CN111823212A - A garbage bottle cleaning robot and control method - Google Patents

Abstract

The invention discloses a garbage bottle cleaning and picking robot and a control method thereof, wherein the garbage bottle cleaning and picking robot comprises a bottom plate, a middle layer clapboard, a shell and a mechanical arm, and further comprises a micro host, a development board, a binocular vision camera and a laser radar. The robot generates a map through equipment such as a laser radar module and a GPS module, automatically patrols and examines and avoids obstacles, and can be remotely operated and acquire various data through a remote controller. The robot provided by the invention can be used for automatically cleaning and picking up the garbage bottles, and has the advantages that: the automatic cleaning and sorting of the garbage bottles are realized, the recycling difficulty of the garbage bottles is reduced, the urban environment is beautified, and the labor force and the cleaning cost are saved.

Description

A garbage bottle cleaning robot and control method

technical field

The invention relates to the technical field of intelligent robots, in particular to a garbage bottle cleaning robot and a control method.

Background technique

With the increasingly prominent phenomenon of China's aging society, domestic labor costs continue to rise, and the demographic dividend is gradually disappearing. The current method of manual maintenance and cleaning has problems such as artificial dead ends, low cleaning efficiency, and untimely cleaning. Moreover, the cleaners are not only very hard, but also The labor is mechanically repetitive and labor-intensive, and the labor environment leads to a high incidence of chronic respiratory diseases, and even complex and changeable traffic and road conditions will put their lives in danger.

However, the existing sweeping robots still have many drawbacks: 1. The sweeping robot generally adopts a rotating brush structure, which makes internal cleaning and maintenance difficult; 2. Most sweeping robots have small application scenarios and are only suitable for indoor dry and flat ground; 3. The scope of application is also small. It is only suitable for cleaning small garbage such as dust and debris. It is powerless to face slightly larger garbage such as plastic bottles. Garbage bottles are recyclable garbage. Placing plastic or glass bottles together with other garbage will increase the difficulty of recycling, reduce the recycling rate of recyclable materials, and increase pollution.

SUMMARY OF THE INVENTION

In view of this, the present invention provides a garbage bottle cleaning robot.

The invention provides a garbage bottle cleaning robot, comprising: a bottom plate, a middle layer partition, a casing, a mechanical arm and a micro-host; the lower surface of the bottom plate is provided with a driving wheel, a stepping motor and a universal driven wheel; the upper surface of the bottom plate is provided with a driving wheel, a stepping motor and a universal driven wheel The micro-host, the development board and the stepper motor driver, the stepper motor driver is used to drive the stepper motor, and then drives the driving wheel to control the movement of the robot, the micro-host is electrically connected to the development board, and is used as a host computer to control as a subordinate computer. The development board of the machine;

The intermediate layer partition is fixedly connected to the bottom plate through a connecting column, and the mechanical arm is fixedly connected to one end of the upper surface of the intermediate layer partition;

The outer shell is fixed on the bottom plate and wraps the middle layer partition, and one end of the upper surface of the outer shell is provided with a reserved opening, so that the robotic arm can extend from the reserved opening and put the collected garbage bottles into the upper surface of the outer shell. In the garbage basket fixed in the middle, the lidar is fixed on the other end of the upper surface;

The end of the robotic arm is equipped with a binocular vision camera, which together with the robotic arm constitutes a hand-eye system for picking up garbage bottles;

The micro-host includes a neural network chip, and the neural network chip is used for judging whether the object to be cleaned is a garbage bottle according to the feedback information obtained by the lidar and the binocular vision camera.

The invention designs a garbage bottle cleaning robot, learns through a neural network chip, judges whether the object to be cleaned is a garbage bottle according to the feedback information obtained by the laser radar and the binocular vision camera, and performs efficient cleaning. Picking up and processing can increase the recovery rate of recyclable materials, reduce the difficulty of daily garbage cleaning, and can also have a better cleaning effect than traditional garbage cleaning robots in special environments such as environments with many tourists.

Preferably, the development board is an Arduino Uno development board.

