CN110908387A - Method, medium and electronic device for planning paths of unmanned surface vehicle in dynamic environment - Google Patents
Method, medium and electronic device for planning paths of unmanned surface vehicle in dynamic environment Download PDFInfo
- Publication number
- CN110908387A CN110908387A CN201911280763.5A CN201911280763A CN110908387A CN 110908387 A CN110908387 A CN 110908387A CN 201911280763 A CN201911280763 A CN 201911280763A CN 110908387 A CN110908387 A CN 110908387A
- Authority
- CN
- China
- Prior art keywords
- path
- obstacle
- unmanned
- dynamic environment
- map
- 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
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/0206—Control of position or course in two dimensions specially adapted to water vehicles
Abstract
The application discloses a method, a medium and an electronic device for planning paths of unmanned surface vehicles in a dynamic environment; the method is characterized in that a reaction technology based on a millimeter wave radar sensor is simply used for determining the direction of an obstacle obstructing a path of the unmanned surface vehicle in the navigation process, the detection range of the millimeter wave radar sensor is divided into three region angles to define three equal detection ranges, the obstacle is expanded by using a morphological expansion technology before the path is generated, and therefore a new path is generated through the current position of the unmanned surface vehicle to obtain the path after the obstacle is avoided.
Description
Technical Field
The application relates to a method, medium and electronic equipment for planning paths of unmanned surface vehicles in dynamic environments.
Background
The unmanned ship is a naval ship which is unmanned and can navigate autonomously, can be commanded by wireless communication equipment or controlled by a control system of the unmanned ship, and is mostly used in relatively dangerous environments or used for executing tasks which cannot be finished by a common manned ship. Together with unmanned aerial vehicles, unmanned vehicles and unmanned underwater vehicles, four unmanned carrier systems which are generally known by us are formed. Compared with other unmanned systems, the unmanned ship has relatively lagged development, and as a new scientific and technical field, the unmanned ship has great development potential in many aspects, such as appearance design of the unmanned ship, improvement of a propulsion system, automation and autonomous control and the like. The path planning under the unmanned ship re-dynamic environment is an important component for realizing the autonomous operation of the unmanned ship.
The inventors have found that random obstacles can prevent the optimally generated path during surface drones navigation. The obstacle may be moving or stationary; the method comprises the steps of calculating the direction of the unmanned surface vehicle and the position of an obstacle by utilizing the angle position of the unmanned surface vehicle and the angle position of the obstacle, comparing the difference of the angles with an angle threshold value to determine the direction of the obstacle, and then replanning the action.
Disclosure of Invention
The method, the medium and the electronic equipment are used for planning the path of the unmanned surface vehicle in the dynamic environment; the front is detected by a radar sensor, and the obstacle is expanded by a morphological expansion technology before the path is generated, so that a new path is generated through the current position of the unmanned surface vehicle to obtain the path after the obstacle is avoided.
The first purpose of the application is to provide a dynamic environment water surface unmanned ship path planning method, which comprises the following steps:
the unmanned ship scans the front area through the radar sensor and judges whether an obstacle exists in a safe distance;
if an obstacle exists in the safe distance, acquiring a map through a camera, and carrying out binarization processing on the map image;
judging and acquiring the position of the obstacle, and performing morphological expansion technical processing on the obstacle;
modifying and using the target deviation rrt to generate a road map, and enabling the generated tree to face the target;
optimizing the route graph by applying an A-ray heuristic algorithm and obtaining a shortest path;
performing smoothness processing on the shortest path by using CSI;
the path is executed and the scan continues.
Further, the morphological dilation technique comprises:
p represents a map, Q represents an expanded structural element, r represents a set of all points on the map, and Qi represents a mapping of the set of Q;
(bmap⊕q)R=max{bmap(R-x)+q(x)|(R-x),∈Sbmap&∈Sq}
before generating the tree, expanding the obstacles on the map; bmap is a given expansion binary image matrix, q (x, y) is a structural element, S is a map dimension, and R is the radius of a safety space required by the unmanned surface vehicle.
