CN104007762B - Navigation method of electric power inspection robot - Google Patents
Navigation method of electric power inspection robot Download PDFInfo
- Publication number
- CN104007762B CN104007762B CN201410232105.XA CN201410232105A CN104007762B CN 104007762 B CN104007762 B CN 104007762B CN 201410232105 A CN201410232105 A CN 201410232105A CN 104007762 B CN104007762 B CN 104007762B
- Authority
- CN
- China
- Prior art keywords
- fuzzy
- obstacle information
- inspection process
- degree
- electric inspection
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000007689 inspection Methods 0.000 title claims abstract description 46
- 230000000875 corresponding effect Effects 0.000 claims abstract description 7
- 230000033001 locomotion Effects 0.000 claims abstract description 5
- 230000008569 process Effects 0.000 claims description 39
- 230000006870 function Effects 0.000 claims description 14
- 230000009471 action Effects 0.000 claims description 8
- 230000004888 barrier function Effects 0.000 claims description 5
- 230000007935 neutral effect Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Feedback Control In General (AREA)
Abstract
The invention provides a navigation method of an electric power inspection robot. The navigation method comprises the steps that a fuzzy controller for movement of the electric power inspection robot is established, and the input variable and the output variable of the fuzzy controller are determined; a fuzzy set of the input variable and the output variable is set, and a fuzzy set of the acceptance level of the output variable is set; a qualitative reasoning principle is determined according to a fuzzy control theory, and a fuzzy control rule is established according to the input variable and the output variable of the fuzzy controller; the subordinating degree function of the input variable and the output variable is established; voting is conducted according to a subordinating degree function maximum principle, corresponding action is conducted on the electric power inspection robot, and navigation to the electric power inspection robot is achieved. A practicable navigation method can be provided for the electric power inspection robot, and the obstacle avoidance rate of the electric power inspection robot can be improved.
Description
Technical field
The present invention relates to a kind of air navigation aid, in particular for the air navigation aid of electric inspection process robot.
Background technology
Navigation is indispensable important component part in mobile robot autonomous intelligence, and it requires robot according to giving
Instruction and the autonomous decision path of environmental information, avoiding obstacles, realize task object.Navigation is that mobile robot completes to appoint
The safety guarantee of business, is also the important symbol of mobile robot intelligence degree, especially in robot hardware's system simultaneously
In the case that precision can not be resolved in a short time, the research to navigation algorithm is more particularly important, and this will fundamentally
Change the navigation performance of mobile robot, the level of intelligence of mobile robot will be improved, reduce mobile robot in moving process
Present in nondeterministic statement, improve the speed of mobile robot movement and activity, for the high intelligent remote carrying implement of exploitation
Device people, sniffing robot, service robot, automatic vehicle control system lay the first stone.
And roboticses are applied in power industry, both can efficiently, efficiently task have completed speed using robot
Degree, can also solve the problems, such as that cost of human resources goes up at a high speed.Using crusing robot, automatization is carried out on transmission line of electricity
Check, can not only be applied to that some natural conditions are relatively severe, the mankind cannot or the immalleable area of the mankind, can also be high
The work completing complexity of reliability.In addition, utilizing some special sensing equipments, it can be found that common patrol officer cannot send out
Existing incipient fault, the fault and reduce risk for preventing and solving power circuit indicates the road of a novelty.
But for crusing robot, various barriers will be run into during patrolling and examining, how effectively
Avoid these barriers, there is presently no a kind of practicable air navigation aid.
Content of the invention
The technical problem to be solved in the present invention is to provide a kind of navigation of the high electric inspection process robot of rate of avoidance effectively
Method.