Preferably, the number of the connecting columns is 6, so that the overall structure is more stable.

Preferably, the driving wheel, the universal driven wheel, the stepping motor and the stepping motor driver are all two.

Preferably, a step-down module, a 4G communication module, a GPS module and a battery are also provided on the bottom plate;

The micro-host is electrically connected with the development board, lidar, robotic arm, binocular vision camera, 4G communication module and GPS module, and is used to communicate as a host computer and control all components electrically connected to the micro-host;

Preferably, the binocular vision camera and the robotic arm are connected to the host computer, the camera is used to identify the garbage bottles, and the robotic arm is used for grabbing. The angle of the camera is fixed on the gripper of the manipulator, which is convenient to control the shooting angle of the camera by judging the posture of the manipulator.

Optionally, the lidar is connected to the upper computer, and performs auxiliary judgment on the size, shape and material of the garbage bottle.

A 4G antenna is also fixed on the casing, and is electrically connected with the 4G communication module.

Optionally, the robot is installed with other communication modules such as Bluetooth modules for remote communication.

Preferably, the stepper motor driver is electrically connected to the development board and the stepper motor at the same time, and receives pulse information of the development board, so as to drive the stepper motor according to the pulse information, and the stepper motor drives the driving wheel to move.

Preferably, the battery is electrically connected to the stepper motor driver, the micro-host, the lidar and the robotic arm through the step-down module, and supplies power.

Preferably, the garbage bottle cleaning robot further includes a WIFI module,

The WIFI module is electrically connected with the micro-host for remote communication.

Optionally, it is judged whether the WIFI module is connected to the network, if connected, the WIFI module is used for remote communication, and if not, the 4G communication module is used for remote communication.

Optionally, the robot has two stepper motors, and an acceleration sensor is installed near each stepper motor and is electrically connected to the development board for correcting the speed of the robot.

The end of the robotic arm is also equipped with a laser ranging sensor and a temperature and humidity sensor, and is electrically connected to the development board for correcting the robot's accuracy.

The present invention also provides a control method for a garbage bottle cleaning robot, which is designed based on the robot system framework ROS to control any of the above garbage bottle cleaning robots. The method includes:

S1. The micro-host of the robot obtains the map of the working area through the lidar;

S2, the micro-host automatically plans a route inspection on the working area;

S3. The neural network chip controls the lidar and the binocular vision camera to identify garbage bottles during the inspection process;

S4, the laser radar combined with the GPS module to measure the coordinates of the garbage bottle relative to the robot on the map;

S5, the robot travels to the location of the garbage bottle;

S6, the binocular vision camera measures the relative position information of the garbage bottle and the mechanical arm;

S7. The micro-host controls the robotic arm to pick up the garbage bottle and put it into the garbage basket, and continue to perform inspection.

Preferably, the map of the working area is constructed by SLAM.

Optionally, the map of the working area can also be acquired through remote communication means such as a WIFI module.

Preferably, the control method for the garbage bottle cleaning robot further includes:

The micro-host communicates with the remote controller through the WIFI module or 4G module electrically connected to the micro-host, and the communication includes: receiving a remote control signal sent by the remote controller, or sending information on obstacles in the surrounding environment, robot positioning information and robot field of view information to the remote controller.

Preferably, the step S3 includes:

The neural network chip constructs a neural network for training according to the feedback information of the lidar and the binocular vision camera, and recognizes the shape and material of the garbage bottle.

Optionally, the lidar and binocular vision cameras respectively obtain target information to construct corresponding training sets and verification sets, and construct a neural network for training, identify the shape of the garbage bottle through artificial intelligence image recognition technology, and determine whether the target is a garbage bottle. Neural network training can also be performed together with lidar and binocular vision cameras to further improve the accuracy of judging the material of garbage bottles, and achieve the effect of accurately picking up plastic or glass bottles.

