CN108873915A - Dynamic obstacle avoidance method and its omnidirectional's security robot - Google Patents
Dynamic obstacle avoidance method and its omnidirectional's security robot Download PDFInfo
- Publication number
- CN108873915A CN108873915A CN201811189513.6A CN201811189513A CN108873915A CN 108873915 A CN108873915 A CN 108873915A CN 201811189513 A CN201811189513 A CN 201811189513A CN 108873915 A CN108873915 A CN 108873915A
- Authority
- CN
- China
- Prior art keywords
- robot
- advance
- path
- distance
- obstacle avoidance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
Abstract
The invention discloses a kind of dynamic obstacle avoidance methods, including receive target point information and global path information, and the validity of decision paths command information；The node and unsanctioned node passed through in path label；The direction of advance of calculating robot simultaneously adjusts in real time；Reasonable forward speed is calculated, and forward speed and method of advance advance to be currently calculated, to complete dynamic obstacle avoidance.The present invention also provides a kind of omnidirectional's security robots including the dynamic obstacle avoidance method.The method of the present invention can be realized the dynamic obstacle avoidance of robot, and algorithm is reliable, and avoidance effect is preferable.
Description
Technical field
Present invention relates particularly to a kind of dynamic obstacle avoidance method and its omnidirectional's security robots.
Background technique
With the development of economic technology, intelligent equipment is had been widely used in people's production and life, gives people
Production and life bring endless convenience.And bringing with intelligent equipment, robot technology have also obtained considerable
Development, robot also gradually initially entered people's production and life.
As a critical function of robot, the mobile control of robot is always the most important thing of robot research.
Under normal circumstances, static-obstacle thing evade it is just arranged when carrying out global path planning get off, and it is dynamic careless
Barrier just need to evade in real time.This real-time avoiding barrier is known as local paths planning, and this local path is advised
Drawing just has following feature：(1) environment is unknown；(2) algorithm is real-time；(3) evade is dynamic obstacle avoidance.
The avoidance of mobile robot mainly passes through design detection of obstacles strategy and avoidance obstacle algorithm, according to sensor
Feedback information adjusts the velocity magnitude and directional information of robot in real time, to take certain tactful avoiding obstacles, to guarantee
The normal walking of robot.Currently, there are mainly two types of for the avoidance scheme based on this mobile robot：The first is to be based on
The method of vision ties up point cloud information using the 3 of monocular, binocular or depth camera acquired disturbance object, and uses certain avoidance plan
Slightly.It is this that certain limitation is had based on the method for being vision, enough illumination and texture information abundant are depended on, therefore
Comparatively requirement to environment wants higher.Second is to be mainly based upon the theory in flow field, manually based on Artificial Potential Field Method
Potential field method considers the relevant location information of mobile robot and barrier, carries out dynamic using the gravitation and repulsion relationship in flow field
The judgement of barrier.It is attractive for Artificial Potential Field Method relative target, and for barrier, then there is repulsive interaction.But
It is that this method has a defect, when being exactly complicated for environment and fast-changing barrier, just shows helpless, can go out
Existing missing inspection or erroneous detection situation.
Summary of the invention
One of the objects of the present invention is to provide a kind of dynamic obstacle avoidance that can be realized robot, algorithm is reliable and effect compared with
Good dynamic obstacle avoidance method.
The second object of the present invention is to provide a kind of omnidirectional's security robot, which includes described
Dynamic obstacle avoidance method.
This dynamic obstacle avoidance method provided by the invention, includes the following steps：
S1. robot receives target point information and global path information；
S2. robot RX path command information, and the validity of decision paths command information；
S3. the node and unsanctioned node passed through in robot label outbound path；
S4. according to the flag node of step S1 received information and step S3, the direction of advance of calculating robot；
S5. robot using the data information of laser acquisition periphery obstacle, and adjusts robot during advance in real time
Direction of advance；
S6. according to the step S5 obstruction data information obtained and obtained direction of advance information, reasonable speed of advancing is calculated
Degree, and forward speed and method of advance advance to be currently calculated, to complete dynamic obstacle avoidance.
