CN116236092A - Obstacle avoidance method of intelligent sweeping robot - Google Patents

Obstacle avoidance method of intelligent sweeping robot Download PDF

Info

Publication number
CN116236092A
CN116236092A CN202310104241.XA CN202310104241A CN116236092A CN 116236092 A CN116236092 A CN 116236092A CN 202310104241 A CN202310104241 A CN 202310104241A CN 116236092 A CN116236092 A CN 116236092A
Authority
CN
China
Prior art keywords
machine body
obstacle
information
coordinates
obstacle avoidance
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310104241.XA
Other languages
Chinese (zh)
Inventor
李焱
刘芳
王鑫
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.)
Ruiyi Technology Shandong Co ltd
Original Assignee
Ruiyi Technology Shandong 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 Ruiyi Technology Shandong Co ltd filed Critical Ruiyi Technology Shandong Co ltd
Priority to CN202310104241.XA priority Critical patent/CN116236092A/en
Publication of CN116236092A publication Critical patent/CN116236092A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/24—Floor-sweeping machines, motor-driven
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L11/00—Machines for cleaning floors, carpets, furniture, walls, or wall coverings
    • A47L11/40—Parts or details of machines not provided for in groups A47L11/02 - A47L11/38, or not restricted to one of these groups, e.g. handles, arrangements of switches, skirts, buffers, levers
    • A47L11/4011—Regulation of the cleaning machine by electric means; Control systems and remote control systems therefor
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L2201/00—Robotic cleaning machines, i.e. with automatic control of the travelling movement or the cleaning operation
    • A—HUMAN NECESSITIES
    • A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
    • A47L—DOMESTIC WASHING OR CLEANING; SUCTION CLEANERS IN GENERAL
    • A47L2201/00—Robotic cleaning machines, i.e. with automatic control of the travelling movement or the cleaning operation
    • A47L2201/04—Automatic control of the travelling movement; Automatic obstacle detection
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E10/00—Energy generation through renewable energy sources
    • Y02E10/50—Photovoltaic [PV] energy

Abstract

The invention provides an obstacle avoidance method of an intelligent sweeping robot. The technical scheme is based on the 3D TOF technology for imaging and positioning the space obstacle, and is combined with a laser radar and a 3D optical structure to acquire the space distribution state of the obstacle, so that an obstacle avoidance strategy is formed. Specifically, firstly, acquiring image information, then acquiring contour information based on an image algorithm, and fitting the contour information acquired by repeated positioning for a plurality of times to acquire barrier distribution information of a detection area; on the basis, judging the influence of the coordinates of the obstacles on a preset route, calculating the minimum distance between any two obstacles, and determining an avoidance area; then, determining optional travel points which do not cover the distribution coordinates of the obstacle and the avoidance area, and further forming an optional path; and finally, fitting the optional path with the non-driving range of the machine body to determine the driving path. The invention realizes high-efficiency visual obstacle avoidance, not only obviously improves the obstacle avoidance accuracy, but also has more efficient positioning and path planning.

