Towards Map-Agnostic Policies for Adaptive Informative Path Planning

TL;DR

This paper introduces a new map-agnostic approach for adaptive informative path planning that works across various terrain representations, combining classical and learning-based methods for efficient real-world deployment.

Contribution

It proposes a unified formulation for adaptive path planning that is independent of specific map representations, enhancing versatility and applicability.

Findings

The approach integrates with classical planning methods without performance loss.

The learned policy performs comparably to map-specific state-of-the-art policies.

Validation on real-world terrains demonstrates practical effectiveness.

Abstract

Robots are frequently tasked to gather relevant sensor data in unknown terrains. A key challenge for classical path planning algorithms used for autonomous information gathering is adaptively replanning paths online as the terrain is explored given limited onboard compute resources. Recently, learning-based approaches emerged that train planning policies offline and enable computationally efficient online replanning performing policy inference. These approaches are designed and trained for terrain monitoring missions assuming a single specific map representation, which limits their applicability to different terrains. To address these issues, we propose a novel formulation of the adaptive informative path planning problem unified across different map representations, enabling training and deploying planning policies in a larger variety of monitoring missions. Experimental results validate that our novel formulation easily integrates with classical non-learning-based planning approaches while maintaining their performance. Our trained planning policy performs similarly to state-of-the-art map-specifically trained policies. We validate our learned policy on unseen real-world terrain datasets.