cs.ROMar 4, 2026

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

Authors: Jonas le Fevre Sejersen, Toyotaro Suzumura, Erdal Kayacan

Organizations: Artificial Intelligence in Robotics Laboratory (AiR Lab), Department of Electrical and Computer Engineering, Aarhus University, 8000 Aarhus C, Denmark · Foundation Models for Artificial Intelligence group, Department of Information and Communication Engineering, Tokyo University, Tokyo, Japan · Automatic Control Group, Department of Electrical Engineering and Information Technology, Paderborn University, Paderborn, Germany

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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.

Figures & tables

Figure 1: The figure illustrates the trajectory chosen by our model, where the robot navigates through highly dense and dynamic environments while adhering to the global path
Figure 2: Overall illustration of the observation space. (a) Illustrates the environmental obstacles captured by the LiDAR, the velocity of the agent, and the goal distance. (b) Illustrates the global path observations, with the distance from the agent (red) to the target point (blue), the angle difference between the agent heading and the target point, and the direction of the global path at the target point. (c) Illustrates the estimated dynamic clusters extracted from the LiDAR. The position and velocity of each cluster are tracked over time and fed to the network as a graph.
Figure 3: An illustration of the actor-network architecture. The network includes three observation encoders: a static LiDAR encoder that processes the current frame through Conv1D layers to capture static features, a temporal LiDAR encoder that processes the last three frames through Conv1D layers to learn dynamic features, and a neighbor attentive Graph Neural Network encoder. The combined encoded features are passed to fully connected layers and the network outputs the mean and standard deviation for the action normal distributions, which include linear and angular velocities. The critic network follows an identical structure but outputs state values instead.
ParametersValues ParametersValues
learning rate critic4e-4 Δt\Delta t0.1s
learning rate actor2e-5 H\mathcal{H}5
entropy coefficient0 rpr_{p}2.5
reward discount0.99 rsr_{s}-0.25m
GAE discount0.95 PS0.3m
PPO train epoch10 rgoalr_{\text{goal}}15
Table I: Training hyperparameters
Figure 4: The six different environments used during training.
MetricFull ModelNo Global PathNo GNN
Success Rate (%)96.792.793.2
Stuck / Collision Rate (%)3.3 / 0.7.1 / 0.22.2 / 4.6
Extra Time (Normalized)18.721.814.7
Average Speed (m/s)0.420.340.57
Table II: Ablation Study Results in the Doorway Environment with 15 Agents.
Training settingsTest environments with variable number of agents:
MetricsMethodsCircle (radius 7.5m)DoorwayNarrow CorridorRandom (8 obstacles)
1020405101581216102040
 NH-ORCA [ 12 ] 72.5 32.7 91.67 9395.597.25
 DRL-Nav [ 1 ] 91.393.8 82.5 95.3
 GA3C-CADRL [ 4 ] 52.5 14.773.7553.17 83.8
Success Rate (%)GIANT [ours] 96.67 97.5 99.599.25
Table III: Model performance on evaluation scenarios

Explore similar work

CardsList

  1. Global Path Planner with Multi-Model Switching

    Sep 11, 2026Pietro Gori, Francesco Iotti, Eduard Zelenay +5Robot Trajectory TrackingFeedback Control

    Centro di Ricerca “Enrico Piaggio” and the Dipartimento di Ingegneria dell’Informazione, Universit`a di Pisa, Largo Lucio Lazzarino 1, 56126 Pisa, Italy · Institute of Robotics and Cybernetics, Faculty of Electrical Engineering and Information Technology, Slovak University of Technology in Bratislava, Ilkovicova 3, 812 19 Bratislava, Slovakia · Panza Robotics, National Center of Robotics, Ilkovicova 3, 841 04 Bratislava, Slovakia +1

  2. CTS-PLL: A Robust and Anytime Framework for Collaborative Task Sequencing and Multi-Agent Path Finding

    Mar 26, 2026Junkai Jiang, Yitao Xu, Ruochen Li +2Multi-Agent PlanningMulti-Agent Path Finding

  3. VORL-EXPLORE: A Hybrid Learning Planning Approach to Multi-Robot Exploration in Dynamic Environments

    Mar 9, 2026Ning Liu, Sen Shen, Zheng Li +4Multi-Robot ExplorationMulti-Robot Motion Planning

    The University of Western Australia · The Chinese University of Hong Kong · Karlsruhe Institute of Technology +1