CN111893930A - Unmanned intelligent sweeping machine based on machine vision - Google Patents

Unmanned intelligent sweeping machine based on machine vision Download PDF

Info

Publication number
CN111893930A
CN111893930A CN201911365946.7A CN201911365946A CN111893930A CN 111893930 A CN111893930 A CN 111893930A CN 201911365946 A CN201911365946 A CN 201911365946A CN 111893930 A CN111893930 A CN 111893930A
Authority
CN
China
Prior art keywords
machine vision
vehicle
sweeping machine
machine
motors
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
CN201911365946.7A
Other languages
Chinese (zh)
Inventor
周汉杰
朱金栋
沈永峰
其他发明人请求不公开姓名
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.)
Shanghai Yupei Automobile Technology Co ltd
Original Assignee
Shanghai Yupei Automobile Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Yupei Automobile Technology Co ltd filed Critical Shanghai Yupei Automobile Technology Co ltd
Priority to CN201911365946.7A priority Critical patent/CN111893930A/en
Publication of CN111893930A publication Critical patent/CN111893930A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • EFIXED CONSTRUCTIONS
    • E01CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
    • E01HSTREET CLEANING; CLEANING OF PERMANENT WAYS; CLEANING BEACHES; DISPERSING OR PREVENTING FOG IN GENERAL CLEANING STREET OR RAILWAY FURNITURE OR TUNNEL WALLS
    • E01H1/00Removing undesirable matter from roads or like surfaces, with or without moistening of the surface
    • E01H1/005Mobile installations, particularly for upkeeping in situ road or railway furniture, for instance road barricades, traffic signs; Mobile installations particularly for upkeeping tunnel walls
    • EFIXED CONSTRUCTIONS
    • E01CONSTRUCTION OF ROADS, RAILWAYS, OR BRIDGES
    • E01HSTREET CLEANING; CLEANING OF PERMANENT WAYS; CLEANING BEACHES; DISPERSING OR PREVENTING FOG IN GENERAL CLEANING STREET OR RAILWAY FURNITURE OR TUNNEL WALLS
    • E01H1/00Removing undesirable matter from roads or like surfaces, with or without moistening of the surface
    • E01H1/02Brushing apparatus, e.g. with auxiliary instruments for mechanically loosening dirt
    • E01H1/05Brushing apparatus, e.g. with auxiliary instruments for mechanically loosening dirt with driven brushes
    • E01H1/053Brushing apparatus, e.g. with auxiliary instruments for mechanically loosening dirt with driven brushes having vertical axes
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/50Context or environment of the image
    • G06V20/56Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/58Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00Scenes; Scene-specific elements
    • G06V20/50Context or environment of the image
    • G06V20/56Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/588Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Architecture (AREA)
  • Civil Engineering (AREA)
  • Structural Engineering (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

The invention relates to an unmanned intelligent road sweeper based on machine vision, belonging to the field of sanitation vehicles. In order to solve the problems of low efficiency and low automation degree of the existing sweeping machine, the sweeping machine has the functions of autonomous navigation, autonomous driving and autonomous operation through machine vision and an artificial neural network. According to the invention, the lane lines are pasted on the advancing route of the vehicle, the camera positioned in front of the vehicle transmits the captured lane line images to the development board, and then the development board processes the images to extract the path navigation information in the images, so that the autonomous driving function of the vehicle is realized by changing the rotating speed of the motor. In addition, the invention is additionally provided with an infrared sensor and a photoelectric encoder to carry out double closed-loop control on the sweeping machine, thereby ensuring the safe and autonomous driving of the sweeping machine.