In order to solve above-mentioned technical problem, the invention provides a kind of air navigation aid of electric inspection process robot, including such as
Lower step：
Step 1, sets up the fuzzy controller of electric inspection process robot motion, and determine fuzzy controller input variable and
Output variable, concretely comprises the following steps：
(1-1) scope of 180 degree in front of electric inspection process robot is divided into dead ahead, left front and right front three
Point, measure the obstacle information in 3 directions respectively by sensor, i.e. dead ahead obstacle information F, left front obstacle information
L and right front obstacle information R, and the input variable as fuzzy controller；
(1-2) set up electric inspection process robot and patrol and examine the straight line path of impact point, and by straight line path and electric inspection process
Relative angle θ between the direction of advance of robot is as the input variable of fuzzy controller；
(1-3) by the next step steering angle of electric inspection process robotOutput variable as fuzzy controller；
Step 2, sets the fuzzy set of input variable and output variable, and set output variable acceptance level fuzzy
Set, concretely comprises the following steps：
(2-1) set dead ahead obstacle information F, left front obstacle information L and right front obstacle information R these three
The each self-corresponding fuzzy set of input variable is all small distance s, middle apart from m and big apart from l；
(2-2) fuzzy set setting relative angle θ as honest PL, just little PS, zero Z, negative little NS and bears big NL；
(2-3) set steering angleFuzzy subset be big right-hand rotation RLT, right-hand rotation RT, do not turn NT, left-hand rotation LT and big turn left
LLT；
(2-4) set steering angleAcceptance level αiFuzzy subset, αi=1 expression does not allow, αiDuring=2 represent
Vertical, αi=3 represent permission, acceptance level αiThe degree being allowed to more greatly or accepting is higher, wherein, i=1,2,3,4,5, right respectively
Should turn right greatly RLT, right-hand rotation RT, do not turn NT, left-hand rotation LT and left-hand rotation LLT greatly；
Step 3, establishes qualitative reasoning principle, the input variable according to fuzzy controller and output according to fuzzy control theory
Variable, sets up fuzzy control rule, concretely comprises the following steps：
(3-1) determine the avoidance rule of dead ahead, left front and right front, due to dead ahead obstacle information F, left front
Obstacle information L and right front obstacle information R all to having three fuzzy subsets s, m and l, by corresponding to F, L and R fuzzy son
Collection carries out permutation and combination, then have 33=27 rules, every rule both corresponds to this five actions of RLT, RT, NT, LT and LLT
Acceptance level αi；
(3-2) determine the avoidance rule of relative angle, because relative angle θ is to should have five fuzzy subsets PL, PS, Z, NS
And NL, then there are 5 rules, every rule both corresponds to acceptance level α of this five actions of RLT, RT, NT, LT and LLTi；
Step 4, determines the membership function of input language variable and output language variable, concretely comprises the following steps：
(4-1) respectively dead ahead obstacle information F, left front obstacle information L and right front obstacle information R are made
For the domain of degree of membership, determine dead ahead obstacle information F, left front obstacle information L and right front obstacle information R
Membership function；
(4-2) using relative angle θ as the domain of degree of membership, determine the membership function of relative angle θ；
(4-3) by steering angleAs the domain of degree of membership, determine steering angleMembership function；
Step 5, carries out defuzzification, puts to the vote according to maximum membership degree method, and electric inspection process robot is carried out accordingly
Action, completes the navigation of electric inspection process robot, concretely comprises the following steps：
(5-1) put to the vote according to maximum membership degree method, obtain steering angleClear amount；
(5-2) by the steering angle obtainingClear amount carry out spatial scaling, obtain electric inspection process robot actual for
The steering angle of actionI.e. electric inspection process robot will need the angle adjusting, and completes the navigation of electric inspection process robot.
As the further limits scheme of the present invention, obstacle information is the range information of barrier.
The beneficial effects of the present invention is：Using the method for fuzzy controller, can not only carry for electric inspection process robot
For a kind of practicable air navigation aid, and guidance path can be optimized using fuzzy controller, improve electric power and patrol
The avoidance ability of inspection robot.
Brief description
Fig. 1 is method of the present invention flow chart；
Fig. 2 is the three direction obstacle information degree of membership schematic diagrams of the present invention；
Fig. 3 is the relative angle degree of membership schematic diagram of the present invention；
Fig. 4 is the steering angle degree of membership schematic diagram of the present invention.
