CN111338361A - Obstacle avoidance method, device, equipment and medium for low-speed unmanned vehicle - Google Patents
Obstacle avoidance method, device, equipment and medium for low-speed unmanned vehicle Download PDFInfo
- Publication number
- CN111338361A CN111338361A CN202010441901.XA CN202010441901A CN111338361A CN 111338361 A CN111338361 A CN 111338361A CN 202010441901 A CN202010441901 A CN 202010441901A CN 111338361 A CN111338361 A CN 111338361A
- Authority
- CN
- China
- Prior art keywords
- obstacle avoidance
- obstacle
- low
- unmanned vehicle
- point cloud
- 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 55
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 45
- 238000004364 calculation method Methods 0.000 claims description 14
- 238000001914 filtration Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 230000007246 mechanism Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 230000004888 barrier function Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 4
- 230000006870 function Effects 0.000 description 7
- 230000008859 change Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000002939 conjugate gradient method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000000007 visual effect 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
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a low-speed unmanned vehicle obstacle avoidance method, relates to the technical field of automatic driving, and is used for solving the problem that the conventional obstacle avoidance does not consider a low-speed unmanned vehicle motion model, and the method comprises the following steps: acquiring a three-dimensional point cloud map and a local grid map; acquiring positioning information according to the three-dimensional point cloud map; detecting an obstacle, acquiring pose information of the obstacle, and judging the distance between the pose information and the positioning information; and when the distance is smaller than a preset threshold value, calculating to obtain an obstacle avoidance path through a Hybrid A algorithm according to the local grid map. The invention also discloses a low-speed unmanned vehicle obstacle avoidance device, electronic equipment and a computer storage medium. The invention realizes the low-speed unmanned vehicle obstacle avoidance method combined with the motion model through the Hybrid A-star algorithm.
Description
Technical Field
The invention relates to the technical field of automatic driving, in particular to a low-speed unmanned vehicle obstacle avoidance method, device, equipment and medium.
Background
The low-speed unmanned vehicle mainly refers to an automatic driving vehicle with relatively simple and fixed application scene and low speed per hour, and the main application scene of the automatic driving vehicle comprises a campus, a scenic spot, a park, an airport, a mine and the like; the low-speed unmanned vehicles are mainly used for logistics distribution, mining, unmanned agricultural machinery, catering and retail service and the like in specific areas.
At present, a path planning method of a low-speed unmanned vehicle is mainly realized by Dijkstra, A, D and D _ lite algorithms, and both D and an improved D _ lite algorithm can be used for realizing dynamic local obstacle avoidance, but the algorithms do not consider an actual kinematics model of the vehicle, and lack of judgment on factors such as vehicle body size, steering angle change during driving, reversing and the like, so that the unmanned vehicle still has the situation of touching obstacles during actual operation, or the obstacle avoidance is difficult to perform according to an obstacle avoidance route due to unsmooth obstacle avoidance route.
Disclosure of Invention
In order to overcome the defects of the prior art, one of the objectives of the present invention is to provide a method for avoiding obstacles of a low-speed unmanned vehicle, which is implemented by positioning the low-speed unmanned vehicle and using a Hybrid a-algorithm.
One of the purposes of the invention is realized by adopting the following technical scheme:
a low-speed unmanned vehicle obstacle avoidance method comprises the following steps:
acquiring a three-dimensional point cloud map and a local grid map;
acquiring positioning information according to the three-dimensional point cloud map;
detecting an obstacle, acquiring pose information of the obstacle, and judging the distance between the pose information and the positioning information;
and when the distance is smaller than a preset threshold value, calculating to obtain an obstacle avoidance path through a Hybrid A algorithm according to the local grid map.
Further, acquiring a three-dimensional point cloud map, comprising the following steps:
acquiring a point cloud pcd file;
and filtering the point cloud pcd file to obtain the three-dimensional point cloud map.
Further, an obstacle is detected by the multiline lidar.
Further, the method for detecting the obstacle and acquiring the pose information of the obstacle comprises the following steps:
acquiring point cloud data detected by the multi-line laser radar;
segmenting the point cloud data and filtering the ground point cloud data;
carrying out point cloud clustering on the obstacles according to the filtered point cloud data;
and extracting the characteristics of the clustered obstacles to obtain the obstacle position and posture information.
