CN107092252A - A kind of robot automatic obstacle avoidance method and its device based on machine vision - Google Patents

A kind of robot automatic obstacle avoidance method and its device based on machine vision Download PDF

Info

Publication number
CN107092252A
CN107092252A CN201710233985.6A CN201710233985A CN107092252A CN 107092252 A CN107092252 A CN 107092252A CN 201710233985 A CN201710233985 A CN 201710233985A CN 107092252 A CN107092252 A CN 107092252A
Authority
CN
China
Prior art keywords
pedestrian
path
obstacle
msub
mrow
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
Application number
CN201710233985.6A
Other languages
Chinese (zh)
Inventor
余小欢
钱锋
姚金良
张秀达
白云峰
吴旷
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Guangbo Intelligent Technology Co Ltd
Original Assignee
Hangzhou Guangbo Intelligent Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Hangzhou Guangbo Intelligent Technology Co Ltd filed Critical Hangzhou Guangbo Intelligent Technology Co Ltd
Priority to CN201710233985.6A priority Critical patent/CN107092252A/en
Publication of CN107092252A publication Critical patent/CN107092252A/en
Pending legal-status Critical Current

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
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course 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
    • G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Multimedia (AREA)
  • Electromagnetism (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Manipulator (AREA)

Abstract

The present invention provides a kind of robot automatic obstacle avoidance method based on machine vision, including step obtains visual information, and visual information is resolved, detection of obstacles, obstacle identity identification.The invention further relates to a kind of robot automatic obstacle avoidance device based on machine vision, the present invention combines the detection, identification and avoidance of barrier, and the strategy of different avoidances is used according to the difference of barrier.Particularly, the identification of the barrier based on depth camera, is divided into pedestrian and non-pedestrian two types by barrier, using active avoidance, it is ensured that avoidance safety, improves the intelligent and interactivity of robot.

