ActFormer: Scalable Collaborative Perception via Active Queries

arXiv:2403.04968v1 Announce Type: new
Abstract: Collaborative perception leverages rich visual observations from multiple robots to extend a single robot's perception ability beyond its field of view. Many prior works receive messages broadcast from all collaborators, leading to a scalability challenge when dealing with a large number of robots and sensors. In this work, we aim to address \textit{scalable camera-based collaborative perception} with a Transformer-based architecture. Our key idea is to enable a single robot to intelligently discern the relevance of …

abstract arxiv beyond broadcast challenge collaborative cs.cv messages multiple perception prior queries robot robots scalability scalable sensors type via view visual work