The present invention also provides a control system for a garbage bottle cleaning robot, which is designed based on the robot system framework ROS to control any of the above garbage bottle cleaning robots, including:

The map service node is used to obtain the map of the working area through the lidar and GPS module;

A path planning node, used for automatically planning a route inspection on the work area through the micro-host;

A neural network node, used to control the lidar and binocular vision camera to identify garbage bottles during the inspection process through the neural network chip;

The GPS node is used to measure the coordinates of the garbage bottle relative to the robot on the map through the GPS module and the lidar;

a motor control node for driving to the position of the garbage bottle;

a camera node, used to measure the relative position information of the garbage bottle and the robotic arm through the binocular vision camera;

The robotic arm node is used to control the robotic arm to pick up the garbage bottle and put it into the garbage basket through the micro-host, and continue the inspection.

Preferably, the system further includes:

The lidar node is used to publish the obstacle information scanned by the lidar to the path planning node, or publish the scanned garbage bottle information to the neural network node.

The robot attitude publishing node is used to publish the coordinate transformation of each sensor and component of the robot to each node, such as sending the value of the laser ranging sensor to the micro-host for processing.

Preferably, the system further includes:

A communication node for communicating with a remote controller through the micro-host through the WIFI module or 4G module electrically connected to the micro-host, and the communication includes: receiving a remote control signal sent by the remote controller, or sending Surrounding environment obstacle information, robot positioning information and robot vision information are sent to the remote controller.

Preferably, the remote controller can be an industrial robot controller or a mobile phone APP, which can communicate with the communication node of the robot through the WIFI module or 4G module connected to the micro-host, and can manually control the robot to drive and receive the robot lidar, The information released by the GPS module and binocular vision camera module can remotely control the robot both indoors and outdoors.

The present invention also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program At the same time, some or all of the steps of the control method of any garbage bottle cleaning robot described in the above method embodiments are realized.

The present invention further provides a computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, any one of the garbage bottles described in the foregoing method embodiments is implemented. Part or all of the steps of the control method of the pick-up robot.

Description of drawings

The accompanying drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present application. The schematic embodiments and descriptions of the present application are used to explain the present invention and do not constitute an improper limitation of the present invention. In the attached image:

1 is a schematic structural diagram of a garbage bottle cleaning robot according to an embodiment of the present invention;

2 is a flowchart of a control method for a garbage bottle cleaning robot in an embodiment of the present invention;

FIG. 3 is a schematic diagram of a rightward internal structure of a robot in an embodiment of the present invention;

4 is a schematic diagram of the left-hand internal structure of a robot in an embodiment of the present invention;

FIG. 5 is a schematic diagram of actual communication of each node in an embodiment of the present invention.

In the picture:

1. Bottom plate 2, driving wheel 3, stepping motor 4, driven wheel 5, micro host 6, development board 7, stepping motor driver 8, step-down module 9, 4G communication module 10, GPS module 11, battery 12, middle Layer partition 13, connecting column 14, robotic arm 15, housing 16, trash can 17, 4G antenna 18, lidar 19, binocular vision camera.

Detailed ways

The principles and features of the present invention will be described below with reference to the accompanying drawings. The examples are only used to explain the present invention, but not to limit the scope of the present invention.

An embodiment of the present invention provides a garbage bottle cleaning robot, as shown in FIG. 1 , comprising: a bottom plate 1 , a middle layer partition 12 , a casing 15 , a mechanical arm 14 and a micro host 5 , and a driving wheel is provided on the lower surface of the bottom plate 1 2. The stepping motor 3 and the universal driven wheel 4, the upper surface of the base plate 1 is provided with the micro-host 5, the development board 6 and the stepping motor driver 7, and the stepping motor driver 7 is used to drive the stepping motor 3, Then drive the driving wheel 2 to control the movement of the robot, and the micro-host 5 is electrically connected with the development board 6, as the upper computer controls the development board 6 as the lower computer;

The intermediate layer partition plate 12 is fixedly connected to the bottom plate 1 through the connecting column 13, and the mechanical arm 14 is fixedly connected to one end of the upper surface of the intermediate layer partition plate 12;

