Active Robotic Mapping through Deep Reinforcement Learning

TL;DR

This paper introduces a deep reinforcement learning approach for active robotic mapping that learns to explore environments efficiently, outperforming traditional methods in simulated disaster scenarios by adapting to environment priors.

Contribution

It presents a novel exploration policy learning method that incorporates user-specified environment priors, enabling specialized and efficient mapping strategies.

Findings

Achieves slightly better performance than near-optimal myopic exploration.

Demonstrates effectiveness in simulated disaster mapping scenarios.

Shows potential for application in complex real-world environments.

Abstract

We propose an approach to learning agents for active robotic mapping, where the goal is to map the environment as quickly as possible. The agent learns to map efficiently in simulated environments by receiving rewards corresponding to how fast it constructs an accurate map. In contrast to prior work, this approach learns an exploration policy based on a user-specified prior over environment configurations and sensor model, allowing it to specialize to the specifications. We evaluate the approach through a simulated Disaster Mapping scenario and find that it achieves performance slightly better than a near-optimal myopic exploration scheme, suggesting that it could be useful in more complicated problem scenarios.