Correspondence identification for collaborative multi-robot perception under uncertainty

Correspondence identification is a critical capability for multi-robot collaborative perception, which allows a group of robots to consistently refer to the same objects in their own fields of view. Correspondence identification is challenging due to the existence of non-covisible objects that cannot be observed by all robots, and due to uncertainty in robot perception. In this paper, we introduce a novel principled approach that formulates correspondence identification as a graph matching problem under the mathematical framework of regularized constrained optimization. We develop a regularization term to explicitly address perception uncertainties by penalizing the object correspondences with a high uncertainty. We also introduce a second regularization term to explicitly address non-covisible objects by penalizing the correspondences built by the non-covisible objects. Our approach is evaluated in robotic simulations and real physical robots. Experimental results show that our method is able to address correspondence identification under uncertainty and non-covisibility, and achieves the state-of-the-art performance.