CN116985090A - Intelligent garbage sorting robot - Google Patents
Intelligent garbage sorting robot Download PDFInfo
- Publication number
- CN116985090A CN116985090A CN202310984520.XA CN202310984520A CN116985090A CN 116985090 A CN116985090 A CN 116985090A CN 202310984520 A CN202310984520 A CN 202310984520A CN 116985090 A CN116985090 A CN 116985090A
- Authority
- CN
- China
- Prior art keywords
- robot
- garbage
- mechanical arm
- control system
- processing system
- 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
- 238000012545 processing Methods 0.000 claims abstract description 39
- 230000009471 action Effects 0.000 claims abstract description 14
- 210000000078 claw Anatomy 0.000 claims abstract description 12
- 210000000707 wrist Anatomy 0.000 claims abstract description 7
- 238000004064 recycling Methods 0.000 claims description 22
- 238000001514 detection method Methods 0.000 claims description 12
- 230000007246 mechanism Effects 0.000 claims description 4
- 238000012546 transfer Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 2
- 238000000034 method Methods 0.000 abstract description 8
- 230000001105 regulatory effect Effects 0.000 abstract 1
- 238000004140 cleaning Methods 0.000 description 8
- 210000003128 head Anatomy 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000003062 neural network model Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 210000004247 hand Anatomy 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000003137 locomotive effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J5/00—Manipulators mounted on wheels or on carriages
- B25J5/007—Manipulators mounted on wheels or on carriages mounted on wheels
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/34—Sorting according to other particular properties
- B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
- B07C5/3422—Sorting according to other particular properties according to optical properties, e.g. colour using video scanning devices, e.g. TV-cameras
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
- B07C5/36—Sorting apparatus characterised by the means used for distribution
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J11/00—Manipulators not otherwise provided for
- B25J11/008—Manipulators for service tasks
- B25J11/0085—Cleaning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J19/00—Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1656—Programme controls characterised by programming, planning systems for manipulators
- B25J9/1664—Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1674—Programme controls characterised by safety, monitoring, diagnostic
- B25J9/1676—Avoiding collision or forbidden zones
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65F—GATHERING OR REMOVAL OF DOMESTIC OR LIKE REFUSE
- B65F3/00—Vehicles particularly adapted for collecting refuse
-
- 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
- Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
- Y02W30/00—Technologies for solid waste management
- Y02W30/10—Waste collection, transportation, transfer or storage, e.g. segregated refuse collecting, electric or hybrid propulsion
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Robotics (AREA)
- Multimedia (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an intelligent garbage sorting robot which comprises a motion module, an action module and a control system, wherein the motion module is used for moving garbage; the motion module comprises a chassis running gear consisting of four Mecanum wheels and a motor; the action module comprises a six-axis mechanical arm and a mechanical claw; a Intel RealSense D455 binocular camera is mounted on the wrist of the six-axis mechanical arm; the bottom layer control system completes control of the motor and the steering engine and signal processing of the obstacle avoidance sensor, the upper layer processing system completes SLAM map building, positioning and navigation, garbage classification and path planning of positioning and mechanical arm grabbing based on the laser radar and the ROS, information processed by the upper layer processing system is transmitted to the bottom layer control system through serial port communication, the speed of the motor is regulated, each steering engine of the mechanical arm is controlled, and therefore movement of the robot and movement of the mechanical arm are controlled. The method and the device can identify the household garbage type of the appointed area through identifying the household garbage of the appointed area, finish positioning, picking and classifying operations, and realize the full-automatic unmanned garbage sorting work of the appointed area through the mobile searching of the robot.
Description
Technical Field
The invention relates to the field of intelligent robots, in particular to a robot capable of sorting garbage.
Technical Field
At present, garbage classification is required in many cities, but partial garbage is generated in some places such as the ground of communities, public places and the like; to the cleaning and the processing of the rubbish on community ground, the mainstream is electric community cleaning vehicle in the market at present, and though rubbish can be cleaned more efficiently, the ground rubbish that cleans still needs to carry out classification processing through the manual work at last, can't fine liberation labour. For ground garbage in residential communities, cleaning personnel are often required to pick up the garbage and then sort the garbage; in addition, at present, although intelligent garbage classification barrels exist at home and abroad, the garbage classification barrel is imperfect and expensive, people are usually required to primarily judge the garbage types and then convey the garbage types to a machine, the use process is complicated, the garbage classification barrel can only be placed in a plurality of places at fixed points in a community as the traditional garbage can, and the garbage classification barrel is inconvenient. Therefore, the design of the intelligent garbage sorting robot which can clean the ground garbage and meet the garbage sorting requirement and avoid the manual sorting defect is low in cost.