Further, in the process of generating the roadmap, the random value rand is compared with the random threshold rt:
when rand < rt, calculating the random sample equation according to the equation; when rand is greater than or equal to rt bias, the growth of the tree is biased towards the target.
Further, the nearest node is calculated using k-nearest neighbors:
wherein, the urand ═ sample;
the direction angle θ expands the samples to create a new node is given by:
θ=atan2(urand-unearest);
wherein unerest is nerarest (T, urand);
the new node is given by:
sz1 and sz2 each represent a different step size.
Further, a heuristic cost algorithm is calculated as follows:
f(p)=g(p)+h(p);
g (p) ═ c (s, p) refers to the cost from the initial point s to the node p, and h (p) is a heuristic component of the cost function, specifically:
where p ═ represents points on the path (p0, p1, p2..., pn).
Further, the path obtained after applying the a-x algorithm is a cubic spline curve, and is smoothed:
wherein, Pi here denotes a cubic function,
Pi(x)=ai+bix+cix2+dix3
where ai, bi, ci, di are coefficients for each i.
Further, in the process of detecting by the radar sensor, the judgment is made according to the condition of detecting the obstacle:
wherein Pcross is the path of the moving obstacle through the surface unmanned boat, Psame is the obstacle is static, moves forwards in the same direction as the surface unmanned boat or in the same direction of the surface unmanned boat; if the condition is Pacross, continue navigating after waiting for the obstacle to pass, and if the condition is Psame, replanning the path.
Furthermore, the detection range of the radar sensor is divided into three detection areas for detecting the movement condition of the obstacle; the radar sensor is a millimeter wave radar sensor.
A second object of the present application is to provide a medium, comprising the following technical solutions:
stored thereon is a program which, when executed by a processor, carries out the steps in the dynamic environment surface unmanned boat path planning method as described above.
A third object of the present application is to provide an electronic device, including the following technical solutions:
comprising a memory, a processor and a program stored on the memory and executable on the processor, the processor implementing the steps of the dynamic environment surface unmanned ship path planning method as described above when executing the program.
Compared with the prior art, the application has the advantages and positive effects that:
before generating the path, adopting a Morphological Dilation (MD) technology to dilate the obstacles, adopting a Cubic Spline (CSI) method to carry out smooth processing on the path, and when a random obstacle obstructs the navigation path of the unmanned surface ship, generating a new path from the current position of the unmanned surface ship to replan the path. The improved RRT-a method solves the local minimum problem and generates a safe and optimal path at the lowest time cost in partially known environments.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
Fig. 1 is a schematic flow chart of a planning method in embodiment 1 of the present invention;
fig. 2 is a schematic diagram of detection by a radar sensor in embodiment 1 of the present invention.
Detailed Description
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an", and/or "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof;
as introduced in the background art, in the prior art, the direction of the unmanned surface vehicle and the position of the obstacle are calculated by using the angle position of the unmanned surface vehicle and the angle position of the obstacle, the difference of the angles is compared with an angle threshold to determine the direction of the obstacle, and then the action is re-planned, although the position of the unmanned surface vehicle is easily obtained in the calculation, the coordinates of the obstacle are difficult to obtain in a real-time environment, so that the existing unmanned vehicle obstacle avoidance method cannot meet the obstacle avoidance requirement during the inspection operation of the unmanned vehicle.
Example 1
In an exemplary embodiment of the present application, as shown in fig. 1-2, a method for planning a path of a dynamic environment surface unmanned ship is provided.
The method comprises the following steps:
the method comprises the following steps: acquiring and processing a map;
step two: calculating an RRT route map;
step three: path query and optimization;
step four: smoothing a path;
step five: and (6) path re-planning.
Specifically, the method comprises the following steps: before generating the path, adopting a Morphological Dilation (MD) technology to dilate the obstacles, adopting a Cubic Spline (CSI) method to carry out smooth processing on the path, and when a random obstacle obstructs the navigation path of the unmanned surface ship, generating a new path from the current position of the unmanned surface ship to replan the path. The improved RRT-a method solves the local minimum problem and generates a safe and optimal path at the lowest time cost in partially known environments.
