CN108919806A - A kind of outdoor automatic obstacle avoiding method based on Fusion - Google Patents
A kind of outdoor automatic obstacle avoiding method based on Fusion Download PDFInfo
- Publication number
- CN108919806A CN108919806A CN201810769403.0A CN201810769403A CN108919806A CN 108919806 A CN108919806 A CN 108919806A CN 201810769403 A CN201810769403 A CN 201810769403A CN 108919806 A CN108919806 A CN 108919806A
- Authority
- CN
- China
- Prior art keywords
- sensing unit
- data
- fusion
- shaped
- automatic obstacle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
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)
- Manipulator (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The present invention discloses a kind of outdoor automatic obstacle avoiding method based on Fusion, top layer vision acquisition zone, upper layer sensing unit, middle layer sensing unit, lower layer sensing unit including constructing seamless connection, host computer obtains Distance-sensing data from U-shaped sensing unit, middle bit wide away from fan-shaped sensing unit, high-order narrow space rectangle sensing unit respectively, constructs the processes such as real-time dynamic 3D modeling image data.Through the above way, the present invention provides a kind of outdoor automatic obstacle avoiding method based on Fusion, and single laser radar and the sensors such as infrared, ultrasonic are carried out data fusion, can be to avoid the blind area at laser video angle, application range is wider, and moderate cost is suitble to mass product.
Description
Technical field
The present invention relates to robotic technology fields more particularly to a kind of outdoor based on Fusion independently to keep away
Barrier method.
Background technique
Existing robot outdoor sport avoidance scheme generally uses laser radar and machine vision, and both technologies exist
Certain limitation;Two aspect first below the major defect of laser radar:(1) single laser radar is by installation site shadow
It rings, some low obstructions can not scan, and there are visual angle blind zones;(2) data fusion is carried out using multiple laser radars simultaneously,
So that cost is excessively high;Machine vision major defect be it is affected by environment larger, application scenarios more limit to.
Summary of the invention
The invention mainly solves the technical problem of providing a kind of outdoor automatic obstacle avoiding based on Fusion
Single laser radar and the sensors such as infrared, ultrasonic are carried out data fusion, can answered to avoid the blind area at laser video angle by method
It is wider with range, while moderate cost is suitble to mass product.
In order to solve the above technical problems, one technical scheme adopted by the invention is that:It provides a kind of based on multisensor number
According to the outdoor automatic obstacle avoiding method of fusion, include the following steps:
Step 1:Construct top layer vision acquisition zone, the upper layer sensing of seamless connection along the vertical direction on robot body
Area, middle layer sensing unit, lower layer sensing unit;
Step 2:U-shaped infrared sensing array is constructed in lower layer's sensing unit same level, forms 1.5 meters of low levels of radius
Short distance U-shaped sensing unit;
Step 3:Sensing unit building in middle level is superimposed upon the ultrasonic sensor on U-shaped infrared sensing array, forms half
5 meters of diameter of middle bit wide is away from fan-shaped sensing unit;
Step 4:In upper layer sensing unit, building is superimposed upon laser radar on ultrasonic sensor, and 100 meters of formation length
High-order narrow space rectangle sensing unit;
Step 5:It is sensed respectively from U-shaped sensing unit, middle bit wide away from fan-shaped sensing unit, high-order narrow space rectangle using host computer
Area, the synchronous acquisition Distance-sensing data in top layer vision acquisition zone and video stream data, real-time integration construct dynamic 3D modeling image
Data;
Step 6:Host computer plans obstacle route using dynamic 3D modeling image data, is handed down to robot execution;
Step 7:Frame data are read from video stream data, extract characteristic information, carry out characteristic matching, generate vision mileage
It counts, is corrected by visual odometry and data of the fused data of imu to robot chassis odometer, compensated because of machine
Misalignment data caused by device people jolts or skids;
Step 8:Characteristic information is accurately relocated by winding detection, and repeats step 6.
In a preferred embodiment of the present invention, the U row infrared sensing array is equidistantly arranged infrared by least five
Range sensor composition.
The beneficial effects of the invention are as follows:A kind of outdoor automatic obstacle avoiding based on Fusion provided by the invention
Single laser radar and the sensors such as infrared, ultrasonic are carried out data fusion, can answered to avoid the blind area at laser video angle by method
It is wider with range, while moderate cost is suitble to mass product.
Specific embodiment
The technical scheme in the embodiments of the invention will be clearly and completely described below, it is clear that described implementation
Example is only a part of the embodiments of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, this field is common
Technical staff's all other embodiment obtained without making creative work belongs to the model that the present invention protects
It encloses.