Specific embodiment
As shown in figure 1, the air navigation aid of the electric inspection process robot of the present invention, comprise the steps：
Step 1, sets up the fuzzy controller of electric inspection process robot motion, and determine fuzzy controller input variable and
Output variable, concretely comprises the following steps：
(1-1) scope of 180 degree in front of electric inspection process robot is divided into dead ahead, left front and right front three
Point, measure the obstacle information in 3 directions respectively by sensor, i.e. dead ahead obstacle information F, left front obstacle information
L and right front obstacle information R, in actual acquisition, can align preceding object thing distance, left front barrier using range sensor
Thing distance and right front obstacle distance is hindered to be acquired, before dead ahead obstacle distance, left front obstacle distance and the right side
Square obstacle distance is as the input variable of fuzzy controller；
(1-2) set up electric inspection process robot and patrol and examine the straight line path of impact point, and by straight line path and electric inspection process
Relative angle θ between the direction of advance of robot is as the input variable of fuzzy controller；
(1-3) by the next step steering angle of electric inspection process robotOutput variable as fuzzy controller；
Step 2, sets the fuzzy set of input variable and output variable, and set output variable acceptance level fuzzy
Set, concretely comprises the following steps：
(2-1) set dead ahead obstacle information F, left front obstacle information L and right front obstacle information R these three
The each self-corresponding fuzzy set of input variable is all small distance s, middle apart from m and big apart from l；
(2-2) fuzzy set setting relative angle θ as honest PL, just little PS, zero Z, negative little NS and bears big NL；
(2-3) set steering angleFuzzy subset be big right-hand rotation RLT, right-hand rotation RT, do not turn NT, left-hand rotation LT and big turn left
LLT；
(2-4) set steering angleAcceptance level αiFuzzy subset, αi=1 expression does not allow, αiDuring=2 represent
Vertical, αi=3 represent permission, acceptance level αiThe degree being allowed to more greatly or accepting is higher, wherein, i=1,2,3,4,5, table respectively
Show RLT, RT, NT, LT and LLT；
Step 3, establishes qualitative reasoning principle, the input variable according to fuzzy controller and output according to fuzzy control theory
Variable, sets up fuzzy control rule, concretely comprises the following steps：
(3-1) determine the avoidance rule of dead ahead, left front and right front, due to dead ahead obstacle information F, left front
Obstacle information L and right front obstacle information R all to having three fuzzy subsets s, m and l, by corresponding to F, L and R fuzzy son
Collection carries out permutation and combination, then have 33=27 rules, every rule both corresponds to this five actions of RLT, RT, NT, LT and LLT
Acceptance level αi, for example, if { L=l, F=m, R=s }, then { α1=3, α2=2, α3=1, α4=1, α5=1 }；
(3-2) determine the avoidance rule of relative angle, because relative angle θ is to should have five fuzzy subsets PL, PS, Z, NS
And NL, then there are 5 rules, every rule both corresponds to acceptance level α of this five actions of RLT, RT, NT, LT and LLTi, example
As if { θ=PS }, { α1=2, α2=3, α3=2, α4=1, α5=1 }；
Step 4, determines the membership function of input language variable and output language variable, concretely comprises the following steps：
(4-1) respectively dead ahead obstacle information F, left front obstacle information L and right front obstacle information R are made
For the domain of degree of membership, determine dead ahead obstacle information F, left front obstacle information L and right front obstacle information R
Membership function, as shown in Fig. 2 because F, L and R have tri- fuzzy variables of l, m and s, the wherein value of s isThe value of m isThe value of l isX represents F, L
Or the size of the value of R, that is, when F, L and R value [0,1) interior when, the degree that F, L and R are under the jurisdiction of s is maximum, when the value of F, L and R
[1,2) in increase when, the degree that F, L and R are under the jurisdiction of s is gradually reduced, and is under the jurisdiction of the degree of m being gradually increased, as F, L and
The value of R [2,3) in increase when, the degree that F, L and R are under the jurisdiction of m is gradually reduced, and is under the jurisdiction of the degree of l being gradually increased, when
The value of F, L and R [3, ∞) in increase when, the degree that F, L and R are under the jurisdiction of l is maximum；