The method comprises the following steps: obtaining and processing maps
1. A camera is used for collecting a map and binarizing the map;
2. to avoid collisions, the barrier MD is processed before the RRT route is constructed.
MD expression:
p represents a map, Q represents an expanded structural element, r represents a set of all points on the map, and Qi represents a mapping of the set of Q;
(bmap⊕q)R=max{bmap(R-x)+q(x)|(R-x),∈Sbmap&∈Sq} (2)
bmap is a given expansion binary image matrix, q (x, y) is a structural element S and a map dimension, and R is the radius of a safety space required by the unmanned surface vehicle.
Equation (2) is used to inflate the obstacles on the map before generating the tree to ensure safe navigation.
Step two: computing RRT roadmaps
The invention modifies and uses the target bias rrt to generate a roadmap to ensure a fast generated tree towards the target. The generated tree is biased towards the target when it is determined that the random value rand of the sample calculation is less than the random threshold rt. Two different step sizes, sz1 and sz2 (used to assign higher values than sz 1). Sz2 is used for tree growth when growth is biased towards the target. This is to reduce the number of nodes generated before reaching the target, thereby reducing time and spatial complexity of the algorithm.
The generated random value rand is compared with a random threshold value (rt). If rand < rt, then calculate the random sample equation (3) as per the equation. When rand is greater than or equal to rt bias, the growth of the tree is biased towards the target.
The nearest node is calculated using k-nearest neighbors. The formula is as follows:
here, urand ═ sample is given by equation (3).
The direction angle θ expands the samples to create a new node is given by equation (5).
θ=atan2(urand-unearest) (5)
Let uneartt ═ nerest (T, urand).
The calculation formula of the new node is given by equation (6).
sz1 and sz2 respectively indicate different step sizes, and if ura and target, sz2 is used to calculate the position of the new node new with higher step size towards the target. This is to promote faster growth of the tree towards the target and a reduction in the number of nodes. A collision check is performed to ensure that the tree is generated within the CSfree range. Once the target point is reached or the iterative attempt terminates, the growth of the tree ends. CS denotes a reconstruction space, including a CSobs obstacle space and a CSfree free space.
Step three: path query and optimization
The method comprises the steps of firstly generating a path by using an improved target offset RRT algorithm, then optimizing a path graph by using an A-heuristic algorithm and obtaining the shortest path.
A is the formula of the heuristic cost algorithm as follows:
f(p)=g(p)+h(p) (7)
here, g (p) ═ c (s, p) refers to the cost from the initial point s to the node p.
h (p) is the heuristic component of the cost function that estimates the lowest cost from node p to the target point.
The formula for h (p) is as follows:
where p ═ represents points on the path (p0, p1, p2..., pn).
A is considered because it is both complete and optimal. It is complete because once a path exists in the CSfree, a can find it. A is acceptable and continuous. Acceptability and continuity are properties of optimality. If g (P) is the actual cost to reach point p, then f (P) does not overestimate the cost to reach the target, making A acceptable. Considering c (p, p ') as the cost from point p to p ', continuity is achieved from h (p) ≦ c (p, p ') + h (p '), while acceptability is achieved from all arcs of the path c (p, p ') > ε ≧ 0.
Step four: path smoothing
The path obtained after the A-star algorithm is applied is not smooth enough, and the easy navigation of the unmanned surface vehicle cannot be realized. CSI is employed to improve the smoothness of the optimized path. For cubic spline curves, the function of the curve is represented using a different cubic function for each data point interval. Considering the m data points, the cubic spline function is represented as follows:
pi here denotes a cubic function. In general, cubic splines are defined as
Pi(x)=ai+bix+cix2+dix3(10)
Ai, bi, ci, di are coefficients for each i, so 4m coefficients need to be computed for m node intervals. MD techniques are proposed to inflate obstacles in the map before calculating the roads, in the present invention, the probability of collision is reduced.
