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

10/01/2022
by   Aaron Zellner, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/27/2019

A Constant-Factor Approximation Algorithm for Online Coverage Path Planning with Energy Constraint

In this paper, we study the problem of coverage planning by a mobile rob...
research
05/13/2021

Changeable Sweep Coverage Problem

Sweep coverage is to realize the periodic coverage of targets by plannin...
research
08/07/2018

Efficient Multi-Robot Coverage of a Known Environment

This paper addresses the complete area coverage problem of a known envir...
research
01/20/2023

Optimal multiple FSO transceiver configuration for using on High-altitude platforms

Free-space optical (FSO) communication requires light of sight (LoS) bet...
research
05/29/2019

ORangE: Operational Range Estimation for Mobile Robot Exploration on a Single Discharge Cycle

This paper presents an approach for estimating the operational range for...
research
08/13/2021

BESS Aided Reconfigurable Energy Supply using Deep Reinforcement Learning for 5G and Beyond

The year of 2020 has witnessed the unprecedented development of 5G netwo...
research
06/21/2023

Linear and Non-Linear Barrier Coverage in Deterministic and Uncertain environment in WSNs: A New Classification

This paper Various studies cited in the literature deal with the classic...

Please sign up or login with your details

Forgot password? Click here to reset