Multi-Cleaning Robots Using Cleaning Distribution Method Based on Map Decomposition in Large Environments

Abstract

Most cleaning robots have a good cleaning performance for small environments such as houses but require a longer cleaning time due to problems such as slow cleaning progress and low battery capacity, making the robots unsuitable for large environments such as libraries and airports. Cleaning large environments with multiple robots is faster than cleaning them with a single robot. Multi-cleaning robots can utilize several robots to simultaneously clean and share the task of cleaning among the robots. However, as the number of robots increases and the effective distribution of cleaning is not efficient during the cleaning process, the cleaning time will consequently be longer due to the frequent collisions between the robots. Therefore, to shorten the cleaning time, multi-cleaning robots require a coverage path planning that uses an effective cleaning distribution method in the cleaning process. In this paper, a coverage path planning using a cleaning distribution method based on map decomposition is proposed to reduce the cleaning time of multi-cleaning robots. The experimental results demonstrated that the proposed multi-cleaning robots' coverage path planning could be used in large environments in the presence of several types of obstacles. Furthermore, the cleaning time was found to be shorter than that of the previous methods in the case of multi-cleaning robots. INDEX TERMS Coverage path planning, cleaning robot, computational efficiency, multi-robots system, robot path planning.

Multi-Robot Hybrid Coverage Path Planning for 3D Reconstruction of Large Structures

“…The robots coordinate to cover the unknown areas with the neighboring robots within their communication range. The work in [3] proposed a map decomposition method and spiral CPP method using multi-cleaning robots to cover large unknown 2D environments. Additionally, unknown 2D environments are covered in [34], where the authors proposed an information correlated Levy walk exploration algorithm.…”

“…Different CPP approaches have been proposed in literature addressing various challenges depending on the environment dimensionality, and the structure complexity [2]. Most of these approaches utilizes single robot or multi-robot systems for wide 2D areas coverage utilizing classical approaches [3]. However, in many cases, generating efficient coverage paths for different large unknown 3D environments using a team of robots remains an open research challenge.…”

“…Most proposed approaches in the literature perform CPP using multi-robot systems to cover 2D large unknown environmental areas [3], [9] or perform model based CPP which requires a reference model to plan the path offline [10]- [12]. Some of the proposed approaches utilize ML, such as Reinforcement learning (RL) [7].…”

A Comprehensive Review of Coverage Path Planning in Robotics Using Classical and Heuristic Algorithms

“…In [2], a knowledge reasoning for robot CPP combines with the BFS to avoid the dynamic obstacles under an uncertain environment, lowering repetition rate and computation time. Miao et al [162] proposed a distribution technique by using sub-map decomposition and BFS methods. This technique decomposes an unknown map into several subareas, distributes each robot to select the nearest sub-areas to be covered by using a spiral pattern.…”

UltraBot: Autonomous Mobile Robot for Indoor UV-C Disinfection

“…This conclusion about preferable robot movement behaviour could be considered into setting up of a collabo- rative work of multiple disinfection robots, where generated robot trajectories must not intersect along with performing coverage path planning task [21].…”