Research Analyzer
← Back ICRA 2026

Real-Time Communication Relay Planning with a Low-Complexity Network Quality Prediction Model in Dynamic Indoor Missions

Jaemin Seo, Jongyun Kim, Seunghwan Kim, Changseung Kim, Woojae Shin, Hyondong Oh

PDF

AI summary

Key figure (auto-extracted from paper)
The proposed real-time relay system achieves near-continuous network availability (99.1%) and significantly boosts packet delivery ratios in dynamic indoor environments.
Multi-robot systems communication relay network prediction real-time planning Gaussian process regression indoor navigation

Problem

Existing network prediction and relay planning methods struggle with real-time operation due to high computational costs and poor adaptability to frequently changing missions in complex indoor environments.

Approach

The method combines a low-complexity Kalman filter-based Gaussian process regression model for constant-time network prediction with a hierarchical relay planning strategy that uses Monte Carlo tree search to generate communication-aware trajectories.

Key results

  • Low-complexity KF-GPR model enabling constant-time (~0.02s) online network prediction
  • Hierarchical relay planner using Monte Carlo tree search for communication-aware trajectory generation
  • Achieved 99.1% channel reliability and increased packet delivery ratio from 44.7% to 73.7% in real-world experiments
  • Demonstrated robust connectivity maintenance under dynamically changing mission points

Why it matters

Enables reliable, real-time multi-hop communication for mobile robots operating in complex, infrastructure-limited indoor environments.

Abstract

Relay robots are crucial for extending communica- tion when a client robot performs long-range missions. However, existing network quality prediction models and relay planning methods often struggle with real-time operation due to their high computational cost and poor adaptability to frequently changing missions. To address this, we propose a real-time communication relay system featuring two key contributions. First, a low-complexity network quality prediction model using Kalman filter-based Gaussian process regression achieves efficient online inference with constant-time updates (∼0.02s). Second, a hierarchical relay planning strategy, employing a Monte Carlo tree search-based sequential planner, generates communication- aware trajectories satisfying network constraints at discrete steps. Real-world experiments validate our system’s effective- ness, demonstrating near-continuous network availability (99.1% channel reliability) and boosting the packet delivery ratio from a baseline of 44.7% to 73.7%. Our integrated approach offers a practical and robust solution for dynamic indoor missions.

Index terms

Multi-Robot Systems Networked Robots Path Planning for Multiple Mobile Robots or Agents

Related papers