Description

Obstacle avoidance method of intelligent sweeping robot
Technical Field
The invention relates to the technical field of sweeping robots, in particular to an obstacle avoidance method of an intelligent sweeping robot.
Background
The floor sweeping robot, also called automatic sweeping machine, intelligent dust collector, robot dust collector, etc., is one kind of intelligent household appliance and can complete floor cleaning automatically inside room via artificial intelligence. Generally, the brushing and vacuum modes are adopted, and the ground sundries are firstly absorbed into the garbage storage box of the ground, so that the function of cleaning the ground is completed. Generally, robots that perform cleaning, dust collection, and floor scrubbing work are also collectively referred to as floor cleaning robots.
The machine body of the sweeping machine is a wireless machine and mainly comprises a disc type machine. The operation is performed by using a rechargeable battery, and the operation mode is a remote controller or an operation panel on the machine. The cleaning can be reserved for a set time and the self-charging can be realized. The front is provided with a sensor which can detect obstacles, such as a wall or other obstacles, can turn by itself, and can travel different routes according to different manufacturer settings, thereby planning cleaning areas. (some earlier models may lack some functions) are becoming popular in the past because of their simple operation and convenience, and are becoming common household appliances for office workers or modern families. For the robot of sweeping floor, effective obstacle avoidance ability is the important prerequisite of guaranteeing that motion system keeps steady operation, because in the room object is various, the form is various and the distribution is complicated, therefore put forward higher requirement to motion system. At present, the obstacle avoidance capability of the conventional movement system is still insufficient, and the effective planning capability for the space with more complex obstacle distribution is insufficient.
Disclosure of Invention
Aiming at the technical defects of the prior art, the invention provides an obstacle avoidance method of an intelligent sweeping robot, which aims to solve the technical problem that the obstacle avoidance capability of a common motion system is to be improved.
In order to achieve the technical purpose, the invention adopts the following technical scheme:
an obstacle avoidance method of an intelligent sweeping robot comprises the following steps:
1) Acquiring current position information of a machine body, acquiring an image in front of the position of the machine body by using a laser radar, extracting candidate contour points in the image by using a Canny edge detector, extracting patches with different scales around each candidate point, and acquiring contour information of an obstacle through a pre-trained convolution layer;
2) Changing the travelling direction for a plurality of times, and executing the step 1 successively); fitting the acquired obstacle profile information in space coordinates to obtain obstacle distribution information of a detection area,
3) When the obstacle coordinates are in a preset running route of the machine body, the machine body controller respectively acquires current position information, preset running route information and obstacle distribution information of the machine body, calculates the minimum distance between any two obstacles in the obstacle distribution information, and marks the minimum distance smaller than the diameter of the machine body as an avoidance area;
4) Removing the avoidance region from space coordinates around the machine body, determining a plurality of optional travel points which do not cover the obstacle distribution coordinates and the avoidance region between the current position coordinates and the target position coordinates of the machine body, and connecting the current position coordinates and the target position coordinates of the machine body by utilizing the plurality of optional travel points to form a plurality of optional paths;
5) Fitting a plurality of optional paths with the non-running range of the machine body recorded by the machine body controller respectively, and determining a running path according to the fitting; the machine body controller recalculates the target speed and the target steering angle according to the current running speed information and the running direction information of the machine body and the determined running path.
Preferably, in step 1), the current position information of the machine body includes coordinate values of the machine body and a non-driving range of the machine body.
Preferably, in step 1), the three-dimensional coordinates are acquired by using a binocular camera while the image in front of the location of the body is acquired.
Preferably, in step 1), the number of patches is at least 4, and the number of convolution layers is at least 5.
Preferably, in the step 2), the included angle between the changed travelling direction and the original travelling direction is 10-30 degrees, and the travel distance between the two changes of the travelling direction is 10-15 cm.
Preferably, in step 3), the travel preset route information is characterized by sequential connection of spatial coordinate points.
Preferably, in step 3), after calculating the minimum distance between any two obstacles, projecting each minimum distance on a vertical plane of a preset running route of the machine body, and marking the projection smaller than the diameter of the machine body as an avoidance area.
Preferably, in step 4), when the optional travel point is located at a position adjacent to the obstacle distribution coordinates or at the edge of the avoidance area, the coordinate value of the optional travel point is adjusted.
Preferably, in step 5), when the difference between the target speed and the current running speed of the machine body is greater than 50%, setting a transitional target speed; when the target steering angle is greater than 60 °, a transitional target steering angle is set.
Preferably, step 5) further comprises: the body drive controller receives the recalculated target speed and target steering angle, and executes drive control.
The invention provides an obstacle avoidance method of an intelligent sweeping robot. The technical scheme is based on the 3D TOF technology for imaging and positioning the space obstacle, and is combined with a laser radar and a 3D optical structure to acquire the space distribution state of the obstacle, so that an obstacle avoidance strategy is formed. Specifically, firstly, acquiring image information, then acquiring contour information based on an image algorithm, and fitting the contour information acquired by repeated positioning for a plurality of times to acquire barrier distribution information of a detection area; on the basis, judging the influence of the coordinates of the obstacles on a preset route, calculating the minimum distance between any two obstacles, and determining an avoidance area; then, determining optional travel points which do not cover the distribution coordinates of the obstacle and the avoidance area, and further forming an optional path; and finally, fitting the optional path with the non-running range of the machine body recorded by the machine body controller, determining a running path, and recalculating the target speed and the target steering angle. The invention realizes high-efficiency visual obstacle avoidance, not only obviously improves the obstacle avoidance accuracy, but also has more efficient positioning and path planning, and has outstanding technical advantages.
Drawings
Fig. 1 is a flow chart of the method of the present invention.
Detailed Description
Hereinafter, embodiments of the present invention will be described in detail. In order to avoid unnecessary detail, well-known structures or functions will not be described in detail in the following embodiments. Approximating language, as used in the following examples, may be applied to create a quantitative representation that could permissibly vary without resulting in a change in the basic function. Unless defined otherwise, technical and scientific terms used in the following examples have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
Example 1
An obstacle avoidance method of an intelligent sweeping robot, as shown in fig. 1, comprises the following steps:
1) Acquiring current position information of a machine body, acquiring an image in front of the position of the machine body by using a laser radar, extracting candidate contour points in the image by using a Canny edge detector, extracting patches with different scales around each candidate point, and acquiring contour information of an obstacle through a pre-trained convolution layer;
2) Changing the travelling direction for a plurality of times, and executing the step 1 successively); fitting the acquired obstacle profile information in space coordinates to obtain obstacle distribution information of a detection area,
3) When the obstacle coordinates are in a preset running route of the machine body, the machine body controller respectively acquires current position information, preset running route information and obstacle distribution information of the machine body, calculates the minimum distance between any two obstacles in the obstacle distribution information, and marks the minimum distance smaller than the diameter of the machine body as an avoidance area;
