DRL-TH: Jointly Utilizing Temporal Graph Attention and Hierarchical Fusion for UGV Navigation in Crowded Environments

TL;DR

This paper introduces DRL-TH, a novel deep reinforcement learning framework that uses temporal graph attention and hierarchical fusion to improve UGV navigation in crowded environments by capturing temporal context and adaptively integrating multi-modal data.

Contribution

The paper presents a new DRL-based navigation framework with temporal graph attention and hierarchical fusion, enhancing scene understanding and multi-modal data integration for UGVs in crowded settings.

Findings

Outperforms existing methods in crowded environments

Successfully applied on real UGVs in real-world scenarios

Improves scene correlation modeling and multi-modal fusion

Abstract

Deep reinforcement learning (DRL) methods have demonstrated potential for autonomous navigation and obstacle avoidance of unmanned ground vehicles (UGVs) in crowded environments. Most existing approaches rely on single-frame observation and employ simple concatenation for multi-modal fusion, which limits their ability to capture temporal context and hinders dynamic adaptability. To address these challenges, we propose a DRL-based navigation framework, DRL-TH, which leverages temporal graph attention and hierarchical graph pooling to integrate historical observations and adaptively fuse multi-modal information. Specifically, we introduce a temporal-guided graph attention network (TG-GAT) that incorporates temporal weights into attention scores to capture correlations between consecutive frames, thereby enabling the implicit estimation of scene evolution. In addition, we design a graph hierarchical abstraction module (GHAM) that applies hierarchical pooling and learnable weighted fusion to dynamically integrate RGB and LiDAR features, achieving balanced representation across multiple scales. Extensive experiments demonstrate that our DRL-TH outperforms existing methods in various crowded environments. We also implemented DRL-TH control policy on a real UGV and showed that it performed well in real world scenarios.