(4-2) using relative angle θ as the domain of degree of membership, determine the membership function of relative angle θ, as shown in figure 3,
Relative angle θ has five fuzzy variables of NL, NS, Z, PS and PL, and the wherein value of NL isThe value of NS isThe value of Z isThe value of PS isThe value of PL isY represents the size of the value of θ, that is, when the value of θ existsWhen interior, θ is under the jurisdiction of the journey of NL
Degree is maximum, when the value of θ existsDuring interior increase, the degree that θ is under the jurisdiction of NL is gradually reduced, and be under the jurisdiction of the degree of NS by
Cumulative big, when the value of θ existsDuring interior increase, the degree that θ is under the jurisdiction of NS is gradually reduced, and the degree being under the jurisdiction of Z gradually increases
Greatly, when the value of θ existsDuring interior increase, the degree that θ is under the jurisdiction of Z is gradually reduced, and the degree being under the jurisdiction of PS is gradually increased, and works as θ
Value existDuring interior increase, the degree that θ is under the jurisdiction of PS is gradually reduced, and the degree being under the jurisdiction of PL is gradually increased, when the value of θ
?During interior increase, the degree that θ is under the jurisdiction of PL is maximum；
(4-3) by steering angleAs the domain of degree of membership, determine steering angleMembership function, as Fig. 4 institute
Show, steering angleThere are five fuzzy variables of LLT, LT, NT, RT and RLT, the wherein value of LLT is LLT=-2z-1, z ∈ [-
1, -0., 5) value of LT is.NT value isRT
Value beThe value of RLT is RLT=2z-1, z ∈ [0.5,1], and z represents steering angle
Quantized value size, whenQuantized value value [- 1, -0.5) in increase when,The degree being under the jurisdiction of LLT is gradually reduced, and
The degree being under the jurisdiction of LT is gradually increased, whenQuantized value value [- 0.5,0) in increase when,The degree being under the jurisdiction of LT gradually subtracts
Little, and the degree being under the jurisdiction of NT is gradually increased, whenQuantized value value [0,0.5) in increase when,Be under the jurisdiction of the degree of NT by
Decrescence little, and the degree being under the jurisdiction of RT is gradually increased, whenQuantized value value when increasing in [0.5,1],It is under the jurisdiction of the journey of RT
Degree is gradually reduced, and the degree being under the jurisdiction of RLT is gradually increased；
Step 5, carries out defuzzification to each fuzzy variable, puts to the vote according to maximum membership degree method, to electric inspection process
Robot carries out corresponding actions, completes the navigation of electric inspection process robot, concretely comprises the following steps：
(5-1) put to the vote according to maximum membership degree method, obtain steering angleClear amount；
(5-2) by the steering angle obtainingClear amount carry out spatial scaling, obtain electric inspection process robot actual for
The steering angle of actionI.e. electric inspection process robot will need the angle adjusting, and completes the navigation of electric inspection process robot.
The membership function of the present invention determines the side being all to combine the present invention according to existing membership function theoretical method
Method is empirically determined.
Claims (2)
1. a kind of air navigation aid of electric inspection process robot is it is characterised in that comprise the steps：
Step 1, sets up the fuzzy controller of electric inspection process robot motion, and determines input variable and the output of fuzzy controller
Variable, concretely comprises the following steps：
(1-1) scope of 180 degree in front of electric inspection process robot is divided into dead ahead, left front and right front three part, leads to
Cross the obstacle information that 3 directions measured respectively by sensor, i.e. dead ahead obstacle information F, left front obstacle information L and the right side
Preceding object thing information R, and the input variable as fuzzy controller；
(1-2) set up electric inspection process robot and patrol and examine the straight line path of impact point, and by straight line path and electric inspection process machine
Relative angle θ between the direction of advance of people is as the input variable of fuzzy controller；
(1-3) by the next step steering angle of electric inspection process robotOutput variable as fuzzy controller；
Step 2, sets the fuzzy set of input variable and output variable, and sets the fuzzy set of the acceptance level of output variable
Close, concretely comprise the following steps：
