Design and implementation of a cleaning robot

Yung-Hsiang  Chen; Sheng-Yan  Pan

doi:10.59400/mea2150

Design and implementation of a cleaning robot

Yung-Hsiang Chen Department of Mechanical Engineering, National Pingtung University of Science and Technology, Pingtung 912301, Taiwan
Sheng-Yan Pan Department of Mechanical Engineering, National Pingtung University of Science and Technology, Pingtung 912301, Taiwan

Article ID: 2150

Keywords: cleaning robot; mechanical design; circuit design; software design; image recognition; waste classification; YOLO

Abstract

This study focuses on the development of a cleaning robot, covering the three main aspects of mechanical design, circuit design, and software design. First, in the area of mechanical design, we created a structure capable of agile movement and efficient cleaning to ensure the robot can operate smoothly in various environments. Second, for circuit design, we developed a microcontroller-based control system to coordinate the operation of various components, including drive motors, sensors, and image recognition modules. Furthermore, in the software design aspect, we utilized YOLO (You Only Look Once) and OpenCV technologies to enable the robot to accurately identify and classify waste during the automatic cleaning process. Finally, we conducted practical cleaning experiments to verify the robot’s ability to recognize waste and the accuracy of waste classification. The experimental results show that the cleaning robot not only possesses the ability to recognize waste but also accurately classify it, demonstrating its potential for practical applications.

References

[1]Canedo D, Fonseca P, Georgieva P, et al. A Deep Learning-Based Dirt Detection Computer Vision System for Floor-Cleaning Robots with Improved Data Collection. Technologies. 2021; 9(4): 94. doi: 10.3390/technologies9040094

[2]Malik M, Sharma S, Uddin M, et al. Waste Classification for Sustainable Development Using Image Recognition with Deep Learning Neural Network Models. Sustainability. 2022; 14(12): 7222. doi: 10.3390/su14127222

[3]Feng H, Mu G, Zhong S, et al. Benchmark Analysis of YOLO Performance on Edge Intelligence Devices. Cryptography. 2022; 6(2): 16. doi: 10.3390/cryptography6020016

[4]Shin DJ, Kim JJ. A Deep Learning Framework Performance Evaluation to Use YOLO in Nvidia Jetson Platform. Applied Sciences. 2022; 12(8): 3734. doi: 10.3390/app12083734

[5]Wu W, Liu H, Li L, et al. Application of local fully Convolutional Neural Network combined with YOLO v5 algorithm in small target detection of remote sensing image. Lv H, ed. PLOS ONE. 2021; 16(10): e0259283. doi: 10.1371/journal.pone.0259283

[6]Dang C, Wang Z, He Y, et al. The Accelerated Inference of a Novel Optimized YOLOv5-LITE on Low-Power Devices for Railway Track Damage Detection. IEEE Access. 2023; 11: 134846-134865. doi: 10.1109/access.2023.3334973

[7]Gams M, Gu IYH, Härmä A, et al. Artificial intelligence and ambient intelligence. Journal of Ambient Intelligence and Smart Environments. 2019; 11(1): 71-86. doi: 10.3233/ais-180508

[8]Huang Q. Towards Indoor Suctionable Object Classification and Recycling: Developing a Lightweight AI Model for Robot Vacuum Cleaners. Applied Sciences. 2023; 13(18): 10031. doi: 10.3390/app131810031

[9]Miao X, Lee HS, Kang BY. Multi-Cleaning Robots Using Cleaning Distribution Method Based on Map Decomposition in Large Environments. IEEE Access. 2020; 8: 97873-97889. doi: 10.1109/access.2020.2997095

[10]Kopytko V, Shevchuk L, et al. Smart Home and Artificial Intelligence as Environment for the Implementation of New Technologies. Path of Science. 2018; 4(9): 2007-2012. doi: 10.22178/pos.38-2

[11]Yin J, Apuroop KGS, Tamilselvam YK, et al. Table Cleaning Task by Human Support Robot Using Deep Learning Technique. Sensors. 2020; 20(6): 1698. doi: 10.3390/s20061698

[12]Narkhede P, Walambe R, Mandaokar S, et al. Gas Detection and Identification Using Multimodal Artificial Intelligence Based Sensor Fusion. Applied System Innovation. 2021; 4(1): 3. doi: 10.3390/asi4010003

[13]Mistry SK, Chatterjee S, Verma AK, et al. Drone-vs-Bird: Drone Detection Using YOLOv7 with CSRT Tracker. IEEE; 2023.

[14]Kwon KR, Lee SH, Farkhodov K. Object Tracking using CSRT Tracker and RCNN. In: Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies; 2020.

[15]Lin YW, Chiu CF, Chen LH, et al. Real-Time Dynamic Intelligent Image Recognition and Tracking System for Rockfall Disasters. Journal of Imaging. 2024; 10(4): 78. doi: 10.3390/jimaging10040078

[16]Vega J, Cañas JM. PyBoKids: An Innovative Python-Based Educational Framework Using Real and Simulated Arduino Robots. Electronics. 2019; 8(8): 899. doi: 10.3390/electronics8080899

[17]Spector L. Evolution of artificial intelligence. Artificial Intelligence. 2006; 170(18): 1251-1253. doi: 10.1016/j.artint.2006.10.009

[18]Strautiņa S, Kalniņa I, Kaufmane E, et al. RaspberrySet: Dataset of Annotated Raspberry Images for Object Detection. Data. 2023; 8(5): 86. doi: 10.3390/data8050086

[19]Hirakawa S, Mori S, Kaneda M. A Navigation and Object Detection Method Using Multisensory Fusion for a Cleaning Robot. IEEE Robotics and Automation Letters. 2020; 5(4): 6609-6616.

[20]Vasquez D, Lopez J. Detecting Different Objects in an Industrial Scenario Using Deep Learning with YOLOv4. Procedia CIRP. 2021; 99: 207-212. doi: 10.1016/j.procir.2021.01.064

[21]Liu D, Chen X, Guo Z, et al. Research on the Online Parameter Identification Method of Train Driving Dynamic Model. International Journal of Computational Vision and Robotics. 2022; 1(1): 497-509.

[22]Jiang Y, Yin S. Heterogenous-view occluded expression data recognition based on cycle-consistent adversarial network and K-SVD dictionary learning under intelligent cooperative robot environment. Computer Science and Information Systems. 2023; 20(4): 1869-1883. doi: 10.2298/csis221228034j

Published

2025-02-27

How to Cite

Chen, Y.-H., & Pan, S.-Y. (2025). Design and implementation of a cleaning robot. Mechanical Engineering Advances, 3(1), 2150. https://doi.org/10.59400/mea2150

Download Citation

Issue

Vol. 3 No. 1 (2025)

Section

Article

This work is licensed under a Creative Commons Attribution 4.0 International License.

In the paper, the MATLAB-Simulink model of simulation of operation of the fast light innovative regional train from “Serbian Railways” in traction and braking mode is exposed where changes are observed: stator currents of three-phase traction motors, traction electric motor speeds and electric multiple units, electromagnetic torque on the rotor shaft of the traction electric motor, and direct current bus voltage. The model allowed review of the listed parameters for: different allowed values of contact network voltage and total voltage distortion at the place of connection of the electric multiple unit to the contact network; different mechanical loads of the electric multiple unit and traction electric motor; and different train speeds and rotations of traction electric motors. Appropriate conclusions were made through the analysis of the simulation results obtained.

This paper defines vehicles and buildings as main sources of United Kingdom (UK) carbon dioxide (CO₂) and seeks to cut such emissions using green hydrogen made from combined wind and solar energy. Combustion vehicles powered by fossil petroleum emit near half of UK climate-warming CO₂ while buildings heated by natural gas provide a third. First, current UK grid problems are defined: Electricity, gas and petroleum grids. Refueling green vehicles has been a particular problem. Then experiments on the private wire community of Keele University show how green hydrogen could integrate both green vehicles and buildings. Next, the model supply chain is planned and tested. Finally, experiments and calculations are outlined, analyzing the optimum system design criteria proposed. We conclude that economic green hydrogen can displace petroleum in vehicles, while powering buildings instead of natural gas. Also, the prospect in 2024 is that profits can be made all along the green hydrogen supply chain, such that new businesses involved in local private clean communities can cost less than the National Grid monopoly and other dominant fossil energy companies.

Presently, dynamic impacts occurrences caused by car crashes have been frequently reported. Statistical results from different articles indicate that vehicle crashworthiness of bridge pier supersedes the other events. However, majority of the published articles focusses on sustainability and finding severity of distressed pier due to impact correlating faster construction methods, like accelerated bridge construction (ABC). This article is an attempt to examine post impacted behavior of a commonly used connector in ABC for resisting short duration shock. Static and dynamic performance analyses of a connector embedded within a coupler system has been examined. A representative ABC pier with the standardized and selected material properties collected from manufacturer’s data has been utilized. Coupler composite materials consisting of a hollow uniform cross-section cast iron cylinder filled up with specified concrete grout conforms higher strength. The performance examination has been conducted by numerical modeling using finite element method (FEM). A commercially used software ANSYS has been utilized for carrying out the simulations. To investigate the post impact dynamic behavior, mesh-independent studies seems inevitable and hence are executed to evaluate dynamic impact factor (DIF). Sensitivity studies are carried out for validating results in precision. The DIF of the main reinforcing tensile steel embedded into the grout placed inside the connector has been determined. Results captured from simulations to identify material properties at plastic stage in sustaining such load have been conducted. The results provide significant information that aids opting for selecting suitable connectors for attaining help the design offices.