UDON: Uncertainty-weighted Distributed Optimization for Multi-Robot Neural Implicit Mapping under Extreme Communication Constraints

2025-09-16

AI Summary

Multi-robot systems struggle to achieve high-fidelity, consistent neural implicit mapping under extreme communication constraints—e.g., communication success rates as low as 1%. Method: We propose a real-time distributed neural implicit mapping framework integrating uncertainty-weighted fusion and distributed optimization. The former prioritizes aggregation of high-confidence local maps, while the latter incorporates a mapping divergence penalty to suppress error accumulation induced by communication failures. Technically, the framework unifies neural implicit representations, online uncertainty estimation, and a multi-agent cooperative optimization architecture. Results: Experiments on standard benchmarks and real robotic platforms demonstrate significant improvements over state-of-the-art methods. Our approach maintains geometrically rich, cross-robot consistent scene reconstructions even at ultra-low communication success rates, establishing a robust and practical solution for collaborative mapping in weakly connected multi-robot systems.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Multiagent Systems: Agent Communication
• Search and Optimization: Distributed Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Multi-robot mapping with neural implicit representations enables the compact reconstruction of complex environments. However, it demands robustness against communication challenges like packet loss and limited bandwidth. While prior works have introduced various mechanisms to mitigate communication disruptions, performance degradation still occurs under extremely low communication success rates. This paper presents UDON, a real-time multi-agent neural implicit mapping framework that introduces a novel uncertainty-weighted distributed optimization to achieve high-quality mapping under severe communication deterioration. The uncertainty weighting prioritizes more reliable portions of the map, while the distributed optimization isolates and penalizes mapping disagreement between individual pairs of communicating agents. We conduct extensive experiments on standard benchmark datasets and real-world robot hardware. We demonstrate that UDON significantly outperforms existing baselines, maintaining high-fidelity reconstructions and consistent scene representations even under extreme communication degradation (as low as 1% success rate).

Problem

• Multi-robot neural mapping under extreme communication constraints
• Robustness against packet loss and bandwidth limitations
• Maintaining mapping accuracy under low communication rates

Innovation

• Uncertainty-weighted distributed optimization for mapping
• Prioritizes reliable map portions under communication constraints
• Penalizes mapping disagreement between communicating agent pairs