Disclosure of Invention
Based on the problems, the intelligent garbage sorting robot provided by the invention can clean, process and sort garbage which is generated in communities or public places at any time, keep communities clean and tidy, replace part of labor force in garbage cleaning and sorting, greatly reduce labor cost required by garbage sorting, and improve garbage sorting efficiency.
The adopted technical scheme is as follows: the intelligent garbage sorting robot comprises a motion module, an action module and a control system; the motion module comprises a chassis running gear consisting of four Mecanum wheels and a motor; the chassis is provided with a machine body; the machine body comprises a machine head, a machine body and a machine back plate; the vehicle head is provided with an action module, the vehicle body is provided with a plurality of garbage recycling boxes, a laser radar is arranged above a vehicle rear plate, and a display screen is arranged at the rear side of the vehicle rear plate; the chassis is internally provided with a control system, a power module and a motor drive board.
The action module comprises a six-axis mechanical arm and a mechanical claw; the six-axis mechanism arm is arranged on the headstock through a tripod head; the front end of the six-axis mechanical arm is provided with a mechanical claw; the wrist of the six-axis mechanical arm is provided with a binocular camera;
the control system comprises a bottom layer control system and an upper layer processing system, and the bottom layer control system and the upper layer processing system are communicated in a serial port mode.
The bottom layer control system takes an STM32F405RGT6 main board as a core; the steering mechanism is used for controlling the rotation of the motor and each steering engine on the six-axis mechanical arm, and the rotation of the steering engine adjusts the pose of the six-axis mechanical arm; the bottom layer control system also detects signals of the ultrasonic obstacle avoidance sensor;
the upper processing system adopts Inlet Weida Jetson TX2 as a core, and is provided with an ROS system; integrating a machine vision module on the Inlet Weida Jetson TX 2; the upper layer processing system comprises a classification and positioning system for garbage based on a machine vision module for yolo target detection, a SLAM map building navigation system based on a laser radar and ROS, and a grabbing path planning system for the six-axis mechanical arm; the three are combined to realize the recognition of the robot to the garbage type to realize garbage sorting;
the bottom layer control system firstly receives the information of the upper layer processing system and then transmits an instruction to control a motor and a steering engine on the six-axis mechanical arm, so that the chassis of the robot is controlled to walk and the six-axis mechanical arm is controlled to move.
And the motion module is used for planning a motion path of the robot based on an SLAM map building navigation system in the upper layer processing system, driving a motor according to the planned path and combining information of the ultrasonic obstacle avoidance sensor to realize the overall motion of the robot, and navigating to the vicinity of the nearest target garbage.
Further, an ultrasonic obstacle avoidance sensor and an LED illuminating lamp are arranged at the front end of the chassis.
Further, four garbage recycling boxes are placed on the vehicle body, and a pressure sensor is arranged at the bottom of each garbage recycling box.
The intelligent garbage sorting robot is characterized by comprising the following working steps:
step one: placing the intelligent garbage sorting robot on the ground of a working area, turning on a main power supply of a power supply module arranged on a chassis, turning on a display screen on a rear plate of the vehicle, and entering a robot running mode;
step two: the running mode of the robot is a full-automatic navigation mode;
selecting a full-automatic navigation mode in a display screen, and setting the moving speed of the intelligent garbage sorting robot; the robot starts to move, whether an obstacle exists in front of the robot or not is detected through an ultrasonic obstacle avoidance sensor and a laser radar, and map information is gradually perfected; the upper layer processing system runs a classification and positioning system for garbage based on a machine vision module, starts to acquire and analyze and monitor pictures in front of the binocular camera in real time, judges whether the images obtained in real time are garbage or not through a yolo target detection algorithm, and conveys path information of an SLAM map building navigation system in the upper layer processing system to a bottom control system so as to control a robot to move and accurately avoid obstacles;
step three: when the binocular camera detects that garbage exists in front of the robot, the machine vision module integrated on the Injettson tx2 performs garbage positioning and garbage classification through image information acquired by the binocular camera, the upper-layer processing system transmits a control instruction to the bottom-layer control system, the bottom-layer control system controls a motor, so that the robot moves to the vicinity of target garbage, the upper-layer processing system plans the movement track of the six-axis mechanical arm, the six-axis mechanical arm can accurately reach the positioned garbage position, then the mechanical claw at the front end of the six-axis mechanical arm is controlled to grasp the garbage, and the robot is placed in a specified garbage classification recovery box;
step four: be provided with a plurality of rubbish classification recycling bin on the automobile body of robot, pressure sensor is all installed to the bottom of every recycling bin, when the rubbish in the recycling bin is full or reaches certain weight, pressure sensor can give bottom control system with pressure data transfer, and the robot can remove appointed rubbish and place the region this moment, reminds the user to empty the rubbish in the recycling bin, resumes the ground rubbish and cleans classification work.