Further, when the distance is smaller than a preset threshold, calculating an obstacle avoidance path through a Hybrid A algorithm according to the local grid map, and the method comprises the following steps:
acquiring global path points;
initializing an OPEN list, and obtaining a starting point s and a target point o from the global path point, wherein the starting point s and the target point o are in the local grid map;
adding surrounding nodes i between the starting point s and the target point o into the OPEN list;
screening out a minimum cost value node Nmin from the surrounding nodes i as a father node, and storing the minimum cost value node Nmin into a CLOSE list;
using an A-star algorithm as a heuristic function to obtain a heuristic cost F _ h;
calculating the distance from the father node to the starting point s to obtain an actual cost F _ g;
judging whether the target point o is reached;
when the target point o is reached, constructing an obstacle avoidance path through a Reeds-Shepp curve;
otherwise, the node Nmin with the minimum cost value is continuously screened as a father node until the target point o is reached.
Further, when detecting the obstacle, the method comprises the following steps:
polling vehicle states through a finite state machine mechanism, wherein the vehicle states comprise a tracking state, a stopping state and an obstacle avoidance state;
when the vehicle state is a tracking state, controlling the low-speed unmanned vehicle to run along the global path point; detecting an obstacle in real time, acquiring obstacle position and posture information of the obstacle, and judging the distance between the position and posture information and the positioning information;
when the distance between the pose information and the positioning information is smaller than a preset threshold value, switching the tracking state to the stopping state;
after an obstacle avoidance path is obtained through Hybrid A algorithm calculation, the stop state is switched to be the obstacle avoidance state;
when the vehicle is in an obstacle avoidance state, continuously detecting obstacles and obstacle position and posture information in real time, judging the distance between the acquired obstacle position and posture information and the positioning information, and if the distance is smaller than a preset threshold value, switching the obstacle avoidance state to be in a stop state;
calculating through a Hybrid A-algorithm again to obtain a new obstacle avoidance path, and switching the stop state to the obstacle avoidance state until obstacle avoidance is completed;
and switching the obstacle avoidance state into the tracking state.
Further, the method for controlling the low-speed unmanned vehicle to travel along the global path point further comprises the following steps:
acquiring global path points and vehicle parameter information;
and tracking the global path point through a pure _ pure algorithm according to the vehicle parameter information.
The invention also aims to provide the obstacle avoidance device for the low-speed unmanned vehicle, which can realize the real-time obstacle avoidance of the low-speed unmanned vehicle by positioning the low-speed unmanned vehicle and using a Hybrid A algorithm.
The second purpose of the invention is realized by adopting the following technical scheme:
an obstacle avoidance device for a low-speed unmanned vehicle, comprising:
the acquisition module is used for acquiring a three-dimensional point cloud map and a local grid map; acquiring positioning information according to the three-dimensional point cloud map;
the detection module is used for detecting the barrier, acquiring pose information of the barrier and judging the distance between the pose information and the positioning information;
and the calculation module is used for calculating to obtain an obstacle avoidance path through a Hybrid A algorithm according to the local grid map when the distance is smaller than a preset threshold value.
It is a further object of the present invention to provide an electronic device for implementing one of the above objects, which includes a processor, a storage medium, and a computer program, the computer program being stored in the storage medium, wherein the computer program, when executed by the processor, implements the above-mentioned obstacle avoidance method for an unmanned vehicle.
It is a fourth object of the present invention to provide a computer-readable storage medium storing one of the objects of the present invention, having a computer program stored thereon, which when executed by a processor, implements the above-mentioned low-speed unmanned vehicle obstacle avoidance method.
Compared with the prior art, the invention has the beneficial effects that:
the invention realizes the positioning of the low-speed unmanned vehicle through the three-dimensional point cloud map and the local grid map, and obtains a smooth obstacle avoidance path suitable for the low-speed unmanned vehicle motion model through the Hybrid A-star algorithm, thereby realizing the obstacle avoidance of the low-speed unmanned vehicle.
Drawings
Fig. 1 is a flowchart of a low-speed unmanned vehicle obstacle avoidance method according to a first embodiment;
fig. 2 is a flowchart of a method for detecting an obstacle according to the first embodiment;
fig. 3 is a flowchart of an obstacle avoidance path calculation method according to the third embodiment;
fig. 4 is a block diagram of a low-speed unmanned vehicle obstacle avoidance device according to a fourth embodiment;
fig. 5 is a block diagram of the electronic apparatus according to the fifth embodiment.
Detailed Description
The present invention will now be described in more detail with reference to the accompanying drawings, in which the description of the invention is given by way of illustration and not of limitation. The various embodiments may be combined with each other to form other embodiments not shown in the following description.
Example one
The embodiment provides a low-speed unmanned vehicle obstacle avoidance method, which aims to realize global positioning by acquiring a three-dimensional point cloud map of a low-speed unmanned vehicle driving area and complete real-time construction of an obstacle avoidance path according to a local grid map and a Hybrid A algorithm.
