CN114253272A - Indoor autonomous exploration method for unmanned vehicle - Google Patents

Indoor autonomous exploration method for unmanned vehicle Download PDF

Info

Publication number
CN114253272A
CN114253272A CN202111587216.9A CN202111587216A CN114253272A CN 114253272 A CN114253272 A CN 114253272A CN 202111587216 A CN202111587216 A CN 202111587216A CN 114253272 A CN114253272 A CN 114253272A
Authority
CN
China
Prior art keywords
unmanned vehicle
wall
exploration
indoor
room
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
CN202111587216.9A
Other languages
Chinese (zh)
Inventor
王咸锋
孙健
俞成浦
陈伟
张天勇
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.)
Chongqing Innovation Center of Beijing University of Technology
Original Assignee
Chongqing Innovation Center of Beijing University of Technology
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 Chongqing Innovation Center of Beijing University of Technology filed Critical Chongqing Innovation Center of Beijing University of Technology
Priority to CN202111587216.9A priority Critical patent/CN114253272A/en
Publication of CN114253272A publication Critical patent/CN114253272A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0238Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
    • G05D1/024Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0221Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0223Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0257Control of position or course in two dimensions specially adapted to land vehicles using a radar
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0276Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Optics & Photonics (AREA)
  • Electromagnetism (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention provides an autonomous exploration method in an unmanned vehicle room, which combines wall exploration and RRT: searching along the wall outside the room, so that the searching speed is improved, and the directivity and the purposiveness are increased; and RRT is adopted to rapidly explore in the room, so that region traversal is avoided, path repetition is reduced, exploration time is saved, and exploration efficiency is improved.