The machine vision module is matched with the ultrasonic obstacle avoidance sensor and the laser radar to plan an optimal obstacle avoidance route so as to control the movement of the robot; the robot adjusts the travelling speed of the robot according to different road conditions, and the highest speed is 0.8 m/s.
Before the robot works, a garbage bag can be sleeved on four garbage recycling boxes on the vehicle body, so that dumping and treatment of garbage after the garbage bag is convenient, and the robot is kept clean.
The beneficial effects of the invention are as follows: the invention is designed into a vehicle-shaped structure and comprises a chassis and a machine body; a control board, a power panel and a rechargeable battery are arranged in the chassis; the control board comprises an STM32F405RGT6 main board and an English Jetson TX2 main board; the rechargeable battery provides power for the robot; an ultrasonic obstacle avoidance sensor and an LED illuminating lamp are arranged in front of the chassis, and the LED illuminating lamp can provide illumination under the condition of insufficient light; the obstacle avoidance sensor and the laser radar system are used for realizing the obstacle avoidance and detection functions.
The six-axis mechanical arm is arranged on the headstock through a tripod head; the wrist of the six-axis mechanical arm is provided with a binocular camera, and the front mounting end is provided with a mechanical claw; the upper processing system takes the Inlet Weida Jetson TX2 as a core, and the bottom control system takes an STM32F405RGT6 mainboard as a core.
The three modules in the invention, namely the machine vision module, the action module and the motion module in the upper layer processing system are combined and combined with the YOLO deep learning model to finish the full-automatic unmanned garbage sorting work of garbage pickup and classification in a certain area. The machine vision module is integrated on the Injetson tx2, and the machine vision module performs garbage positioning and garbage classification through image information collected by the binocular camera.
The automobile body of robot sets up four rubbish collection boxes, and every dustbin bottom all is equipped with pressure sensor, and when the rubbish in the collection box was fully filled or reached certain weight, pressure sensor can give bottom control system with pressure data transfer, then the robot can remove appointed rubbish and place the region, reminds the user to empty the rubbish in the collection box, resumes the classification work of ground rubbish cleaning.
The bottom layer control system is mainly responsible for controlling a robot chassis motor, rotating a steering engine on the six-axis mechanical arm, adjusting the pose of the six-axis mechanical arm, and detecting signals of the ultrasonic obstacle avoidance sensor and signals of the pressure sensor.
The upper processing system uses Inlet Weida Jetson TX2 as a core, runs the ROS system, and realizes the detection of the robot on garbage through a YOLOv5 deep neural network model; and acquiring image information of each frame right in front of the robot in real time by using a binocular camera, transmitting the images to a target detection model trained by a YOLOv5 network, further selecting garbage in the images by a frame, identifying the garbage, deducing the position of the garbage in the frame image from the robot, planning a moving path of the robot and a grabbing track of a six-axis mechanical arm in an ROS system after the robot identifies the garbage type, and further controlling a motion module and an action module of the robot to complete grabbing tasks.
The machine vision module is integrated on an Inlet Weida Jetson TX2, the acquisition of external image information is finished by a binocular camera arranged on the wrist of the six-axis mechanical arm, and then the detection and classification of garbage are finished by adopting an Open CV combined with a YOLOv5 deep neural network model through image processing information processing.