Referring to fig. 1, a method for avoiding obstacles by a low-speed unmanned vehicle includes the following steps:
s110, acquiring a three-dimensional point cloud map and a local grid map;
the specific method for generating the three-dimensional point cloud map in S110 is not particularly limited in this embodiment, and any method that can generate the three-dimensional point cloud map may be used in S110.
The local grid map is constructed in real time, the local grid map is a coordinate system with a low-speed unmanned vehicle, and the constructed local grid map is mainly used for a local cost map of a Hybrid A algorithm.
After the map is built through the point cloud data, the generated pcd file is often large, so that the pcd file needs to be filtered to obtain point cloud characteristics required by calculation, and the three-dimensional point cloud map is more convenient to read and calculate; specifically, the method for acquiring the three-dimensional point cloud map comprises the following steps:
acquiring a point cloud pcd file;
and filtering the point cloud pcd file to obtain the three-dimensional point cloud map.
The embodiment does not limit the specific filtering method, and for example, the LIDAR point cloud filtering algorithm, the gradient filtering method, and the like may be used to implement the point cloud pcd file filtering of the embodiment.
It should be noted that the low-speed unmanned aerial vehicle in this embodiment is mainly applied to a fixed area (a fixed application scene, such as an airport, a train station, and the like), and thus the three-dimensional point cloud map is a point cloud map in a certain area.
S120, acquiring positioning information according to the three-dimensional point cloud map;
the specific positioning method in S120 is not limited in this embodiment, and methods such as laser positioning and GPS positioning may be used to obtain the positioning information, and the map on which the positioning method depends is the three-dimensional point cloud map obtained in S110.
S130, detecting an obstacle, acquiring pose information of the obstacle, and judging the distance between the pose information and the positioning information;
in the embodiment, the multi-line laser radar senses the obstacles in the three-dimensional point cloud map, and compared with obstacle sensing methods such as visual sensing, the multi-line laser radar senses the obstacles more accurately and obtains accurate pose information more easily.
Of course, when the obstacle is not detected, the obstacle is continuously detected without calculating the obstacle avoidance path.
Referring to fig. 2, S130 specifically includes the following steps:
s1301, point cloud data detected by the multi-line laser radar are obtained;
s1302, segmenting the point cloud data, and filtering ground point cloud data;
since the ground information is likely to affect the detection of the obstacle, the step S1302 is mainly used to segment the ground information.
S1303, carrying out point cloud clustering on the obstacles according to the filtered point cloud data;
the point cloud clustering in S1303 refers to clustering targets according to the distribution of points to reduce the subsequent calculation amount, and the clustering method adopts an euclidean clustering method in this embodiment, but may also be implemented by other clustering methods in other embodiments.
And S1304, extracting the characteristics of the clustered obstacles to obtain the obstacle position and posture information.
By extracting the obstacle features after the point cloud clustering in S1304, the obstacle category, the obstacle position and posture information, and the like can be obtained.
And S140, when the distance is smaller than a preset threshold value, calculating to obtain an obstacle avoidance path through a Hybrid A algorithm according to the local grid map.
The preset threshold value can be set according to the actual volume of the low-speed unmanned vehicle, the environment where the low-speed unmanned vehicle is located and the like.
The Hybrid A-algorithm is an algorithm meeting vehicle kinematics, and a smooth obstacle avoidance path can be obtained through the Hybrid A-algorithm; the relevant parameters of the vehicle kinematics are relevant parameters set according to the vehicle information, such as a steering angle, a steering radius and the like.
Example two
The second embodiment is performed on the basis of the first embodiment, and mainly explains and explains a state polling mechanism of the low-speed unmanned vehicle.
Specifically, when the obstacle is detected, the method comprises the following steps:
polling vehicle states through a finite state machine mechanism, wherein the vehicle states comprise a tracking state, a stopping state and an obstacle avoidance state;
when the vehicle state is a tracking state, controlling the low-speed unmanned vehicle to run along the global path point; detecting an obstacle in real time, acquiring obstacle position and posture information of the obstacle, and judging the distance between the position and posture information and the positioning information;
when the distance between the pose information and the positioning information is smaller than a preset threshold value, switching the tracking state to the stopping state;
after an obstacle avoidance path is obtained through Hybrid A algorithm calculation, the stop state is switched to be the obstacle avoidance state;
when the vehicle is in an obstacle avoidance state, continuously detecting obstacles and obstacle position and posture information in real time, judging the distance between the acquired obstacle position and posture information and the positioning information, and if the distance is smaller than a preset threshold value, switching the obstacle avoidance state to be in a stop state;
calculating through a Hybrid A-algorithm again to obtain a new obstacle avoidance path, and switching the stop state to the obstacle avoidance state until obstacle avoidance is completed;
and switching the obstacle avoidance state into the tracking state.