4) Removing the avoidance region from space coordinates around the machine body, determining a plurality of optional travel points which do not cover the obstacle distribution coordinates and the avoidance region between the current position coordinates and the target position coordinates of the machine body, and connecting the current position coordinates and the target position coordinates of the machine body by utilizing the plurality of optional travel points to form a plurality of optional paths;
5) Fitting a plurality of optional paths with the non-running range of the machine body recorded by the machine body controller respectively, and determining a running path according to the fitting; the machine body controller recalculates the target speed and the target steering angle according to the current running speed information and the running direction information of the machine body and the determined running path.
Example 2
An obstacle avoidance method of an intelligent sweeping robot, as shown in fig. 1, comprises the following steps:
1) Acquiring current position information of a machine body, acquiring an image in front of the position of the machine body by using a laser radar, extracting candidate contour points in the image by using a Canny edge detector, extracting patches with different scales around each candidate point, and acquiring contour information of an obstacle through a pre-trained convolution layer;
2) Changing the travelling direction for a plurality of times, and executing the step 1 successively); fitting the acquired obstacle profile information in space coordinates to obtain obstacle distribution information of a detection area,
3) When the obstacle coordinates are in a preset running route of the machine body, the machine body controller respectively acquires current position information, preset running route information and obstacle distribution information of the machine body, calculates the minimum distance between any two obstacles in the obstacle distribution information, and marks the minimum distance smaller than the diameter of the machine body as an avoidance area;
4) Removing the avoidance region from space coordinates around the machine body, determining a plurality of optional travel points which do not cover the obstacle distribution coordinates and the avoidance region between the current position coordinates and the target position coordinates of the machine body, and connecting the current position coordinates and the target position coordinates of the machine body by utilizing the plurality of optional travel points to form a plurality of optional paths;
5) Fitting a plurality of optional paths with the non-running range of the machine body recorded by the machine body controller respectively, and determining a running path according to the fitting; the machine body controller recalculates the target speed and the target steering angle according to the current running speed information and the running direction information of the machine body and the determined running path.
In step 1), the current position information of the machine body includes coordinate values of the machine body and a non-driving range of the machine body. In step 1), a binocular camera is used to acquire three-dimensional coordinates while acquiring an image in front of the position of the body. In step 1), the number of patches is at least 4, and the number of convolution layers is at least 5. In the step 2), the included angle between the changed travelling direction and the original travelling direction is 10-30 degrees, and the travel distance between the two changes of the travelling direction is 10-15 cm. In the step 3), the traveling preset route information is characterized by sequential connection lines of the space coordinate points. In the step 3), after calculating the minimum distance between any two obstacles, projecting each minimum distance on the vertical plane of the preset running route of the machine body, and marking the projection smaller than the diameter of the machine body as an avoidance area. In the step 4), when the optional travel point is located at a position adjacent to the obstacle distribution coordinates or at the edge of the avoidance area, the coordinate values of the optional travel point are adjusted. In the step 5), when the difference between the target speed and the current running speed of the machine body is more than 50%, setting a transitional target speed; when the target steering angle is greater than 60 °, a transitional target steering angle is set. Step 5) further comprises: the body drive controller receives the recalculated target speed and target steering angle, and executes drive control.
The foregoing describes the embodiments of the present invention in detail, but the description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the scope of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. An obstacle avoidance method of an intelligent sweeping robot is characterized by comprising the following steps:
1) Acquiring current position information of a machine body, acquiring an image in front of the position of the machine body by using a laser radar, extracting candidate contour points in the image by using a Canny edge detector, extracting patches with different scales around each candidate point, and acquiring contour information of an obstacle through a pre-trained convolution layer;
2) Changing the travelling direction for a plurality of times, and executing the step 1 successively); fitting the acquired obstacle profile information in space coordinates to obtain obstacle distribution information of a detection area,
3) When the obstacle coordinates are in a preset running route of the machine body, the machine body controller respectively acquires current position information, preset running route information and obstacle distribution information of the machine body, calculates the minimum distance between any two obstacles in the obstacle distribution information, and marks the minimum distance smaller than the diameter of the machine body as an avoidance area;
4) Removing the avoidance region from space coordinates around the machine body, determining a plurality of optional travel points which do not cover the obstacle distribution coordinates and the avoidance region between the current position coordinates and the target position coordinates of the machine body, and connecting the current position coordinates and the target position coordinates of the machine body by utilizing the plurality of optional travel points to form a plurality of optional paths;
5) Fitting a plurality of optional paths with the non-running range of the machine body recorded by the machine body controller respectively, and determining a running path according to the fitting; the machine body controller recalculates the target speed and the target steering angle according to the current running speed information and the running direction information of the machine body and the determined running path.
2. The obstacle avoidance method of claim 1 wherein in step 1), the current location information of the machine body includes coordinate values of the machine body and a non-driving range of the machine body.
3. The obstacle avoidance method of claim 1 wherein in step 1), a binocular camera is used to acquire three-dimensional coordinates while an image of the front of the location of the body is acquired.
4. The obstacle avoidance method of claim 1 wherein in step 1), the number of patches is at least 4 and the number of convolution layers is at least 5.
5. The obstacle avoidance method of an intelligent robot as claimed in claim 1, wherein in the step 2), an included angle between the changed traveling direction and the original traveling direction is 10 ° to 30 °, and a travel distance between the two changes of the traveling direction is 10 cm to 15cm.
6. The obstacle avoidance method of claim 1 wherein, in step 3), the travel preset route information is characterized by sequential connection of spatial coordinate points.
7. The obstacle avoidance method of an intelligent robot as claimed in claim 1, wherein in step 3), after calculating the minimum distance between any two obstacles, each minimum distance is projected on a vertical plane of a preset path traveled by the robot body, and the projection smaller than the diameter of the robot body is marked as an avoidance area.
8. The obstacle avoidance method of the intelligent sweeping robot according to claim 1, wherein in the step 4), when the selectable travel point is located at a position adjacent to the obstacle distribution coordinates or at the edge of the avoidance area, the coordinate value of the selectable travel point is adjusted.
9. The obstacle avoidance method of an intelligent robot as set forth in claim 1, wherein in step 5), when the difference between the target speed and the current travel speed of the body is greater than 50%, a transition target speed is set; when the target steering angle is greater than 60 °, a transitional target steering angle is set.
10. The obstacle avoidance method of an intelligent floor sweeping robot of claim 1, wherein step 5) further comprises: the body drive controller receives the recalculated target speed and target steering angle, and executes drive control.
CN202310104241.XA 2023-02-13 2023-02-13 Obstacle avoidance method of intelligent sweeping robot Pending CN116236092A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310104241.XA CN116236092A (en) 2023-02-13 2023-02-13 Obstacle avoidance method of intelligent sweeping robot

