CN112631276A - Unmanned vehicle dynamic obstacle decision method, system, medium and equipment - Google Patents
Unmanned vehicle dynamic obstacle decision method, system, medium and equipment Download PDFInfo
- Publication number
- CN112631276A CN112631276A CN202011397727.XA CN202011397727A CN112631276A CN 112631276 A CN112631276 A CN 112631276A CN 202011397727 A CN202011397727 A CN 202011397727A CN 112631276 A CN112631276 A CN 112631276A
- Authority
- CN
- China
- Prior art keywords
- unmanned vehicle
- time
- dynamic obstacle
- intersection
- dynamic
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000004888 barrier function Effects 0.000 claims abstract description 23
- 230000001133 acceleration Effects 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 10
- 230000006399 behavior Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 15
- 230000000875 corresponding effect Effects 0.000 claims description 11
- 230000007613 environmental effect Effects 0.000 claims description 6
- 208000012661 Dyskinesia Diseases 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 230000008447 perception Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000004927 fusion Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000007790 scraping Methods 0.000 description 1
- 239000007787 solid Substances 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
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0234—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using optical markers or beacons
- G05D1/0236—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using optical markers or beacons 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
- G05D1/0212—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
- G05D1/0238—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, 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
-
- 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
- G05D1/02—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
-
- 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
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
- G05D1/0278—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle using satellite positioning signals, e.g. GPS
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Electromagnetism (AREA)
- Optics & Photonics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a method, a system, a medium and equipment for deciding a dynamic obstacle of an unmanned vehicle, belongs to the technical field of unmanned vehicle obstacle avoidance, and is used for solving the problems that the current unmanned vehicle has low prediction precision on the dynamic obstacle behavior and greatly influences the working efficiency. The method comprises the following steps: 1) creating a map of the environment where the unmanned vehicle is located, and drawing environment information on the map; 2) acquiring pose information of the unmanned vehicle on a map, and map environment and dynamic obstacle information around the unmanned vehicle; 3) predicting the motion track of the dynamic obstacle in a period of time; 4) judging whether the planned track of the unmanned vehicle and the motion track of the dynamic obstacle have an intersection point; if the intersection exists, entering the step 5); 5) and comparing the time of the dynamic barrier reaching the intersection with the time of the unmanned vehicle reaching the intersection, and if the time difference between the two times is less than the safe time, executing acceleration or deceleration processing to avoid collision. The invention has the advantages of safely avoiding dynamic obstacles in a complex environment, ensuring the working efficiency and the like.
Description
Technical Field
The invention mainly relates to the technical field of unmanned vehicles, in particular to a method, a system, a medium and equipment for deciding dynamic obstacles of an unmanned vehicle.
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. The related patents for obstacle avoidance currently include:
for example, CN111650945A dynamic obstacle collision avoidance method, which calculates the safe speed without collision according to whether the movement tracks of the target and the unmanned vehicle intersect, has the following disadvantages:
1. the prediction result of the dynamic obstacle is instantaneous speed, a certain time length and a simple linear track, and the accuracy of the prediction result is low and incomplete. Without considering the high-precision map information, the map information is useful for predicting the behavior of a dynamic obstacle, such as a left turn, a right turn, or the like.
2. Without considering the target class attributes and behavior, the identification of dynamic obstacles, such as vehicles, pedestrians, etc., is not classified.
3. The efficiency of the host vehicle is not considered in consideration of only safety. The information of the 1 st point and the 2 nd point is lacked, the same strategy is adopted for treating the dyskinesia, and if the dyskinesia is treated in a complex traffic environment or an environment with large pedestrian volume, the working efficiency can be greatly reduced by frequent deceleration and parking.
4. The behavior of the host vehicle is not decision classified. The speed is limited only according to the safe distance, and the normal running of other vehicles can be influenced by random parking in a complex road environment.
5. Only the possibility of collision in the space within a preset time period is considered, and the time difference is not considered. The tracks are intersected, only the possibility of collision exists in the preset time, the situation that the collision is possible is judged if the preset time is too short, the situation that the collision is not safe is avoided if the preset time is too long, the situation that the unmanned vehicle stops due to the fact that the distance of the dynamic obstacle is long is possible, the time quantum is added, and the position relation at the same time point is considered to judge whether the collision exists or not.