In this embodiment, the finite state machine mechanism is used to control the states of the three vehicles, and the states of the low-speed unmanned vehicle and the operations that can be executed in the states can be guaranteed to be known at any time through the finite state machine mechanism, and each state is independent, so that the low-speed unmanned vehicle can be debugged more conveniently, and rapid switching between the states can be realized only by setting state change conditions.
Wherein, control low-speed unmanned vehicle is followed global path point traveles, still includes following step:
acquiring global path points and vehicle parameter information;
and tracking the global path point through a pure _ pure algorithm according to the vehicle parameter information.
The vehicle parameter information can be set according to requirements, and generally comprises a forward looking distance, a vehicle wheel base, a vehicle size and the like; the vehicle parameter information can also be used for a vehicle motion model in obstacle avoidance path calculation.
In this embodiment, the control of the driving route can be realized through the pure _ pure algorithm, so that the low-speed unmanned vehicle can drive according to the global route point.
The pure tracking algorithm is a pure _ pursuit algorithm, the pure _ pursuit algorithm takes the rear axle of the vehicle as a tangent point, the longitudinal body of the vehicle as a tangent line, and the vehicle can run along an arc passing through a global path point by controlling the corner of the front wheel.
It should be noted that, when the pure _ pure tracks the route, vehicle positioning information is required, and the positioning information is obtained according to the three-dimensional point cloud map in the first embodiment.
EXAMPLE III
The third embodiment mainly explains and explains the specific process of computing the obstacle avoidance path by the Hybrid a-star algorithm.
Referring to fig. 3, when the distance is smaller than the preset threshold, the obstacle avoidance path is calculated by a Hybrid a-algorithm according to the local grid map, which includes the following steps:
s210, acquiring global path points;
the global waypoint is a fixed travel route of a low-speed unmanned vehicle in a certain designated area, for example, a park, and may be a route obtained by recording or a manually set route reference line.
S220, initializing an OPEN list, and obtaining a starting point S and a target point o from the global path point, wherein the starting point S and the target point o are in the local grid map;
the OPEN list in S220 is a list of stored parameters in the Hybrid a algorithm. The starting point s is the current position of the low-speed unmanned vehicle, the target point o is the position reached after the low-speed unmanned vehicle bypasses the obstacle, and the starting point s and the target point o are required to be ensured to be both in the local grid map, so that errors are prevented from occurring in calculation.
S230, adding surrounding nodes i between the starting point S and the target point o into the OPEN list;
the surrounding nodes i in S230 refer to nodes that a low-speed unmanned vehicle can pass through in the local grid map, that is, passable nodes obtained according to the low-speed unmanned vehicle motion model.
S240, screening out a node Nmin with a minimum cost value from the surrounding nodes i as a father node, and storing the node Nmin with the minimum cost value into a CLOSE list;
the above-mentioned CLOSE list refers to a list of stored routes, i.e. the node N with the smallest cost valueminA list of (a).
S250, obtaining a heuristic cost F _ h by using an A-star algorithm as a heuristic function;
in the embodiment, the A-star algorithm is used as a heuristic function to calculate the total cost, and compared with the traditional Hybrid A-star algorithm which calculates the total cost through a Reeds-Shepp curve, the method is higher in calculation efficiency and is suitable for the scenes that the environment change of the low-speed unmanned vehicle is small and the route is relatively fixed.
By calculating the heuristic cost, the path with the minimum heuristic cost, namely the path with the shortest distance can be obtained.
S260, calculating the distance from the father node to the starting point S to obtain an actual cost F _ g;
the heuristic cost F _ h and the actual cost F _ g in S250 and S260 are used for the calculation of the Hybrid a evaluation function, and the calculation formula is: f _ n = F _ h + F _ g, where F _ n is the total cost, the shortest local path around the obstacle is obtained by the evaluation function.
S270, judging whether the target point o is reached;
since the Hybrid a-x algorithm obtains a local path during calculation, the obtained path may not reach the vicinity of the target point o, and therefore, it is necessary to determine whether the target point o is reached.
S280, when the target point o is reached, constructing an obstacle avoidance path through a Reeds-Shepp curve;
otherwise, continuously screening the minimum cost value node NminAs a parent node until the target point o is reached.
The Reeds-Shepp curve is a curve for finding the shortest path, the obstacle avoidance path can be obtained through the curve, the obstacle avoidance path is smooth, the low-speed unmanned vehicle can conveniently track the obstacle avoidance path, the obstacle avoidance path can be made smoother through a conjugate gradient method, a vehicle motion model required by the Reeds-Shepp curve is the same as a vehicle motion model required by Hybrid A, and the vehicle motion model are preset vehicle parameters.