Step five: path re-planning
The invention provides a simple reaction technology based on a millimeter wave radar sensor to determine the direction of an obstacle obstructing a path of an unmanned surface vehicle in a navigation process. The detection range of the millimeter wave radar sensor is divided into three region angles to define three equal detection ranges. Two main conditions for making a decision that an obstacle is needed: (1) whether the moving barrier passes through the path of the unmanned surface vehicle or not, Pcross; (2) whether the obstacle is stationary, moving forward in the same direction as the surface drone or in the same direction of the surface drone, Psame. The expected re-planning action Ra of the unmanned surface vehicle is given:
if the condition is PCross, the surface unmanned boat waits for the obstacle to pass through, and then navigation is continued. If the condition is Psame, path re-planning is performed.
Referring to fig. 2, the sensors are millimeter wave radar sensors on the unmanned surface vehicle, (s1, s2, s3) are three areas equally divided by the millimeter wave radar sensors, (θ s1, θ s2, θ s3) are three area angles equally divided by the millimeter wave radar sensors, (p1, p2, p3) are three state points of the same obstacle, d1 and d2 respectively represent different distance thresholds, and sd is a safe distance between the unmanned surface vehicle and the obstacle.
The millimeter wave radar sensor tracks obstacles in the navigation process. When the distance between the minimum distance dist of the millimeter wave radar sensor and the obstacle is smaller than d1, the fact that the obstacle is detected by the unmanned surface vehicle at a longer distance indicates that the collision threat to the unmanned surface vehicle is smaller, and the millimeter wave radar sensor for detecting the obstacle is recorded. To check the direction of the obstacle, the millimeter wave radar sensor reading is recorded to dist ≦ d2, and the millimeter wave radar sensor with the reading is recorded.
If the millimeter wave radar sensor in the same area detects an obstacle with dist not more than d2, the Psame condition is met, calling is carried out, a new feasible navigation path is re-planned and calculated, and the path re-planning task comprises the following four steps:
the method comprises the following steps: obtaining and processing maps
Step two: computing RRT roadmaps
Step three: path query and optimization
Step four: path smoothing
The current position of the surface drone is used as a new node for the re-planning.
However, if an obstacle is detected in the other region of the millimeter wave radar sensor at dist ≦ d2, the Pacross condition is satisfied. The surface unmanned boat comes to a stop and waits for dist > d 1.
As shown in fig. 2: an obstacle obs is detected in the regions s3 and s2 of the millimeter wave radar sensor at points P1 and P2, respectively, and since the minimum distance dist of the millimeter wave radar sensor is in the middle region of d2 and d1, the threat of collision to the surface unmanned boat is small, and the s3 and s2 of the millimeter wave radar sensor detecting the obstacle are recorded. Then, the obstacle obs is detected in an s1 area of the millimeter wave radar sensor with the point P3, and the minimum distance dist of the millimeter wave radar sensor is within d2, so that the unmanned surface vehicle is threatened to collide, and the millimeter wave radar sensor with the reading is recorded. This state satisfies Pacross, so at dist ≦ d1, the surface drone stops moving and waits for the obstacle to pass, otherwise it will be replanned.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
Claims (10)
1. A path planning method for an unmanned surface vehicle in a dynamic environment is characterized by comprising the following steps:
the unmanned ship scans the front area through the radar sensor and judges whether an obstacle exists in a safe distance;
if an obstacle exists in the safe distance, acquiring a map through a camera, and carrying out binarization processing on the map image;
judging and acquiring the position of the obstacle, and performing morphological expansion technical processing on the obstacle;
modifying and using the target deviation rrt to generate a road map, and enabling the generated tree to face the target;
optimizing the route graph by applying an A-ray heuristic algorithm and obtaining a shortest path;
performing smoothness processing on the shortest path by using CSI;
the path is executed and the scan continues.
2. The dynamic environment surface unmanned surface vehicle path planning method of claim 1, wherein detection ranges of the radar sensors are divided into three detection areas for detecting movement of obstacles.