In addition, the problems of points 1 to 4 also exist in the dynamic obstacle avoidance method based on collision detection, such as CN109960261A and CN 109960261B. CN111703420A is a method for collision avoidance of unmanned vehicles, which also has the problems of points 1 to 5.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: aiming at the problems in the prior art, the invention provides a method, a system, a medium and equipment for deciding the dynamic obstacle of the unmanned vehicle, which can safely avoid the dynamic obstacle and ensure the working efficiency in a complex environment.
In order to solve the technical problems, the technical scheme provided by the invention is as follows:
a decision-making method for unmanned vehicle dynamic barrier comprises the following steps:
1) creating a map of the environment where the unmanned vehicle is located, and drawing environment information on the map;
2) acquiring pose information of the unmanned vehicle on a map, and map environment and dynamic obstacle information around the unmanned vehicle;
3) predicting the motion track of the dynamic obstacle in a period of time;
4) judging whether the planned track of the unmanned vehicle and the predicted motion track of the dynamic obstacle have an intersection point; if the intersection exists, entering the step 5);
5) and comparing the time of the dynamic barrier reaching the intersection with the time of the unmanned vehicle reaching the intersection, and if the time difference between the two times is less than the safe time, executing acceleration or deceleration processing to avoid collision.
As a further improvement of the above technical solution:
in the step 3), the movement track of the dynamic barrier in a period of time is predicted according to the position, the instantaneous speed and the environmental information on the map of the dynamic barrier; the motion trail comprises x and y coordinates and corresponding time t, the motion trail is predicted at a constant speed, the starting time is 0, and the ending time is t.
In the step 5), generating a predicted track with a time stamp for the unmanned vehicle, and generating a group of track point sequences with positions x, y and time points by uniform acceleration with the current speed as an initial speed and the planned path speed as an expected speed to form a planned track of the unmanned vehicle; and obtaining the time of the dynamic obstacle reaching the intersection point through the predicted motion track of the dynamic obstacle, and obtaining the time of the unmanned vehicle reaching the intersection point through the planned track of the unmanned vehicle.
In step 1), the environment information comprises one or more of a lane, an intersection, a traffic light and a sidewalk.
In step 4), the body contour of the unmanned vehicle and the contour of the dynamic obstacle are considered when judging whether there is an intersection.
In step 5), the corresponding security policy is simultaneously selected when the acceleration or deceleration process is performed.
The security policy specifically includes: in the step 3), when the track of the dynamic obstacle is predicted, the behaviors of the dynamic obstacle are classified according to the attribute and the speed of the dynamic obstacle; and in step 5), different obstacle avoidance strategies are adopted according to the motion trail and the type of the dynamic obstacle.
In the step 5), if a plurality of predicted tracks exist in the dynamic obstacle, the time of reaching the intersection point in all the predicted tracks is compared with the time of reaching the intersection point of the unmanned vehicle, different acceleration and deceleration instructions and safety strategies are generated according to the comparison result, and the minimum speed and the safest safety strategy are selected to control the unmanned vehicle.
The invention also discloses a system for deciding the dynamic obstacle of the unmanned vehicle, which comprises the following components:
the system comprises a first module, a second module and a third module, wherein the first module is used for creating a map of the environment where the unmanned vehicle is located and drawing environment information on the map;
the second module is used for acquiring pose information of the unmanned vehicle on a map, and surrounding map environment and dynamic obstacle information;
a third module for predicting a motion trajectory of the dynamic barrier over a period of time;
the fourth module is used for judging whether the planned track of the unmanned vehicle and the predicted motion track of the dynamic obstacle have intersection points; if the intersection exists, corresponding actions are executed through a fifth module;
and the fifth module is used for comparing the time of the dynamic barrier reaching the intersection with the time of the unmanned vehicle reaching the intersection, and if the time difference between the dynamic barrier reaching the intersection and the unmanned vehicle reaching the intersection is less than the safe time, executing acceleration or deceleration processing to avoid collision.
The invention further discloses a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method for determining a dynamic obstacle of an unmanned vehicle as described above.
