Communication-Efficient Relative Pose Estimation with Vision Foundation Models for Ephemeral Collaborative Perception
This work addresses the problem of relative pose estimation for multi-robot systems operating under limited communication and intermittent visual overlap, which is critical for real-world collaborative perception.
CERPE introduces a communication-efficient framework for relative pose estimation in multi-robot systems, reducing bandwidth usage by sharing fixed-size descriptors and handling non-overlapping views via ego-motion propagation. It improves 6-DoF pose estimation over baselines in ephemeral collaborative perception scenarios.
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.