the present invention and are not intended to limit the scope of the present invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method of dynamic obstacle collision avoidance, the method comprising:
acquiring obstacle information; the obstacle information includes dynamic obstacle information including instantaneous speed and current position information of a dynamic obstacle;
predicting to obtain linear predicted track information of the dynamic barrier within a preset time length according to the instantaneous speed and the current position information of the dynamic barrier; the straight line prediction track information comprises the direction and the length of the straight line prediction track;
judging whether the straight line prediction track is intersected with the planned path or not according to the direction of the straight line prediction track, the length of the straight line prediction track and the planned path;
when the straight line prediction track intersects with the planned path, judging whether the straight line prediction track and the planned path are in opposite directions or not according to the direction of the straight line prediction track and the planned path;
when the straight line prediction track and the planned path are not in opposite directions, determining the area attribute of the dynamic obstacle according to the current position information of the vehicle and the current position information of the dynamic obstacle;
performing speed planning through a trapezoidal speed planning algorithm according to the region attribute of the dynamic obstacle and the age of the dynamic obstacle; the age of the dynamic barrier is the time length from the clustering moment to time;
and generating a control signal according to the planned speed, and sending the control signal to an actuator for execution.
2. The method according to claim 1, wherein the predicting the linear predicted trajectory information of the dynamic obstacle within a preset time period according to the instantaneous speed and the current position information of the dynamic obstacle specifically comprises:
determining the origin of the straight line prediction track according to the current position information of the dynamic barrier;
determining the direction of the straight line predicted track according to the direction of the instantaneous speed of the dynamic obstacle;
and determining the length of the straight line prediction track according to the product of the instantaneous speed of the dynamic obstacle and the prediction duration.
3. The method of claim 1, further comprising:
when the straight line prediction track and the local planning path are in non-opposite directions, determining a collision point according to the straight line prediction track information and the planning path;
determining a deceleration distance according to the current position information of the vehicle and a preset first acceleration threshold; the deceleration distance is a distance for the vehicle to decelerate from the current position by a preset first acceleration threshold value;
and planning the distance between the deceleration distance and the collision point by a trapezoidal speed planning algorithm.
4. The method according to claim 1, wherein the speed planning according to the region attribute where the dynamic obstacle is located and the age of the dynamic obstacle specifically comprises:
when the area attribute of the dynamic barrier is a first area, judging whether the age of the dynamic barrier is greater than a preset time length, and when the age of the dynamic barrier is greater than the preset time length, calling a trapezoidal speed planning algorithm to plan parking;
and when the area attribute of the dynamic barrier is a second area, judging whether the age of the dynamic barrier is greater than a preset time length, and calling a trapezoidal speed planning algorithm to plan deceleration when the age of the dynamic barrier is greater than the preset time length.
5. The method according to claim 1, wherein after the straight-line predicted trajectory information of the dynamic obstacle within a preset time length is predicted according to the instantaneous speed and the current position information of the dynamic obstacle, the method further comprises:
discretizing the straight line prediction track to obtain cell points of a plurality of virtual obstacles; the cell point of the virtual obstacle is a contour point of the dynamic obstacle on the straight line prediction track.
6. The method according to claim 5, wherein the trapezoidal velocity planning algorithm is specifically:
calculating a pre-aiming distance according to the speed information of the vehicle, a preset second acceleration threshold, a safety distance and a preset distance constant;
judging whether the pre-aiming distance is intersected with the cell point of the virtual obstacle;
when the pre-aiming distance is intersected with the cell point of the virtual obstacle, the cell point of the intersected virtual obstacle is determined, and the speed of a road point between a road point in a safety distance before the intersected cell point of the virtual obstacle and the end point of a planned path of the intersected cell point of the virtual obstacle is set to be 0.
7. The method according to claim 6, wherein the calculating the pre-aiming distance according to the speed information of the vehicle, a preset second acceleration threshold, the safe distance and a preset distance constant specifically comprises:
and dividing the square of the speed information of the vehicle by a preset second acceleration threshold value, and adding the safety distance and a preset distance constant to obtain the pre-aiming distance.
