OffRIPP: Offline RL-based Informative Path Planning

TL;DR

This paper introduces OffRIPP, an offline reinforcement learning framework for informative path planning in robotics, which learns from pre-collected data to optimize information gathering efficiently and safely without real-time environment interaction.

Contribution

The paper presents a novel offline RL-based approach for IPP that avoids environment interaction during training, improving safety, cost-efficiency, and performance over existing methods.

Findings

Outperforms baseline methods in simulations

Effective in real-world experiments

Mitigates extrapolation errors with batch-constrained RL

Abstract

Informative path planning (IPP) is a crucial task in robotics, where agents must design paths to gather valuable information about a target environment while adhering to resource constraints. Reinforcement learning (RL) has been shown to be effective for IPP, however, it requires environment interactions, which are risky and expensive in practice. To address this problem, we propose an offline RL-based IPP framework that optimizes information gain without requiring real-time interaction during training, offering safety and cost-efficiency by avoiding interaction, as well as superior performance and fast computation during execution -- key advantages of RL. Our framework leverages batch-constrained reinforcement learning to mitigate extrapolation errors, enabling the agent to learn from pre-collected datasets generated by arbitrary algorithms. We validate the framework through extensive simulations and real-world experiments. The numerical results show that our framework outperforms the baselines, demonstrating the effectiveness of the proposed approach.