Description

Indoor autonomous exploration method for unmanned vehicle
Technical Field
The invention relates to the technical field of unmanned aerial vehicle autonomous exploration, in particular to an unmanned aerial vehicle indoor autonomous exploration method.
Background
The unmanned vehicle autonomous exploration mainly aims at multi-room scenes such as office buildings, garages and indoor shopping malls of modern urban buildings, and performs obstacle identification, autonomous exploration, positioning and map construction on the site by means of an unmanned vehicle built-in sensor and a control system, and plays an important role in tasks such as urban anti-terrorism operation, fire search and rescue and the like.
At present, the traditional unmanned vehicle indoor exploration method mainly comprises region traversal, front edge detection and the like, and has strong randomness and high path repeatability. The ideal autonomous exploration effect is difficult to achieve under the requirement of a specific task scene.
Disclosure of Invention
The invention provides an indoor autonomous exploration method for an unmanned vehicle, which mainly solves the technical problems that: the existing indoor exploration method has the advantages of strong randomness, high path repeatability and poor autonomous exploration effect.
In order to solve the technical problem, the invention provides an autonomous indoor exploration method for an unmanned vehicle, which comprises the following steps:
the unmanned vehicle enters the indoor environment and starts an exploration task from the starting point;
when the wall body is identified, keeping a set distance with the wall, and exploring along the wall;
in the process of exploring along the wall, if a room door is detected, recording the position of the room door;
entering a room, identifying the size of the room, and determining a room exploration area;
exploring the room by using a rapid exploration random tree algorithm;
after the indoor exploration is finished, the indoor door is taken out and the indoor exploration is continued along the wall until the whole indoor environment exploration is finished, and the starting point is returned.
Optionally, the method further includes: when at least two walls are identified simultaneously, the closest wall is selected for wall-following exploration.
Optionally, during the wall-following exploration process, the method further includes: and when the fact that the wall body has the corner is detected, correcting the advancing direction and enabling the wall body after the corner to keep the set distance to continue exploring along the wall.
Optionally, the method further includes: when a room door is detected, measuring the distances between the unmanned vehicle and the wall bodies on the two sides of the room door respectively through a laser radar, and calculating the width of the room door by combining the angle of a laser beam; when the width of the room door is smaller than a set width threshold value, the unmanned vehicle ignores the room door and continues to search along the wall; when the width of the room door is larger than or equal to the set width threshold value, the unmanned vehicle enters the room along the perpendicular bisector of the room door.
Optionally, the unmanned vehicle is equipped with a laser radar, and measures distances between the unmanned vehicle and the wall and the obstacle through the laser radar.
Optionally, the unmanned vehicle is further equipped with a mileage meter for measuring the travel distance information in the search process.
Optionally, the unmanned vehicle is developed based on an ROS system, and each node communicates using an ROS standard protocol.
Optionally, the unmanned vehicle receives monitoring information of the laser radar and the odometer through a controller, and realizes object feature identification and positioning navigation.
Optionally, the controller is further configured to establish a motion rule base according to the historical environment motion state, the current environment motion state, and the turning direction information, so as to perform local path planning.
The invention has the beneficial effects that:
according to the unmanned vehicle indoor autonomous exploration method provided by the invention, wall-following exploration and RRT (Rapid-exploration Random Tree) are combined: searching along the wall outside the room, so that the searching speed is improved, and the directivity and the purposiveness are increased; and RRT is adopted to rapidly explore in the room, so that region traversal is avoided, path repetition is reduced, exploration time is saved, and exploration efficiency is improved.
Drawings
FIG. 1 is a schematic flow chart of an autonomous indoor search method for an unmanned vehicle according to the present invention;
FIG. 2 is a first schematic diagram of the unmanned vehicle path planning of the present invention;
FIG. 3 is a schematic diagram of the unmanned vehicle route planning of the present invention;
fig. 4 is a schematic diagram of the path planning of the unmanned vehicle according to the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following detailed description and accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The first embodiment is as follows:
aiming at the problems of stronger randomness, higher path repeatability and poorer autonomous exploration effect of the existing indoor exploration method, the embodiment provides the autonomous exploration method in the unmanned vehicle room, which combines the wall exploration and RRT: searching along the wall outside the room, so that the searching speed is improved, and the directivity and the purposiveness are increased; and RRT is adopted to rapidly explore in the room, so that region traversal is avoided, path repetition is reduced, exploration time is saved, and exploration efficiency is improved.
Referring to fig. 1, the autonomous discovery method in an unmanned vehicle mainly includes the following steps:
s101, the unmanned vehicle enters an indoor environment and starts an exploration task from a starting point.
When the unmanned vehicle enters the room, the unmanned vehicle can record the position of the unmanned vehicle and start exploration.
And S102, when the wall body is identified, keeping a set distance with the wall, and searching along the wall.
In other optional embodiments of the present invention, during the scanning process of the drone vehicle by the 360 ° lidar, multiple walls within the detection range may be identified at the same time, and at this time, the drone may choose to travel directly to the nearest wall for wall-following exploration.
Referring to fig. 2, the unmanned vehicle monitors the wall 21 and the wall 22 at the same time, the distance to the object is determined by measuring the time difference between the emitted laser and the reflected laser, and the distance from the unmanned vehicle to the wall 21 is calculated as S1, and the distance from the unmanned vehicle to the wall 22 is calculated as S2, and by comparison, S1 is smaller than S2, that is, the unmanned vehicle is closer to the wall 21, and the wall 21 is selected nearby to search along the wall, so that the search efficiency is improved.
S103, recording the position of the room door if the room door is detected in the process of searching along the wall.
It should be understood that, the unmanned vehicle may extract the characteristic information through processing the data of the laser radar, and then identify the wall, the room door, the corner, the obstacle, the local protrusion or the recess, and any existing identification method may be adopted, which is not limited in this embodiment.
