Simulating Coverage Path Planning with Roomba

TL;DR

This paper investigates using Deep Reinforcement Learning to solve Coverage Path Planning for vacuum robots in unknown environments, comparing it with Roomba's built-in algorithm, and highlights the potential of learning-based approaches.

Contribution

It introduces a novel application of Deep Reinforcement Learning to Coverage Path Planning and compares its effectiveness with existing robotic algorithms.

Findings

Learning-based approach shows promising results in unknown environments.

Deep RL outperforms traditional algorithms in certain scenarios.

The study highlights the potential of AI in autonomous cleaning tasks.

Abstract

Coverage Path Planning involves visiting every unoccupied state in an environment with obstacles. In this paper, we explore this problem in environments which are initially unknown to the agent, for purposes of simulating the task of a vacuum cleaning robot. A survey of prior work reveals sparse effort in applying learning to solve this problem. In this paper, we explore modeling a Cover Path Planning problem using Deep Reinforcement Learning, and compare it with the performance of the built-in algorithm of the Roomba, a popular vacuum cleaning robot.