Description

A kind of robot automatic obstacle avoidance method and its device based on machine vision
Technical field
The present invention relates to robot obstacle-avoiding, and in particular to a kind of robot automatic obstacle avoidance method based on machine vision and its Device.
Background technology
With the development of science and technology, the purposes of robot is also more and more extensive, particularly service robot is in the path of traveling On would ordinarily be encountered a variety of barriers, the method for the avoidance of traditional service class robot is using depth camera, swashed Optical radar, binocular vision system etc. obtain the environmental information of current scene, then using Visual Graph method, grid map method, topological approach, Artificial Potential Field Method etc. obtains transitable path and then realizes the function of avoidance, and this mode has the following disadvantages：
1st, intelligence degree is low, it is impossible to the type of cognitive disorders thing, it is impossible to which the type for different barriers is carried out not Same avoidance action, and can only halt and wait when running into crowd than comparatively dense；
2nd, security is low, the barrier in motion, pedestrian especially on the move, and it is suitable that service robot is shown Answering property is poor, and easy synkinematic barrier collides；
3rd, interactivity is poor, without any interaction prompts, during actual motion, service-delivery machine when running into the barrier of pedestrian target People actively can not send warning to pedestrian's obstacle around, remind pedestrian to take care, cause man-machine interaction poor.
The content of the invention
It is an object of the invention to the problem above for overcoming prior art presence, there is provided a kind of machine based on machine vision People's automatic obstacle avoidance method and its device, realize that degree of intelligence is high, safe, the strong service robot avoidance of interactivity.
To realize above-mentioned technical purpose and the technique effect, the present invention is achieved through the following technical solutions：
A kind of robot automatic obstacle avoidance method based on machine vision, comprises the following steps：
Visual information is obtained, the forward directional vision information of robot is gathered by camera；
Visual information is resolved, and is resolved visual information and is obtained corresponding 3D point cloud figure；
Detection of obstacles, judges in direction of advance with the presence or absence of the forward obstacle of robot is hindered, enters if it there is obstacle Enter obstacle identity identification, robot moves ahead by original Global motion planning path if in the absence of obstacle；
Obstacle identity is recognized, is matched using visual information with pedestrian's standard vision information model, whether disturbance in judgement thing For pedestrian, enter pedestrian's avoidance pattern if barrier is pedestrian, enter non-pedestrian avoidance pattern if barrier is non-pedestrian；
Pedestrian's avoidance pattern, calculates and corrects pass, judge path whether P Passable, if the P Passable of path Pass through and taken care by voice reminder pedestrian by calculating path, stop moving ahead and voice message if path cannot pass through Pedestrian is avoided；Non-pedestrian avoidance pattern, calculates and corrects pass, judge path whether P Passable, if path can With current then current by path is calculated, stop moving ahead if path cannot pass through and wait.Further, described acquisition is regarded Feel that information includes obtaining robot direction of advance depth map information by depth camera.
Further, described visual information is resolved resolves 3D point cloud using depth map information, and formula is as follows,
Xworld、Yworld、ZworldWorld coordinates under correspondence depth camera coordinate system, x, y are depth map image coordinates Coordinate under system, deep is the depth value at (x, y) point, c in depth mapx、cyThe seat of image center point under correspondence image coordinate system Mark, Tx、TyCorrespondence single pixel point x directions and the size in y directions, fx、fyFocus information on correspondence x directions and y directions.
Further, described obstacle identity identification comprises the following steps：Barrier marginal information in depth map is extracted, Marginal information local maximum, and the pedestrian head summit using maximum point as candidate are resolved, with pedestrian's standard vision information Template matches, according to matching result disturbance in judgement species type.
Further, described template matching method is based on Chamfer matchings.
Further, visual information also includes RGB image or gray level image in the identification of described obstacle identity.
A kind of robot automatic obstacle avoidance device based on machine vision, including software module, hardware module；Described hardware Module includes a camera, a voice device, a processor；Described camera is used to obtain the forward directional vision information of robot； Described voice device points out pedestrian to take care or note avoiding for sending caveat；Described processor is used to carry soft Part module, described software module couples communication with described camera, voice device by described processor；Described software The obstacle information that module is used for during being moved ahead according to visual information identification, and selection avoidance mould is judged according to obstacle information Formula；Described avoidance pattern includes pedestrian's avoidance pattern, non-pedestrian avoidance pattern, and avoidance is performed according to the avoidance pattern of selection. Further, described camera is depth camera.
Further, described software module includes obstacle detection module, obstacle identification module, path planning module, language Sound reminding module；The depth map that described obstacle detection module is used to be obtained according to depth camera detects whether deposited in direction of advance Hindering the forward obstacle of robot；Whether it is pedestrian that described obstacle identification module is used for according to depth map cognitive disorders thing； Described path planning module is used for according to obstacle information planning robot's forward path；Described voice cue module is used for The described voice device of control sends caveat prompting pedestrian and takes care or note avoiding；；Described pedestrian's avoidance pattern bag Include and pass calculated and corrected by described path planning module, judge path whether P Passable, if path can lead to It is capable then current and remind pedestrian to take care by described voice module by path is calculated, pass through if path cannot be passed through Described voice message pedestrian is avoided；Described non-pedestrian avoidance pattern includes leading to described path planning module calculating simultaneously Correct pass, judge path whether P Passable, it is current by path is calculated if the P Passable of path, if path cannot Current then stopping moves ahead and waited.
Further, the planning algorithm that described path planning module is used includes steepest descent algorithm, the greedy calculation in part Method, the most short algorithm of dijkstra's algorithm, Floyed algorithms, SPFA algorithms, graph theory, genetic algorithm, cellular automata, immune calculation Method, TABU search, simulated annealing, artificial neural network, ant group algorithm, particle cluster algorithm.
The beneficial effects of the invention are as follows:The present invention provides a kind of robot automatic obstacle avoidance method based on machine vision, bag Include step and obtain visual information, visual information is resolved, detection of obstacles, obstacle identity identification.The invention further relates to a kind of base In the robot automatic obstacle avoidance device of machine vision, the present invention combines the detection, identification and avoidance of barrier, according to barrier Difference use different avoidances strategy.Particularly, the identification of the barrier based on depth camera, is divided into pedestrian by barrier With non-pedestrian two types, using active avoidance, it is ensured that avoidance safety, the intelligent and interactivity of robot is improved.
Described above is only the general introduction of technical solution of the present invention, in order to better understand the technological means of the present invention, And can be practiced according to the content of specification, below with presently preferred embodiments of the present invention and coordinate accompanying drawing describe in detail as after. The embodiment of the present invention is shown in detail by following examples and its accompanying drawing.
Brief description of the drawings
Accompanying drawing described herein is used for providing a further understanding of the present invention, constitutes the part of the application, this hair Bright schematic description and description is used to explain the present invention, does not constitute inappropriate limitation of the present invention.In the accompanying drawings：
Fig. 1 is a kind of robot automatic obstacle avoidance method flow diagram based on machine vision of the present invention；
Fig. 2 is the robot automatic obstacle avoidance method flow diagram based on depth camera of the present invention；
Fig. 3 is barrier marginal information schematic diagram in depth map of the invention；
Fig. 4 is pedestrian's standard vision information model schematic diagram based on depth camera of the present invention；
Fig. 5 is a kind of robot automatic obstacle avoidance device organization chart based on machine vision of the present invention.
Embodiment
Below with reference to the accompanying drawings and in conjunction with the embodiments, the present invention is described in detail.
Shown in reference picture 1-5, a kind of robot automatic obstacle avoidance method based on machine vision, as shown in Figure 1 and Figure 2, including Following steps：
Visual information is obtained, the forward directional vision information of robot is gathered by camera；Preferably, in one embodiment, Visual information obtains robot direction of advance depth map information by depth camera.
Visual information is resolved, and is resolved visual information and is obtained corresponding 3D point cloud figure；In one embodiment, depth camera is passed through The depth map of acquisition, depth map is converted to the 3D point cloud figure under camera coordinates system, and formula is as follows,
Xworld、Yworld、ZworldWorld coordinates under correspondence depth camera coordinate system, x, y are depth map image coordinates Coordinate under system, deep is the depth value at (x, y) point, c in depth mapx、cyThe seat of image center point under correspondence image coordinate system Mark, Tx、TyCorrespondence single pixel point x directions and the size in y directions, fx、fyFocus information on correspondence x directions and y directions.
Detection of obstacles, judges in direction of advance with the presence or absence of the forward obstacle of robot is hindered, enters if it there is obstacle Enter obstacle identity identification, robot moves ahead by original Global motion planning path if in the absence of obstacle；By in depth camera 3D point cloud information under coordinate system is compared and screened, and screens and records out in 3D point cloud on the original path of robot Point, judges there is obstacle if the point is present, general, provided with motion positions modules such as GPS modules in service robot, pass through Original path and robot physical model, energy rapid build robot motion's passage zone, and combine motion positions, real-time update Robot motion position, and be synchronized in the depth camera of machine vision and the present embodiment, realize that kinetic coordinate system is sat with vision Mark the mutual unification of system.
Obstacle identity is recognized, is matched using visual information with pedestrian's standard vision information model, whether disturbance in judgement thing For pedestrian, enter pedestrian's avoidance pattern if barrier is pedestrian, enter non-pedestrian avoidance pattern if barrier is non-pedestrian； In one embodiment, by extracting barrier marginal information in depth map, marginal information local maximum is resolved, and with maximum Point as candidate pedestrian head summit, as shown in figure 3, in small circle be maximum point, using this as candidate pedestrian's head Portion summit, obtains final human upper limb target, such as Fig. 4 near the pedestrian head summit of candidate using the mode of template matches Shown, according to matching result disturbance in judgement species type, this is in embodiment, and template matching method is to be matched based on Chamfer, Chamfer matchings are remained to detect object, had because it is in the case of target occurs slightly rotation, distorts and be asymmetrical Good robustness, its calculation formula is as follows：
In formula, T={ tiBe template image edge point set；| T | represent set T points；E={ ejIt is target figure The edge point set of picture；tiAnd ejI-th, j-th of marginal point respectively in T and E；dT(T, E) is the marginal point in template T The average distance of nearest pixel into image E；T and E2 edge similar degree are higher, dTThe value of (T, E) will be smaller, as T and E It is d if identical edgeT(T, E)=0.
Pedestrian's avoidance pattern, calculates and corrects pass, judges whether path can pass through, if path can pass through based on Calculate path to pass through and take care by voice reminder pedestrian, voice message pedestrian could avoid if path is infeasible.Pedestrian Avoidance pattern Real time identification pedestrian position, judges according to the pedestrian position information of present frame and corrects pass, to each frame Deep image information carries out matching judgment, updates pedestrian's dynamic, P Passable is judged whether according to the pedestrian position of present frame, if Path P Passable then passes through by calculating path and reminds pedestrian to take care by described voice module, if path cannot It is current then avoided by described voice message pedestrian.
Non-pedestrian avoidance pattern, calculates and corrects pass, judges whether path can pass through, and is pressed if path can be passed through Calculate path to pass through, stop moving ahead if the impassabitity of path and wait.
It should be appreciated that when calculating and correcting pass, being located in the 3D point cloud filtered out on the original path of robot Point wrapped up, parcel radius according to robot size depending on, in the area of space after parcel, to forward path carry out Again plan, general planning algorithm includes steepest descent algorithm, part greedy algorithm, dijkstra's algorithm, Floyed algorithms, The most short algorithm of SPFA algorithms, graph theory, genetic algorithm, cellular automata, immune algorithm, TABU search, simulated annealing, artificial god Through network, ant group algorithm, particle cluster algorithm, algorithm is prior art, chooses algorithms of different according to practical application scene, herein not Do excessive narration.
Preferably, in another embodiment, the visual information obtained from the industrial camera of non-depth camera, in barrier Visual information also includes RGB image or gray level image in type identification, by RGB image or gray level image are carried out two inhibition and generation, Boundary Extraction, can also resolve boundary information local maximum, method and mould in obstacle identity identification to the boundary information of extraction Plate matching is identical, will not be repeated here.
A kind of robot automatic obstacle avoidance device based on machine vision, as shown in figure 5, including software module, hardware module； Described hardware module includes a camera, a voice device, a processor；Described camera is used to obtain line direction before robot Visual information；Described voice device points out pedestrian to take care or note avoiding for sending caveat；Described processor For carrying software module, described software module couples communication with described camera, voice device by described processor； The obstacle information that described software module is used for during being moved ahead according to visual information identification, and judged according to obstacle information Select avoidance pattern；Described avoidance pattern includes pedestrian's avoidance pattern, non-pedestrian avoidance pattern, according to the avoidance pattern of selection Perform avoidance.
Preferably, described camera is depth camera, and described software module includes obstacle detection module, obstacle identification mould Block, path planning module, voice cue module；The depth map that described obstacle detection module is used to be obtained according to depth camera is examined Survey in direction of advance with the presence or absence of the obstacle for hindering robot to move ahead；Described obstacle identification module is used to be recognized according to depth map Whether barrier is pedestrian；Described path planning module is used for according to obstacle information planning robot's forward path；It is described Voice cue module be used for control described voice device send caveat prompting pedestrian take care or point out avoidance；It is described Avoidance pattern include pedestrian's avoidance pattern, non-pedestrian avoidance pattern；Described pedestrian's avoidance pattern includes passing through described road Footpath planning module calculates and corrects pass, judge path whether P Passable, if the P Passable of path by calculate path Pass through and remind pedestrian to take care by described voice module, pass through described voice message pedestrian if path is infeasible Avoided；Described non-pedestrian avoidance pattern includes logical described path planning module and calculates and correct pass, judges Whether path can pass through, current by path is calculated if the P Passable of path, stop moving ahead if path cannot pass through and wait Treat.
The present invention provides a kind of robot automatic obstacle avoidance method and apparatus based on machine vision, by the detection of barrier, Identification and avoidance are combined, and the strategy of different avoidances is used according to the difference of barrier.Particularly, the obstacle based on depth camera The identification of thing, is divided into pedestrian and non-pedestrian two types by barrier, using active avoidance, it is ensured that avoidance safety, improves machine The intelligent and interactivity of device people.
The foregoing is only a preferred embodiment of the present invention, not makees any formal limitation to the present invention；It is all The those of ordinary skill of the industry can be shown in by specification accompanying drawing and described above and swimmingly implement the present invention；But, it is all Those skilled in the art without departing from the scope of the present invention, are done using disclosed above technology contents The equivalent variations of a little variation, modification and evolution gone out, are the equivalent embodiment of the present invention；Meanwhile, it is all according to the present invention's Variation, modification and evolution of any equivalent variations that substantial technological is made to above example etc., still fall within the skill of the present invention Within the protection domain of art scheme.