The invention also discloses computer equipment which comprises a memory and a processor, wherein the memory is stored with a computer program, and the computer program executes the steps of the unmanned vehicle dynamic obstacle decision method when being executed by the processor.
Compared with the prior art, the invention has the advantages that:
after a high-precision map is constructed, the movement track of the high-precision map is predicted by using map information and the perception result of the dyskinesia, so that the prediction result accords with the actual map environment and is more accurate and comprehensive; firstly, judging whether dynamic obstacles and unmanned vehicles are intersected with each other or not within a period of time, and primarily screening targets with possible collision; and then adding time quantum, and judging whether collision occurs or not by considering the position relation at the same time point, so that the rapid and efficient collision detection can be realized, a smooth speed curve of the unmanned vehicle can be ensured, and the working efficiency is not excessively reduced.
The invention predicts the action track of the dynamic obstacle and classifies the dynamic obstacle, such as pedestrian crossing, vehicle overtaking, vehicle intersection turning, opposite direction road occupation and the like, different types have different actions, the obstacle avoidance grade is distinguished according to the task and the environment, and different obstacle avoidance strategies are adopted after distinguishing the action and the type of the target, thereby being beneficial to improving the task efficiency of the unmanned vehicle.
The invention carries out decision classification on the behavior of the unmanned vehicle, and improves the working efficiency and the smooth movement smoothness of the unmanned vehicle on the premise of ensuring the safety; the speed is limited only according to the safe distance, normal driving of other vehicles can be influenced by random parking in a complex road environment, stable following, side-by-side giving, accelerated overtaking and the like can be realized by adding decision information, the working efficiency of the unmanned vehicle can be improved, and driving is smoother.
Drawings
FIG. 1 is a flow chart of an embodiment of the method of the present invention.
Detailed Description
The invention is further described below with reference to the figures and the specific embodiments of the description.
As shown in fig. 1, the method for determining a dynamic obstacle of an unmanned vehicle in this embodiment includes the steps of:
1) creating a high-precision map of the environment where the unmanned vehicle is located, and drawing environment information on the map;
2) acquiring pose information of the unmanned vehicle on a high-precision map, and map environment and dynamic obstacle information around the unmanned vehicle;
3) predicting the motion track of the dynamic obstacle in a period of time;
4) judging whether the planned track of the unmanned vehicle and the predicted track of the dynamic obstacle have an intersection point; if the intersection exists, entering the step 5);
5) and comparing the time of the dynamic barrier reaching the intersection with the time of the unmanned vehicle reaching the intersection, and if the time difference between the two times is less than the safety time, selecting a corresponding safety strategy to execute acceleration or deceleration processing so as to avoid collision.
According to the invention, after the high-precision map is constructed, the movement track of the high-precision map is predicted by using the map information and the dyskinesia perception result, so that the prediction result conforms to the actual map environment, and is more accurate and comprehensive.
Firstly, judging whether dynamic obstacles and unmanned vehicles intersect in track within a period of time, and primarily screening targets with possible collision; and then adding time quantum, and judging whether collision occurs or not by considering the position relation at the same time point, so that the rapid and efficient collision detection can be realized, a smooth speed curve of the unmanned vehicle can be ensured, and the working efficiency is not excessively reduced.
In a specific embodiment, in step 1), a high-precision map of the unmanned vehicle task area is created by means of multi-sensor fusion, and environmental information in the area is marked, especially the intersection area. Specifically, the environmental information further includes one or more of a lane, an intersection, a traffic light, and a sidewalk.
In a specific embodiment, in step 4), when determining whether there is an intersection, the contour of the vehicle body and the contour of the dynamic obstacle are considered to avoid occurrence of vehicle body scraping and the like.
In a specific embodiment, in step 3), the motion track of the dynamic obstacle in a period of time is predicted according to the position, the instantaneous speed and the environmental information on the map of the dynamic obstacle; the motion trail comprises x and y coordinates and corresponding time t, wherein the starting time is 0 and the ending time is t by uniform speed prediction. Meanwhile, the behaviors of the dynamic barrier can be classified according to the attribute and the speed of the dynamic barrier, including but not limited to pedestrian crossing, vehicle overtaking, vehicle intersection turning, opposite direction road occupation and the like.