(2-1) these three inputs of dead ahead obstacle information F, left front obstacle information L and right front obstacle information R are set
The each self-corresponding fuzzy set of variable is all small distance s, middle apart from m and big apart from l；
(2-2) fuzzy set setting relative angle θ as honest PL, just little PS, zero Z, negative little NS and bears big NL；
(2-3) set steering angleFuzzy subset be big right-hand rotation RLT, right-hand rotation RT, do not turn NT, left-hand rotation LT and left-hand rotation LLT greatly；
(2-4) set steering angleAcceptance level αiFuzzy subset, αi=1 expression does not allow, αi=2 represent neutral, αi=
3 represent permission, acceptance level αiThe degree being allowed to more greatly or accepting is higher, wherein, i=1,2,3,4,5, corresponding right greatly respectively
Turn RLT, right-hand rotation RT, do not turn NT, left-hand rotation LT and left-hand rotation LLT greatly；
Step 3, establishes qualitative reasoning principle according to fuzzy control theory, and the input variable according to fuzzy controller and output become
Amount, sets up fuzzy control rule, concretely comprises the following steps：
(3-1) determine the avoidance rule of dead ahead, left front and right front, due to dead ahead obstacle information F, left front obstacle
Thing information L and right front obstacle information R, to having three fuzzy subsets s, m and l, corresponding to F, L and R fuzzy subset are entered
Row permutation and combination, then have 33=27 rules, every rule both corresponds to the acceptance of this five actions of RLT, RT, NT, LT and LLT
Degree αi；
(3-2) determine relative angle avoidance rule, due to relative angle θ to should have five fuzzy subsets PL, PS, Z, NS and
NL, then have 5 rules, and every rule both corresponds to acceptance level α of this five actions of RLT, RT, NT, LT and LLTi；
Step 4, determines the membership function of input language variable and output language variable, concretely comprises the following steps：
(4-1) respectively using dead ahead obstacle information F, left front obstacle information L and right front obstacle information R as person in servitude
The domain of genus degree, determines dead ahead obstacle information F, being subordinate to of left front obstacle information L and right front obstacle information R
Degree function；
(4-2) using relative angle θ as the domain of degree of membership, determine the membership function of relative angle θ；
(4-3) by steering angleAs the domain of degree of membership, determine steering angleMembership function；
Step 5, carries out defuzzification, puts to the vote according to maximum membership degree method, carries out corresponding actions to electric inspection process robot,
Complete the navigation of electric inspection process robot, concretely comprise the following steps：
(5-1) put to the vote according to maximum membership degree method, obtain steering angleClear amount；
(5-2) by the steering angle obtainingClear amount carry out spatial scaling, obtain electric inspection process robot actual for action
Steering angleI.e. electric inspection process robot will need the angle adjusting, and completes the navigation of electric inspection process robot.
2. electric inspection process robot according to claim 1 air navigation aid it is characterised in that：Described obstacle information is
The range information of barrier.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410232105.XA CN104007762B (en) | 2014-05-28 | 2014-05-28 | Navigation method of electric power inspection robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410232105.XA CN104007762B (en) | 2014-05-28 | 2014-05-28 | Navigation method of electric power inspection robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104007762A CN104007762A (en) | 2014-08-27 |
| CN104007762B true CN104007762B (en) | 2017-02-15 |
Family
ID=51368465
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410232105.XA Active CN104007762B (en) | 2014-05-28 | 2014-05-28 | Navigation method of electric power inspection robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104007762B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104637051A (en) * | 2014-12-31 | 2015-05-20 | 广东电网有限责任公司中山供电局 | High-variable precision photographing method based on mobile carrier |
| CN104898665A (en) * | 2015-04-16 | 2015-09-09 | 山东建筑大学 | Method and device for programming track of tour inspection robot |
| CN107463175A (en) * | 2017-08-04 | 2017-12-12 | 河南工程学院 | Automatic obstacle avoidance trolley, barrier-avoiding method and system |
| CN107825984A (en) * | 2017-11-11 | 2018-03-23 | 成都海逸机电设备有限公司 | A kind of suspension type monorail traffic track beam routing inspection trolley control device and control method |
| CN109227007B (en) * | 2018-09-20 | 2021-06-08 | 北京博清科技有限公司 | Welding crawling machine body tracking method and system based on attitude sensor |