The embodiment of the present invention includes:
A kind of outdoor automatic obstacle avoiding method based on Fusion, includes the following steps:
Step 1:Construct top layer vision acquisition zone, the upper layer sensing of seamless connection along the vertical direction on robot body
Area, middle layer sensing unit, lower layer sensing unit;
Step 2:U-shaped infrared sensing array is constructed in lower layer's sensing unit same level, forms 1.5 meters of low levels of radius
Short distance U-shaped sensing unit;
Step 3:Sensing unit building in middle level is superimposed upon the ultrasonic sensor on U-shaped infrared sensing array, forms half
5 meters of diameter of middle bit wide is away from fan-shaped sensing unit;
Step 4:In upper layer sensing unit, building is superimposed upon laser radar on ultrasonic sensor, and 100 meters of formation length
High-order narrow space rectangle sensing unit;
Step 5:It is sensed respectively from U-shaped sensing unit, middle bit wide away from fan-shaped sensing unit, high-order narrow space rectangle using host computer
Area, the synchronous acquisition Distance-sensing data in top layer vision acquisition zone and video stream data, real-time integration construct dynamic 3D modeling image
Data;
Step 6:Host computer plans obstacle route using dynamic 3D modeling image data, is handed down to robot execution;
Step 7:Frame data are read from video stream data, extract characteristic information, carry out characteristic matching, generate vision mileage
It counts, is corrected by visual odometry and data of the fused data of imu to robot chassis odometer, compensated because of machine
Misalignment data caused by device people jolts or skids;
Step 8:Characteristic information is accurately relocated by winding detection, and repeats step 6.
Wherein, the U row infrared sensing array is made of the infrared distance sensor that at least five is equidistantly arranged.
In conclusion the present invention provides a kind of outdoor automatic obstacle avoiding method based on Fusion, it will be single
A laser radar and the sensors such as infrared, ultrasonic carry out data fusion, can to avoid the blind area at laser video angle, application range compared with
Extensively, while moderate cost is suitble to mass product.
The present invention does long-distance barrier analyte detection and avoidance by laser radar, makes closely of infrared or ultrasonic sensor
Special angle detection of obstacles, the data that will test are uploaded to laser and do data fusion, carry out part without dead angle by DWA algorithm
Avoidance ensure that robot in the safety and stability of outdoor sport;Avoid infrared or ultrasonic sensor as emergency stop simultaneously
Switch individually controls robot motion, increases the complexity of control system.
Beneficial effect has:1. hardware and software cost is moderate;2. being restricted by application scenarios less;3. detection of obstacles range
Extensively;4. control system complexity is low, real-time is preferable.
The above description is only an embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright description is applied directly or indirectly in other relevant technology necks
Domain is included within the scope of the present invention.
Claims (2)
1. a kind of outdoor automatic obstacle avoiding method based on Fusion, which is characterized in that include the following steps:
Step 1:Constructed along the vertical direction on robot body the top layer vision acquisition zone of seamless connection, upper layer sensing unit, in
Layer sensing unit, lower layer sensing unit;
Step 2:U-shaped infrared sensing array is constructed in lower layer's sensing unit same level, forms 1.5 meters of low level short distance U of radius
Shape sensing unit;
Step 3:Sensing unit building in middle level is superimposed upon the ultrasonic sensor on U-shaped infrared sensing array, forms radius 5
The middle bit wide of rice is away from fan-shaped sensing unit;
Step 4:In upper layer sensing unit, building is superimposed upon the laser radar on ultrasonic sensor, the height that 100 meters of formation length
Position narrow space rectangle sensing unit;
Step 5:Using host computer respectively from U-shaped sensing unit, middle bit wide away from fan-shaped sensing unit, high-order narrow space rectangle sensing unit, top
Floor vision collecting area is synchronous to obtain Distance-sensing data and video stream data, and real-time integration constructs dynamic 3D modeling image data;
Step 6:Host computer plans obstacle route using dynamic 3D modeling image data, is handed down to robot execution;
Step 7:Frame data are read from video stream data, extract characteristic information, carry out characteristic matching, generate visual odometry number
According to, corrected by visual odometry and data of the fused data of imu to robot chassis odometer, compensate because of robot
Misalignment data caused by jolting or skidding;
Step 8:Characteristic information is accurately relocated by winding detection, and repeats step 6.
