Search papers, labs, and topics across Lattice.
This paper introduces a communication-efficient relative pose estimation (CERPE) framework that enhances collaborative perception in multi-robot systems operating under constraints of limited communication bandwidth and intermittent visual overlap. By utilizing fixed-size descriptors to manage raw-image requests and propagating relative poses through ego-motion, CERPE effectively maintains accurate pose estimates even during non-overlapping encounters. Experimental results demonstrate that CERPE significantly outperforms existing methods, achieving improved 6-DoF relative pose estimation in both simulated and real-world scenarios.
Robots can now maintain accurate relative pose estimates even when visual overlap is absent, thanks to a novel communication-efficient framework.
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.