When a room door is detected, the room door position may be recorded. Specifically, the display can be represented by coordinate positions or directly constructed by an indoor map. It should be understood that during the exploration process, the unmanned vehicle can detect and record its position in real time based on sensor modules such as a speedometer (which can be used for measuring the driving distance information during the exploration process), a gyroscope (which can be used for measuring information such as direction and acceleration), and the like, and can realize the identification of indoor objects and the detection of distance, direction and size based on the laser radar, so that the related indoor objects can be positioned and an indoor map can be constructed.
During the wall exploration process, there may be several situations:
1. in the process of searching along the wall, when the fact that the wall body has the corner is detected, the advancing direction of the unmanned vehicle is corrected, and the wall body after the corner keeps the set distance to continue searching along the wall.
Referring to fig. 3, during the process of searching along the wall, the unmanned vehicle detects that a corner exists on the right wall 31 and the corner is located on the right side, and at this time, the traveling direction of the unmanned vehicle is controlled to be adjusted to be 90 degrees to the right (the rotation angle is parallel to the wall 32 after the corner), and the unmanned vehicle travels to the end point of the wall 32, and at this time, the unmanned vehicle can detect that the wall 32 also has the corner, and at this time, the corner is on the left side, so the unmanned vehicle is controlled to adjust the traveling direction to be 90 degrees to the left (the rotation angle is parallel to the wall 33 after the corner), and the search along the wall is continued.
2. When an obstacle/local protrusion/depression is detected during the wall tracing, the wall tracing is continued by bypassing the obstacle/local protrusion/depression.
Referring to fig. 4, when the obstacle/local protrusion/depression is detected, the distance between the obstacle and the wall is detected, and if the distance between the obstacle and the wall is greater than the minimum passing distance of the unmanned vehicle, the distance between the unmanned vehicle and the wall is controlled to be 0, that is, the unmanned vehicle approaches the wall and travels along the wall to pass through the obstacle; and if the distance between the barrier and the wall is smaller than the minimum passing distance of the unmanned vehicle, the obstacle is selected to bypass from the outside of the barrier, and the search is continued along the wall.
3. In the wall-following search process, a room door is detected, and the room is entered and processed in step S104.
In other embodiments of the invention, when a room door is detected, the distances between the unmanned vehicle and the wall bodies on the two sides of the room door are measured through a laser radar, and the width of the room door is calculated by combining the angle of a laser beam; when the width of the room door is smaller than a set width threshold value, the unmanned vehicle ignores the room door and continues to search along the wall; when the width of the room door is larger than or equal to the set width threshold value, the unmanned vehicle enters the room along the perpendicular bisector of the room door.
The set width threshold value is set as the minimum passing width of the unmanned vehicle, when the width of the room door is smaller than the set width threshold value, the unmanned vehicle cannot normally pass through the room door, and the unmanned vehicle directly ignores the room door to continue to search along the wall, so that the searching efficiency is improved; when the width of the room door is larger than or equal to the set width threshold value, the room door can be normally passed through, in order to directly enter the room door and avoid touching two sides of the room door, the unmanned vehicle can pass through the room along the perpendicular bisector of the room door.
S104, entering the room, identifying the size (length and width) of the room, and determining a room searching area.
The room size can be measured by laser radar transmission. After entering a room and primarily measuring the size of the room, the unmanned vehicle determines the coordinates of the rrt-expansion exploration area boundary points according to self positioning and coordinate conversion. And evaluating the exploration result, and clearing related coordinate point information and related state flag bits after the evaluation result is 'exploration is finished'.
And S105, searching the room by using a rapid search random tree algorithm.
Aiming at the exploration in a room, the method adopts the RRT to rapidly explore, avoids region traversal, reduces the repetition of paths, saves the exploration time and improves the exploration efficiency.
And S106, after the indoor exploration is finished, the indoor door is taken out and the indoor exploration is continued along the wall until the whole indoor environment exploration is finished, and the starting point is returned.
Optionally, the unmanned vehicle may be developed based on an ROS system, and each node communicates using an ROS standard protocol. And performing amcl positioning, slam graph building and navigation by using a milemeter and a laser radar. And the unmanned vehicle receives the monitoring information of the laser radar and the odometer through the controller, and realizes object feature identification and positioning navigation. The controller is also used for establishing a motion rule base according to the historical environment motion state, the current environment motion state and the turning information so as to plan the local path. It should be understood that the motion rule base may be established in any conventional manner, and will not be described herein.
The unmanned vehicle indoor autonomous exploration method provided by the invention aims at indoor search tasks such as urban fire emergency, anti-terrorism and explosive disposal, and is small in size, simple in structure and strong in expansibility. The combination of wall exploration and rrt-exploration makes the exploration more purposeful and efficient; the method not only can make up the randomness of fast random tree exploration, but also can make up the low efficiency of wall exploration.
It will be apparent to those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be centralized on a single computing device or distributed across a network of computing devices, and optionally they may be implemented in program code executable by a computing device, such that they may be stored on a computer storage medium (ROM/RAM, magnetic disks, optical disks) and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The foregoing is a more detailed description of the present invention that is presented in conjunction with specific embodiments, and the practice of the invention is not to be considered limited to those descriptions. For those skilled in the art to which the invention pertains, several simple deductions or substitutions can be made without departing from the spirit of the invention, and all shall be considered as belonging to the protection scope of the invention.