| CN110297496B (en) * | 2019-06-28 | 2020-04-21 | 四川大学 | Control method and device for power inspection robot, electronic equipment and storage medium |
| CN115576328B (en) * | 2022-11-15 | 2023-03-28 | 之江实验室 | Robot navigation obstacle avoidance method and device based on fuzzy controller |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU110065U1 (en) * | 2011-05-25 | 2011-11-10 | Общество с ограниченной ответственностью "Океан-Инвест СПб" | UNIVERSAL RELEASED SYSTEM FOR THE EXAMINATION AND REPAIR OF HYDROTECHNICAL AND OIL AND GAS INDUSTRY INFRASTRUCTURE |
| CN103064416A (en) * | 2012-12-10 | 2013-04-24 | 江西洪都航空工业集团有限责任公司 | Indoor and outdoor autonomous navigation system for inspection robot |
| CN103400392A (en) * | 2013-08-19 | 2013-11-20 | 山东鲁能智能技术有限公司 | Binocular vision navigation system and method based on inspection robot in transformer substation |
-
2014
- 2014-05-28 CN CN201410232105.XA patent/CN104007762B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| RU110065U1 (en) * | 2011-05-25 | 2011-11-10 | Общество с ограниченной ответственностью "Океан-Инвест СПб" | UNIVERSAL RELEASED SYSTEM FOR THE EXAMINATION AND REPAIR OF HYDROTECHNICAL AND OIL AND GAS INDUSTRY INFRASTRUCTURE |
| CN103064416A (en) * | 2012-12-10 | 2013-04-24 | 江西洪都航空工业集团有限责任公司 | Indoor and outdoor autonomous navigation system for inspection robot |
| CN103400392A (en) * | 2013-08-19 | 2013-11-20 | 山东鲁能智能技术有限公司 | Binocular vision navigation system and method based on inspection robot in transformer substation |
Non-Patent Citations (5)
| Title |
|---|
| Development and Fuzzy Control of a Pipe Inspection Robot;Han-Pang Huang，etc;《IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS》;20100331;第57卷(第3期);第1088-1095页 * |
| 变电站巡检机器人视觉导航模糊控制;历广伟，等;《济南大学学报（自然科学版）》;20110131;第25卷(第1期);第31-35页 * |
| 基于模糊控制的移动机器人导航系统设计;钱华;《中国优秀硕士学位论文全文数据库信息科技辑（月刊）》;20111215(第S1期);第1-58页 * |
| 基于虚拟定标线的巡检机器人视觉导航;李金屏，等;《中国体视学与图像分析》;20110331;第16卷(第1期);第50-56页 * |
| 架空电力线路巡线机器人的研究综述;张运楚，等;《机器人》;20040930;第26卷(第5期);第467-473页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104007762A (en) | 2014-08-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104007762B (en) | Navigation method of electric power inspection robot | |
| Peng et al. | The obstacle detection and obstacle avoidance algorithm based on 2-d lidar | |
| CN107168324A (en) | A kind of robot path planning method based on ANFIS fuzzy neural networks | |
| CN105487544B (en) | Method is surrounded and seize in multirobot angle control based on fuzzy inference system | |
| CN103324196A (en) | Multi-robot path planning and coordination collision prevention method based on fuzzy logic | |
| CN103381603B (en) | The active obstacle planing method of deicing high-voltage power transmission line inspection robot | |
| CN108491071B (en) | Brain-controlled vehicle sharing control method based on fuzzy control | |
| CN110553660A (en) | unmanned vehicle trajectory planning method based on A-star algorithm and artificial potential field | |
| CN103455033A (en) | Fuzzy formation and obstacle avoidance control method for multi-mobile-robot system | |
| Tang et al. | An overview of path planning algorithms | |
| Yang et al. | A trajectory planning and fuzzy control for autonomous intelligent parking system | |
| CN208119291U (en) | A kind of intelligent vehicle moved for simulating intelligent body in unmanned test | |
| Wang et al. | Mobile robot dynamic path planning based on improved genetic algorithm | |
| CN112560571A (en) | Intelligent autonomous visual navigation method based on convolutional neural network | |
| Huang et al. | Study on obstacle avoidance of AGV based on fuzzy neural network | |
| Zhang et al. | Trajectory planning of overtaking for intelligent vehicle based on X-Sin function | |
| CN108255165A (en) | Robot path planning method based on neighborhood potential field | |
| Jiang et al. | Research on path guidance of logistics transport vehicle based on image recognition and image processing in port area | |
| CN112783133B (en) | AGV running state prediction method | |
| Sun et al. | Apf-Bug-Based Intelligent Path Planning for Autonomous Vehicle with High Precision in Complex Environment | |
| Shan et al. | Path planning of robot based on ant colony optimization algorithm | |
| Huang et al. | Research on vehicle control system of construction machinery based on machine vision | |
| Gilda | Implementation of Intelligent Control Techniques Applied on a Line Follower Vehicle Controller | |
| Wang et al. | A fuzzy control based self-optimizing PID model for autonomous car following on highway | |
| Meng et al. | A navigation framework for mobile robots with 3D LiDAR and monocular camera |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |