Intelligent stair cleaning robot based on binocular vision

Abstract

The intelligent stair cleaning robot based on binocular vision comprises a double-rocker-arm crawler chassis, a binocular vision camera module, a cleaning device and a control system, a binocular vision camera is fixed right in front of the double-rocker-arm crawler chassis, and the cleaning device is fixed right above the double-rocker-arm crawler chassis. The robot can automatically sense and plan the path and execute cleaning, solves the problems that existing equipment is weak in environment perception, poor in path planning and the like, improves the stair cleaning efficiency and quality, reduces the labor intensity of workers, is suitable for cleaning and maintenance of various building stairs, and achieves intelligence and high efficiency of stair cleaning.

Description

Technical Field

[0001] The present invention relates to the technical field of robots, and particularly to an intelligent stair cleaning robot based on binocular vision. Background Art

[0002] With the acceleration of the urbanization process, the cleaning of stairs in buildings has become a heavy task. The traditional manual cleaning method is inefficient, labor-intensive, and has safety hazards in some special environments (such as high-rise buildings, dangerous areas, etc.). Most of the existing cleaning equipment is designed for flat ground and is difficult to adapt to the special terrain of stairs. Although there are also some cleaning equipment with climbing functions on the market, there are many deficiencies in aspects such as environmental perception, path planning, and cleaning effect, and they cannot meet the requirements of efficient and intelligent stair cleaning. For example, the existing equipment may not be able to accurately identify the structure of the stairs, resulting in omissions or collisions during the cleaning process; the path planning is not intelligent enough and cannot dynamically adjust the cleaning path according to the actual situation, thus reducing the cleaning efficiency. Therefore, there is an urgent need for a robot that can accurately identify the stair environment, intelligently plan the path, and clean efficiently. Summary of the Invention

[0003] The purpose of the present invention is to provide an intelligent stair cleaning robot based on binocular vision, which solves the problems of existing stair cleaning equipment in aspects such as environmental perception, path planning, climbing stability, and cleaning effect through innovative hardware structure design and advanced intelligent control algorithms, realizes the automation, intelligence, and high efficiency of stair cleaning, reduces the manual labor intensity, and improves the cleaning efficiency and quality.

[0004] To achieve the above purpose, an intelligent stair cleaning robot based on binocular vision adopted by the present invention includes a double rocker tracked chassis, a binocular vision camera module, a cleaning device, and a control system. The binocular vision camera is fixed in the front of the double rocker tracked chassis, and the cleaning device is fixed above the double rocker tracked chassis.

[0005] Among them, the double rocker tracked chassis includes a main track, a secondary track, secondary wheels, a reduction gearbox, a motor, and a battery, etc. The main track and the secondary track provide contact and friction with the stair surface. The secondary wheels assist the movement of the track. The reduction gearbox is used to reduce the motor speed and increase the torque to meet the chassis driving requirements. The motor provides power for the chassis movement, and the battery supplies power to the entire chassis system.

[0006] Among them, the binocular vision camera module consists of two cameras and related image recognition and processing circuits, and is installed at the front of the chassis. The cameras have high resolution and wide viewing angles, and can obtain clear images of the stair environment. Using the binocular vision principle, the two cameras simultaneously acquire image information of the surrounding environment, and perform processing such as stereo rectification, feature extraction, and target recognition on the images through the image recognition and processing circuits, accurately identifying the length, step height, width, slope of the stairs, and three-dimensional information of surrounding obstacles. The recognized information is transmitted to the intelligent control system of the robot to provide accurate data for path planning and cleaning control.

[0007] Among them, the cleaning device includes a dust suction head, a multi-link mechanism, a stepping motor for controlling the movement of the dust suction head, a stainless steel deep groove ball bearing, a stepping motor for providing suction to the dust suction head, a dust collection box, etc. The surface of the dust suction head is provided with a flexible fitting layer, which can automatically deform according to the shape of the stair surface to ensure close fitting and improve the dust suction effect. The dust suction head is connected to the dust collection box through a pipeline, and is internally provided with a dust suction channel and an air flow regulating device. The multi-link mechanism consists of multiple links and rotating joints, one end is connected to the robot body, and the other end is connected to the dust suction head. By controlling the rotation angles of the joints of the multi-link mechanism, the position and angle of the dust suction head can be flexibly adjusted to enable it to adapt to stair surfaces with different inclination angles and shapes, realizing full-range cleaning coverage. The stepping motor for controlling the movement of the dust suction head is connected to the multi-link mechanism, and by accurately controlling the rotation steps and angles of the stepping motor, precise control of the multi-link mechanism is achieved, and then the position and movement trajectory of the dust suction head are accurately adjusted. The stainless steel deep groove ball bearing is used to support the rotating shaft of the stepping motor for providing suction to the dust suction head, reducing rotational friction and improving the motor efficiency and service life. The stepping motor for providing suction to the dust suction head controls the suction force of the dust suction head by adjusting the rotation speed, and can be adaptively adjusted according to the type and degree of stains. The dust collection box is used to collect the dirt sucked in by the dust suction head, and is internally provided with an efficient filtering device to prevent dust and debris from being discharged into the environment again. The dust collection box has a certain volume and is equipped with a convenient cleaning interface for convenient regular cleaning.

[0008] Among them, the control system includes a main control panel and a control module. The main control panel has a built-in microprocessor MCU that processes the received information in real time through program code and sends instructions in real time. The control module is used to execute the instructions sent by the microprocessor MCU to control the functions of each part of the structure. The control module also includes sensor detection, and the sensor detection periodically feeds back the collected signals to the microprocessor MCU to facilitate the operator to monitor and manage the work of the robot.

[0009] Among them, the control system, the double rocker arm crawler chassis, the binocular vision camera module, and the cleaning device are electrically connected.

[0010] An intelligent stair cleaning robot based on binocular vision of the present invention, under the coordinated control of the control system, controls the robot to achieve automation, intelligence and high efficiency of stair cleaning, reduces the labor intensity of manual work, and improves the cleaning efficiency and quality. Brief Description of the Drawings

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0012] Figure 1 It is a schematic diagram of the overall structure of an intelligent stair cleaning robot based on binocular vision of the present invention.

[0013] Figure 2 It is a sectional view of the double swing arm crawler chassis of the present invention.

[0014] Figure 3 It is a schematic diagram of the structure of the main control tablet of the present invention.

[0015] 1 - Double swing arm crawler chassis, 11 - Reducer box, 12 - Motor, 13 - Battery, 14 - Motor, 15 - Reducer box, 16 - Auxiliary crawler, 17 - Auxiliary wheel, 18 - Main crawler, 2 - Binocular vision camera module, 3 - Dust suction head, 4 - Multi-link mechanism, 5 - Stepper motor for controlling the movement of the dust suction head, 6 - Stainless steel deep groove ball bearing and stepper motor for providing suction force for the dust suction head, 7 - Dust collection box, 8 - Main control tablet of the control module, 81 - Liquid crystal touch display screen, 82 - Power button, 83 - Function button, 84 - Tablet shell, 9 - Motor frame. Detailed Embodiments

[0016] The following will describe in detail the embodiments of the present invention. The examples of the embodiments are shown in the drawings, where the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are intended to explain the present invention and should not be construed as a limitation of the present invention.

[0017] In the description of the present invention, it should be understood that the orientation or positional relationship indicated by the terms "length", "width", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In addition, in the description of the present invention, the meaning of "a plurality" is two or more, unless otherwise specifically defined.

[0018] Please refer to Figures 1 to 3 , the present invention provides an intelligent stair cleaning robot based on binocular vision, including a double rocker tracked chassis, a binocular vision camera module, a cleaning device and a control system. The binocular vision camera is fixed directly in front of the double rocker tracked chassis, and the cleaning device is fixed directly above the double rocker tracked chassis.

[0019] Among them, the double rocker tracked chassis 1 includes a main track 18, a secondary track 16, a secondary wheel 17, a reduction gearbox 11, a reduction gearbox 15, a motor 12, a motor 14, and a storage battery 13, etc. The main track 18 and the secondary track 16 provide contact and friction with the stair surface. The secondary wheel 17 assists the movement of the track. The reduction gearbox 11 and the reduction gearbox 15 are used to reduce the motor speed and increase the torque to meet the chassis driving requirements. The motor 12 and the motor 14 provide power for the chassis movement. The storage battery 13 supplies power to the entire chassis system.

[0020] Among them, the binocular vision camera module 2 is composed of two cameras and related image recognition and processing circuits, and is installed at the front of the chassis. The cameras have high resolution and wide viewing angle, and can obtain clear images of the stair environment. Using the binocular vision principle, the two cameras simultaneously acquire image information of the surrounding environment, and perform stereo correction, feature extraction, target recognition, etc. on the images through the image recognition and processing circuits, accurately identify the length, step height, width, slope of the stairs, and three-dimensional information of surrounding obstacles. The recognized information is transmitted to the intelligent control system of the robot to provide accurate data for path planning and cleaning control.