The outer shell 15 is fixed on the bottom plate 1 and wraps the intermediate layer partition 12. One end of the upper surface of the outer shell 15 is provided with a reserved opening, so that the robotic arm 14 can extend from the reserved opening and put the collected garbage bottles into into the trash can 16 fixed in the middle of the upper surface of the casing 15, and the lidar 18 is fixed at the other end of the upper surface;

The end of the robotic arm 14 is equipped with a binocular vision camera 19, which together with the robotic arm 14 constitutes a hand-eye system for picking up garbage bottles;

The micro host 5 includes a neural network chip, and the neural network chip is used to judge whether the object to be cleaned is a garbage bottle according to the feedback information obtained by the lidar 18 and the binocular vision camera 19 .

Preferably, the bottom plate 1 is also provided with a step-down module 8, a 4G communication module 9, a GPS module 10 and a battery 11, and the interior of the robot is shown in Figures 3 and 4;

The micro-host 5 is electrically connected to the development board 6 , the lidar 18 , the robotic arm 14 , the binocular vision camera 19 , the 4G communication module 9 and the GPS module 10 , and is used to communicate as a host computer and control all the components that are electrically connected to the micro-host 5 ;

A 4G antenna 17 is also fixed on the casing 15 and is electrically connected with the 4G communication module 9 .

Preferably, the stepper motor driver 7 is electrically connected to the development board 6 and the stepper motor 3 at the same time, and receives the pulse information of the development board 6, so as to drive the stepper motor 3 according to the pulse information, and the stepper motor 3 drives the active Wheel 2 to move.

Preferably, the battery 11 is electrically connected to the stepper motor driver 7 , the micro-host 5 , the lidar 18 and the robotic arm 14 through the step-down module 8 , and supplies power.

Preferably, the garbage bottle cleaning robot further includes a WIFI module,

The WIFI module is electrically connected with the micro host 5 for remote communication.

An embodiment of the present invention also provides a control method for a garbage bottle cleaning robot, which is designed based on the robot system framework ROS to control any of the above garbage bottle cleaning robots, as shown in FIG. 2 , the method includes:

S1. The micro-host of the robot obtains a map of the working area through the lidar;

S2, the micro-host automatically plans a route inspection on the working area;

S3, the neural network chip controls the lidar and the binocular vision camera to identify garbage bottles during the inspection process;

S4, the lidar combined with the GPS module to measure the coordinates of the garbage bottle relative to the robot on the map;

S5, the robot travels to the location of the garbage bottle;

S6, the binocular vision camera measures the relative position information of the garbage bottle and the robotic arm;

S7. The micro-host controls the robotic arm to pick up the garbage bottle and put it into the garbage basket, and continue to perform inspection.

Preferably, the control method for the garbage bottle cleaning robot further includes:

The micro-host communicates with the remote controller through the WIFI module or 4G module electrically connected to the micro-host, and the communication includes: receiving a remote control signal sent by the remote controller, or sending information on obstacles in the surrounding environment, robot positioning information and robot field of view information to the remote controller.

Preferably, the step S3 includes:

The neural network chip constructs a neural network for training according to the feedback information of the lidar and the binocular vision camera, and recognizes the shape and material of the garbage bottle.

Optionally, the lidar and binocular vision cameras respectively construct corresponding training sets and verification sets through feedback information, and construct a neural network for training, identify the shape of the garbage bottle through artificial intelligence image recognition technology, and determine whether the target is a garbage bottle. Neural network training can also be performed together with lidar and binocular vision cameras to further improve the accuracy of judging the material of garbage bottles, and achieve the effect of accurately picking up plastic or glass bottles.

The cellular neural network or convolutional neural network (Cellular/ConvolutionalNeural Networks, CNN) chip involved in the above-mentioned embodiment can also be replaced with other machine vision recognition chips in actual implementation, for example, based on shallow learning (Shallow Learning) based on deep learning algorithms such as AutoEncoder, Sparse Coding, Restricted Boltzmann Machine (RBM), and Deep Belief Networks. Machine vision recognition chip.