The action module is mainly used for controlling the mechanical arm, the six-axis mechanical arm is composed of a cradle head, six steering engines and a plurality of U-shaped frames for connection, the front end of the six-axis mechanical arm adopts a mechanical claw, a binocular camera is arranged on the wrist of the six-axis mechanical arm, and three-dimensional positioning of a target is provided for the six-axis mechanical arm, so that 'eyes' are manually operated. The six steering engines are respectively used for driving six joints of the mechanical arm. The six-axis mechanical arm structure can ensure the free movement of the mechanical arm in the three-dimensional space, and the garbage pickup operation is conveniently completed. The mechanical arm control related to various aspects such as motion control, attitude control, path planning and the like is realized by a controller. Describing a kinematic model of the mechanical arm by adopting a D-H parameter method at a mechanical arm grabbing operation part, establishing a coordinate system for each joint of the six-axis mechanical arm, and analyzing the forward and reverse movement process of the mechanical arm; and solving the pose required by the mechanical arm to grasp after knowing the spatial position of the object by adopting the calibration method of the eyes on the hands to finish garbage sorting.
The motion module is based on an SLAM map building navigation system, plans a motion path of the robot, drives a motor according to the planned path and information of the ultrasonic obstacle avoidance sensor to realize the overall motion of the robot, and navigates to the vicinity of the nearest target garbage. The chassis of the robot adopts the Mecanum wheel, the included angle between the roller axis of the Mecanum wheel and the axis of the wheel hub is 45 degrees, a plurality of small wheels are obliquely distributed on the rim of the wheel hub, and when the wheels rotate around the fixed wheel spindle, the envelope line of each small roller is a cylindrical surface, so that the wheels can roll forwards continuously, thereby realizing the omnibearing movement function of the machine body.
After the robot movement module acquires the positioning, classifying and path planning information of the target garbage through the binocular camera combined with the machine vision module, the upper computer issues a control instruction to the STM32 bottom control system of the lower computer, and then controls the motor to drive and combines the feedback of the Hall encoder to carry out the integral movement on the Mecanum wheel. The Hall encoder can convert mechanical geometric displacement of the motor into pulse signals or digital quantity, related information such as a rotating angle and rotating speed of the motor can be obtained by utilizing the pulse signals output by the detection encoder, and offset errors are reduced through a PID algorithm, so that linear walking, turning around and other motion operations of the trolley are realized, and the robot is ensured to travel according to a planned path.
The map building navigation system of the robot can complete tasks such as SLAM map building, path planning and the like, wherein the SLAM map building is completed by a laser radar and an ultrasonic obstacle avoidance sensor, surrounding obstacle information is sensed by the laser radar, the robot is completed to estimate the position of the robot by combining wheel mileage information, environment accurate map building is completed, and the robot is enabled to perform closed-loop autonomous obstacle avoidance movement according to a known environment map and a path calculated by motion planning.
The invention also provides man-machine interaction, and on the touch display screen at the rear side of the car rear plate, a user can set the moving speed of the robot and set patrol time for the robot; the display screen can play relevant videos related to garbage classification in the running process of the robot; after the robot finishes the cleaning task, a user can view the area cleaned by the robot and the video of the cleaning process through the display screen. The invention mainly uses the cleaning and classifying treatment of the community ground garbage.
The robot is in a full-automatic navigation mode, the intelligent garbage sorting robot in the mode recognizes the type of garbage belonging to the community household garbage through recognition of the community household garbage, positioning, picking and classifying operations are completed, and the full-automatic unmanned garbage sorting work of the community is realized through mobile searching of the robot.
Drawings
FIG. 1 is a schematic diagram of the structure of the present invention;
fig. 2 is a schematic view of another angle structure of the present invention.
Detailed Description
The present invention will be described in further detail by way of examples with reference to the accompanying drawings, which are illustrative of the present invention and not limited to the following examples. The binocular camera of the present embodiment will be described by taking Intel RealSense D and 455 binocular cameras as an example.
Referring to fig. 1 to 2, the intelligent garbage sorting robot comprises a motion module, an action module and a control system; the motion module comprises a chassis running gear consisting of four Mecanum wheels 1 and a motor; the chassis 2 is provided with a machine body 3; the body comprises a headstock 31, a car body 32 and a car rear plate 33; the action module is installed to locomotive 31, and automobile body 32 sets up four rubbish recycling bin 4, and the bottom of every rubbish recycling bin is provided with pressure sensor. A laser radar 5 is arranged above the vehicle rear plate 33, and a display screen 6 is arranged at the rear side of the vehicle rear plate 33; the chassis 2 is internally provided with a control system, a power module and a motor drive board. The front end of the chassis 2 is provided with an ultrasonic obstacle avoidance sensor 22 and an LED illuminating lamp 21.
