Technologies of Indoor Cleaning Robots

Wenjing Wang

doi:10.54097/mspckc62

Authors

Wenjing Wang

DOI:

https://doi.org/10.54097/mspckc62

Keywords:

Indoor cleaning robots, intelligent navigation, multi-modal perception, garbage recognition.

Abstract

Indoor cleaning robots are with the profound connection of artificial intelligence and robotics, transforming automated tools into smart cleaning assistants. The paper offers a systematic discussion of the technological advances made in two fundamental capabilities of indoor cleaning robots: garbage recognition and handling, and navigation control. The paper is good in the field of navigation outlines the technological development between inertial navigation and SLAM-based path in real-time planning to a Vision-Language-Action (VLA) model-based multi-modal navigation, computation of the benefits, objectives, and difficulties of each strategy. It recognizes such intelligent navigation that merges learning via semantic understanding and reinforcement learning as one of the major future directions. Regarding garbage surveying, the paper discusses vision-based (e.g., YOLO, ViT) and multi-modal sensor fusion solid and liquid waste recognition and classification technologies and potential application of manipulation akin to humans. The review concludes that existing studies continue to have loopholes in the profound assimilation of cross-modal data and system-level execution. Future research will be on smart navigation, multi-mode garbage handling, and delicate anthropomorphic control, finally to achieve extremely autonomous cleaning robot systems based on a closed (perception-decision-action) loop.

Downloads

Download data is not yet available.

References

[1] Zhou Shengrong. Research on Intelligent Household Cleaning Robots [D]. Harbin Institute of Technology, 2006.

[2] Guans, Si. Design Innovation of Intelligent Cleaning Robot [D]. Nanchang University, 2018.

[3] Liu Zongkun. Design of Remote Intelligent Operation and Maintenance System for Cleaning Robots [D]. University of Jinan, 2023.

[4] G. Patrizi, M. Carratù, L. Ciani, P. Sommella, M. Catelani and A. Pietrosanto, "Analysis of Inertial Measurement Units Performances Under Dynamic Conditions," in IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1-13, 2023, Art no. 3520713 DOI: https://doi.org/10.1109/TIM.2023.3284957

[5] Woodman, Oliver J. An introduction to inertial navigation. No. UCAM-CL-TR-696. University of Cambridge, Computer Laboratory, 2007.

[6] Joon, A. Kowalczyk, W. Design of Autonomous Mobile Robot for Cleaning in the Environment with Obstacles. Appl. Sci. 2021, 11, 8076. DOI: https://doi.org/10.3390/app11178076

[7] Debeunne, C., & Vivet, D. A review of visual-LiDAR fusion based simultaneous localization and mapping. Sensors, 2020, 20(7), 2068. DOI: https://doi.org/10.3390/s20072068

[8] Xu Yu. Research on Autonomous Navigation of Indoor Mobile Robots Based on the Fusion of Vision and Lidar [D]. Wuhan Textile University, 2025.

[9] Ma Chenlong. Autonomous Operation Algorithm for Manipulator Based on Visual Language Model and Imitation Learning [D]. Hangzhou Dianzi University, 2025.

[10] Du Xin. Research and Implementation of Robot Complex Indoor Environment Mapping Based on Multi-sensor Fusion [D]. Xi'an University of Technology, 2024.

[11] Ma Xingzhe. Design of Multi-sensor Fusion-Based Mobile Robot Motion Control and Navigation System [D]. Dalian University of Technology, 2024.

[12] Li Yinqi. Research on Laser SLAM Algorithm for Indoor Mobile Robots [D]. Changchun University of Technology, 2025.

[13] ZHOU Z, ATREYA P, TAN Y L, et al. Autoeval: autonomous evaluation of generalist robot manipulation policies in the real world [A], 2025.

[14] HO D, MONAS J, REN J, et al. 1X World Model: Evaluating bits, not atoms[EB/OL], 2025

[15] SHI L X, ICHTER B, EQUI M, et al. Hi Robot: open-ended instruction following with hierarchical vision-language-action models[J]. CoRR, abs/2502.19417.

[16] Gao Yan. Research on Obstacle Detection for Indoor Cleaning Robots Based on Deep Learning [D]. University of Electronic Science and Technology of China, 2025.

[17] Chen Xiaoxuan. Real-time Detection and Tracking of Orbital Obstacles Based on Point Cloud Analysis [D]. Dalian Jiaotong University, 2025.

[18] He Kaixuan. Research on 3D Point Cloud Object Recognition Algorithm Based on Deep Learning [D]. Xi'an Polytechnic University, 2025.

[19] Jiang Peng. Research on Obstacle Avoidance Strategies for Indoor Mobile Robots Based on Reinforcement Learning.