Example four
The fourth embodiment discloses a device corresponding to the low-speed unmanned vehicle obstacle avoidance method in the foregoing embodiment, which is a virtual device structure in the foregoing embodiment, and as shown in fig. 4, the device includes:
an obtaining module 310, configured to obtain a three-dimensional point cloud map and a local grid map; acquiring positioning information according to the three-dimensional point cloud map;
the detection module 320 is configured to detect an obstacle, acquire pose information of the obstacle, and determine a distance between the pose information and the positioning information;
and the calculating module 330 is configured to calculate, according to the local grid map, an obstacle avoidance path by a hybrid a-x algorithm when the distance is smaller than a preset threshold.
EXAMPLE five
Fig. 5 is a schematic structural diagram of an electronic device according to a fifth embodiment of the present invention, as shown in fig. 5, the electronic device includes a processor 410, a memory 420, an input device 430, and an output device 440; the number of the processors 410 in the computer device may be one or more, and one processor 410 is taken as an example in fig. 5; the processor 410, the memory 420, the input device 430 and the output device 440 in the electronic apparatus may be connected by a bus or other means, and the connection by the bus is exemplified in fig. 5.
The memory 420 serves as a computer-readable storage medium, and can be used for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the low-speed unmanned vehicle obstacle avoidance method in the embodiment of the present invention (for example, the obtaining module 310, the detecting module 320, and the calculating module 330 in the low-speed unmanned vehicle obstacle avoidance method apparatus). The processor 410 executes various functional applications and data processing of the electronic device by running the software programs, instructions and modules stored in the memory 420, that is, the low-speed unmanned vehicle obstacle avoidance method of the first to third embodiments is implemented.
The memory 420 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 420 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 420 may further include memory located remotely from processor 410, which may be connected to an electronic device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 430 may be used to receive input of user identity information, a three-dimensional point cloud map, and the like. The output device 440 may include a display device such as a display screen.
EXAMPLE six
The sixth embodiment of the present invention further provides a storage medium containing computer-executable instructions, where the storage medium may be used for a computer to execute a low-speed unmanned vehicle obstacle avoidance method, where the method includes:
acquiring a three-dimensional point cloud map and a local grid map;
acquiring positioning information according to the three-dimensional point cloud map;
detecting an obstacle, acquiring pose information of the obstacle, and judging the distance between the pose information and the positioning information;
and when the distance is smaller than a preset threshold value, calculating to obtain an obstacle avoidance path through a Hybrid A algorithm according to the local grid map.
Of course, the storage medium containing the computer-executable instructions provided by the embodiments of the present invention is not limited to the method operations described above, and may also perform related operations in the low-speed unmanned vehicle-based obstacle avoidance method provided by any embodiments of the present invention.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes instructions for enabling an electronic device (which may be a mobile phone, a personal computer, a server, or a network device) to execute the methods according to the embodiments of the present invention.
It should be noted that, in the embodiment of the low-speed unmanned vehicle obstacle avoidance method-based device, each included unit and module are only divided according to functional logic, but are not limited to the above division, as long as corresponding functions can be realized; in addition, specific names of the functional units are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present invention.
Various other modifications and changes may be made by those skilled in the art based on the above-described technical solutions and concepts, and all such modifications and changes should fall within the scope of the claims of the present invention.
Claims (10)
1. A low-speed unmanned vehicle obstacle avoidance method is characterized by comprising the following steps:
acquiring a three-dimensional point cloud map and a local grid map;
acquiring positioning information according to the three-dimensional point cloud map;
detecting an obstacle, acquiring pose information of the obstacle, and judging the distance between the pose information and the positioning information;
and when the distance is smaller than a preset threshold value, calculating to obtain an obstacle avoidance path through a Hybrid A algorithm according to the local grid map.
2. The obstacle avoidance method of the low-speed unmanned vehicle as claimed in claim 1, wherein the step of obtaining the three-dimensional point cloud map comprises the steps of:
acquiring a point cloud pcd file;
and filtering the point cloud pcd file to obtain the three-dimensional point cloud map.
3. The obstacle avoidance method for the low speed unmanned aerial vehicle of claim 1, wherein the obstacle is detected by a multi-line lidar.
4. The obstacle avoidance method of the low-speed unmanned vehicle as claimed in claim 3, wherein detecting an obstacle and acquiring pose information of the obstacle comprises the following steps:
acquiring point cloud data detected by the multi-line laser radar;
segmenting the point cloud data and filtering the ground point cloud data;
carrying out point cloud clustering on the obstacles according to the filtered point cloud data;
and extracting the characteristics of the clustered obstacles to obtain the obstacle position and posture information.