2. the outdoor automatic obstacle avoiding method according to claim 1 based on Fusion, which is characterized in that institute
U row infrared sensing array is stated to be made of the infrared distance sensor that at least five is equidistantly arranged.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810769403.0A CN108919806A (en) | 2018-07-13 | 2018-07-13 | A kind of outdoor automatic obstacle avoiding method based on Fusion |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810769403.0A CN108919806A (en) | 2018-07-13 | 2018-07-13 | A kind of outdoor automatic obstacle avoiding method based on Fusion |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108919806A true CN108919806A (en) | 2018-11-30 |
Family
ID=64412665
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810769403.0A Pending CN108919806A (en) | 2018-07-13 | 2018-07-13 | A kind of outdoor automatic obstacle avoiding method based on Fusion |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108919806A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111897338A (en) * | 2020-08-04 | 2020-11-06 | 安徽国钜工程机械科技有限公司 | Sensing system for shield construction method automatic driving horizontal transport locomotive |
CN112612037A (en) * | 2020-12-01 | 2021-04-06 | 珠海市一微半导体有限公司 | Fusion positioning method and mobile robot |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090045766A1 (en) * | 2000-01-24 | 2009-02-19 | Irobot Corporation | Obstacle following sensor scheme for a mobile robot |
CN202075626U (en) * | 2011-04-14 | 2011-12-14 | 山东大学 | Multi-sensor system of intelligent space and nurse robot |
CN106598039A (en) * | 2015-10-14 | 2017-04-26 | 山东鲁能智能技术有限公司 | Substation patrol robot obstacle avoidance method based on laser radar |
CN107703935A (en) * | 2017-09-12 | 2018-02-16 | 安徽胜佳和电子科技有限公司 | Multiple data weighting fusions carry out method, storage device and the mobile terminal of avoidance |
CN108227523A (en) * | 2017-11-01 | 2018-06-29 | 深圳乐动机器人有限公司 | robot control method, device, storage medium and computer equipment |
-
2018
- 2018-07-13 CN CN201810769403.0A patent/CN108919806A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20090045766A1 (en) * | 2000-01-24 | 2009-02-19 | Irobot Corporation | Obstacle following sensor scheme for a mobile robot |
CN202075626U (en) * | 2011-04-14 | 2011-12-14 | 山东大学 | Multi-sensor system of intelligent space and nurse robot |
CN106598039A (en) * | 2015-10-14 | 2017-04-26 | 山东鲁能智能技术有限公司 | Substation patrol robot obstacle avoidance method based on laser radar |
CN107703935A (en) * | 2017-09-12 | 2018-02-16 | 安徽胜佳和电子科技有限公司 | Multiple data weighting fusions carry out method, storage device and the mobile terminal of avoidance |
CN108227523A (en) * | 2017-11-01 | 2018-06-29 | 深圳乐动机器人有限公司 | robot control method, device, storage medium and computer equipment |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111897338A (en) * | 2020-08-04 | 2020-11-06 | 安徽国钜工程机械科技有限公司 | Sensing system for shield construction method automatic driving horizontal transport locomotive |
CN112612037A (en) * | 2020-12-01 | 2021-04-06 | 珠海市一微半导体有限公司 | Fusion positioning method and mobile robot |
WO2022116657A1 (en) * | 2020-12-01 | 2022-06-09 | 珠海一微半导体股份有限公司 | Fused positioning method and mobile robot |
CN112612037B (en) * | 2020-12-01 | 2023-10-24 | 珠海一微半导体股份有限公司 | Fusion positioning method and mobile robot |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11022976B2 (en) | Path planning method of intelligent robot | |
US11525887B2 (en) | Systems and methods for intelligently calibrating infrastructure devices using onboard sensors of an autonomous agent | |
CN106227212B (en) | The controllable indoor navigation system of precision and method based on grating map and dynamic calibration | |
WO2019233222A1 (en) | Automatic wall-climbing radar photoelectric robot system for use in non-destructive detection and diagnosis of bridge-tunnel structure damage | |
CN105425803B (en) | Autonomous obstacle avoidance method, device and system | |
Kim et al. | Cooperative perception for autonomous vehicle control on the road: Motivation and experimental results | |
CN103064416B (en) | Crusing robot indoor and outdoor autonomous navigation system | |
CN107093328A (en) | Parking ground navigation system and method based on machine vision | |
CN112415998A (en) | Obstacle classification and obstacle avoidance control system based on TOF camera | |
CN109828581A (en) | A kind of Multimode Intelligent electric cleaning car with automated driving system | |
CN108898638A (en) | A kind of on-line automatic scaling method of vehicle-mounted camera | |
CN107389026A (en) | A kind of monocular vision distance-finding method based on fixing point projective transformation | |
CN111624997A (en) | Robot control method and system based on TOF camera module and robot | |
CN107256019A (en) | A kind of paths planning method of clean robot | |
CN111161322B (en) | LSTM neural network pedestrian trajectory prediction method based on human-vehicle interaction | |
CN110082783B (en) | Cliff detection method and device | |
CN108919806A (en) | A kind of outdoor automatic obstacle avoiding method based on Fusion | |
CN110554700A (en) | method for identifying room and door of mobile robot | |
CN105136155B (en) | A kind of air navigation aid and electronic equipment | |
WO2018083005A1 (en) | Method for operating a partially autonomous or autonomous motor vehicle, and motor vehicle | |
KR20210063791A (en) | System for mapless navigation based on dqn and slam considering characteristic of obstacle and processing method thereof | |
CN113085896A (en) | Auxiliary automatic driving system and method for modern rail cleaning vehicle | |
WO2021168854A1 (en) | Method and apparatus for free space detection | |
CN209570854U (en) | A kind of Multimode Intelligent electric cleaning car with automated driving system | |
CN204398994U (en) | A kind of intelligent vehicle |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181130 |
|
RJ01 | Rejection of invention patent application after publication |