Claims (10)

1. a kind of robot automatic obstacle avoidance method based on machine vision, it is characterised in that comprise the following steps：
Visual information is obtained, the forward directional vision information of robot is gathered by camera；
Visual information is resolved, and is resolved visual information and is obtained corresponding 3D point cloud figure；
Detection of obstacles, judges with the presence or absence of the obstacle for hindering robot to move ahead in direction of advance,
The barriers to entry thing type identification if it there is obstacle, robot is pressed before original Global motion planning path if in the absence of obstacle OK；
Obstacle identity is recognized, is matched using visual information with pedestrian's standard vision information model,
Whether disturbance in judgement thing is pedestrian, enters pedestrian's avoidance pattern if barrier is pedestrian,
Enter non-pedestrian avoidance pattern if barrier is non-pedestrian；
Pedestrian's avoidance pattern, calculates and corrects pass, judge path whether P Passable,
Pass through and taken care by voice reminder pedestrian by calculating path if the P Passable of path,
Voice message pedestrian is avoided if path cannot pass through；
Non-pedestrian avoidance pattern, calculates and corrects pass, judge path whether P Passable,
It is current by path is calculated if the P Passable of path, stop moving ahead if path cannot pass through and wait.
2. a kind of robot automatic obstacle avoidance method based on machine vision according to claim 1, it is characterised in that：It is described Acquisition visual information include by depth camera acquisition robot direction of advance depth map information.
3. a kind of robot automatic obstacle avoidance method based on machine vision according to claim 2, it is characterised in that：It is described Visual information resolve and resolve 3D point cloud using depth map information, formula is as follows,
<mfenced open = "{" close = ""> <mtable> <mtr> <mtd> <msub> <mi>X</mi> <mrow> <mi>w</mi> <mi>o</mi> <mi>r</mi> <mi>l</mi> <mi>d</mi> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <mo>-</mo> <mi>d</mi> <mi>e</mi> <mi>e</mi> <mi>p</mi> <mo>*</mo> <mrow> <mo>(</mo> <mi>x</mi> <mo>-</mo> <msub> <mi>c</mi> <mi>x</mi> </msub> <mo>)</mo> </mrow> <mo>*</mo> <msub> <mi>T</mi> <mi>x</mi> </msub> </mrow> <msub> <mi>f</mi> <mi>x</mi> </msub> </mfrac> </mtd> </mtr> <mtr> <mtd> <mrow> <msub> <mi>Y</mi> <mrow> <mi>w</mi> <mi>o</mi> <mi>r</mi> <mi>l</mi> <mi>d</mi> </mrow> </msub> <mo>=</mo> <mfrac> <mrow> <mi>d</mi> <mi>e</mi> <mi>e</mi> <mi>p</mi> <mo>*</mo> <mrow> <mo>(</mo> <mo>-</mo> <mi>y</mi> <mo>+</mo> <msub> <mi>c</mi> <mi>y</mi> </msub> <mo>)</mo> </mrow> <mo>*</mo> <msub> <mi>T</mi> <mi>y</mi> </msub> </mrow> <msub> <mi>f</mi> <mi>y</mi> </msub> </mfrac> </mrow> </mtd> </mtr> <mtr> <mtd> <mrow> <msub> <mi>Z</mi> <mrow> <mi>w</mi> <mi>o</mi> <mi>r</mi> <mi>l</mi> <mi>d</mi> </mrow> </msub> <mo>=</mo> <mi>d</mi> <mi>e</mi> <mi>e</mi> <mi>p</mi> </mrow> </mtd> </mtr> </mtable> </mfenced>
Xworld、Yworld、ZworldWorld coordinates under correspondence depth camera coordinate system, under x, y are depth map image coordinate system Coordinate, deep is the depth value at (x, y) point, c in depth mapx、cyThe coordinate of image center point, T under correspondence image coordinate systemx、 TyCorrespondence single pixel point x directions and the size in y directions, fx、fyFocus information on correspondence x directions and y directions.
4. a kind of robot automatic obstacle avoidance method based on machine vision according to claim 2, it is characterised in that described Obstacle identity identification comprise the following steps：Barrier marginal information in depth map is extracted, marginal information local maximum is resolved Value, and the pedestrian head summit using maximum point as candidate, are matched with pedestrian's standard vision information model, according to matching result Disturbance in judgement species type.
5. a kind of robot automatic obstacle avoidance method based on machine vision according to claim 4, it is characterised in that：It is described Template matching method be based on Chamfer matching.
6. a kind of robot automatic obstacle avoidance method based on machine vision according to claim 1, it is characterised in that：It is described Obstacle identity identification in visual information also include RGB image or gray level image.
7. a kind of robot automatic obstacle avoidance device based on machine vision, including software module, hardware module, it is characterised in that： Described hardware module includes a camera, a voice device, a processor；Described camera is used to obtain line direction before robot Visual information；Described voice device points out pedestrian to take care or note avoiding for sending caveat；Described processor For carrying software module, described software module couples communication with described camera, voice device by described processor； The obstacle information that described software module is used for during being moved ahead according to visual information identification, and judged according to obstacle information Select avoidance pattern；Described avoidance pattern includes pedestrian's avoidance pattern, non-pedestrian avoidance pattern, according to the avoidance pattern of selection Perform avoidance.
8. a kind of robot automatic obstacle avoidance device based on machine vision according to claim 7, it is characterised in that：It is described Camera be depth camera.
9. a kind of robot automatic obstacle avoidance device based on machine vision according to claim 8, it is characterised in that：It is described Software module include obstacle detection module, obstacle identification module, path planning module, voice cue module；Described obstacle The depth map that detection module is used to be obtained according to depth camera is detected in direction of advance with the presence or absence of the barrier for hindering robot to move ahead Hinder；Whether it is pedestrian that described obstacle identification module is used for according to depth map cognitive disorders thing；Described path planning module is used According to obstacle information planning robot's forward path；Described voice cue module is used to control described voice device to send out Go out caveat prompting pedestrian to take care or note avoiding；；Described pedestrian's avoidance pattern includes passing through described path planning Module calculates pass, judge path whether P Passable, pass through if the P Passable of path and pass through institute by calculating path The voice module stated reminds pedestrian to take care, and is kept away if path cannot pass through by described voice message pedestrian Allow；
Described non-pedestrian avoidance pattern includes logical described path planning module and calculates and correct pass, judges that path is No P Passable, it is current by path is calculated if the P Passable of path, stop moving ahead if path cannot pass through and wait.
10. a kind of robot automatic obstacle avoidance device based on machine vision according to claim 9, it is characterised in that：Institute The planning algorithm that the path planning module stated is used includes steepest descent algorithm, part greedy algorithm, dijkstra's algorithm, The most short algorithm of Floyed algorithms, SPFA algorithms, graph theory, genetic algorithm, cellular automata, immune algorithm, TABU search, simulation are moved back Fire, artificial neural network, ant group algorithm, particle cluster algorithm.
CN201710233985.6A 2017-04-11 2017-04-11 A kind of robot automatic obstacle avoidance method and its device based on machine vision Pending CN107092252A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201710233985.6A CN107092252A (en) 2017-04-11 2017-04-11 A kind of robot automatic obstacle avoidance method and its device based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201710233985.6A CN107092252A (en) 2017-04-11 2017-04-11 A kind of robot automatic obstacle avoidance method and its device based on machine vision

Publications (1)

Publication Number Publication Date
CN107092252A true CN107092252A (en) 2017-08-25

Family

ID=59636969

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201710233985.6A Pending CN107092252A (en) 2017-04-11 2017-04-11 A kind of robot automatic obstacle avoidance method and its device based on machine vision

Country Status (1)

Country Link
CN (1) CN107092252A (en)

Cited By (41)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107831760A (en) * 2017-09-27 2018-03-23 安徽硕威智能科技有限公司 Robot barrier thing processing system and method
CN107894773A (en) * 2017-12-15 2018-04-10 广东工业大学 A kind of air navigation aid of mobile robot, system and relevant apparatus
CN108516024A (en) * 2018-03-20 2018-09-11 马乐平 A kind of imitative worm specialized robot and its control method
CN108553042A (en) * 2018-05-21 2018-09-21 安克创新科技股份有限公司 A kind of clean robot
CN108647781A (en) * 2018-05-18 2018-10-12 中国科学院计算技术研究所 A kind of artificial intelligence chip processing device
CN108764470A (en) * 2018-05-18 2018-11-06 中国科学院计算技术研究所 A kind of processing method of artificial neural network operation
CN108764465A (en) * 2018-05-18 2018-11-06 中国科学院计算技术研究所 A kind of processing unit carrying out neural network computing
CN108958263A (en) * 2018-08-03 2018-12-07 江苏木盟智能科技有限公司 A kind of Obstacle Avoidance and robot
CN109213157A (en) * 2018-08-28 2019-01-15 北京秦圣机器人科技有限公司 Data center's crusing robot paths planning method based on improved Ant Colony System
CN109298708A (en) * 2018-08-31 2019-02-01 中船重工鹏力（南京）大气海洋信息系统有限公司 A kind of unmanned boat automatic obstacle avoiding method merging radar and photoelectric information
CN109445438A (en) * 2018-12-05 2019-03-08 英华达（上海）科技有限公司 Cruise control method and system based on the cruising device that map is shared
CN109461185A (en) * 2018-09-10 2019-03-12 西北工业大学 A kind of robot target automatic obstacle avoidance method suitable for complex scene
CN109547702A (en) * 2018-12-13 2019-03-29 清华大学 A kind of light draws photography machine people's system
CN109540022A (en) * 2019-01-03 2019-03-29 沈阳天骄科技有限公司 Close a position robot path planning and decision-making technique based on TOF depth camera
CN109571502A (en) * 2018-12-30 2019-04-05 深圳市普渡科技有限公司 Robot allocator
CN109634286A (en) * 2019-01-21 2019-04-16 深圳市傲基电子商务股份有限公司 Grass-removing robot vision barrier-avoiding method, grass-removing robot and readable storage medium storing program for executing
CN109895780A (en) * 2017-12-07 2019-06-18 北京京东尚科信息技术有限公司 A kind of method and apparatus realizing unmanned equipment autonomously and getting rid of poverty
CN109960263A (en) * 2019-03-26 2019-07-02 深兰科技（上海）有限公司 One kind peddling robot control method, device and storage medium
CN110033612A (en) * 2019-05-21 2019-07-19 上海木木聚枞机器人科技有限公司 A kind of pedestrian's based reminding method, system and robot based on robot
CN110442128A (en) * 2019-07-20 2019-11-12 河北科技大学 AGV paths planning method based on feature point extraction ant group algorithm
CN110622085A (en) * 2019-08-14 2019-12-27 珊口（深圳）智能科技有限公司 Mobile robot and control method and control system thereof
CN110941279A (en) * 2019-12-21 2020-03-31 上海有个机器人有限公司 Control method for preventing presser foot of robot in dense stream scene
CN111046776A (en) * 2019-12-06 2020-04-21 杭州成汤科技有限公司 Mobile robot traveling path obstacle detection method based on depth camera
CN111178286A (en) * 2019-12-31 2020-05-19 智车优行科技（上海）有限公司 Attitude trajectory prediction method and device and electronic equipment
CN111376258A (en) * 2018-12-29 2020-07-07 纳恩博（常州）科技有限公司 Control method, device, equipment and storage medium
CN111374607A (en) * 2018-12-29 2020-07-07 尚科宁家(中国)科技有限公司 Target identification method and device based on sweeping robot, equipment and medium
CN111487958A (en) * 2019-01-28 2020-08-04 北京奇虎科技有限公司 Control method and device of sweeping robot
CN111872928A (en) * 2020-06-08 2020-11-03 特斯联科技集团有限公司 Obstacle attribute distinguishing method and system and intelligent robot
CN112230652A (en) * 2020-09-04 2021-01-15 安克创新科技股份有限公司 Walking robot, method of controlling movement of walking robot, and computer storage medium
CN112327854A (en) * 2020-11-12 2021-02-05 炬星科技（深圳）有限公司 Path blocking processing method and robot
CN112405532A (en) * 2020-11-06 2021-02-26 深圳优地科技有限公司 Movement control method and device and robot
CN112506204A (en) * 2020-12-17 2021-03-16 深圳市普渡科技有限公司 Robot obstacle meeting processing method, device, equipment and computer readable storage medium
CN112711250A (en) * 2019-10-25 2021-04-27 科沃斯机器人股份有限公司 Self-walking equipment movement control method and self-walking equipment
WO2021082964A1 (en) * 2019-10-31 2021-05-06 灵动科技（北京）有限公司 Autonomous moving device and warehouse logistics system
WO2021103987A1 (en) * 2019-11-29 2021-06-03 深圳市杉川机器人有限公司 Control method for sweeping robot, sweeping robot, and storage medium
US20210209367A1 (en) * 2018-05-22 2021-07-08 Starship Technologies Oü Method and system for analyzing robot surroundings
CN113397437A (en) * 2021-07-12 2021-09-17 丁杨 Sweeping robot and obstacle avoidance method thereof
CN113786125A (en) * 2021-08-17 2021-12-14 科沃斯机器人股份有限公司 Operation method, self-moving device and storage medium
CN114442644A (en) * 2022-04-11 2022-05-06 季华实验室 Multi-robot obstacle avoidance method and device, electronic equipment and storage medium
CN117506857A (en) * 2024-01-04 2024-02-06 佛山科学技术学院 Mobile robot and safe motion control method
CN117506857B (en) * 2024-01-04 2024-04-30 佛山科学技术学院 Mobile robot and safe motion control method

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103576686A (en) * 2013-11-21 2014-02-12 中国科学技术大学 Automatic guide and obstacle avoidance method for robot
KR101539270B1 (en) * 2015-02-27 2015-07-24 군산대학교산학협력단 sensor fusion based hybrid reactive motion planning method for collision avoidance and autonomous navigation, recording medium and mobile robot for performing the method
CN104865965A (en) * 2015-05-20 2015-08-26 深圳市锐曼智能装备有限公司 Barrier-avoidance control method combining depth camera and supersonic wave for robot and system thereof
CN105045263A (en) * 2015-07-06 2015-11-11 杭州南江机器人股份有限公司 Kinect-based robot self-positioning method
CN105109484A (en) * 2015-08-21 2015-12-02 奇瑞汽车股份有限公司 Target-barrier determining method and device
CN105652873A (en) * 2016-03-04 2016-06-08 中山大学 Mobile robot obstacle avoidance method based on Kinect
CN205721353U (en) * 2016-03-04 2016-11-23 中山大学 A kind of omni-directional mobile robots based on Kinect avoidance
CN106289232A (en) * 2016-07-24 2017-01-04 广东大仓机器人科技有限公司 A kind of Obstacle Avoidance based on depth transducer
CN106324619A (en) * 2016-10-28 2017-01-11 武汉大学 Automatic obstacle avoiding method of substation inspection robot

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103576686A (en) * 2013-11-21 2014-02-12 中国科学技术大学 Automatic guide and obstacle avoidance method for robot
KR101539270B1 (en) * 2015-02-27 2015-07-24 군산대학교산학협력단 sensor fusion based hybrid reactive motion planning method for collision avoidance and autonomous navigation, recording medium and mobile robot for performing the method
CN104865965A (en) * 2015-05-20 2015-08-26 深圳市锐曼智能装备有限公司 Barrier-avoidance control method combining depth camera and supersonic wave for robot and system thereof
CN105045263A (en) * 2015-07-06 2015-11-11 杭州南江机器人股份有限公司 Kinect-based robot self-positioning method
CN105109484A (en) * 2015-08-21 2015-12-02 奇瑞汽车股份有限公司 Target-barrier determining method and device
CN105652873A (en) * 2016-03-04 2016-06-08 中山大学 Mobile robot obstacle avoidance method based on Kinect
CN205721353U (en) * 2016-03-04 2016-11-23 中山大学 A kind of omni-directional mobile robots based on Kinect avoidance
CN106289232A (en) * 2016-07-24 2017-01-04 广东大仓机器人科技有限公司 A kind of Obstacle Avoidance based on depth transducer
CN106324619A (en) * 2016-10-28 2017-01-11 武汉大学 Automatic obstacle avoiding method of substation inspection robot

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
WILBERT G. AGUILAR 等: "3D Environment Mapping Using the Kinect V2 and Path Planning Based on RRT Algorithms", 《ELECTRONICS》 *
邓琪琳: "基于势场和Kinect的移动机器人导航研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 *
马利红 等: "基于深度图像的室内机器人避障系统", 《浙江师范大学学报(自然科学版)》 *