An embodiment of the present invention also provides a control system for a garbage bottle cleaning robot, which is designed based on the robot system framework ROS to control any of the above garbage bottle cleaning robots, including:

a map service node, used to obtain a map of the work area through the lidar;

A path planning node, used for automatically planning a route inspection on the work area through the micro-host;

A neural network node, used to control the lidar and binocular vision camera to identify garbage bottles during the inspection process through the neural network chip;

The GPS node is used to measure the coordinates of the garbage bottle relative to the robot on the map through the GPS module and the lidar;

a motor control node for driving to the position of the garbage bottle;

a camera node, used to measure the relative position information of the garbage bottle and the robotic arm through the binocular vision camera;

The robotic arm node is used to control the robotic arm to pick up the garbage bottle and put it into the garbage basket through the micro-host, and continue the inspection.

In a specific embodiment, each node is designed based on the robot system framework ROS, and a schematic diagram of specific node communication is shown in Figure 5:

The motor control node processes the speed command and outputs a pulse signal to the lower computer according to the speed command. The node will subscribe to the cmd_vel topic published by the path planning node or the remote control node. The specific message format of the topic is mainly:

Vector3 linear

Vector3 angular

Vector3 is defined in the ROS system framework as:

float32x

float32 y

float32z

This topic covers the linear and angular velocities of the robot in the three directions of x, y, and z in the space coordinate system. After receiving the topic, the motor control node calculates the speed into the respective rotation speeds of the two driving wheels, and then further converts it into a pulse frequency to control the pulse signal of the pin of the lower computer, thereby driving the motor.

In a specific embodiment, the map service node publishes the map obtained by SLAM as a map topic, and the main message format of the map topic is as follows:

MapMetaData info

int8[]data

This topic contains the metadata of the map, the probability of occupancy.

In a specific embodiment, the GPS node publishes the odom topic, and the odom topic message format is mainly:

geometry_msgs/PoseWithCovariance pose

This topic contains the location information of the robot, and the GPS node publishes the odom topic after calibrating and converting the latitude and longitude coordinates provided by GPS on the map obtained by SLAM.

In a specific embodiment, the camera node publishes the captured image information through the compressed_image topic, identifies plastic bottles through a trained network, monitors whether there is plastic bottle garbage in the field of view in real time, and uses binocular parallax if a target is detected. Measure the distance of the target, calculate the coordinates of the target on the map obtained by SLAM, and issue a move_goal action request. After receiving the feedback information of the completion of the request, further measure the relative position of the target and the robot, and issue a grip_goal action request. When no target is detected, randomly generate a reachable target point and send a move_goal request.

The main message format of compressed_image is:

string format

uint8[]data

This topic contains the format of the image data, the buffered data of the image.

The main message format of move_goal is:

float64x

float64 y

float64 z

The action message indicates the location coordinates of the target point on the SLAM map.

The message format of grip_goal is:

float64x

float64 y

float64 z

float64 w

Contains the coordinates of the target relative to the robot and the pose of the target.

In a specific embodiment, after receiving the grip_goal action request, the robot arm node learns the target posture of the robot arm through inverse kinematics, controls the movement of the robot arm, grabs the target, puts it in the trash, and then feeds back the completion information to the camera node.

In a specific embodiment, the path planning node is a path planning node provided in ROS, including global planning and local planning nodes. The path planning node subscribes to tf, odom, scan, and map topics. The overall path to the target point is planned by the global planning, and the driving speed of each short distance is planned by the local planning to achieve real-time obstacle avoidance. The speed is published through the cmd_vel topic. After reaching the vicinity of the target point, the completion information is fed back to the camera node. . The path planning node also updates the SLAM map.

Preferably, the system further includes:

The lidar node is used to publish the obstacle information scanned by the lidar to the path planning node, or publish the scanned garbage bottle information to the neural network node.

The robot attitude publishing node is used to publish the coordinate transformation of each sensor and component of the robot to each node, such as sending the value of the laser ranging sensor to the micro-host for processing.