5. The obstacle avoidance method for the low-speed unmanned vehicle according to claim 1, wherein when the distance is smaller than a preset threshold, an obstacle avoidance path is calculated by a Hybrid a-algorithm according to the local grid map, and the method comprises the following steps:
acquiring global path points;
initializing an OPEN list, and obtaining a starting point s and a target point o from the global path point, wherein the starting point s and the target point o are in the local grid map;
adding surrounding nodes i between the starting point s and the target point o into the OPEN list;
screening out the node N with the minimum cost value from the surrounding nodes iminAs a father node, and the minimum cost value node NminStoring the list into a CLOSE list;
using an A-star algorithm as a heuristic function to obtain a heuristic cost F _ h;
calculating the distance from the father node to the starting point s to obtain an actual cost F _ g;
judging whether the target point o is reached;
when the target point o is reached, constructing an obstacle avoidance path through a Reeds-Shepp curve;
otherwise, continuously screening the minimum cost value node NminAs a parent node until the target point o is reached.
6. The obstacle avoidance method for the low-speed unmanned vehicle as claimed in claim 5, wherein when detecting the obstacle, the method comprises the following steps:
polling vehicle states through a finite state machine mechanism, wherein the vehicle states comprise a tracking state, a stopping state and an obstacle avoidance state;
when the vehicle state is a tracking state, controlling the low-speed unmanned vehicle to run along the global path point; detecting an obstacle in real time, acquiring obstacle position and posture information of the obstacle, and judging the distance between the position and posture information and the positioning information;
when the distance between the pose information and the positioning information is smaller than a preset threshold value, switching the tracking state to the stopping state;
after an obstacle avoidance path is obtained through Hybrid A algorithm calculation, the stop state is switched to be the obstacle avoidance state;
when the vehicle is in an obstacle avoidance state, continuously detecting obstacles and obstacle position and posture information in real time, judging the distance between the acquired obstacle position and posture information and the positioning information, and if the distance is smaller than a preset threshold value, switching the obstacle avoidance state to be in a stop state;
calculating through a Hybrid A-algorithm again to obtain a new obstacle avoidance path, and switching the stop state to the obstacle avoidance state until obstacle avoidance is completed;
and switching the obstacle avoidance state into the tracking state.
7. The obstacle avoidance method for the low speed unmanned vehicle as claimed in claim 6, wherein the low speed unmanned vehicle is controlled to travel along the global waypoint, further comprising the steps of:
acquiring global path points and vehicle parameter information;
and tracking the global path point through a pure _ pure algorithm according to the vehicle parameter information.
8. The utility model provides an obstacle-avoiding device for low-speed unmanned vehicles, which is characterized in that:
the acquisition module is used for acquiring a three-dimensional point cloud map and a local grid map; acquiring positioning information according to the three-dimensional point cloud map;
the detection module is used for detecting the barrier, acquiring pose information of the barrier and judging the distance between the pose information and the positioning information;
and the calculation module is used for calculating to obtain an obstacle avoidance path through a Hybrid A algorithm according to the local grid map when the distance is smaller than a preset threshold value.
9. An electronic device comprising a processor, a storage medium, and a computer program, the computer program being stored in the storage medium, wherein the computer program, when executed by the processor, implements the low speed unmanned vehicle obstacle avoidance method of any of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the low-speed unmanned vehicle obstacle avoidance method of any of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010441901.XA CN111338361A (en) | 2020-05-22 | 2020-05-22 | Obstacle avoidance method, device, equipment and medium for low-speed unmanned vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010441901.XA CN111338361A (en) | 2020-05-22 | 2020-05-22 | Obstacle avoidance method, device, equipment and medium for low-speed unmanned vehicle |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111338361A true CN111338361A (en) | 2020-06-26 |