Cited By (60)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107831760A (en) * 2017-09-27 2018-03-23 安徽硕威智能科技有限公司 Robot barrier thing processing system and method
CN109895780A (en) * 2017-12-07 2019-06-18 北京京东尚科信息技术有限公司 A kind of method and apparatus realizing unmanned equipment autonomously and getting rid of poverty
CN109895780B (en) * 2017-12-07 2021-03-30 北京京东乾石科技有限公司 Method and device for realizing autonomous escaping of unmanned equipment
CN107894773A (en) * 2017-12-15 2018-04-10 广东工业大学 A kind of air navigation aid of mobile robot, system and relevant apparatus
CN108516024A (en) * 2018-03-20 2018-09-11 马乐平 A kind of imitative worm specialized robot and its control method
CN108764465A (en) * 2018-05-18 2018-11-06 中国科学院计算技术研究所 A kind of processing unit carrying out neural network computing
CN108764470A (en) * 2018-05-18 2018-11-06 中国科学院计算技术研究所 A kind of processing method of artificial neural network operation
CN108647781A (en) * 2018-05-18 2018-10-12 中国科学院计算技术研究所 A kind of artificial intelligence chip processing device
CN108764465B (en) * 2018-05-18 2021-09-24 中国科学院计算技术研究所 Processing device for neural network operation
CN108647781B (en) * 2018-05-18 2021-08-27 中国科学院计算技术研究所 Artificial intelligence chip processing apparatus
CN108553042A (en) * 2018-05-21 2018-09-21 安克创新科技股份有限公司 A kind of clean robot
US11741709B2 (en) * 2018-05-22 2023-08-29 Starship Technologies Oü Method and system for analyzing surroundings of an autonomous or semi-autonomous vehicle
US20210209367A1 (en) * 2018-05-22 2021-07-08 Starship Technologies Oü Method and system for analyzing robot surroundings
CN108958263A (en) * 2018-08-03 2018-12-07 江苏木盟智能科技有限公司 A kind of Obstacle Avoidance and robot
CN109213157A (en) * 2018-08-28 2019-01-15 北京秦圣机器人科技有限公司 Data center's crusing robot paths planning method based on improved Ant Colony System
CN109298708B (en) * 2018-08-31 2021-08-17 中船重工鹏力（南京）大气海洋信息系统有限公司 Unmanned ship autonomous obstacle avoidance method integrating radar and photoelectric information
CN109298708A (en) * 2018-08-31 2019-02-01 中船重工鹏力（南京）大气海洋信息系统有限公司 A kind of unmanned boat automatic obstacle avoiding method merging radar and photoelectric information
CN109461185A (en) * 2018-09-10 2019-03-12 西北工业大学 A kind of robot target automatic obstacle avoidance method suitable for complex scene
CN109445438B (en) * 2018-12-05 2022-03-04 英华达（上海）科技有限公司 Cruise control method and system of cruise device based on map sharing
CN109445438A (en) * 2018-12-05 2019-03-08 英华达（上海）科技有限公司 Cruise control method and system based on the cruising device that map is shared
CN109547702A (en) * 2018-12-13 2019-03-29 清华大学 A kind of light draws photography machine people's system
CN109547702B (en) * 2018-12-13 2020-09-04 清华大学 Optical drawing and photographing robot system
CN111376258A (en) * 2018-12-29 2020-07-07 纳恩博（常州）科技有限公司 Control method, device, equipment and storage medium
CN111376258B (en) * 2018-12-29 2021-12-17 纳恩博（常州）科技有限公司 Control method, device, equipment and storage medium
CN111374607A (en) * 2018-12-29 2020-07-07 尚科宁家(中国)科技有限公司 Target identification method and device based on sweeping robot, equipment and medium
CN109571502A (en) * 2018-12-30 2019-04-05 深圳市普渡科技有限公司 Robot allocator
CN109540022B (en) * 2019-01-03 2020-07-07 沈阳天骄科技有限公司 Method for planning and deciding path of flat-cabin robot based on TOF depth camera
CN109540022A (en) * 2019-01-03 2019-03-29 沈阳天骄科技有限公司 Close a position robot path planning and decision-making technique based on TOF depth camera
CN109634286A (en) * 2019-01-21 2019-04-16 深圳市傲基电子商务股份有限公司 Grass-removing robot vision barrier-avoiding method, grass-removing robot and readable storage medium storing program for executing
CN111487958A (en) * 2019-01-28 2020-08-04 北京奇虎科技有限公司 Control method and device of sweeping robot
CN109960263A (en) * 2019-03-26 2019-07-02 深兰科技（上海）有限公司 One kind peddling robot control method, device and storage medium
CN110033612A (en) * 2019-05-21 2019-07-19 上海木木聚枞机器人科技有限公司 A kind of pedestrian's based reminding method, system and robot based on robot
CN110033612B (en) * 2019-05-21 2021-05-04 上海木木聚枞机器人科技有限公司 Robot-based pedestrian reminding method and system and robot
CN110442128B (en) * 2019-07-20 2022-08-16 河北科技大学 AGV path planning method based on characteristic point extraction ant colony algorithm
CN110442128A (en) * 2019-07-20 2019-11-12 河北科技大学 AGV paths planning method based on feature point extraction ant group algorithm
US11042760B2 (en) 2019-08-14 2021-06-22 Ankobot (Shanghai) Smart Technologies Co., Ltd. Mobile robot, control method and control system thereof
CN110622085A (en) * 2019-08-14 2019-12-27 珊口（深圳）智能科技有限公司 Mobile robot and control method and control system thereof
WO2021026831A1 (en) * 2019-08-14 2021-02-18 珊口（深圳）智能科技有限公司 Mobile robot, and control method and control system therefor
CN112711250A (en) * 2019-10-25 2021-04-27 科沃斯机器人股份有限公司 Self-walking equipment movement control method and self-walking equipment
WO2021082964A1 (en) * 2019-10-31 2021-05-06 灵动科技（北京）有限公司 Autonomous moving device and warehouse logistics system
WO2021103987A1 (en) * 2019-11-29 2021-06-03 深圳市杉川机器人有限公司 Control method for sweeping robot, sweeping robot, and storage medium
CN111046776B (en) * 2019-12-06 2023-06-09 杭州成汤科技有限公司 Method for detecting obstacle of path of mobile robot based on depth camera
CN111046776A (en) * 2019-12-06 2020-04-21 杭州成汤科技有限公司 Mobile robot traveling path obstacle detection method based on depth camera
CN110941279B (en) * 2019-12-21 2024-01-16 上海有个机器人有限公司 Control method for preventing robot from pressing foot in dense people stream scene
CN110941279A (en) * 2019-12-21 2020-03-31 上海有个机器人有限公司 Control method for preventing presser foot of robot in dense stream scene
CN111178286A (en) * 2019-12-31 2020-05-19 智车优行科技（上海）有限公司 Attitude trajectory prediction method and device and electronic equipment
CN111178286B (en) * 2019-12-31 2023-09-12 智车优行科技（上海）有限公司 Gesture track prediction method and device and electronic equipment
CN111872928A (en) * 2020-06-08 2020-11-03 特斯联科技集团有限公司 Obstacle attribute distinguishing method and system and intelligent robot
CN111872928B (en) * 2020-06-08 2022-04-05 特斯联科技集团有限公司 Obstacle attribute distinguishing method and system and intelligent robot
CN112230652A (en) * 2020-09-04 2021-01-15 安克创新科技股份有限公司 Walking robot, method of controlling movement of walking robot, and computer storage medium
CN112405532B (en) * 2020-11-06 2021-12-28 深圳优地科技有限公司 Movement control method and device and robot
CN112405532A (en) * 2020-11-06 2021-02-26 深圳优地科技有限公司 Movement control method and device and robot
CN112327854A (en) * 2020-11-12 2021-02-05 炬星科技（深圳）有限公司 Path blocking processing method and robot
WO2022127439A1 (en) * 2020-12-17 2022-06-23 深圳市普渡科技有限公司 Robot obstacle avoidance processing method and apparatus, device, and computer readable storage medium
CN112506204A (en) * 2020-12-17 2021-03-16 深圳市普渡科技有限公司 Robot obstacle meeting processing method, device, equipment and computer readable storage medium
CN113397437A (en) * 2021-07-12 2021-09-17 丁杨 Sweeping robot and obstacle avoidance method thereof
CN113786125A (en) * 2021-08-17 2021-12-14 科沃斯机器人股份有限公司 Operation method, self-moving device and storage medium
CN114442644A (en) * 2022-04-11 2022-05-06 季华实验室 Multi-robot obstacle avoidance method and device, electronic equipment and storage medium
CN117506857A (en) * 2024-01-04 2024-02-06 佛山科学技术学院 Mobile robot and safe motion control method
CN117506857B (en) * 2024-01-04 2024-04-30 佛山科学技术学院 Mobile robot and safe motion control method

