GIANT - Global Path Integration and Attentive Graph Networks for Multi-Agent Trajectory Planning

TL;DR

This paper introduces GIANT, a novel multi-agent trajectory planning method combining global path integration with attentive graph neural networks, achieving superior collision avoidance and navigation efficiency in dynamic environments.

Contribution

The paper presents a new multi-robot navigation approach that integrates global path planning with attentive graph neural networks, improving robustness and adaptability in complex scenarios.

Findings

Higher success rates compared to baselines

Lower collision rates in dynamic environments

More efficient navigation in complex scenarios

Abstract

This paper presents a novel approach to multi-robot collision avoidance that integrates global path planning with local navigation strategies, utilizing attentive graph neural networks to manage dynamic interactions among agents. We introduce a local navigation model that leverages pre-planned global paths, allowing robots to adhere to optimal routes while dynamically adjusting to environmental changes. The models robustness is enhanced through the introduction of noise during training, resulting in superior performance in complex, dynamic environments. Our approach is evaluated against established baselines, including NH-ORCA, DRL-NAV, and GA3C-CADRL, across various structurally diverse simulated scenarios. The results demonstrate that our model achieves consistently higher success rates, lower collision rates, and more efficient navigation, particularly in challenging scenarios where baseline models struggle. This work offers an advancement in multi-robot navigation, with implications for robust performance in complex, dynamic environments with varying degrees of complexity, such as those encountered in logistics, where adaptability is essential for accommodating unforeseen obstacles and unpredictable changes.