In a specific embodiment, in step 5), generating a planned track with a time stamp for the unmanned vehicle, taking the current speed as the initial speed and the planned path speed as the expected speed, and generating a group of track point sequences with positions x and y and time points by uniform acceleration to form the planned track of the unmanned vehicle; and obtaining the time of the dynamic obstacle reaching the intersection point through the motion trail of the dynamic obstacle, and obtaining the time of the unmanned vehicle reaching the intersection point through the planned path of the unmanned vehicle.
In a specific embodiment, in step 5), when performing the acceleration or deceleration processing, a corresponding security policy is selected at the same time, wherein the security policy is stable following, side-by-side yielding, acceleration overtaking, and the like. Specifically, the dynamic obstacles are classified while behavior tracks are predicted, different classes of behaviors such as pedestrian crossing, vehicle overtaking, vehicle intersection turning, opposite direction road occupation and the like are provided, obstacle avoidance levels are distinguished according to task types and map environments, different obstacle avoidance strategies are adopted after behavior and classes of targets are distinguished, and therefore task efficiency of unmanned vehicles is improved.
In addition, decision classification is carried out on the behavior of the unmanned vehicle, and the working efficiency and the movement smoothness of the unmanned vehicle are improved on the premise of ensuring safety. The speed is limited only according to the safe distance, normal driving of other vehicles can be influenced by random parking in a complex road environment, stable following, side-by-side giving, accelerated overtaking and the like can be realized by adding decision information, the working efficiency of the unmanned vehicle can be improved, and driving is smoother.
In a specific embodiment, on the basis of a high-precision map and high-precision positioning, the movement track of the dynamic obstacle is predicted, the same dynamic obstacle can have a plurality of behavior tracks, and possible behavior tracks of the movement obstacle are comprehensively estimated. Therefore, in the step 5), if a plurality of dynamic obstacles with intersections exist, the time of all the dynamic obstacles reaching the intersections is compared with the time of the unmanned vehicle reaching the intersections, different acceleration and deceleration commands and safety strategies are generated according to the comparison result, and the minimum speed and the safest safety strategy are selected to control the unmanned vehicle. Specifically, different safety strategies are adopted for dynamic barriers according to a high-precision map, task attributes and target behaviors, and decision classification is carried out on the behaviors of the unmanned vehicle. The decision information comprises and is not limited to stable following, side-by-side line giving, accelerated overtaking and the like, so that the working efficiency of the unmanned vehicle is improved, and the unmanned vehicle can drive more smoothly.
The invention also discloses a system for deciding the dynamic obstacle of the unmanned vehicle, which comprises the following components:
the system comprises a first module, a second module and a third module, wherein the first module is used for creating a map of the environment where the unmanned vehicle is located and drawing environment information on the map;
the second module is used for acquiring pose information of the unmanned vehicle on a map, and surrounding map environment and dynamic obstacle information;
a third module for predicting a motion trajectory of the dynamic barrier over a period of time;
the fourth module is used for judging whether the planned track of the unmanned vehicle and the motion track of the dynamic obstacle have an intersection point; if the intersection exists, corresponding actions are executed through a fifth module;
and the fifth module is used for comparing the time of the dynamic barrier reaching the intersection with the time of the unmanned vehicle reaching the intersection, and if the time difference between the dynamic barrier reaching the intersection and the unmanned vehicle reaching the intersection is less than the safe time, executing acceleration or deceleration processing to avoid collision.
The unmanned vehicle dynamic obstacle decision-making system is used for executing the method, and has the advantages of the method.
