GIANT - Global Path Integration and Attentive Graph Networks for Multi-Agent Trajectory Planning
#GIANT #trajectory planning #multi-agent #graph neural networks #attention mechanisms #path integration #autonomous systems
📌 Key Takeaways
- GIANT is a new framework for multi-agent trajectory planning
- It integrates global path planning with local interactions
- Uses graph neural networks with attention mechanisms
- Aims to improve coordination and efficiency in complex environments
📖 Full Retelling
arXiv:2603.04659v1 Announce Type: cross
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
🏷️ Themes
AI Planning, Multi-Agent Systems
📚 Related People & Topics
Giant (disambiguation)
Topics referred to by the same term
A giant is a being of human appearance, sometimes of prodigious size and strength, common in folklore.
Entity Intersection Graph
No entity connections available yet for this article.
Mentioned Entities
Original Source
--> Computer Science > Robotics arXiv:2603.04659 [Submitted on 4 Mar 2026] Title: GIANT - Global Path Integration and Attentive Graph Networks for Multi-Agent Trajectory Planning Authors: Jonas le Fevre Sejersen , Toyotaro Suzumura , Erdal Kayacan View a PDF of the paper titled GIANT - Global Path Integration and Attentive Graph Networks for Multi-Agent Trajectory Planning, by Jonas le Fevre Sejersen and 1 other authors View PDF HTML 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. Comments: Published in: 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems Subjects: Robotics (cs.RO) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2603.04659 [cs.RO] (or arXiv:2603.04659v1 [cs.RO] for this version) https://doi.org/10.48550/arXiv.2603.04659 Focus to learn more arXiv-issued DOI ...
Read full article at source