CaMeRL: Collision-Aware and Memory-Enhanced Reinforcement Learning for UAV Navigation in Multi-Scale Obstacle Environments

TL;DR

CaMeRL introduces a novel UAV navigation framework that enhances obstacle detection and navigation reliability across multiple obstacle scales by incorporating collision-aware representations and memory modules.

Contribution

It presents a new reinforcement learning approach that encodes risk-sensitive features and integrates temporal information to improve multi-scale obstacle avoidance.

Findings

CaMeRL outperforms existing methods in ultra-small and extra-large obstacle environments.

It achieves success rate improvements of 0.48 and 0.28 in different obstacle scale settings.

CaMeRL enables reliable outdoor UAV navigation in cluttered environments.

Abstract

In obstacle avoidance navigation of unmanned aerial vehicles (UAVs), variations in obstacle scale have received strangely less attention than obstacle number or density. Existing methods typically extract purely geometric features from single-frame depth observations. Such representations tend to neglect small obstacles and lose spatial context under occlusions caused by large obstacles, leading to noticeable degradation in environments with multi-scale obstacles. To address this issue, we propose CaMeRL, a Collision-aware and Memory-enhanced Reinforcement Learning framework for UAV navigation. The collision-aware latent representation encodes risk-sensitive depth cues to preserve fine-grained obstacle structures, thereby improving sensitivity to small obstacles. The temporal memory module integrates observations across frames, mitigating partial observability caused by large-obstacle occlusions. We evaluate CaMeRL with multi-scale obstacles, including ultra-small and extra-large obstacle settings. Results show that CaMeRL outperforms state-of-the-art baselines across all scales, with success rate gains of 0.48 and 0.28 in the ultra-small and extra-large settings, respectively. More importantly, CaMeRL achieves reliable navigation in cluttered outdoor environments.