The invention further discloses a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method for unmanned vehicle dynamic obstacle decision-making as described above. The invention also discloses computer equipment which comprises a memory and a processor, wherein the memory is stored with a computer program, and the computer program executes the steps of the unmanned vehicle dynamic obstacle decision method when being executed by the processor. All or part of the flow of the method of the embodiments may be implemented by a computer program, which may be stored in a computer-readable storage medium and executed by a processor, to implement the steps of the embodiments of the methods. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like. The memory may be used to store computer programs and/or modules, and the processor may perform various functions by executing or executing the computer programs and/or modules stored in the memory, as well as by invoking data stored in the memory. The memory may include high speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The invention will be described more fully hereinafter with reference to a specific embodiment:
firstly, a high-precision map building module builds a high-precision map of the environment where the unmanned vehicle is located, and draws environment information such as lanes, intersections, traffic lights, sidewalks and the like on the map;
the high-precision positioning module obtains pose information of the unmanned vehicle in a map through sensors such as a GPS (global positioning system), an IMU (inertial measurement unit) and the like;
the perception fusion module obtains surrounding environment and obstacle information through sensors such as a laser radar and a camera, wherein the obstacle information comprises dynamic obstacles;
the behavior prediction module predicts the movement track of the dynamic obstacle within a period of time according to the position, the instantaneous speed, the lane intersection of the high-precision map and other environmental information of the dynamic obstacle; the motion trail comprises x and y coordinates and corresponding time t, the motion trail is predicted at a constant speed, the starting time is 0, and the ending time is t;
then, the local path planning module judges whether the planned track has an intersection point with the motion track of the dynamic obstacle or not on the basis of the current path track and speed of the unmanned vehicle, and if the planned track has the intersection point, the next step is carried out; wherein the vehicle body contour and the contour of the dynamic obstacle are considered when the intersection is judged;
generating a planned path with a timestamp for the self-vehicle, and generating a group of track point sequences with positions x and y and time points by uniform acceleration by taking the current speed as the initial speed and the planned path speed as the expected speed;
the safe collision time is limited according to the type, the outline size, the speed and the like of the dynamic barrier, namely the self-vehicle can reach the collision point after the dynamic barrier passes for a long time, or the dynamic barrier reaches the collision point after the self-vehicle passes for a long time;
under the limit of safe time, firstly calculating the position of the vehicle when the movement obstacle reaches a collision point, and if the remaining time is more than the safe time, needing no speed reduction processing; if the remaining time is less than the safe time, calculating the expected deceleration speed, and selecting different decisions;
the control module correspondingly generates a deceleration command, and the executing mechanism controls the braking system to reduce or increase the speed of the vehicle, thereby avoiding collision.
The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above-mentioned embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may be made by those skilled in the art without departing from the principle of the invention.
Claims (11)
1. A decision-making method for unmanned vehicle dynamic barrier is characterized by comprising the following steps:
1) creating a map of the environment where the unmanned vehicle is located, and drawing environment information on the map;
2) acquiring pose information of the unmanned vehicle on a map, and map environment and dynamic obstacle information around the unmanned vehicle;
3) predicting the motion track of the dynamic obstacle in a period of time;
4) judging whether the planned track of the unmanned vehicle and the motion track of the dynamic obstacle have an intersection point; if the intersection exists, entering the step 5);
5) and comparing the time of the dynamic barrier reaching the intersection with the time of the unmanned vehicle reaching the intersection, and if the time difference between the two times is less than the safe time, executing acceleration or deceleration processing to avoid collision.
2. The unmanned vehicle dynamic obstacle decision method according to claim 1, wherein in step 3), a motion trajectory of the dynamic obstacle within a period of time is predicted according to a position, an instantaneous speed of the dynamic obstacle, and environmental information on a map; the motion trail comprises x and y coordinates and corresponding time t, the motion trail is predicted at a constant speed, the starting time is 0, and the ending time is t.
3. The unmanned vehicle dynamic obstacle decision method according to claim 2, wherein in step 5), a predicted track with a time stamp is generated for the unmanned vehicle, a current speed is taken as an initial speed, a planned path speed is taken as an expected speed, and a group of track point sequences with positions x, y and time points are generated with uniform acceleration to form a planned track of the unmanned vehicle; and obtaining the time of the dynamic obstacle reaching the intersection point through the predicted motion track of the dynamic obstacle, and obtaining the time of the unmanned vehicle reaching the intersection point through the planned track of the unmanned vehicle.
4. The unmanned vehicle dynamic obstacle decision method according to any one of claims 1-3, wherein in step 1), the environment information comprises one or more of a lane, an intersection, a traffic light, and a sidewalk.
5. The unmanned vehicle dynamic obstacle decision method according to any one of claims 1 to 3, wherein in step 4), when determining whether there is an intersection, a body contour of the unmanned vehicle and a contour of the dynamic obstacle are considered.
