RAMEN: Real-time Asynchronous Multi-agent Neural Implicit Mapping

2025-02-26

AI Summary

To address bandwidth sensitivity and poor interruption robustness caused by synchronous communication in multi-agent neural implicit mapping, this paper proposes a decentralized asynchronous collaborative framework. The method eliminates reliance on global clock synchronization, instead enabling agents to operate with local, asynchronous, low-frequency communication under dynamic and partially connected topologies. Its core innovations include: (i) the first incorporation of parameter-level uncertainty modeling into neural implicit map fusion; (ii) an uncertainty-weighted asynchronous consensus optimization mechanism; and (iii) a weighted distributed C-ADMM algorithm for scalable, topology-adaptive coordination. Extensive evaluations on real robotic platforms and multiple field datasets demonstrate that, under 70% communication interruption rates, the approach achieves 18.6% higher mapping accuracy and 2.3× faster convergence compared to baseline methods—significantly enhancing practicality and robustness in resource-constrained scenarios.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Multiagent Systems: Agent Communication
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Multi-agent neural implicit mapping allows robots to collaboratively capture and reconstruct complex environments with high fidelity. However, existing approaches often rely on synchronous communication, which is impractical in real-world scenarios with limited bandwidth and potential communication interruptions. This paper introduces RAMEN: Real-time Asynchronous Multi-agEnt Neural implicit mapping, a novel approach designed to address this challenge. RAMEN employs an uncertainty-weighted multi-agent consensus optimization algorithm that accounts for communication disruptions. When communication is lost between a pair of agents, each agent retains only an outdated copy of its neighbor's map, with the uncertainty of this copy increasing over time since the last communication. Using gradient update information, we quantify the uncertainty associated with each parameter of the neural network map. Neural network maps from different agents are brought to consensus on the basis of their levels of uncertainty, with consensus biased towards network parameters with lower uncertainty. To achieve this, we derive a weighted variant of the decentralized consensus alternating direction method of multipliers (C-ADMM) algorithm, facilitating robust collaboration among agents with varying communication and update frequencies. Through extensive evaluations on real-world datasets and robot hardware experiments, we demonstrate RAMEN's superior mapping performance under challenging communication conditions.

Problem

• Real-time asynchronous multi-agent mapping
• Handling communication disruptions in robotics
• Uncertainty-weighted neural network consensus

Innovation

• Asynchronous multi-agent neural mapping
• Uncertainty-weighted consensus optimization
• Decentralized C-ADMM algorithm variant