The validity of decision paths command information described in step S2 specially determines validity using following steps：
A. the path termination in the routing instruction information received is calculated, with the Euclidean between the received target point of step S1
Distance；
B. validity is determined using following rule：
If the Euclidean distance that step A is obtained is less than the threshold value being previously set, assert that the routing instruction information is effective；
If the Euclidean distance that step A is obtained is greater than or equal to the threshold value that is previously set, assert the routing instruction information without
Effect then continues waiting for next instruction.
The direction of advance of calculating robot described in step S4 specially uses the advance side of following steps calculating robot
To：
A. according to two specified in advance empirical value index points, four direction is chosen at angle from different directions based on experience value
Target point；
B. the distance between four target points that current location and step a are chosen and deflection are determined；
C. weight is arranged to four target points that step a is obtained, and the sum of weight of four target points is 1；
D. according to the obtained distance of step b and deflection, final target point and direction of advance are calculated using following formula：
Yaw=arctan (yVector, xVector)
XVector is the coordinate in the direction x of final goal point in formula, and yVector is the seat in the direction y of final goal point
Mark, yaw is direction of advance；Wherein, xVector (i)=cos (thetai) * d (i), yVector (i)=sin (thetai)*d
(i), d (i) is the distance value of the target point in 4 different orientations of current point distance, thetaiFor the orientation of 4 different directions
Angle.
The direction of advance of real-time adjustment robot described in step S5 is specially adjusted using following steps in real time：
(1) according to the information of laser radar detection, the range information of to acquisite approachs preceding object, and judge that current path is
It is no feasible；If can walk, robot advances along target point, if can not walk, continues path computing；
(2) all directions in the set angle of current path direction two sides are traversed, in selected directions nearest barrier away from
From determining path direction；
(3) combine current path direction, calculate each direction cost and preferred index；
(4) direction of advance of the maximum direction of preferred index as robot is selected.
Judge whether current path is feasible described in step (1), specially judges whether path is feasible using following rule：
If robot is greater than the physical radius of robot at a distance from barrier, assert that path is feasible；Otherwise, then assert that path can not
Row.
The nearest obstacle distance of distance, the specially present bit of calculating robot in selected directions described in step (2)
Set the Euclidean distance with nearest barrier.
The cost in each direction of calculating and preferred index, are specially calculated using following steps described in step (3)：
All directions in I 60 degree of traverse path direction two sides, nearest obstacle distance in selected directions；
II combine current path direction, calculate each direction cost and preferred index；Cost is that robot avoids obstacle
The distance that object is advanced；And distance is shorter, preferably index is higher.
The reasonable forward speed of calculating described in step S6 is specially calculated using step：
1) according to the present speed of complaint message and robot in current direction of advance, the first suggestion speed is provided；
2) according to the present speed of complaint message and robot on target direction, the second suggestion speed is provided；
3) suggest that speed and second is suggested in speed first, choose smaller value as final forward speed.
The present invention also provides a kind of omnidirectional's security robot, which includes the dynamic obstacle avoidance
Method.
This dynamic obstacle avoidance method provided by the invention, has carried out smoothing processing in the robot global path planning stage,
4 directions are chosen in optional path, determine optimal objective point using the form of weight sum, ensure that robot ambulation smoothness；
Vector field histogram avoidance core algorithm is used simultaneously calculates the cost in each path in conjunction with nearest obstacle information, and
Determine optimal direction；Therefore the method for the present invention can be realized the dynamic obstacle avoidance of robot, and algorithm is reliable, avoidance effect compared with
It is good.
Detailed description of the invention
Fig. 1 is the method flow diagram of the method for the present invention.
Fig. 2 is the path smooth process schematic in the method for the present invention.
Specific embodiment
It is as shown in Figure 1 the method flow diagram of the method for the present invention：This dynamic obstacle avoidance method provided by the invention, including such as
Lower step：
S1. robot receives target point information and global path information；
S2. robot RX path command information, and the validity of decision paths command information；Specially using following step
It is rapid to determine validity：
A. it according to the path termination in the routing instruction information received, calculates between the received target point of step S1
Euclidean distance；
B. validity is determined using following rule：
If the Euclidean distance that step A is obtained is less than the threshold value being previously set, assert that the routing instruction information is effective；
If the Euclidean distance that step A is obtained is greater than or equal to the threshold value that is previously set, assert the routing instruction information without
Effect；Then continue waiting for next instruction.