Description

Unmanned intelligent sweeping machine based on machine vision
Technical Field
The invention belongs to the field of sanitation vehicles, and particularly relates to a novel driverless sanitation vehicle.
Background
The sweeping machine is a special vehicle for sweeping road surface garbage. The sweeping machine is one of the environmental sanitation equipments, and has the functions of saving time and labor. Is a novel efficient cleaning device integrating road surface cleaning, garbage recovery and transportation. Can be widely applied to road cleaning operations of city streets, municipal squares, airport road surfaces, city residential areas, parks and the like. The sweeping machine not only can sweep garbage, but also can remove dust and purify air on a road, ensures the cleanness and tidiness of the road, prevents dust from flying, prolongs the service life of the road surface, and has the advantages of reducing and preventing traffic accidents.
On the one hand, the existing sweeping machine has certain requirements on the driving technique and the operation technique of drivers, and if the sweeping machine is not operated properly, accidents are easily caused. Most importantly, most of the existing sweeping machines need to be driven or controlled by sanitation workers, so that automatic and intelligent operation cannot be realized, the work efficiency cannot be improved, and the waste of manpower and financial resources is caused.
Disclosure of Invention
In view of the above situation, the present invention provides a sweeping machine with simple structure, convenient operation, safety, reliability, high automation and intelligence, which realizes the functions of autonomous navigation, autonomous driving and autonomous operation through machine vision and artificial neural network. The invention mainly aims at the environment of parks, high-grade districts, logistics parks, industrial parks and the like which have simple vehicle conditions but heavy cleaning tasks. The main work of the invention is to autonomously sweep one or more turns around the work site at a rate of three to five kilometers per hour. Only a small amount of guard and maintenance personnel are needed, the labor cost is greatly reduced, and the core value of energy conservation, environmental protection and intelligence is emphatically reflected.
The function of the invention is realized as follows:
firstly, starting from the autonomous operation function of the sweeping machine, the main driving wheels of the sweeping machine are two rear wheels which are respectively driven by two driving motors. The driven wheel is a universal wheel positioned in front and plays a role in auxiliary steering. The two disk brushes in front of the vehicle are respectively driven by two disk brush motors, and the rolling brush is driven by a rolling brush motor. What the dish brush played with the round brush is the effect of cleaning operation, and dish brush motor clockwise rotation on the left side, dish brush motor anticlockwise rotation on the right side sweep the vehicle both sides rubbish to the dead ahead of vehicle, sweep rubbish into the dustbin of sweeping machine by the round brush again to the autonomous operation function of sweeping machine has been realized.
Then starting from the autonomous driving function of the sweeping machine, firstly, a lane line is pasted on the advancing route of the vehicle, a camera positioned in front of the vehicle transmits a shot lane line image to a raspberry development board, the image is subjected to a series of processing such as graying processing, filtering noise reduction, image segmentation, expansion and corrosion, shadow removal and the like through the development board, and path navigation information in the image is extracted, so that the rotating speed of a motor is changed to realize the autonomous driving function of the vehicle. The specific operation is as follows:
when the lane line is a straight line, the lane line indicates that the vehicle moves straight ahead, and the dual-drive motor is controlled to move forward at the same rotating speed.
When the lane line is a right-turn curved line, the lane line shows a right turn ahead, the rotating speed of the left driving motor is kept unchanged, and the rotating speed of the right driving motor is reduced.
When the lane line is a left-turn bending line, the lane line shows a left turn ahead, the rotating speed of the right driving motor is kept unchanged, and the rotating speed of the left driving motor is reduced.
When the infrared sensor of the development board displays that an obstacle exists in front of the development board, the requirement for braking is indicated, and the dual-drive motor is controlled to stop rotating.
In addition, in order to ensure the low-speed safe running of the vehicle, the invention is respectively provided with a photoelectric encoder on the driving motor, the photoelectric encoders are used for measuring the rotating speed of the motor and feeding the rotating speed back to the development board, the actual rotating speed is compared with the given rotating speed of the development board, and the driving motor is immediately controlled to stop rotating when the error is large, thereby effectively avoiding the occurrence of accidents.
The invention has the beneficial effects that: the problem of unmanned driving of sweeping is tentatively solved, and the intellectuality of environmental protection work has been realized, has saved time cost and cost of labor, has alleviateed sanitationman's work burden greatly.
Drawings
Fig. 1 is a schematic structural view of a front sweeping machine.
Fig. 2 is a schematic structural view of the side sweeping machine.
Fig. 3 is a view of the entire vehicle with the outer shell attached.
Fig. 4 is a structural view of the universal wheel.
Fig. 5 is a pin diagram of the single chip microcomputer.
Fig. 6 is a circuit diagram of the infrared sensor.
In the figure, 1 disk brush, 2 universal wheels, 3 disk brush motors, 4 cameras, 5 development boards, 6 power supplies, 7 rolling brush motors, 8 rolling brushes, 9 garbage cans, 10 left driving motors, 11 left driving wheels, 12 control circuit bodies, 13 structure bodies, 14 right driving motors and 15 right driving wheels.
Detailed Description
The invention is further described with reference to the following figures and detailed description.
Referring to fig. 1 to 4, an unmanned intelligent sweeping vehicle based on machine vision comprises a sweeping component and a driving component, wherein the sweeping component comprises a rolling brush 8, a disc brush 1 and a garbage can 9. The disc brush collects the garbage on the two sides to the front of the rolling brush, and the garbage is swept into the garbage can by the rolling brush to realize the cleaning function.
The driving part consists of a universal wheel 2, a camera 4, a development board 5, dual-driving motors 10 and 14 and dual- driving wheels 11 and 15. Firstly, a lane line is pasted on the advancing route of a vehicle, a camera 4 positioned in front of the vehicle transmits a captured lane line image to a development board 5, then the development board 5 carries out a series of processing such as graying processing, filtering and noise reduction, image segmentation, expansion and corrosion, shadow removal and the like on the image, and extracts path navigation information in the image, thereby realizing the autonomous driving function of the vehicle by changing the rotating speed of a dual-drive motor.
The specific operation is as follows:
when the lane line after the processing of the development board 5 is displayed as a straight line, the forward straight line is indicated, and the dual drive motors 10 and 14 are controlled to move forward at the same rotating speed.
When the lane line processed by the development board 5 is displayed as a right turn curve, the curve indicates a right turn ahead, the rotation speed of the left drive motor 10 is kept unchanged, and the rotation speed of the right drive motor 14 is reduced.
When the lane line processed by the development board 5 is displayed as a left-turn curve, the curve indicates a left turn ahead, the rotation speed of the right driving motor 14 is kept unchanged, and the rotation speed of the left driving motor 10 is reduced.
The development board 5 comprises the infrared sensor module, and when an obstacle appears in front of the vehicle, the development board can timely control the double motors to stop rotating, so that safe driving is guaranteed.
In addition, in order to ensure the safe running of the vehicle at low speed, the invention respectively installs one photoelectric encoder on the driving motor, the photoelectric encoder is used for measuring the rotating speed of the motor and feeding the rotating speed back to the development board 5, the actual rotating speed is compared with the given rotating speed of the development board, and the driving motor is immediately controlled to stop rotating when the error is large, thereby effectively avoiding the occurrence of accidents.
While the preferred embodiments of the present invention have been described, those skilled in the art will appreciate that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined by the appended claims.