Similar Documents

Publication Publication Date Title
CN107092252A (en) A kind of robot automatic obstacle avoidance method and its device based on machine vision
JP6651678B2 (en) Neural network system for autonomous vehicle control
US11885910B2 (en) Hybrid-view LIDAR-based object detection
US11106927B2 (en) Method for monitoring an interior state of an autonomous vehicle
US20200394393A1 (en) Gesture Control for Communication with an Autonomous Vehicle on the Basis of a Simple 2D Camera
Chung et al. The detection and following of human legs through inductive approaches for a mobile robot with a single laser range finder
US20220156967A1 (en) Device and method for detection and localization of vehicles
CN102915039B (en) A kind of multirobot joint objective method for searching of imitative animal spatial cognition
CN105216797B (en) Method of overtaking and system
CN112965081B (en) Simulated learning social navigation method based on feature map fused with pedestrian information
CN109460709A (en) The method of RTG dysopia analyte detection based on the fusion of RGB and D information
CN110285813A (en) A kind of man-machine co-melting navigation device of indoor mobile robot and method
CN108303972A (en) The exchange method and device of mobile robot
JP2004171165A (en) Moving apparatus
CN107223261A (en) Man-machine hybrid decision method and device
Sales et al. Adaptive finite state machine based visual autonomous navigation system
CN108873915A (en) Dynamic obstacle avoidance method and its omnidirectional&#39;s security robot
Fernandes et al. Intelligent robotic car for autonomous navigation: Platform and system architecture
CN110147748A (en) A kind of mobile robot obstacle recognition method based on road-edge detection
CN104156946A (en) Obstacle detection method for space tether robot in capturing area
Khalilullah et al. Road area detection method based on DBNN for robot navigation using single camera in outdoor environments
Nguyen et al. Deep learning-based multiple objects detection and tracking system for socially aware mobile robot navigation framework
Ong et al. Sensor fusion based human detection and tracking system for human-robot interaction
CN109490926A (en) A kind of paths planning method based on binocular camera and GNSS
Cai et al. Deep representation and stereo vision based vehicle detection

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information

Address after: 323000 room 303-5, block B, building 1, No. 268, Shiniu Road, nanmingshan street, Liandu District, Lishui City, Zhejiang Province

Applicant after: Zhejiang Guangpo Intelligent Technology Co., Ltd

Address before: Hangzhou City, Zhejiang province 310030 Xihu District three Town Shi Xiang Road No. 859 Zijin and building 3 building 1301-1 room

Applicant before: HANGZHOU GENIUS PROS TECHNOLOGY Co.,Ltd.

CB02 Change of applicant information
RJ01 Rejection of invention patent application after publication

Application publication date: 20170825

RJ01 Rejection of invention patent application after publication