S3. the node and unsanctioned node passed through in robot label outbound path；
S4. according to the flag node of step S1 received information and step S3, direction of advance (the specific mistake of calculating robot
Journey is as shown in Figure 2)；Specially use the direction of advance of following steps calculating robot：
A. according to two specified in advance empirical value index points, four direction is chosen at angle from different directions based on experience value
Target point；
B. the distance between four target points that current location and step a are chosen and deflection are determined；
C. weight is arranged to four target points that step a is obtained, and the sum of weight of four target points is 1；
C. according to the obtained distance of step b and deflection, final target point and direction of advance are calculated using following formula：
Yaw=arctan (yVector, xVector)
XVector is the coordinate in the direction x of final goal point in formula, and yVector is the seat in the direction y of final goal point
Mark, yaw is direction of advance；Wherein, xVector (i)=cos (thetai) * d (i), yVector (i)=sin (thetai)*d
(i), d (i) is the distance value of the target point in 4 different orientations of current point distance, thetaiFor the orientation of 4 different directions
Angle；
S5. robot using the data information of laser acquisition periphery obstacle, and adjusts robot during advance in real time
Direction of advance；Specially adjusted in real time using following steps：
(1) according to the information of laser radar detection, the range information of to acquisite approachs preceding object, and judge that current path is
It is no feasible；If can walk, robot advances along target point, if can not walk, continues path computing；Specially use
Following rule judges whether path is feasible：If robot is greater than the physical radius of robot at a distance from barrier, road is assert
Diameter is feasible；Otherwise, then assert that path is infeasible；
(2) all directions in the set angle of current path direction two sides are traversed, in selected directions nearest barrier away from
From determining path direction；The specially Euclidean distance of the current location of calculating robot and nearest barrier；
(3) combine current path direction, calculate each direction cost and preferred index；Specially using following steps into
Row calculates：
All directions in I 60 degree of traverse path direction two sides, nearest obstacle distance in selected directions；
II combine current path direction, calculate each direction cost and preferred index；Cost is that robot avoids obstacle
The distance that object is advanced；And distance is shorter, preferably index is higher；
(4) direction of advance of the maximum direction of preferred index as robot is selected.
S6. according to the step S5 obstruction data information obtained and obtained direction of advance information, reasonable speed of advancing is calculated
Degree, and forward speed and method of advance advance to be currently calculated, to complete dynamic obstacle avoidance；Specially using step into
Row calculates：
1) according to the present speed of complaint message and robot in current direction of advance, the first suggestion speed is provided；
2) according to the present speed of complaint message and robot on target direction, the second suggestion speed is provided；
3) suggest that speed and second is suggested in speed first, choose smaller value as final forward speed.
In the specific implementation, the first suggestion speed and the second suggestion speed can be previously set based on experience value, and build
Discuss a corresponding relationship, for example, first suggest complaint message and robot in speed and current direction of advance present speed it
Between mapping table and second suggest between speed and the present speed of complaint message and robot on target direction
Mapping table, then when algorithm implements, it is only necessary to which table look-up handling can be completed the given of speed.
Claims (9)
1. a kind of dynamic obstacle avoidance method, includes the following steps：
S1. robot receives target point information and global path information；
S2. robot RX path command information, and the validity of decision paths command information；
S3. the node and unsanctioned node passed through in robot label outbound path；
S4. according to the flag node of step S1 received information and step S3, the direction of advance of calculating robot；
S5. robot is during advance, using the data information of laser acquisition periphery obstacle, and before the robot of adjustment in real time
Into direction；
S6. according to the step S5 obstruction data information obtained and obtained direction of advance information, reasonable forward speed is calculated, and
Advanced with the forward speed and method of advance that are currently calculated, to complete dynamic obstacle avoidance.
2. dynamic obstacle avoidance method according to claim 1, it is characterised in that decision paths command information described in step S2
Validity, specially using following steps determine validity：
A. according to the path termination in the routing instruction information received, the Euclidean between the received target point of step S1 is calculated
Distance；
B. validity is determined using following rule：
If the Euclidean distance that step A is obtained is less than the threshold value being previously set, assert that the routing instruction information is effective；
If the Euclidean distance that step A is obtained is greater than or equal to the threshold value being previously set, assert that the routing instruction information is invalid, after
It is continuous to wait next instruction.