Claims (9)

1. An autonomous indoor exploration method for an unmanned vehicle, comprising:
the unmanned vehicle enters the indoor environment and starts an exploration task from the starting point;
when the wall body is identified, keeping a set distance with the wall, and exploring along the wall;
in the process of exploring along the wall, if a room door is detected, recording the position of the room door;
entering a room, identifying the size of the room, and determining a room exploration area;
exploring the room by using a rapid exploration random tree algorithm;
after the indoor exploration is finished, the indoor door is taken out and the indoor exploration is continued along the wall until the whole indoor environment exploration is finished, and the starting point is returned.
2. The method for autonomous indoor search of an unmanned vehicle as claimed in claim 1, wherein the method further comprises: when at least two walls are identified simultaneously, the closest wall is selected for wall-following exploration.
3. The autonomous discovery method in an unmanned vehicle interior according to claim 1, further comprising, during said wall-following discovery process: and when the fact that the wall body has the corner is detected, correcting the advancing direction and enabling the wall body after the corner to keep the set distance to continue exploring along the wall.
4. The method for autonomous indoor search of an unmanned vehicle as claimed in claim 1, wherein the method further comprises: when a room door is detected, measuring the distances between the unmanned vehicle and the wall bodies on the two sides of the room door respectively through a laser radar, and calculating the width of the room door by combining the angle of a laser beam; when the width of the room door is smaller than a set width threshold value, the unmanned vehicle ignores the room door and continues to search along the wall; when the width of the room door is larger than or equal to the set width threshold value, the unmanned vehicle enters the room along the perpendicular bisector of the room door.
5. The method for autonomously searching for the inside of an unmanned vehicle according to any one of claims 1 to 4, wherein the unmanned vehicle is equipped with a lidar, and the distance to a wall or an obstacle is measured by the lidar.
6. The indoor autonomous searching method of an unmanned vehicle according to claim 5, wherein said unmanned vehicle is further equipped with an odometer for measuring traveling distance information of a searching process.
7. The unmanned vehicle indoor autonomous exploration method of claim 6, wherein said unmanned vehicle is based on ROS system development, and each node communicates using ROS standard protocol.
8. The indoor autonomous exploration method for unmanned vehicle of claim 7, wherein the unmanned vehicle receives monitoring information of the laser radar and the odometer through a controller, and realizes object feature recognition and positioning navigation.
9. The autonomous indoor search method for an unmanned vehicle as claimed in claim 8, wherein the controller is further configured to establish a motion rule base according to the historical environmental motion state, the current environmental motion state and the turning direction information, and further perform local path planning.
CN202111587216.9A 2021-12-23 2021-12-23 Indoor autonomous exploration method for unmanned vehicle Pending CN114253272A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111587216.9A CN114253272A (en) 2021-12-23 2021-12-23 Indoor autonomous exploration method for unmanned vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111587216.9A CN114253272A (en) 2021-12-23 2021-12-23 Indoor autonomous exploration method for unmanned vehicle