Family
ID=71186437
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010441901.XA Pending CN111338361A (en) | 2020-05-22 | 2020-05-22 | Obstacle avoidance method, device, equipment and medium for low-speed unmanned vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111338361A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111998864A (en) * | 2020-08-11 | 2020-11-27 | 东风柳州汽车有限公司 | Unmanned vehicle local path planning method, device, equipment and storage medium |
CN112162297A (en) * | 2020-09-24 | 2021-01-01 | 燕山大学 | Method for eliminating dynamic obstacle artifacts in laser point cloud map |
CN112346463A (en) * | 2020-11-27 | 2021-02-09 | 西北工业大学 | Unmanned vehicle path planning method based on speed sampling |
CN112595337A (en) * | 2020-12-01 | 2021-04-02 | 苏州欧菲光科技有限公司 | Obstacle avoidance path planning method and device, electronic device, vehicle and storage medium |
CN112859848A (en) * | 2021-01-06 | 2021-05-28 | 国电内蒙古东胜热电有限公司 | Wireless navigation method and system of pipeline robot |
CN112937563A (en) * | 2021-03-30 | 2021-06-11 | 湖南铁道职业技术学院 | Unmanned vehicle obstacle avoidance method based on model predictive control |
CN113459090A (en) * | 2021-06-15 | 2021-10-01 | 中国农业大学 | Intelligent obstacle avoiding method of palletizing robot, electronic equipment and medium |
CN113468941A (en) * | 2021-03-11 | 2021-10-01 | 长沙智能驾驶研究院有限公司 | Obstacle detection method, device, equipment and computer storage medium |
CN114879704A (en) * | 2022-07-11 | 2022-08-09 | 山东大学 | Robot obstacle-detouring control method and system |
CN115100622A (en) * | 2021-12-29 | 2022-09-23 | 中国矿业大学 | Method for detecting travelable area and automatically avoiding obstacle of unmanned transportation equipment in deep limited space |
CN115309168A (en) * | 2022-10-11 | 2022-11-08 | 天地科技股份有限公司 | Underground unmanned vehicle control method and device |
CN115509215A (en) * | 2021-06-08 | 2022-12-23 | 广东博智林机器人有限公司 | Robot-based floor grinding path generation method and device |
CN116576865A (en) * | 2023-07-07 | 2023-08-11 | 民航成都电子技术有限责任公司 | Flight area path planning method, device, equipment and medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2007143757A2 (en) * | 2006-06-09 | 2007-12-13 | Carnegie Mellon University | Software architecture for high-speed traversal of prescribed routes |
CN106681330A (en) * | 2017-01-25 | 2017-05-17 | 北京航空航天大学 | Robot navigation method and device based on multi-sensor data fusion |
CN109144072A (en) * | 2018-09-30 | 2019-01-04 | 亿嘉和科技股份有限公司 | A kind of intelligent robot barrier-avoiding method based on three-dimensional laser |
CN109557928A (en) * | 2019-01-17 | 2019-04-02 | 湖北亿咖通科技有限公司 | Automatic driving vehicle paths planning method based on map vector and grating map |
CN109799821A (en) * | 2019-01-25 | 2019-05-24 | 汉腾汽车有限公司 | A kind of automatic Pilot control method based on state machine |
CN110015290A (en) * | 2018-01-08 | 2019-07-16 | 湖南中车时代电动汽车股份有限公司 | A kind of control method for intelligent driving system |
CN110361013A (en) * | 2019-07-22 | 2019-10-22 | 上海应用技术大学 | A kind of path planning system and method for auto model |
-
2020
- 2020-05-22 CN CN202010441901.XA patent/CN111338361A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2007143757A2 (en) * | 2006-06-09 | 2007-12-13 | Carnegie Mellon University | Software architecture for high-speed traversal of prescribed routes |
CN106681330A (en) * | 2017-01-25 | 2017-05-17 | 北京航空航天大学 | Robot navigation method and device based on multi-sensor data fusion |
CN110015290A (en) * | 2018-01-08 | 2019-07-16 | 湖南中车时代电动汽车股份有限公司 | A kind of control method for intelligent driving system |
CN109144072A (en) * | 2018-09-30 | 2019-01-04 | 亿嘉和科技股份有限公司 | A kind of intelligent robot barrier-avoiding method based on three-dimensional laser |
CN109557928A (en) * | 2019-01-17 | 2019-04-02 | 湖北亿咖通科技有限公司 | Automatic driving vehicle paths planning method based on map vector and grating map |
CN109799821A (en) * | 2019-01-25 | 2019-05-24 | 汉腾汽车有限公司 | A kind of automatic Pilot control method based on state machine |
CN110361013A (en) * | 2019-07-22 | 2019-10-22 | 上海应用技术大学 | A kind of path planning system and method for auto model |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111998864A (en) * | 2020-08-11 | 2020-11-27 | 东风柳州汽车有限公司 | Unmanned vehicle local path planning method, device, equipment and storage medium |
CN111998864B (en) * | 2020-08-11 | 2023-11-07 | 东风柳州汽车有限公司 | Unmanned vehicle local path planning method, device, equipment and storage medium |
CN112162297B (en) * | 2020-09-24 | 2022-07-19 | 燕山大学 | Method for eliminating dynamic obstacle artifacts in laser point cloud map |
CN112162297A (en) * | 2020-09-24 | 2021-01-01 | 燕山大学 | Method for eliminating dynamic obstacle artifacts in laser point cloud map |
CN112346463A (en) * | 2020-11-27 | 2021-02-09 | 西北工业大学 | Unmanned vehicle path planning method based on speed sampling |