3. dynamic obstacle avoidance method according to claim 1 or 2, it is characterised in that before calculating robot described in step S4
Into direction, the direction of advance of following steps calculating robot is specially used：
A. according to two specified in advance empirical value index points, the target of four direction is chosen at angle from different directions based on experience value
Point；
B. the distance between four target points that current location and step a are chosen and deflection are determined；
C. weight is arranged to four target points that step a is obtained, and the sum of weight of four target points is 1；
C. according to the obtained distance of step b and deflection, final target point and direction of advance are calculated using following formula：
Yaw=arctan (yVector, xVector)
XVector is the coordinate in the direction x of final goal point in formula, and yVector is the coordinate in the direction y of final goal point, yaw
For direction of advance；Wherein, xVector (i)=cos (thetai) * d (i), yVector (i)=sin (thetai) * d (i), d (i)
For the distance value of the target point in 4 different orientations of current point distance, thetaiFor the azimuth of 4 different directions.
4. dynamic obstacle avoidance method according to claim 1 or 2, it is characterised in that real-time adjustment robot described in step S5
Direction of advance, specially adjusted in real time using following steps：
(1) according to the information of laser radar detection, the range information of to acquisite approachs preceding object, and judge that current path whether may be used
Row；If can walk, robot advances along target point, if can not walk, continues path computing；
(2) all directions in the set angle of current path direction two sides are traversed, in selected directions the nearest barrier of distance away from
From determining path direction；
(3) combine current path direction, calculate each direction cost and preferred index；
(4) direction of advance of the maximum direction of preferred index as robot is selected.
5. dynamic obstacle avoidance method according to claim 4, it is characterised in that whether step judges current path described in (1)
It is feasible, specially judge whether path is feasible using following rule：If robot is greater than the object of robot at a distance from barrier
Radius is managed, then assert that path is feasible；Otherwise, then assert that path is infeasible.
6. dynamic obstacle avoidance method according to claim 4, it is characterised in that in selected directions described in step (2) recently
Obstacle distance, the specially Euclidean distance of the current location of calculating robot and nearest barrier.
7. dynamic obstacle avoidance method according to claim 4, it is characterised in that the generation in each direction of calculating described in step (3)
Valence and preferred index are specially calculated using following steps：
All directions in I 60 degree of traverse path direction two sides, nearest obstacle distance in selected directions；
II combine current path direction, calculate each direction cost and preferred index；Cost is avoiding obstacles institute of robot
The distance of traveling；And distance is shorter, preferably index is higher.
8. dynamic obstacle avoidance method according to claim 1 or 2, it is characterised in that calculating described in step S6 is reasonably advanced
Speed is specially calculated using step：
1) according to the present speed of complaint message and robot in current direction of advance, the first suggestion speed is provided；
2) according to the present speed of complaint message and robot on target direction, the second suggestion speed is provided；
3) suggest that speed and second is suggested in speed first, choose smaller value as final forward speed.