Publications (1)

Publication Number Publication Date
CN114253272A true CN114253272A (en) 2022-03-29

Family

ID=80797072

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111587216.9A Pending CN114253272A (en) 2021-12-23 2021-12-23 Indoor autonomous exploration method for unmanned vehicle

Country Status (1)

Country Link
CN (1) CN114253272A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109343521A (en) * 2018-09-27 2019-02-15 深圳乐动机器人有限公司 A kind of robot cleans the method and robot in room
CN110680243A (en) * 2019-09-30 2020-01-14 湖南格兰博智能科技有限责任公司 Wall-following cleaning control algorithm for floor-sweeping robot
CN112698657A (en) * 2020-12-28 2021-04-23 湖南格兰博智能科技有限责任公司 Sweeping robot path planning method
CN113485375A (en) * 2021-08-13 2021-10-08 苏州大学 Indoor environment robot exploration method based on heuristic bias sampling

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109343521A (en) * 2018-09-27 2019-02-15 深圳乐动机器人有限公司 A kind of robot cleans the method and robot in room
CN110680243A (en) * 2019-09-30 2020-01-14 湖南格兰博智能科技有限责任公司 Wall-following cleaning control algorithm for floor-sweeping robot
CN112698657A (en) * 2020-12-28 2021-04-23 湖南格兰博智能科技有限责任公司 Sweeping robot path planning method
CN113485375A (en) * 2021-08-13 2021-10-08 苏州大学 Indoor environment robot exploration method based on heuristic bias sampling

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
蒋林: "结合历史运动状态的机器人高效沿墙算法研究", 《自动化学报》, pages 1176 *

Similar Documents

Publication Publication Date Title
CN110675307B (en) Implementation method from 3D sparse point cloud to 2D grid graph based on VSLAM
CN108983781B (en) Environment detection method in unmanned vehicle target search system
CN105115497B (en) A kind of reliable indoor mobile robot precision navigation positioning system and method
CN111164529B (en) Environment information updating device, environment information updating method, and program
WO2020140860A1 (en) Dynamic region division and region channel identification method, and cleaning robot
JP2501010B2 (en) Mobile robot guidance device
CN111258320A (en) Robot obstacle avoidance method and device, robot and readable storage medium
US11987245B2 (en) Method for controlling vehicle and vehicle control device
CN116576857A (en) Multi-obstacle prediction navigation obstacle avoidance method based on single-line laser radar
US20230205234A1 (en) Information processing device, information processing system, method, and program
Fassbender et al. Landmark-based navigation in large-scale outdoor environments
CN113064430A (en) Quality inspection trolley obstacle avoidance and path planning algorithm based on Android mobile phone
CN114253272A (en) Indoor autonomous exploration method for unmanned vehicle
JP7062558B2 (en) A moving body with a position detecting device and a moving body having a position detecting device.
Yang et al. Towards high accuracy parking slot detection for automated valet parking system
CN113768420B (en) Sweeper and control method and device thereof
JP7396353B2 (en) Map creation system, signal processing circuit, mobile object and map creation method
Abdelhafid et al. Visual and light detection and ranging-based simultaneous localization and mapping for self-driving cars.
CN114740867A (en) Intelligent obstacle avoidance method and device based on binocular vision, robot and medium
CN114489050A (en) Obstacle avoidance route control method, device, equipment and storage medium for straight line driving
Luo et al. Autonomous mobile robot localization based on multisensor fusion approach
CN114415659B (en) Robot safety obstacle avoidance method and device, robot and storage medium
Zhao et al. Development of automatic driving system by robocar
US11662740B2 (en) Position estimating apparatus, method for determining position of movable apparatus, and non-transitory computer readable medium
CN117519275A (en) Boiler inspection method and device, electronic equipment and storage medium

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