6. The unmanned vehicle dynamic obstacle decision method according to any one of claims 1 to 3, wherein in step 5), when performing acceleration or deceleration processing, a corresponding safety policy is selected at the same time.
7. The unmanned vehicle dynamic obstacle decision-making method according to claim 6, wherein the safety policy is specifically: in the step 3), when the track of the dynamic obstacle is predicted, the behaviors of the dynamic obstacle are classified according to the attribute and the speed of the dynamic obstacle; and in step 5), different obstacle avoidance strategies are adopted according to the predicted track and the type of the dynamic obstacle.
8. The unmanned vehicle dynamic obstacle decision method according to any one of claims 1 to 3, wherein in step 5), if the dynamic obstacle has a plurality of predicted tracks, the time of reaching the intersection point in all the predicted tracks is compared with the time of reaching the intersection point by the unmanned vehicle, different acceleration and deceleration commands and safety strategies are generated according to the comparison result, and the unmanned vehicle is controlled by selecting the minimum speed and the safest safety strategy.
9. An unmanned vehicle dynamic obstacle decision system, comprising:
the system comprises a first module, a second module and a third module, wherein the first module is used for creating a map of the environment where the unmanned vehicle is located and drawing environment information on the map;
the second module is used for acquiring pose information of the unmanned vehicle on a map, and surrounding map environment and dynamic obstacle information;
a third module for predicting a motion trajectory of the dynamic barrier over a period of time;
the fourth module is used for judging whether the planned track of the unmanned vehicle and the predicted motion track of the dynamic obstacle have intersection points; if the intersection exists, corresponding actions are executed through a fifth module;
and the fifth module is used for comparing the time of the dynamic barrier reaching the intersection with the time of the unmanned vehicle reaching the intersection, and if the time difference between the dynamic barrier reaching the intersection and the unmanned vehicle reaching the intersection is less than the safe time, executing acceleration or deceleration processing to avoid collision.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for unmanned vehicle dynamic obstacle decision making according to any one of claims 1-8.
11. A computer arrangement comprising a memory and a processor, the memory having stored thereon a computer program, characterized in that the computer program, when executed by the processor, performs the steps of the method for dynamic obstacle decision-making for an unmanned vehicle according to any of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011397727.XA CN112631276A (en) | 2020-12-03 | 2020-12-03 | Unmanned vehicle dynamic obstacle decision method, system, medium and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011397727.XA CN112631276A (en) | 2020-12-03 | 2020-12-03 | Unmanned vehicle dynamic obstacle decision method, system, medium and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112631276A true CN112631276A (en) | 2021-04-09 |
Family
ID=75307548
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011397727.XA Pending CN112631276A (en) | 2020-12-03 | 2020-12-03 | Unmanned vehicle dynamic obstacle decision method, system, medium and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112631276A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113589849A (en) * | 2021-09-29 | 2021-11-02 | 普宙科技(深圳)有限公司 | Unmanned aerial vehicle dynamic control method, system, equipment and storage medium |
| CN114089775A (en) * | 2022-01-20 | 2022-02-25 | 杭州蓝芯科技有限公司 | Mobile robot obstacle stopping control method and device |
| 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 |
| CN116013074A (en) * | 2023-01-05 | 2023-04-25 | 北京清丰智行科技有限公司 | Intelligent travel system based on car Lu Yun cooperation in park |
| CN117576950A (en) * | 2024-01-16 | 2024-02-20 | 长沙行深智能科技有限公司 | Method and device for predicting vehicle to select crossing entrance and crossing exit |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103823466A (en) * | 2013-05-23 | 2014-05-28 | 电子科技大学 | Path planning method for mobile robot in dynamic environment |
| CN109855639A (en) * | 2019-01-15 | 2019-06-07 | 天津大学 | Unmanned method for planning track based on forecasting-obstacle and MPC algorithm |