Claims (3)

1. The utility model provides an unmanned small sweeper based on machine vision, includes automobile body owner frame (13) and machine vision control part (12), its characterized in that: the main vehicle body frame (13) is divided into a main body part and a cleaning part, and the machine vision control part (12) is divided into a main control module (5) and an image acquisition module (4).
2. The machine vision based unmanned sweeping vehicle of claim 1, wherein: the main body part of the main frame (13) of the vehicle body comprises two driving wheels (11) controlled by two motors (10), and the two motors respectively supply different rotating speeds to the two driving wheels to realize the steering function.
3. The two electric motors (10) according to claim 2 give the two driving wheels (11) different rotation speeds, characterized in that: the machine vision control part (12) collects lane lines and road signs through the image collection module (4), processes the collected images through the main control module (5), and outputs different PWM duty ratio signals to the two motors (10) to realize different rotating speeds of the two driving wheels (11).
CN201911365946.7A 2019-12-26 2019-12-26 Unmanned intelligent sweeping machine based on machine vision Pending CN111893930A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911365946.7A CN111893930A (en) 2019-12-26 2019-12-26 Unmanned intelligent sweeping machine based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911365946.7A CN111893930A (en) 2019-12-26 2019-12-26 Unmanned intelligent sweeping machine based on machine vision

Publications (1)

Publication Number Publication Date
CN111893930A true CN111893930A (en) 2020-11-06

Family

ID=73169681

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911365946.7A Pending CN111893930A (en) 2019-12-26 2019-12-26 Unmanned intelligent sweeping machine based on machine vision

Country Status (1)

Country Link
CN (1) CN111893930A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114119434A (en) * 2021-12-02 2022-03-01 东风悦享科技有限公司 Cleaning tool automatic conversion method and system based on image analysis

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114119434A (en) * 2021-12-02 2022-03-01 东风悦享科技有限公司 Cleaning tool automatic conversion method and system based on image analysis

Similar Documents

Publication Publication Date Title
CN205421127U (en) Rubbish cleans machine people
CN208363002U (en) A kind of low speed automated driving system
CN109542097B (en) Underground unmanned trackless rubber-tyred vehicle with infrared top tracking and running control method thereof
CN200974567Y (en) Cleaning robot running gear
CN103866728A (en) Commercial robot floor washing machine
CN105862635B (en) Suitable for the retractable full-automatic sweeping robot and method of work of highway
CN109778750A (en) Intelligent unattended drives falling leave cleaning machine device people
CN107176218A (en) Full landform crusing robot
CN202830853U (en) Driving type electric motor sweeper
CN108614567A (en) Intelligent environmental protection working vehicle control system
CN111962436B (en) Unmanned automatic planning environment-friendly sweeper for non-motor vehicle lane and sweeping method
CN206528403U (en) A kind of unpiloted cleaning maintenance special car of pure multifunctional electric
CN208411674U (en) A kind of new energy Intelligent unattended driving cleaning vehicle
CN211596610U (en) Unmanned automatic garbage sweeper
CN111893930A (en) Unmanned intelligent sweeping machine based on machine vision
CN113152345A (en) Intelligent cleaning vehicle for fallen leaves on road surfaces of garden and non-motor vehicle lane
CN207165109U (en) A kind of municipal administration road indicator
CN107472775A (en) A kind of automatic tracking loop defends the method for cleaning and unmanned electric garbage clearing and transporting vehicle
CN205975443U (en) Totally closed driving formula electricelectric moves four -wheel forerunner sweeping machine
CN205574810U (en) Full -automatic transport vechicle
CN112684784A (en) Low-speed unmanned driving system
CN204229228U (en) A kind of complete unattended control device of intelligent solar automobile
CN212294476U (en) Unmanned small-sized sweeping machine
CN205501902U (en) Dual drive electricelectric moves road and sweeps clean car
CN208673145U (en) Intelligent environmental protection working vehicle control system

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