The action module comprises a six-axis mechanical arm 7 and a mechanical claw 9; the six-axis mechanism arm 7 is arranged on the headstock 31 through the tripod head 10; the front end of the six-axis mechanical arm 7 is provided with a mechanical claw 9; a Intel RealSense D455 binocular camera 8 is mounted on the wrist of the six-axis mechanical arm 7;
the control system comprises a bottom layer control system and an upper layer processing system, and the bottom layer control system and the upper layer processing system are communicated in a serial port mode.
The bottom layer control system takes an STM32F405RGT6 main board as a core; the steering engine is used for controlling the rotation of the motor and each steering engine on the six-axis mechanical arm and adjusting the pose of the six-axis mechanical arm; the bottom layer control system also detects signals of the ultrasonic obstacle avoidance sensor;
the upper processing system adopts Inlet Weida Jetson TX2 as a core, and is provided with an ROS system; integrating a machine vision module on the Inlet Weida Jetson TX 2; the upper layer processing system comprises a classification and positioning system for garbage based on a machine vision module for yolo target detection, a SLAM map building navigation system based on a laser radar and ROS, and a grabbing path planning system for the six-axis mechanical arm; the three are combined and combined with a YOLO deep neural network model to realize the recognition of the robot on the garbage type so as to realize garbage sorting;
the bottom layer control system firstly receives the information of the upper layer processing system and then transmits an instruction to control a motor and a steering engine on the six-axis mechanical arm, so that the chassis of the robot is controlled to walk and the six-axis mechanical arm is controlled to move.
And the motion module is used for planning a motion path of the robot based on an SLAM map building navigation system in the upper layer processing system, driving a motor according to the planned path and combining information of the ultrasonic obstacle avoidance sensor to realize the overall motion of the robot, and navigating to the vicinity of the nearest target garbage.
The intelligent garbage sorting robot is characterized by comprising the following working steps:
step one: placing the intelligent garbage sorting robot on the ground of a working area, turning on a main power supply of a power supply module arranged on a chassis, turning on a display screen on a rear plate of the vehicle, and entering a robot running mode;
step two: the running mode of the robot is a full-automatic navigation mode;
selecting a full-automatic navigation mode in a display screen, and setting the moving speed of the intelligent garbage sorting robot; the robot starts to move, whether an obstacle exists in front of the robot or not is detected through an ultrasonic obstacle avoidance sensor and a laser radar, and map information is gradually perfected; the upper layer processing system runs a classification and positioning system for garbage based on a machine vision module, starts to acquire and analyze and monitor pictures in front of Intel RealSense D455 binocular cameras in real time, judges whether the images obtained in real time are garbage or not through a yolo target detection algorithm, and transmits path information of an SLAM mapping navigation system in the upper layer processing system to a bottom control system so as to control a robot to move and accurately avoid obstacles;
step three: when Intel RealSense D and 455 binocular cameras detect that garbage is in front, a machine vision module integrated on an Injetson tx2 performs garbage positioning and garbage classification through image information acquired by the Intel RealSense D and 455 binocular cameras, an upper-layer processing system transmits a control instruction to a bottom-layer control system, the bottom-layer control system controls a motor, so that a robot moves to the vicinity of target garbage first, a six-axis mechanical arm movement track is planned through the upper-layer processing system, the six-axis mechanical arm can accurately reach the positioned garbage position, then a mechanical claw at the front end of the six-axis mechanical arm is controlled to grasp the garbage, and the garbage is placed in a designated garbage classification recycling box;
step four: be provided with a plurality of rubbish classification recycling bin on the automobile body of robot, pressure sensor is all installed to the bottom of every recycling bin, when the rubbish in the recycling bin is full or reaches certain weight, pressure sensor can give bottom control system with pressure data transfer, and the robot can remove appointed rubbish and place the region this moment, reminds the user to empty the rubbish in the recycling bin, resumes the ground rubbish and cleans classification work.
The machine vision module is matched with the ultrasonic obstacle avoidance sensor and the laser radar to plan an optimal obstacle avoidance route so as to control the movement of the robot; the robot adjusts the travelling speed of the robot according to different road conditions, and the highest speed is 0.8 m/s.
Before the robot works, a garbage bag can be sleeved on four garbage recycling boxes on the vehicle body, so that dumping and treatment of garbage after the garbage bag is convenient, and the robot is kept clean.