CN112595337A (en) * | 2020-12-01 | 2021-04-02 | 苏州欧菲光科技有限公司 | Obstacle avoidance path planning method and device, electronic device, vehicle and storage medium |
CN112595337B (en) * | 2020-12-01 | 2023-08-15 | 苏州欧菲光科技有限公司 | Obstacle avoidance path planning method and device, electronic device, vehicle and storage medium |
CN112859848A (en) * | 2021-01-06 | 2021-05-28 | 国电内蒙古东胜热电有限公司 | Wireless navigation method and system of pipeline robot |
CN112859848B (en) * | 2021-01-06 | 2023-03-10 | 国电内蒙古东胜热电有限公司 | Wireless navigation method and system of pipeline robot |
CN113468941A (en) * | 2021-03-11 | 2021-10-01 | 长沙智能驾驶研究院有限公司 | Obstacle detection method, device, equipment and computer storage medium |
CN112937563A (en) * | 2021-03-30 | 2021-06-11 | 湖南铁道职业技术学院 | Unmanned vehicle obstacle avoidance method based on model predictive control |
CN115509215A (en) * | 2021-06-08 | 2022-12-23 | 广东博智林机器人有限公司 | Robot-based floor grinding path generation method and device |
CN113459090A (en) * | 2021-06-15 | 2021-10-01 | 中国农业大学 | Intelligent obstacle avoiding method of palletizing robot, electronic equipment and medium |
CN115100622A (en) * | 2021-12-29 | 2022-09-23 | 中国矿业大学 | Method for detecting travelable area and automatically avoiding obstacle of unmanned transportation equipment in deep limited space |
CN115100622B (en) * | 2021-12-29 | 2023-09-22 | 中国矿业大学 | Method for detecting driving area of unmanned transportation equipment in deep limited space and automatically avoiding obstacle |
CN114879704B (en) * | 2022-07-11 | 2022-11-25 | 山东大学 | Robot obstacle-avoiding control method and system |
CN114879704A (en) * | 2022-07-11 | 2022-08-09 | 山东大学 | Robot obstacle-detouring control method and system |
CN115309168A (en) * | 2022-10-11 | 2022-11-08 | 天地科技股份有限公司 | Underground unmanned vehicle control method and device |
CN116576865A (en) * | 2023-07-07 | 2023-08-11 | 民航成都电子技术有限责任公司 | Flight area path planning method, device, equipment and medium |
CN116576865B (en) * | 2023-07-07 | 2023-10-17 | 民航成都电子技术有限责任公司 | Flight area path planning method, device, equipment and medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111338361A (en) | Obstacle avoidance method, device, equipment and medium for low-speed unmanned vehicle | |
US11709058B2 (en) | Path planning method and device and mobile device | |
CN108983781B (en) | Environment detection method in unmanned vehicle target search system | |
US10074270B2 (en) | Clustering observations of objects along roads for navigation-related operations | |
CN104833370B (en) | System and method for mapping, positioning and pose correction | |
CN110674705B (en) | Small-sized obstacle detection method and device based on multi-line laser radar | |
US11480967B2 (en) | Pass route planning method and apparatus, device and readable storage medium | |
Pantilie et al. | Real-time obstacle detection in complex scenarios using dense stereo vision and optical flow | |
US20210174113A1 (en) | Method for limiting object detection area in a mobile system equipped with a rotation sensor or a position sensor with an image sensor, and apparatus for performing the same | |
Pantilie et al. | Real-time obstacle detection using dense stereo vision and dense optical flow | |
CN113442908B (en) | Automatic parking path planning method and system and parking control equipment | |
CN118235180A (en) | Method and device for predicting drivable lane | |
CN115900738A (en) | Path planning method, device, vehicle and storage medium | |
WO2022116831A1 (en) | Positioning method and apparatus, electronic device and readable storage medium | |
CN116772846A (en) | Unmanned aerial vehicle track planning method, unmanned aerial vehicle track planning device, unmanned aerial vehicle track planning equipment and unmanned aerial vehicle track planning medium | |
JPWO2017216856A1 (en) | Inter-vehicle distance estimation method and inter-vehicle distance estimation apparatus | |
CN114184203B (en) | Path planning method, electronic equipment and mobile device | |
CN115097826A (en) | Vehicle turning track planning method and device | |
CN115526053A (en) | Road modeling method, device and equipment | |
CN115359332A (en) | Data fusion method and device based on vehicle-road cooperation, electronic equipment and system | |
CN115457486A (en) | Two-stage-based truck detection method, electronic equipment and storage medium | |
CN111951552B (en) | Method and related device for risk management in automatic driving | |
US11544899B2 (en) | System and method for generating terrain maps | |
CN113670632A (en) | Collision detection method and device | |
CN115236672A (en) | Obstacle information generation method, device, equipment and computer readable 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: 20200626 |
|
RJ01 | Rejection of invention patent application after publication |