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310104241.XA CN116236092A (en) 2023-02-13 2023-02-13 Obstacle avoidance method of intelligent sweeping robot

Publications (1)

Publication Number Publication Date
CN116236092A true CN116236092A (en) 2023-06-09

Family

ID=86629171

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310104241.XA Pending CN116236092A (en) 2023-02-13 2023-02-13 Obstacle avoidance method of intelligent sweeping robot

Country Status (1)

Country Link
CN (1) CN116236092A (en)

Similar Documents

Publication Publication Date Title
US11960304B2 (en) Localization and mapping using physical features
US20210251450A1 (en) Automatic cleaning device and cleaning method
CN108852184B (en) Non-blind area sweeping robot based on deep learning algorithm and sweeping control method thereof
CN113110457B (en) Autonomous coverage inspection method for intelligent robot in indoor complex dynamic environment
CN105425801B (en) Intelligent cleaning robot and its clean method based on advanced Path Planning Technique
KR101372482B1 (en) Method and apparatus of path planning for a mobile robot
CA2428360C (en) Autonomous multi-platform robotic system
CN110522359A (en) The control method of clean robot and clean robot
CN111035327A (en) Cleaning robot, carpet detection method, and computer-readable storage medium
CN112004645A (en) Intelligent cleaning robot
CN111624997A (en) Robot control method and system based on TOF camera module and robot
CN111067432B (en) Determination method for charging working area of charging pile of sweeper and sweeper
CN107443385B (en) Detection method and chip for robot linear navigation based on vision and robot
CN113741438A (en) Path planning method and device, storage medium, chip and robot
CN112806912B (en) Robot cleaning control method and device and robot
KR101333496B1 (en) Apparatus and Method for controlling a mobile robot on the basis of past map data
CN113475977B (en) Robot path planning method and device and robot
CN113566808A (en) Navigation path planning method, device, equipment and readable storage medium
CN111700544A (en) Anti-collision control system and control method of intelligent cleaning robot
CN110750092A (en) Mobile robot and control method
CN211933898U (en) Cleaning robot
CN112274063B (en) Robot cleaning method, control device, readable storage medium and robot
CN113017492A (en) Object recognition intelligent control system based on cleaning robot
CN110967703A (en) Indoor navigation method and indoor navigation device using laser radar and camera
CN116236092A (en) Obstacle avoidance method of intelligent sweeping robot

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