Claims (5)
1. Intelligent garbage sorting robot, its characterized in that: the system comprises a motion module, an action module and a control system; the motion module comprises a chassis running gear consisting of four Mecanum wheels and a motor; the chassis is provided with a machine body; the machine body comprises a machine head, a machine body and a machine back plate; the vehicle head is provided with an action module, the vehicle body is provided with a plurality of garbage recycling boxes, a laser radar is arranged above a vehicle rear plate, and a display screen is arranged at the rear side of the vehicle rear plate; the chassis is internally provided with a control system, a power module and a motor driving plate;
the action module comprises a six-axis mechanical arm and a mechanical claw; the six-axis mechanism arm is arranged on the headstock through a tripod head; the front end of the six-axis mechanical arm is provided with a mechanical claw; the wrist of the six-axis mechanical arm is provided with a binocular camera;
the control system comprises a bottom layer control system and an upper layer processing system, and the bottom layer control system and the upper layer processing system are communicated in a serial port mode;
the bottom layer control system takes an STM32F405RGT6 mainboard as a core; the steering engine is used for controlling the rotation of each steering engine on the motor and the six-axis mechanical arm; the bottom layer control system also detects signals of the ultrasonic obstacle avoidance sensor;
the upper processing system takes Indellover Jetson TX2 as a core, and is provided with an ROS system; integrating a machine vision module on the Inlet Weida Jetson TX 2; the upper layer processing system comprises a classification and positioning system for garbage based on a machine vision module for yolo target detection, a SLAM map building navigation system based on a laser radar and ROS, and a grabbing path planning system for the six-axis mechanical arm; the three are combined to realize the recognition of the robot to the garbage type to realize garbage sorting;
the bottom layer control system firstly receives the information of the upper layer processing system and then transmits an instruction to control a motor and a steering engine on the six-axis mechanical arm, so that the chassis of the robot is controlled to walk and the six-axis mechanical arm is controlled to move;
the motion module is used for planning a motion path of the robot based on the SLAM mapping navigation system in the upper-layer processing system, and driving a motor to realize the overall motion of the robot according to the planned path and the information of the ultrasonic obstacle avoidance sensor so as to navigate to the vicinity of the nearest target garbage.
2. The intelligent garbage sorting robot of claim 1, wherein the front end of the chassis is provided with an ultrasonic obstacle avoidance sensor and an LED illuminating lamp.
3. The intelligent garbage sorting robot of claim 1, wherein four garbage collection boxes are placed on the vehicle body, and a pressure sensor is arranged at the bottom of each garbage collection box.
4. The intelligent garbage sorting robot is characterized by comprising the following working steps:
step one: placing the intelligent garbage sorting robot on the ground of a working area, turning on a main power supply of a power supply module arranged on a chassis, turning on a display screen on a rear plate of the vehicle, and entering a robot running mode;
step two: the running mode of the robot is a full-automatic navigation mode;
selecting a full-automatic navigation mode in a display screen, and setting the moving speed of the intelligent garbage sorting robot; the robot starts to move, whether an obstacle exists in front of the robot or not is detected through an ultrasonic obstacle avoidance sensor and a laser radar, and map information is gradually perfected; the upper layer processing system runs a classification and positioning system of garbage based on a machine vision module for yolo target detection, starts to acquire and analyze and monitor pictures in front of the binocular camera in real time, judges whether the images obtained in real time are garbage or not through a yolo target detection algorithm, and conveys path information of an SLAM map building navigation system in the upper layer processing system to a bottom control system so as to control a robot to move and accurately avoid obstacles;
step three: when the binocular camera detects that garbage exists in front of the robot, the machine vision module integrated on the Injettson tx2 performs garbage positioning and garbage classification through image information acquired by the binocular camera, the upper-layer processing system transmits a control instruction to the bottom-layer control system, the bottom-layer control system controls a motor, so that the robot moves to the vicinity of target garbage, the upper-layer processing system plans the movement track of the six-axis mechanical arm, the six-axis mechanical arm can accurately reach the positioned garbage position, and then the mechanical claw at the front end of the six-axis mechanical arm is controlled to grasp the garbage and is placed in a designated garbage recycling bin;
step four: be provided with a plurality of rubbish recycling bin on the automobile body of robot, pressure sensor is all installed to the bottom of every rubbish recycling bin, and when rubbish in the rubbish recycling bin is full or reaches certain weight, pressure sensor can give bottom control system with pressure data transfer, and the robot can remove appointed rubbish and place the region this moment, reminds the user to empty rubbish in the rubbish recycling bin, resumes the ground rubbish and cleans classification work.