9. a kind of omnidirectional's security robot, it is characterised in that including dynamic obstacle avoidance method described in one of claim 1~8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811189513.6A CN108873915B (en) | 2018-10-12 | 2018-10-12 | Dynamic obstacle avoidance method and omnidirectional security robot thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811189513.6A CN108873915B (en) | 2018-10-12 | 2018-10-12 | Dynamic obstacle avoidance method and omnidirectional security robot thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108873915A true CN108873915A (en) | 2018-11-23 |
| CN108873915B CN108873915B (en) | 2021-08-20 |
Family
ID=64325072
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811189513.6A Active CN108873915B (en) | 2018-10-12 | 2018-10-12 | Dynamic obstacle avoidance method and omnidirectional security robot thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108873915B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109872324A (en) * | 2019-03-20 | 2019-06-11 | 苏州博众机器人有限公司 | Ground obstacle detection method, device, equipment and storage medium |
| JP2020135560A (en) * | 2019-02-21 | 2020-08-31 | 新東工業株式会社 | Autonomous mobile robot |
| CN112990129A (en) * | 2021-04-27 | 2021-06-18 | 长沙万为机器人有限公司 | Three-dimensional object detection method and system based on combination of vision and laser radar |
| CN112975938A (en) * | 2019-12-12 | 2021-06-18 | 中国科学院沈阳自动化研究所 | Zero-space-based mechanical arm speed layer trajectory planning method |
| CN113050641A (en) * | 2021-03-18 | 2021-06-29 | 香港中文大学（深圳） | Path planning method and related equipment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005222559A (en) * | 2005-03-11 | 2005-08-18 | Matsushita Electric Works Ltd | Autonomous moving unit and autonomous moving control method |
| US20090125236A1 (en) * | 2007-03-13 | 2009-05-14 | Thales | Method for reducing nuisance alarms for anti-collision with obstacles on aircraft |
| CN102520721A (en) * | 2011-12-08 | 2012-06-27 | 北京控制工程研究所 | Autonomous obstacle-avoiding planning method of tour detector based on binocular stereo vision |
| CN105116902A (en) * | 2015-09-09 | 2015-12-02 | 北京进化者机器人科技有限公司 | Mobile robot obstacle avoidance navigation method and system |
| CN105652870A (en) * | 2016-01-19 | 2016-06-08 | 中国人民解放军国防科学技术大学 | Autonomous patrol control system and method of intelligent security service robot |
| CN106681320A (en) * | 2016-12-15 | 2017-05-17 | 浙江大学 | Mobile robot navigation control method based on laser data |
| CN107703948A (en) * | 2017-11-14 | 2018-02-16 | 上海理工大学 | Mobile robot local dynamic station paths planning method based on adaptive dynamic window |
| CN108469827A (en) * | 2018-05-16 | 2018-08-31 | 江苏华章物流科技股份有限公司 | A kind of automatic guided vehicle global path planning method suitable for logistic storage system |
| CN108549385A (en) * | 2018-05-22 | 2018-09-18 | 东南大学 | A kind of Robotic Dynamic paths planning method of combination A* algorithms and VFH obstacle avoidance algorithms |
| CN108549378A (en) * | 2018-05-02 | 2018-09-18 | 长沙学院 | A kind of mixed path method and system for planning based on grating map |
-
2018
- 2018-10-12 CN CN201811189513.6A patent/CN108873915B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005222559A (en) * | 2005-03-11 | 2005-08-18 | Matsushita Electric Works Ltd | Autonomous moving unit and autonomous moving control method |
| US20090125236A1 (en) * | 2007-03-13 | 2009-05-14 | Thales | Method for reducing nuisance alarms for anti-collision with obstacles on aircraft |
| CN102520721A (en) * | 2011-12-08 | 2012-06-27 | 北京控制工程研究所 | Autonomous obstacle-avoiding planning method of tour detector based on binocular stereo vision |
| CN105116902A (en) * | 2015-09-09 | 2015-12-02 | 北京进化者机器人科技有限公司 | Mobile robot obstacle avoidance navigation method and system |
| CN105652870A (en) * | 2016-01-19 | 2016-06-08 | 中国人民解放军国防科学技术大学 | Autonomous patrol control system and method of intelligent security service robot |
| CN106681320A (en) * | 2016-12-15 | 2017-05-17 | 浙江大学 | Mobile robot navigation control method based on laser data |
| CN107703948A (en) * | 2017-11-14 | 2018-02-16 | 上海理工大学 | Mobile robot local dynamic station paths planning method based on adaptive dynamic window |
| CN108549378A (en) * | 2018-05-02 | 2018-09-18 | 长沙学院 | A kind of mixed path method and system for planning based on grating map |
| CN108469827A (en) * | 2018-05-16 | 2018-08-31 | 江苏华章物流科技股份有限公司 | A kind of automatic guided vehicle global path planning method suitable for logistic storage system |