8. An apparatus, comprising a memory for storing a program and a processor for performing the method of any of claims 1-7.
9. A computer program product comprising instructions for causing a computer to perform the method of any one of claims 1 to 7 when the computer program product is run on a computer.
10. A computer-readable storage medium, characterized in that a computer program is stored on the computer-readable storage medium, which computer program, when being executed by a processor, is adapted to carry out the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010598009.2A CN111650945B (en) | 2020-06-28 | 2020-06-28 | Dynamic obstacle anticollision method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010598009.2A CN111650945B (en) | 2020-06-28 | 2020-06-28 | Dynamic obstacle anticollision method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111650945A true CN111650945A (en) | 2020-09-11 |
| CN111650945B CN111650945B (en) | 2023-10-24 |
Family
ID=72343134
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010598009.2A Active CN111650945B (en) | 2020-06-28 | 2020-06-28 | Dynamic obstacle anticollision method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111650945B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112327888A (en) * | 2021-01-07 | 2021-02-05 | 中智行科技有限公司 | Path planning method and device, electronic equipment and storage medium |
| CN112631276A (en) * | 2020-12-03 | 2021-04-09 | 长沙行深智能科技有限公司 | Unmanned vehicle dynamic obstacle decision method, system, medium and equipment |
| CN113110413A (en) * | 2021-03-10 | 2021-07-13 | 成都永奉科技有限公司 | Following robot, following control method and following control system |
| CN113156947A (en) * | 2021-04-14 | 2021-07-23 | 武汉理工大学 | Method for planning path of ship in dynamic environment |
| CN113867365A (en) * | 2021-10-28 | 2021-12-31 | 广州文远知行科技有限公司 | Method and device for determining variable acceleration of unmanned vehicle and related equipment |
| CN114323044A (en) * | 2021-12-16 | 2022-04-12 | 中汽创智科技有限公司 | Path planning method, device, equipment and storage medium |
| CN114692289A (en) * | 2020-12-31 | 2022-07-01 | 华为技术有限公司 | Automatic driving algorithm testing method and related equipment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017165687A1 (en) * | 2016-03-24 | 2017-09-28 | Honda Motor Co., Ltd. | System and method for trajectory planning for unexpected pedestrians |
| CN109712421A (en) * | 2019-02-22 | 2019-05-03 | 百度在线网络技术（北京）有限公司 | The speed planning method, apparatus and storage medium of automatic driving vehicle |
| CN110389581A (en) * | 2018-04-17 | 2019-10-29 | 百度（美国）有限责任公司 | Method for the prediction locus for automatic driving vehicle dyspoiesis object |
| US20190359205A1 (en) * | 2018-05-24 | 2019-11-28 | Baidu Usa Llc | Determining driving paths for autonomous driving that avoid moving obstacles |
| CN111289008A (en) * | 2020-04-28 | 2020-06-16 | 南京维思科汽车科技有限公司 | Local path planning algorithm for unmanned vehicle |
-
2020
- 2020-06-28 CN CN202010598009.2A patent/CN111650945B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017165687A1 (en) * | 2016-03-24 | 2017-09-28 | Honda Motor Co., Ltd. | System and method for trajectory planning for unexpected pedestrians |
| CN110389581A (en) * | 2018-04-17 | 2019-10-29 | 百度（美国）有限责任公司 | Method for the prediction locus for automatic driving vehicle dyspoiesis object |
| US20190359205A1 (en) * | 2018-05-24 | 2019-11-28 | Baidu Usa Llc | Determining driving paths for autonomous driving that avoid moving obstacles |
| CN109712421A (en) * | 2019-02-22 | 2019-05-03 | 百度在线网络技术（北京）有限公司 | The speed planning method, apparatus and storage medium of automatic driving vehicle |
| CN111289008A (en) * | 2020-04-28 | 2020-06-16 | 南京维思科汽车科技有限公司 | Local path planning algorithm for unmanned vehicle |
Non-Patent Citations (2)
| Title |
|---|
| 曹波 等: "基于梯形规划曲线的智能车速度规划算法研究", 《计算机科学》 * |
