Mariliza Tzes *,1, Nikolaos Bousias *,1, Evangelos Chatzipantazis1, George J. Pappas1

1GRASP Lab, University of Pennsylvania

This paper addresses the Multi-Robot Active Information Acquisition (AIA) problem, where a team of mobile robots, communicating through an underlying graph, estimates a hidden state expressing a phenomenon of interest. Applica- tions like target tracking, coverage and SLAM can be expressed in this framework. Existing approaches, though, are either not scalable, unable to handle dynamic phenomena or not robust to changes in the communication graph. To counter these shortcomings, we propose an Information-aware Graph Block Network (I-GBNet), an AIA adaptation of Graph Neural Networks, that aggregates information over the graph represen- tation and provides sequential-decision making in a distributed manner. The I-GBNet, trained via imitation learning with a centralized sampling-based expert solver, exhibits permutation equivariance and time invariance, while harnessing the superior scalability, robustness and generalizability to previously unseen environments and robot configurations. Experiments on signifi- cantly larger graphs and dimensionality of the hidden state and more complex environments than those seen in training validate the properties of the proposed architecture and its efficacy the application of localization and tracking of dynamic targets.

Song, Y., Naji, S., Kaufmann, E., Loquercio, A. and Scaramuzza, D., 2021, October. Flightmare: A flexible quadrotor simulator. In Conference on Robot Learning (pp. 1147-1157). PMLR.

nbousias@seas.upenn.edu   :  mtzes@seas.upenn.edu

3330 Walnut St, Philadelphia, PA 19104, United States