3. The dynamic environment surface unmanned boat path planning method of claim 1, wherein performing morphological dilation technique processing comprises:
p represents a map, Q represents an expanded structural element, r represents a set of all points on the map, and Qi represents a mapping of the set of Q;
(bmap⊕q)R=max{bmap(R-x)+q(x)|(R-x),∈Sbmap&∈Sq};
before generating the tree, expanding the obstacles on the map; bmap is a given expansion binary image matrix, q (x, y) is a structural element, S is a map dimension, and R is the radius of a safety space required by the unmanned surface vehicle.
4. A dynamic environment surface unmanned surface vehicle path planning method as claimed in claim 3, wherein in generating the roadmap, the random value rand is compared with a random threshold rt:
when rand < rt, calculating the random sample equation according to the equation; when rand is greater than or equal to rt bias, the growth of the tree is biased towards the target.
5. The dynamic environment surface unmanned boat path planning method of claim 4, wherein the nearest node is calculated using k-nearest neighbors to derive:
wherein, the urand ═ sample;
the direction angle θ expands the samples to create a new node is given by:
θ=atan2(urand-unearest);
wherein unerest is nerarest (T, urand);
the new node is given by:
6. The dynamic environment water surface unmanned ship path planning method of claim 5, wherein the A-heuristic cost algorithm is calculated as follows:
f(p)=g(p)+h(p);
g (p) ═ c (s, p) refers to the cost from the initial point s to the node p, and h (p) is a heuristic component of the cost function, specifically:
where p ═ represents points on the path (p0, p1, p2..., pn).
7. The method for planning the path of the unmanned surface vehicle in the dynamic environment according to claim 6, wherein the path obtained by applying the a-x algorithm is a cubic spline curve, and the cubic spline curve is smoothed by:
wherein, Pi here denotes a cubic function,
Pi(x)=ai+bix+cix2+dix3
where ai, bi, ci, di are coefficients for each i.
8. The dynamic environment surface unmanned boat path planning method of claim 1, wherein during the radar sensor detection, a decision is made based on the detection of an obstacle:
wherein Pcross is the path of the moving obstacle through the surface unmanned boat, Psame is the obstacle is static, moves forwards in the same direction as the surface unmanned boat or in the same direction of the surface unmanned boat; if the condition is Pacross, continue navigating after waiting for the obstacle to pass, and if the condition is Psame, replanning the path.
9. A medium having a program stored thereon, wherein the program, when executed by a processor, performs the steps of the dynamic ambient surface unmanned surface vehicle path planning method of any of claims 1-7.
10. An electronic device comprising a memory, a processor, and a program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps in the dynamic environment surface unmanned boat path planning method of any one of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911280763.5A CN110908387A (en) | 2019-12-13 | 2019-12-13 | Method, medium and electronic device for planning paths of unmanned surface vehicle in dynamic environment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911280763.5A CN110908387A (en) | 2019-12-13 | 2019-12-13 | Method, medium and electronic device for planning paths of unmanned surface vehicle in dynamic environment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110908387A true CN110908387A (en) | 2020-03-24 |
Family
ID=69825343
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911280763.5A Pending CN110908387A (en) | 2019-12-13 | 2019-12-13 | Method, medium and electronic device for planning paths of unmanned surface vehicle in dynamic environment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110908387A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113341992A (en) * | 2021-06-18 | 2021-09-03 | 广东工业大学 | Unmanned ship multitask path planning method |