| 段建民 等: "基于中间速度的智能车辆梯形速度规划方法", 《计算机工程》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112631276A (en) * | 2020-12-03 | 2021-04-09 | 长沙行深智能科技有限公司 | Unmanned vehicle dynamic obstacle decision method, system, medium and equipment |
| CN114692289A (en) * | 2020-12-31 | 2022-07-01 | 华为技术有限公司 | Automatic driving algorithm testing method and related equipment |
| CN112327888A (en) * | 2021-01-07 | 2021-02-05 | 中智行科技有限公司 | Path planning method and device, electronic equipment and storage medium |
| CN113110413A (en) * | 2021-03-10 | 2021-07-13 | 成都永奉科技有限公司 | Following robot, following control method and following control system |
| CN113156947A (en) * | 2021-04-14 | 2021-07-23 | 武汉理工大学 | Method for planning path of ship in dynamic environment |
| CN113156947B (en) * | 2021-04-14 | 2024-03-08 | 武汉理工大学 | Method for planning path of ship in dynamic environment |
| CN113867365A (en) * | 2021-10-28 | 2021-12-31 | 广州文远知行科技有限公司 | Method and device for determining variable acceleration of unmanned vehicle and related equipment |
| CN113867365B (en) * | 2021-10-28 | 2024-05-14 | 广州文远知行科技有限公司 | Method and device for determining variable acceleration of unmanned vehicle and related equipment |
| CN114323044A (en) * | 2021-12-16 | 2022-04-12 | 中汽创智科技有限公司 | Path planning method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111650945B (en) | 2023-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111650945B (en) | Dynamic obstacle anticollision method | |
| US11809194B2 (en) | Target abnormality determination device | |
| JP7295012B2 (en) | Vehicle control system and vehicle control method | |
| US11267474B2 (en) | Vehicle control device, vehicle control method, and storage medium | |
| US20190217861A1 (en) | Travel control device and travel control method | |
| JP7234103B2 (en) | Vehicle control device and vehicle control system | |
| CN112384419B (en) | Vehicle driving support control device, vehicle driving support system, and vehicle driving support control method | |
| JP6838525B2 (en) | Vehicle control device | |
| JP6641583B2 (en) | Vehicle control device, vehicle control method, and program | |
| JP6633041B2 (en) | Vehicle, travel control device, and travel control method | |
| CN113844445B (en) | Automatic emergency braking system and method for vehicle based on prediction reference line coordinate system | |
| US20200290624A1 (en) | Vehicle control device, vehicle control method, and storage medium | |
| CN111661055A (en) | Lane changing control method and system for automatic driving vehicle | |
| US20230166764A1 (en) | Method and system for impact-based operation of an autonomous agent | |
| CN114126940A (en) | Electronic control device | |
| JP2022109894A (en) | Active lane change for autonomous vehicle | |
| JP2022060076A (en) | Vehicle travel control device | |
| CN112092805A (en) | Integrated control method and system for collision avoidance and collision damage reduction of intelligent vehicle | |
| JP6838769B2 (en) | Surrounding environment recognition device, display control device | |
| US10801458B2 (en) | Methods for controlling stopping and starting of an engine | |
| CN115675452A (en) | Vehicle brake control method, device, equipment and computer readable storage medium | |
| US11731660B2 (en) | Automatic running vehicle and operation management device for automatic running vehicle | |
| CN115848363A (en) | Collision avoidance and loss reduction trajectory planning method | |
| JP7446216B2 (en) | Vehicle control device | |
| JP7400911B1 (en) | automatic driving device |
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 | ||
| CB02 | Change of applicant information |
Address after: B4-006, maker Plaza, 338 East Street, Huilongguan town, Changping District, Beijing 100096 Applicant after: Beijing Idriverplus Technology Co.,Ltd. Address before: B4-006, maker Plaza, 338 East Street, Huilongguan town, Changping District, Beijing 100096 Applicant before: Beijing Idriverplus Technology Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |