Deep Recurrent Q-learning for Energy-constrained Coverage with a Mobile Robot

TL;DR

This paper introduces a deep recurrent Q-learning approach enabling energy-constrained mobile robots to efficiently cover an environment while managing multiple charging stations and avoiding energy violations.

Contribution

It presents a novel deep Q-learning framework with RNNs for multi-objective coverage under energy constraints, outperforming existing methods.

Findings

The method successfully finds feasible coverage solutions.

It outperforms comparable existing techniques.

The approach effectively manages energy constraints in complex environments.

Abstract

In this paper, we study the problem of coverage of an environment with an energy-constrained robot in the presence of multiple charging stations. As the robot's on-board power supply is limited, it might not have enough energy to cover all the points in the environment with a single charge. Instead, it will need to stop at one or more charging stations to recharge its battery intermittently. The robot cannot violate the energy constraint, i.e., visit a location with negative available energy. To solve this problem, we propose a deep Q-learning framework that produces a policy to maximize the coverage and minimize the budget violations. Our proposed framework also leverages the memory of a recurrent neural network (RNN) to better suit this multi-objective optimization problem. We have tested the presented framework within a 16 x 16 grid environment having charging stations and various obstacle configurations. Results show that our proposed method finds feasible solutions and outperforms a comparable existing technique.