Communication-Efficient Relative Pose Estimation with Vision Foundation Models for Ephemeral Collaborative Perception

2026-07-15

AI Summary

This work addresses the challenge of estimating six-degree-of-freedom relative poses among multiple robots operating under transient encounters, limited communication bandwidth, and no persistent visual overlap. To this end, the authors propose CERPE, a novel framework that, for the first time, integrates vision foundation models into collaborative perception. CERPE employs fixed-size descriptors to enable event-triggered, on-demand image transmission and combines this with a metrically scaled ego-motion propagation mechanism to efficiently infer relative poses without requiring continuous visual overlap. Extensive experiments on both simulated and real robotic platforms demonstrate that CERPE significantly outperforms existing baselines, achieving high-precision relative pose estimation even in low-bandwidth, short-duration interaction scenarios.

Abstract

Relative pose estimation is a fundamental capability for collaborative perception and coordination in multi-robot systems. However, robots encountering each other in real-world environments often operate in short interaction windows and must operate under limited communication bandwidth with intermittent or missing visual overlap caused by occlusions or limited fields of view. Existing approaches typically rely on global reference frames, assume sustained view overlap, or incur prohibitive communication costs, thereby limiting their applicability to ephemeral collaborative perception. To address these challenges, we introduce communication-efficient relative pose estimation (CERPE), a system-level framework that coordinates vision foundation models to jointly estimate ego-motion and inter-robot relative pose. CERPE reduces unnecessary raw-observation exchange by using continuously shared fixed-size descriptors to gate event-triggered raw-image requests independently of pose estimation. Non-overlapping encounters are handled by propagating inter-robot relative poses through metrically scaled ego-motion, thus maintaining relative pose estimates even in the absence of visual overlap. Experiments in simulation and real-world robots show that CERPE improves 6-DoF relative pose estimation over selected baselines in ephemeral collaborative perception.

Problem

• relative pose estimation
• multi-robot systems
• communication efficiency
• ephemeral collaborative perception
• visual overlap

Innovation

• relative pose estimation
• vision foundation models
• communication efficiency
• ephemeral collaboration
• ego-motion propagation