[0021] Among them, the cleaning device includes a dust suction head 3, a multi-link mechanism 4, a stepping motor 5 for controlling the movement of the dust suction head, a stainless steel deep groove ball bearing, a stepping motor 6 for providing suction force to the dust suction head, a dust collection box 7, etc. A flexible fitting layer is provided on the surface of the dust suction head 3, which can automatically deform according to the shape of the stair surface to ensure close fitting and improve the dust suction effect. The dust suction head 3 is connected to the dust collection box 7 through a pipeline, and is internally provided with a dust suction channel and an air flow regulating device. The multi-link mechanism 4 is composed of multiple links and rotating joints, with one end connected to the robot main body and the other end connected to the dust suction head 3. By controlling the rotation angles of the joints of the multi-link mechanism 4, the position and angle of the dust suction head 3 can be flexibly adjusted, enabling it to adapt to stair surfaces with different inclination angles and shapes, and achieving full-range cleaning coverage. The stepping motor 5 for controlling the movement of the dust suction head is connected to the multi-link mechanism 4. By precisely controlling the number of rotation steps and angles of the stepping motor 5, precise control of the multi-link mechanism 4 is achieved, and thus the position and movement trajectory of the dust suction head 3 are precisely adjusted. The stainless steel deep groove ball bearing and the stepping motor 6 for providing suction force to the dust suction head are used to support the rotating shaft of the motor, reduce rotational friction, improve the motor efficiency and service life, and the suction force of the dust suction head 3 can be controlled by adjusting the rotational speed, and can be adaptively adjusted according to the type and degree of stains. The dust collection box 7 is used to collect the dirt sucked in by the dust suction head, and is internally provided with an efficient filtering device to prevent dust and debris from being discharged into the environment again. The dust collection box 7 has a certain volume and is equipped with a convenient cleaning interface for convenient regular cleaning.

[0022] Among them, the control system includes a main control tablet 8 and a control module. The main control tablet includes a liquid crystal touch display screen 81, a power button 82, function buttons 83, and a tablet shell 84. The main control tablet 8 internally has a microprocessor MCU that processes the received information in real time through program code and sends instructions in real time. The control module includes sensor detection, and the sensor detection includes temperature sensor and distance sensor detection. The sensors periodically feedback the collected signals to the microprocessor MCU. The control module is used to execute the instructions sent by the microprocessor MCU to control the structural functions of each part.

[0023] Among them, the control system, the double rocker arm crawler chassis, the binocular vision camera module, and the cleaning device are electrically connected.

[0024] In this embodiment, after the power button 82 of the main control tablet 8 is pressed, the main control tablet 8 establishes a connection with the robot main body through a wireless communication module and sends a start signal to the robot. After the robot receives the start signal, the internal intelligent control system starts to initialize.

[0025] The battery 13 in the double rocker arm crawler chassis 1 powers the entire system. Components such as the motors 12 and 14, the reduction gears 11 and 15 enter the self-check state. The motors 12 and 14 perform no-load running tests to check whether the rotational speed and torque output are normal; the reduction gears 11 and 15 check the gear meshing condition and transmission efficiency. The binocular vision camera module 2 conducts lens cleanliness inspection, focal length calibration, and image sensor initialization, and ensures that it can accurately obtain environmental images through the self-check program. The cleaning device components such as the stepper motor 5 that controls the movement of the dust suction head, the stepper motor 6 that provides suction for the dust suction head, and the multi-link mechanism 4 perform reset operations and function tests to ensure they are in a workable state. At the same time, the various sensors of the robot perform zero calibration and data initialization to prepare for subsequent accurate perception and control.

[0026] Further, after the main control tablet 8 presses the power button 83 or the liquid crystal touch display screen 81, it enters the cleaning task mode. After the binocular vision camera module 2 receives the instruction, the two cameras start working simultaneously to obtain the image information of the front staircase, process and identify the environmental information. The path planning module generates the optimal cleaning path and transmits it to the motion control module and the cleaning control module, and at the same time displays it on the main control tablet 8 to provide guidance for the movement and cleaning operations of the robot.

[0027] The motion control module controls the motors 12 and 14 of the double rocker arm crawler chassis 1 to drive the main crawler 18 and the auxiliary crawler 16 to rotate simultaneously through the reduction gears 11 and 15 according to the path information; when climbing stairs, the sensors monitor the posture and center of gravity in real time, and adjust the state of the rocker arm, motor, and crawler to ensure stable movement.

[0028] The cleaning control module starts the device when the robot reaches the starting position. The multi-link mechanism 4 adjusts the position and angle of the dust suction head 3, adjusts the stepper motor 5 and the stepper motor 6 according to the stain situation, controls the suction and movement of the dust suction head 3, sweeps according to the preset trajectory, and the dirt enters the dust collection box 7. The module monitors the state to ensure normal operation.

[0029] Preferably, the main control tablet 8 can be replaced by a mobile phone APP. The microprocessor MCU in the main control tablet is provided with a Bluetooth connection module. The microprocessor MCU realizes Bluetooth communication with the mobile phone APP and real-time control of data through the Bluetooth connection module. The mobile phone APP can control the cleaning path of the robot, the angle of the dust suction head, the cleaning speed, and the start and stop of the robot. The mobile phone APP can freely control the movement of the robot within a specific range to realize parameter setting, data display, and alarm.

[0030] The above-disclosed is only a preferred embodiment of the present invention. Of course, the scope of the rights of the present invention cannot be limited thereby. Those of ordinary skill in the art can understand all or part of the processes of implementing the above embodiments, and the equivalent changes made according to the claims of the present invention still fall within the scope covered by the invention.

Claims

1. An intelligent stair cleaning robot based on binocular vision, characterized in that it includes a double rocker track chassis, a binocular vision camera module, a cleaning device and a control system. The binocular vision camera is fixed directly in front of the double rocker track chassis, and the cleaning device is fixed directly above the double rocker track chassis.

2. The intelligent stair cleaning robot based on binocular vision according to claim 1, characterized in that the double rocker track chassis is composed of a track, a rocker, a drive wheel and a power system. The track provides good grip to prevent slipping when climbing stairs; the rocker can rotate around the connection point, and by adjusting its extension and contraction, the center of gravity position of the robot is changed to adapt to different step heights and achieve stable stair climbing; the power system drives the drive wheel to drive the track to run.

3. The intelligent stair cleaning robot based on binocular vision according to claim 1, characterized in that the binocular vision camera module consists of two cameras and an image recognition and processing module. Using the binocular vision principle, it obtains a three-dimensional image of the environment. After analysis by the image recognition and processing module, it identifies information such as the length and structure of the stairs and surrounding obstacles, transmits it to the path planning module to plan the best cleaning path, and inputs it into the robot control system; when encountering a flat part in the middle of the stairs, it can automatically plan the path of the upper and lower floors of the stairs and execute it.

4. The intelligent stair cleaning robot based on binocular vision according to claim 1, characterized in that the cleaning device consists of a multi-link mechanism, a dust suction head, a dust collection box, a stepping motor and a motor control system. The multi-link mechanism connects the robot body and the dust suction head, and can flexibly adjust the position and angle of the dust suction head; the dust suction head is connected to the upper bearing and the stepping motor through a connection hole, and the stepping motor generates suction to suck up dirt; the dust suction head is connected to the dust collection box to collect dirt; the motor above the dust collection box is controlled by the motor control system to drive the dust suction head to move back and forth to clean the stairs.

5. The intelligent stair cleaning robot based on binocular vision according to claim 1, characterized in that the rocker of the double rocker track chassis is made of a material with adjustable stiffness, and can adaptively adjust the stiffness according to the load and terrain changes during stair climbing, further enhancing stability.

6. The intelligent stair cleaning robot based on binocular vision according to claim 1, characterized in that the binocular vision camera has a real-time image enhancement function. By performing processing such as contrast enhancement and noise suppression on the acquired image, the recognition accuracy of the stair environment information in low-light or complex lighting environments is improved.

7. The intelligent stair cleaning robot based on binocular vision according to claim 1, characterized in that the surface of the dust suction head of the cleaning device is provided with a flexible fitting layer, which is made of an elastic material and can better fit the fine unevenness of the stair surface during cleaning, improving the dust suction effect.

8. The intelligent stair cleaning robot based on binocular vision according to claim 1, characterized in that It includes an intelligent control system, and the intelligent control system includes a path planning module, a motion control module, a cleaning control module, and a sensor fusion module. The path planning module plans the cleaning path based on the information of the binocular vision camera; the motion control module controls the movement of the double rocker tracked chassis according to the path instructions; the cleaning control module regulates the movement and suction of the suction head of the cleaning device; the sensor fusion module fuses the data of sensors such as the binocular vision camera to improve the accuracy and reliability of environmental perception.

9. The intelligent stair cleaning robot based on binocular vision according to claim 8, wherein the path planning module uses a heuristic search algorithm, combines the stair environment information and the robot's own state, quickly plans the optimal cleaning path, and dynamically adjusts it in real time according to the environmental changes during the cleaning process.

10. The intelligent stair cleaning robot based on binocular vision according to claim 8, wherein the motion control module has a motion compensation function, and can automatically adjust the output of the power system according to the actual motion deviation of the double rocker tracked chassis during stair climbing to ensure the accuracy of the movement.

11. The intelligent stair cleaning robot based on binocular vision according to claim 8, wherein the cleaning control module can automatically adjust the suction force and moving speed of the suction head according to the stain degree and material of the stairs to achieve efficient and energy-saving cleaning.

Images