Graph Neural Networks for Multi-Robot Active Information Acquisition
It addresses scalability and robustness issues in multi-robot systems for applications like target tracking, though it is incremental as it adapts existing Graph Neural Networks to this domain.
This paper tackles the Multi-Robot Active Information Acquisition problem by proposing an Information-aware Graph Block Network (I-GBNet), which improves scalability, robustness, and generalizability in tasks like localization and tracking of dynamic targets, as validated on larger graphs and more complex environments than seen in training.
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. Applications 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 representation 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 significantly 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 in the application of localization and tracking of dynamic targets.