In a specific embodiment, the lidar node is responsible for publishing the obstacle information scanned by the radar to the path planning node, and publishing the scan topic. The message format of the topic is mainly:

Header header

float32 angel_min

float32 angle_max

float32 angle_increment

float32 time_increment

float32 scan_time

float32 range_min

float32 range_max

float32[]ranges

float32[]intensities

This topic contains the sequence of increasing id's in the scan order, the time stamp of the laser data, the name of the scan data, the angle to start the scan, the angle to end the scan, the angle to increase for each scan, the measurement interval, the scan interval, and the ranging. The minimum value of , the maximum value of ranging, the obstacle distance of a week, and the intensity of light. These topic messages will first be used in SLAM to build a map of the robot's surrounding environment. SLAM has a function package in ROS that can be called directly. The map is represented in the form of a grid map for global planning in navigation. This topic is also subscribed by the route planning node, which is used for local planning in navigation and updating the map.

In a specific embodiment, the robot gesture publishing node publishes a tf topic, and the message format of the topic is mainly:

Transform tf::Transform

This topic includes coordinate transformation data of robot parts and sensors.

Preferably, the system further includes:

A communication node for communicating with a remote controller through the micro-host through the WIFI module or 4G module electrically connected to the micro-host, and the communication includes: receiving a remote control signal sent by the remote controller, or sending Surrounding environment obstacle information, robot positioning information and robot vision information are sent to the remote controller.

Preferably, the remote controller can be an industrial robot controller or a mobile phone APP, which can communicate with the communication node of the robot through the WIFI module or 4G module connected to the micro-host, and can manually control the robot to drive and receive the robot lidar, The information released by the GPS module and binocular vision camera module can remotely control the robot both indoors and outdoors.

The present invention also provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program At the same time, some or all of the steps of the control method of any garbage bottle cleaning robot described in the above method embodiments are realized.

The present invention further provides a computer-readable storage medium storing a computer program, characterized in that, when the computer program is executed by a processor, any one of the garbage bottles described in the foregoing method embodiments is implemented. Part or all of the steps of the control method of the pick-up robot.

All the above-mentioned optional technical solutions can be combined arbitrarily to form optional embodiments of the present disclosure, which will not be repeated here.

Those skilled in the art can realize that the method steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two, in order to clearly illustrate the interoperability of hardware and software Alternatively, the components and steps of each example have been described generally in terms of functionality in the foregoing description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may implement the described functionality using different methods for each particular application, but such implementations should not be considered beyond the scope of the present invention.

The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of various equivalent modifications or modifications within the technical scope disclosed by the present invention. Replacement, these modifications or replacements should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims (10)

1. The utility model provides a clear robot of picking up of garbage bottle which characterized in that includes: the robot comprises a bottom plate (1), a middle-layer partition plate (12), a shell (15), a mechanical arm (14) and a micro host (5), wherein a driving wheel (2), a stepping motor (3) and a universal driven wheel (4) are arranged on the lower surface of the bottom plate (1), the micro host (5), a development board (6) and a stepping motor driver (7) are arranged on the upper surface of the bottom plate (1), the stepping motor driver (7) is used for driving the stepping motor (3) to further drive the driving wheel (2) to control the robot to move, and the micro host (5) is electrically connected with the development board (6) and used as an upper computer to control the development board (6) as a lower computer;

the middle layer clapboard (12) is fixedly connected to the bottom plate (1) through a connecting column (13), and the mechanical arm (14) is fixedly connected to one end of the upper surface of the middle layer clapboard (12);

the shell (15) is fixed on the bottom plate (1) and wraps the middle layer partition plate (12), a reserved opening is formed in one end of the upper surface of the shell (15), so that the mechanical arm (14) can extend out of the reserved opening to put the cleaned garbage bottle into a garbage basket (16) fixed in the middle of the upper surface of the shell (15), and a laser radar (18) is fixed to the other end of the upper surface;

a binocular vision camera (19) is mounted at the tail end of the mechanical arm (14), and the mechanical arm (14) and the binocular vision camera form a hand-eye system which is used for cleaning the garbage bottles;

the micro host (5) comprises a neural network chip, and the neural network chip is used for judging whether the target to be picked up is a garbage bottle or not according to feedback information acquired by the laser radar (18) and the binocular vision camera (19).