CN114111825A (en) * | 2021-11-19 | 2022-03-01 | 广西柳工机械股份有限公司 | Path planning method and device, electronic equipment, engineering machinery and storage medium |
Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102929285A (en) * | 2012-11-16 | 2013-02-13 | 中国民用航空飞行学院 | Multi-target distribution and flight path planning method for multiple rescue helicopters |
CN103693040A (en) * | 2013-12-10 | 2014-04-02 | 金陵科技学院 | Vehicle collision avoidance system based on double-mode cooperation |
US20140121833A1 (en) * | 2012-10-30 | 2014-05-01 | Samsung Techwin Co., Ltd. | Apparatus and method for planning path of robot, and the recording media storing the program for performing the method |
WO2016015547A1 (en) * | 2014-08-01 | 2016-02-04 | 深圳中集天达空港设备有限公司 | Machine vision-based method and system for aircraft docking guidance and aircraft type identification |
US9285227B1 (en) * | 2015-01-29 | 2016-03-15 | Qualcomm Incorporated | Creating routing paths in maps |
EP3018626A1 (en) * | 2014-11-04 | 2016-05-11 | Sisvel Technology S.r.l. | Apparatus and method for image segmentation |
CN106909148A (en) * | 2017-03-10 | 2017-06-30 | 南京沃杨机械科技有限公司 | Based on the unmanned air navigation aid of agricultural machinery that farm environment is perceived |
CN106950952A (en) * | 2017-03-10 | 2017-07-14 | 无锡卡尔曼导航技术有限公司 | For the unpiloted farm environment cognitive method of agricultural machinery |
US20170241790A1 (en) * | 2016-02-24 | 2017-08-24 | Honda Motor Co., Ltd. | Path plan generating apparatus for mobile body |
CN107703945A (en) * | 2017-10-30 | 2018-02-16 | 洛阳中科龙网创新科技有限公司 | A kind of intelligent farm machinery paths planning method of multiple targets fusion |
CN108227738A (en) * | 2017-12-28 | 2018-06-29 | 湖北电鹰科技有限公司 | A kind of unmanned plane barrier-avoiding method and system |
CN108490941A (en) * | 2018-03-29 | 2018-09-04 | 奇瑞汽车股份有限公司 | Applied to the automated driving system and its control method of road sweeper, device |
CN109737970A (en) * | 2019-03-21 | 2019-05-10 | 集美大学 | A kind of unmanned surface vehicle paths planning method based on improvement RRT algorithm |
CN110162089A (en) * | 2019-05-30 | 2019-08-23 | 北京三快在线科技有限公司 | A kind of unpiloted emulation mode and device |
CN110208816A (en) * | 2019-06-04 | 2019-09-06 | 浙江海洋大学 | For the automatic differentiating obstacle of marine unmanned boat and recognition methods |
CN110501719A (en) * | 2019-08-27 | 2019-11-26 | 王玉娇 | A kind of train obstacle detection method based on laser radar |
-
2019
- 2019-12-13 CN CN201911280763.5A patent/CN110908387A/en active Pending
Patent Citations (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140121833A1 (en) * | 2012-10-30 | 2014-05-01 | Samsung Techwin Co., Ltd. | Apparatus and method for planning path of robot, and the recording media storing the program for performing the method |
CN102929285A (en) * | 2012-11-16 | 2013-02-13 | 中国民用航空飞行学院 | Multi-target distribution and flight path planning method for multiple rescue helicopters |
CN103693040A (en) * | 2013-12-10 | 2014-04-02 | 金陵科技学院 | Vehicle collision avoidance system based on double-mode cooperation |
WO2016015547A1 (en) * | 2014-08-01 | 2016-02-04 | 深圳中集天达空港设备有限公司 | Machine vision-based method and system for aircraft docking guidance and aircraft type identification |
EP3018626A1 (en) * | 2014-11-04 | 2016-05-11 | Sisvel Technology S.r.l. | Apparatus and method for image segmentation |
US9285227B1 (en) * | 2015-01-29 | 2016-03-15 | Qualcomm Incorporated | Creating routing paths in maps |
US20170241790A1 (en) * | 2016-02-24 | 2017-08-24 | Honda Motor Co., Ltd. | Path plan generating apparatus for mobile body |
CN106950952A (en) * | 2017-03-10 | 2017-07-14 | 无锡卡尔曼导航技术有限公司 | For the unpiloted farm environment cognitive method of agricultural machinery |
CN106909148A (en) * | 2017-03-10 | 2017-06-30 | 南京沃杨机械科技有限公司 | Based on the unmanned air navigation aid of agricultural machinery that farm environment is perceived |
CN107703945A (en) * | 2017-10-30 | 2018-02-16 | 洛阳中科龙网创新科技有限公司 | A kind of intelligent farm machinery paths planning method of multiple targets fusion |