| CN109960261A (en) * | 2019-03-22 | 2019-07-02 | 北京理工大学 | A kind of dynamic barrier preventing collision method based on collision detection |
| CN110081894A (en) * | 2019-04-25 | 2019-08-02 | 同济大学 | A kind of real-time planing method of unmanned wheel paths based on the fusion of road structure weight |
| CN111650945A (en) * | 2020-06-28 | 2020-09-11 | 北京智行者科技有限公司 | Dynamic barrier anti-collision method |
-
2020
- 2020-12-03 CN CN202011397727.XA patent/CN112631276A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103823466A (en) * | 2013-05-23 | 2014-05-28 | 电子科技大学 | Path planning method for mobile robot in dynamic environment |
| CN109855639A (en) * | 2019-01-15 | 2019-06-07 | 天津大学 | Unmanned method for planning track based on forecasting-obstacle and MPC algorithm |
| CN109960261A (en) * | 2019-03-22 | 2019-07-02 | 北京理工大学 | A kind of dynamic barrier preventing collision method based on collision detection |
| CN110081894A (en) * | 2019-04-25 | 2019-08-02 | 同济大学 | A kind of real-time planing method of unmanned wheel paths based on the fusion of road structure weight |
| CN111650945A (en) * | 2020-06-28 | 2020-09-11 | 北京智行者科技有限公司 | Dynamic barrier anti-collision method |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113589849A (en) * | 2021-09-29 | 2021-11-02 | 普宙科技(深圳)有限公司 | Unmanned aerial vehicle dynamic control method, system, equipment and storage medium |
| 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 |
| CN114089775A (en) * | 2022-01-20 | 2022-02-25 | 杭州蓝芯科技有限公司 | Mobile robot obstacle stopping control method and device |
| CN116013074A (en) * | 2023-01-05 | 2023-04-25 | 北京清丰智行科技有限公司 | Intelligent travel system based on car Lu Yun cooperation in park |
| CN117576950A (en) * | 2024-01-16 | 2024-02-20 | 长沙行深智能科技有限公司 | Method and device for predicting vehicle to select crossing entrance and crossing exit |
| CN117576950B (en) * | 2024-01-16 | 2024-04-09 | 长沙行深智能科技有限公司 | Method and device for predicting vehicle to select crossing entrance and crossing exit |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112631276A (en) | Unmanned vehicle dynamic obstacle decision method, system, medium and equipment | |
| US11235763B2 (en) | Method, apparatus, device and readable storage medium for preventing vehicle collision | |
| CN111427369B (en) | Unmanned vehicle control method and device | |
| EP2826687B1 (en) | Technique for lane assignment in a vehicle | |
| CN110751847B (en) | Decision-making method and system for automatically driving vehicle behaviors | |
| CN109421712B (en) | Vehicle control device, vehicle control method, and storage medium | |
| CN113071487B (en) | Automatic driving vehicle control method and device and cloud equipment | |
| Zhang et al. | A framework for turning behavior classification at intersections using 3D LIDAR | |
| Guo et al. | Toward human-like behavior generation in urban environment based on Markov decision process with hybrid potential maps | |
| JP2021082286A (en) | System and method for improving lane change detection, and non-temporary computer-readable medium | |
| CN116198542A (en) | Automatic driving unprotected left turning method and system | |
| US11960292B2 (en) | Method and system for developing autonomous vehicle training simulations | |
| CN112462776A (en) | Unmanned driving decision-making method based on unstructured road | |
| CN114067552A (en) | Pedestrian crossing track tracking and predicting method based on roadside laser radar | |
| Schmidt et al. | Maneuver identification for interaction-aware highway lane change behavior planning based on polygon clipping and convex optimization | |
| CN112365730A (en) | Automatic driving method, device, equipment, storage medium and vehicle | |
| CN112180913A (en) | Special vehicle identification method | |
| CN117496476B (en) | Road network generation method, readable storage medium and intelligent device | |
| CN112904843B (en) | Automatic driving scene determining method and device, electronic equipment and storage medium | |
| Zhu et al. | Functional Testing Scenario Library Generation Framework for Connected and Automated Vehicles | |
| US20230415773A1 (en) | Validating protolanes with actor behavior flowcharts | |
| US20230418291A1 (en) | Testing reuse across protolane families | |
| US20230415767A1 (en) | Protolanes for testing autonomous vehicle intent | |
| US20230030474A1 (en) | Method and system for developing autonomous vehicle training simulations | |
| CN117022262A (en) | Unmanned vehicle speed planning control method and device, electronic equipment and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210409 |
|
| RJ01 | Rejection of invention patent application after publication |