CAMETA: Conflict-Aware Multi-Agent Estimated Time of Arrival Prediction for Mobile Robots

2023-10-01

IEEE/RJS International Conference on Intelligent RObots and Systems

AI Summary

This paper addresses the challenge of estimating time of arrival (ETA) for multiple mobile robots in unstructured environments—characterized by the absence of predefined road networks and the necessity of modeling spatiotemporal conflicts among agents. We propose a three-tier collaborative framework: path planning → conflict-aware multi-agent ETA prediction → optimal path selection. Our approach introduces heterogeneous map representation and a heterogeneous graph neural network (HGNN), eliminating reliance on structured road topology or historical trajectory data. It integrates A*-based heuristic search, conflict cost modeling, and multi-agent cooperative optimization. Experiments demonstrate that our method reduces mean absolute percentage error by 29.5%–44% compared to conventional A*, while significantly improving path quality and robustness under noise and high-conflict conditions. Moreover, it exhibits substantially enhanced generalization capability and adaptability to dynamic inter-agent conflicts.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Localization, Mapping, and Navigation
• Multiagent Systems: Multiagent Planning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This study presents the conflict-aware multi-agent estimated time of arrival (CAMETA) framework, a novel approach for predicting the arrival times of multiple agents in unstructured environments without predefined road infrastructure. The CAMETA framework consists of three components: a path planning layer generating potential path suggestions, a multi-agent ETA prediction layer predicting the arrival times for all agents based on the paths, and lastly, a path selection layer that calculates the accumulated cost and selects the best path. The novelty of the CAMETA framework lies in the heterogeneous map representation and the heterogeneous graph neural network architecture. As a result of the proposed novel structure, CAMETA improves the generalization capability compared to the state-of-the-art methods that rely on structured road infrastructure and historical data. The simulation results demonstrate the efficiency and efficacy of the multi-agent ETA prediction layer, with a mean average percentage error improvement of 29.5% and 44% when compared to a traditional path planning method (A *) which does not consider conflicts. The performance of the CAMETA framework shows significant improvements in terms of robustness to noise and conflicts as well as determining proficient routes compared to state-of-the-art multi-agent path planners.

Problem

• Predicts arrival times for multiple robots in unstructured environments.
• Improves generalization using heterogeneous map and neural network.
• Reduces prediction errors and enhances route robustness.

Innovation

• Heterogeneous map representation for unstructured environments
• Heterogeneous graph neural network architecture
• Conflict-aware multi-agent ETA prediction framework