CN108227738A (en) * | 2017-12-28 | 2018-06-29 | 湖北电鹰科技有限公司 | A kind of unmanned plane barrier-avoiding method and system |
CN108490941A (en) * | 2018-03-29 | 2018-09-04 | 奇瑞汽车股份有限公司 | Applied to the automated driving system and its control method of road sweeper, device |
CN109737970A (en) * | 2019-03-21 | 2019-05-10 | 集美大学 | A kind of unmanned surface vehicle paths planning method based on improvement RRT algorithm |
CN110162089A (en) * | 2019-05-30 | 2019-08-23 | 北京三快在线科技有限公司 | A kind of unpiloted emulation mode and device |
CN110208816A (en) * | 2019-06-04 | 2019-09-06 | 浙江海洋大学 | For the automatic differentiating obstacle of marine unmanned boat and recognition methods |
CN110501719A (en) * | 2019-08-27 | 2019-11-26 | 王玉娇 | A kind of train obstacle detection method based on laser radar |
Non-Patent Citations (2)
Title |
---|
白瑞雪: "彩色自适应数学形态学研究与应用", 《信息科技辑》 * |
白瑞雪: "彩色自适应数学形态学研究与应用", 《信息科技辑》, no. 2, 15 February 2019 (2019-02-15), pages 10 - 15 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113341992A (en) * | 2021-06-18 | 2021-09-03 | 广东工业大学 | Unmanned ship multitask path planning method |
CN113341992B (en) * | 2021-06-18 | 2023-10-27 | 广东工业大学 | Unmanned ship multitasking path planning method |
CN114111825A (en) * | 2021-11-19 | 2022-03-01 | 广西柳工机械股份有限公司 | Path planning method and device, electronic equipment, engineering machinery and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11567502B2 (en) | Autonomous exploration framework for indoor mobile robotics using reduced approximated generalized Voronoi graph | |
Polvara et al. | Obstacle avoidance approaches for autonomous navigation of unmanned surface vehicles | |
CN112327885B (en) | Unmanned ship self-adaptive global-local mixed path planning method | |
Candeloro et al. | A Voronoi-diagram-based dynamic path-planning system for underactuated marine vessels | |
CN108007452B (en) | Method and device for updating environment map according to obstacle and robot | |
CN105589464B (en) | A kind of UUV dynamic obstacle avoidance method based on Speed Obstacles method | |
Mandić et al. | Underwater object tracking using sonar and USBL measurements | |
EP3022618A1 (en) | Route planning | |
KR101628155B1 (en) | Method for detecting and tracking unidentified multiple dynamic object in real time using Connected Component Labeling | |
CN116448115B (en) | Unmanned ship probability distance map construction method based on navigation radar and photoelectricity | |
US11808590B2 (en) | Autonomous navigation in a cluttered environment | |
EP3022619B1 (en) | Route planning | |
EP3690849A1 (en) | Method and device for detecting emergency vehicles in real time and planning driving routes to cope with situations to be expected to be occurred by the emergency vehicles | |
CN110908387A (en) | Method, medium and electronic device for planning paths of unmanned surface vehicle in dynamic environment | |
Pairet et al. | Uncertainty-based online mapping and motion planning for marine robotics guidance | |
Shah et al. | Speeding up A* search on visibility graphs defined over quadtrees to enable long distance path planning for unmanned surface vehicles | |
Park et al. | Autonomous collision avoidance for unmanned surface ships using onboard monocular vision | |
Liu et al. | Multi-usv system cooperative underwater target search based on reinforcement learning and probability map | |
Teo et al. | Obstacle detection, avoidance and anti collision for MEREDITH AUV | |
Mallios et al. | Pose-based SLAM with probabilistic scan matching algorithm using a mechanical scanned imaging sonar | |
Peng et al. | LIDAR based scan matching for indoor localization | |
Praczyk et al. | Concept and first results of optical navigational system | |
Bayerl et al. | Detection and tracking of rural crossroads combining vision and LiDAR measurements | |
Miura et al. | Adaptive robot speed control by considering map and motion uncertainty | |
CN112880678A (en) | Unmanned ship navigation planning method in complex water area environment |
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 |