| CN108549385A (en) * | 2018-05-22 | 2018-09-18 | 东南大学 | A kind of Robotic Dynamic paths planning method of combination A* algorithms and VFH obstacle avoidance algorithms |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2020135560A (en) * | 2019-02-21 | 2020-08-31 | 新東工業株式会社 | Autonomous mobile robot |
| JP7120071B2 (en) | 2019-02-21 | 2022-08-17 | 新東工業株式会社 | autonomous mobile robot |
| CN109872324A (en) * | 2019-03-20 | 2019-06-11 | 苏州博众机器人有限公司 | Ground obstacle detection method, device, equipment and storage medium |
| CN112975938A (en) * | 2019-12-12 | 2021-06-18 | 中国科学院沈阳自动化研究所 | Zero-space-based mechanical arm speed layer trajectory planning method |
| CN112975938B (en) * | 2019-12-12 | 2022-04-05 | 中国科学院沈阳自动化研究所 | Zero-space-based mechanical arm speed layer trajectory planning method |
| CN113050641A (en) * | 2021-03-18 | 2021-06-29 | 香港中文大学（深圳） | Path planning method and related equipment |
| CN113050641B (en) * | 2021-03-18 | 2023-02-28 | 香港中文大学（深圳） | Path planning method and related equipment |
| CN112990129A (en) * | 2021-04-27 | 2021-06-18 | 长沙万为机器人有限公司 | Three-dimensional object detection method and system based on combination of vision and laser radar |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108873915B (en) | 2021-08-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108873915A (en) | Dynamic obstacle avoidance method and its omnidirectional's security robot | |
| CN108762264A (en) | The dynamic obstacle avoidance method of robot based on Artificial Potential Field and rolling window | |
| CN106767860B (en) | A method of shortening intelligent automobile path planning search time based on heuristic search algorithm | |
| CN110262518A (en) | Automobile navigation method, system and medium based on track topological map and avoidance | |
| CN105629974B (en) | A kind of robot path planning method and system based on modified Artificial Potential Field Method | |
| CN107121981A (en) | A kind of AGV line walkings navigation of view-based access control model and localization method | |
| CN109407705A (en) | A kind of method, apparatus, equipment and the storage medium of unmanned plane avoiding barrier | |
| CN106444780A (en) | Robot autonomous navigation method and system based on vision positioning algorithm | |
| CN110361013A (en) | A kind of path planning system and method for auto model | |
| CN108132675A (en) | Unmanned plane is maked an inspection tour from main path cruise and intelligent barrier avoiding method by a kind of factory | |
| CN107990902B (en) | Air navigation aid, navigation system based on cloud, electronic equipment | |
| CN104881045A (en) | Bionic robot fish three-dimensional tracking method based on embedded visual guidance | |
| CN107560620A (en) | A kind of method for path navigation and chip and robot | |
| CN113701780A (en) | Real-time obstacle avoidance planning method based on A-star algorithm | |
| CN113467476B (en) | Collision-free detection rapid random tree global path planning method considering corner constraint | |
| CN109490926A (en) | A kind of paths planning method based on binocular camera and GNSS | |
| Li et al. | Virtual lane boundary generation for human-compatible autonomous driving: A tight coupling between perception and planning | |
| Fareh et al. | A vision-based kinematic tracking control system using enhanced-PRM for differential wheeled mobile robot | |
| Kanaki et al. | Cooperative moving-object tracking with multiple mobile sensor nodes—Size and posture estimation of moving objects using in-vehicle multilayer laser scanner | |
| CN113050642B (en) | Automatic navigation method for intelligent cable trench inspection robot with multi-sensor fusion | |
| Wang et al. | Svpto: Safe visibility-guided perception-aware trajectory optimization for aerial tracking | |
| Meng et al. | A navigation framework for mobile robots with 3D LiDAR and monocular camera | |
| Du et al. | Hierarchical path planning and obstacle avoidance control for unmanned surface vehicle | |
| Dong et al. | Path Planning Research for Outdoor Mobile Robot | |
| Ma et al. | DeepGoal: Learning to drive with driving intention from human control demonstration |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190710 Address after: 410013 16 Floor, F1 Building, Lugu Enterprise Square, 27 Wenxuan Road, Changsha High-tech Development Zone, Hunan Province Applicant after: Changsha Wanwei Robot Co., Ltd. Address before: 410013 16 Floor, F1 Building, Lugu Enterprise Square, 27 Wenxuan Road, Changsha High-tech Development Zone, Hunan Province Applicant before: Hunan Wan Intelligent Robot Technology Co., Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |