Multi-UAV Adaptive Path Planning Using Deep Reinforcement Learning

TL;DR

This paper presents a deep reinforcement learning-based multi-UAV path planning method that enhances cooperative terrain monitoring, achieving faster mapping of regions of interest and outperforming existing non-learning approaches.

Contribution

It introduces a novel multi-agent deep RL framework with new feature representations and counterfactual credit assignment for adaptive, cooperative UAV path planning.

Findings

Improved mapping speed of regions of interest.

Superior performance over non-learning methods.

Transferability to different team sizes and communication constraints.

Abstract

Efficient aerial data collection is important in many remote sensing applications. In large-scale monitoring scenarios, deploying a team of unmanned aerial vehicles (UAVs) offers improved spatial coverage and robustness against individual failures. However, a key challenge is cooperative path planning for the UAVs to efficiently achieve a joint mission goal. We propose a novel multi-agent informative path planning approach based on deep reinforcement learning for adaptive terrain monitoring scenarios using UAV teams. We introduce new network feature representations to effectively learn path planning in a 3D workspace. By leveraging a counterfactual baseline, our approach explicitly addresses credit assignment to learn cooperative behaviour. Our experimental evaluation shows improved planning performance, i.e. maps regions of interest more quickly, with respect to non-counterfactual variants. Results on synthetic and real-world data show that our approach has superior performance compared to state-of-the-art non-learning-based methods, while being transferable to varying team sizes and communication constraints.