5. The intelligent garbage sorting robot of claim 4, wherein the machine vision module is matched with an ultrasonic obstacle avoidance sensor and a laser radar to plan an optimal obstacle avoidance route so as to control the movement of the robot; the robot adjusts the travelling speed of the robot according to different road conditions, and the highest speed is 0.8 m/s.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310984520.XA CN116985090A (en) | 2023-08-04 | 2023-08-04 | Intelligent garbage sorting robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310984520.XA CN116985090A (en) | 2023-08-04 | 2023-08-04 | Intelligent garbage sorting robot |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116985090A true CN116985090A (en) | 2023-11-03 |
Family
ID=88531798
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310984520.XA Pending CN116985090A (en) | 2023-08-04 | 2023-08-04 | Intelligent garbage sorting robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116985090A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117427892A (en) * | 2023-12-21 | 2024-01-23 | 福州城投德正数字科技有限公司 | Machine vision garbage classification recycling system based on edge collaborative computing |
| CN117921622A (en) * | 2024-03-25 | 2024-04-26 | 宁波昂霖智能装备有限公司 | Control method of robot for picking up garbage and robot for picking up garbage |
-
2023
- 2023-08-04 CN CN202310984520.XA patent/CN116985090A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117427892A (en) * | 2023-12-21 | 2024-01-23 | 福州城投德正数字科技有限公司 | Machine vision garbage classification recycling system based on edge collaborative computing |
| CN117427892B (en) * | 2023-12-21 | 2024-04-12 | 福州城投德正数字科技有限公司 | Machine vision garbage classification recycling system based on edge collaborative computing |
| CN117921622A (en) * | 2024-03-25 | 2024-04-26 | 宁波昂霖智能装备有限公司 | Control method of robot for picking up garbage and robot for picking up garbage |
| CN117921622B (en) * | 2024-03-25 | 2024-06-04 | 宁波昂霖智能装备有限公司 | Control method of robot for picking up garbage and robot for picking up garbage |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116985090A (en) | Intelligent garbage sorting robot | |
| US7066291B2 (en) | Robot system | |
| US20230247015A1 (en) | Pixelwise Filterable Depth Maps for Robots | |
| CN106863259B (en) | Wheeled many manipulators intelligence ball robot | |
| CN108852184A (en) | A kind of non-blind area sweeping robot and its cleaning control method based on deep learning algorithm | |
| US20110046784A1 (en) | Asymmetric stereo vision system | |
| WO2020114019A1 (en) | Sanitation intelligent cleaning and sweeping operation robot control system and cleaning machinery | |
| CN118204972A (en) | Method and apparatus for autonomous object learning by remote operator triggered robots | |
| CN109018056A (en) | The sufficient four-wheel of one kind two can be changed walking mechanism multifunctional bionic robot system | |
| US11945106B2 (en) | Shared dense network with robot task-specific heads | |
| CN111844042A (en) | Rubbish letter sorting robot based on vision | |
| CN113821040A (en) | Robot with depth vision camera and laser radar integrated navigation | |
| CN111823228A (en) | Indoor following robot system and operation method | |
| CN213796500U (en) | Leg and arm cooperation robot | |
| CN212522923U (en) | Ball picking robot system | |
| CN107643756A (en) | A kind of unmanned distribution trolley and its mode of progression | |
| CN211906081U (en) | Unmanned small-sized sweeping machine control system based on path tracking | |
| CN211590199U (en) | Pipeline robot based on vision SLAM | |
| CN111367273A (en) | Unmanned small-sized sweeping machine control system based on path tracking and control method thereof | |
| CN110640759A (en) | Full-automatic garbage picking robot | |
| EP3842888A1 (en) | Pixelwise filterable depth maps for robots | |
| CN115061469A (en) | Variable-wheelbase composite motion platform, intelligent unmanned system and motion control method thereof | |
| CN113835436A (en) | Articulated cleaning robot and cleaning system thereof | |
| CN112589766A (en) | Automatic patrol garbage recognition and sorting robot for roads | |
| CN221000796U (en) | Road sweeper based on binocular vision |
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 |