2. The trash bottle picking robot of claim 1,

the bottom plate (1) is also provided with a voltage reduction module (8), a 4G communication module (9), a GPS module (10) and a battery (11);

the micro host (5) is electrically connected with the development board (6), the laser radar (18), the mechanical arm (14), the binocular vision camera (19), the 4G communication module (9) and the GPS module (10) and used for being used as a host computer for communication and controlling all parts electrically connected with the micro host (5);

and a 4G antenna (17) is also fixed on the shell (15) and is electrically connected with the 4G communication module (9).

3. The trash bottle picking robot of claim 2,

step motor driver (7) simultaneously with develop board (6) with step motor (3) electricity is connected, and the receipt the pulse information of development board (6), thereby according to pulse information drive step motor (3), and by step motor (3) drive action wheel (2) move.

4. The trash bottle picking robot of claim 3,

the battery (11) is electrically connected with the stepping motor driver (7), the micro host (5), the laser radar (18) and the mechanical arm (14) through the voltage reduction module (8) and supplies power.

5. The trash bottle picking robot of claim 4, further comprising a WIFI module,

the WIFI module is electrically connected with the micro host (5) and used for remote communication.

6. A control method of a clear garbage bottle picking robot, designed based on a robot system framework ROS, for controlling the clear garbage bottle picking robot according to any one of claims 1-5, comprising:

s1, the micro host of the robot obtains a map of a working area through a laser radar;

s2, automatically planning a route for inspection on the working area by the micro host;

s3, the neural network chip controls the laser radar and the binocular vision camera to identify the trash bottle in the inspection process;

s4, the laser radar is combined with the GPS module to measure and calculate the coordinates of the garbage bottles on a map relative to the robot;

s5, the robot drives to the position of the garbage bottle;

s6, the binocular vision camera measures and calculates the relative position information of the garbage bottle and the mechanical arm;

and S7, the micro host controls the mechanical arm to pick up the trash bottle and place the trash bottle into a trash basket, and the inspection is continued.

7. The method for controlling the trash bottle picking robot according to claim 6, further comprising:

the micro host communicates with the remote controller through a WIFI module or a 4G module electrically connected with the micro host, and the communication comprises: and receiving a remote control signal sent by the remote controller, or sending surrounding environment obstacle information, robot positioning information and robot vision information to the remote controller.

8. The method for controlling a trash bottle picking robot according to claim 6, wherein the step S3 includes:

and the neural network chip constructs a neural network for training according to the feedback information of the laser radar and the binocular vision camera, and identifies the shape and the material of the garbage bottle.

9. A control system of a clear garbage bottle picking robot, designed based on a robot system framework ROS, for controlling the clear garbage bottle picking robot according to any one of claims 1-5, comprising:

the map service node is used for obtaining a map of a working area through the laser radar;

the path planning node is used for automatically planning a route to patrol on a working area through the micro host;

the neural network node is used for controlling the laser radar and the binocular vision camera to identify the garbage bottle in the routing inspection process through the neural network chip;

the GPS node is used for measuring and calculating the coordinates of the garbage bottle on a map relative to the robot through the GPS module and the laser radar;

the motor control node is used for driving to the position of the garbage bottle;

the camera node is used for measuring and calculating the relative position information of the garbage bottle and the mechanical arm through the binocular vision camera;

and the mechanical arm node is used for controlling the mechanical arm to pick up the garbage bottle and put the garbage bottle into the garbage basket through the micro host, and continuously performing routing inspection.

10. The control system of the trash can picking robot of claim 9, further comprising:

the communication node is used for communicating with a remote controller through the WIFI module or the 4G module which is electrically connected with the micro-host through the micro-host, and the communication node comprises: and receiving a remote control signal sent by the remote controller, or sending surrounding environment obstacle information, robot positioning information and robot vision information to the remote controller.

Images