Claire chatted to Pratap Tokekar from the University of Maryland about how teams of robots with different capabilities can work together. Pratap Tokekar is an Associate Professor in the Department of Computer Science and the Institute for Advanced Computer Studies at the University of Maryland, and an Amazon Scholar. Previously, he was a Postdoctoral Researcher at the GRASP lab of University of Pennsylvania and later, an Assistant Professor at Virginia Tech. He has a degree in Electronics and Telecommunication from the College of Engineering Pune in India and a Ph.D. in Computer Science from the University of Minnesota. He received the Amazon Research Award in 2022, and the NSF CAREER award in 2020.

We consider the setting where a team of robots is tasked with tracking multiple targets with the following property: approaching the targets enables more accurate target position estimation, but also increases the risk of sensor failures. Therefore, it is essential to address the trade-off between tracking quality maximization and risk minimization. In the previous work [1], a centralized controller is developed to plan motions for all the robots - however, this is not a scalable approach. Here, we present a decentralized and risk-aware multi-target tracking framework, in which each robot plans its motion trading off tracking accuracy maximization and aversion to risk, while only relying on its own information and information exchanged with its neighbors. We use the control barrier function to guarantee network connectivity throughout the tracking process. Extensive numerical experiments demonstrate that our system can achieve similar tracking accuracy and risk-awareness to its centralized counterpart.

Centralized approaches for multi-robot coverage planning problems suffer from the lack of scalability. Learning-based distributed algorithms provide a scalable avenue in addition to bringing data-oriented feature generation capabilities to the table, allowing integration with other learning-based approaches. To this end, we present a learning-based, differentiable distributed coverage planner (D2COPL A N) which scales efficiently in runtime and number of agents compared to the expert algorithm, and performs on par with the classical distributed algorithm. In addition, we show that D2COPlan can be seamlessly combined with other learning methods to learn end-to-end, resulting in a better solution than the individually trained modules, opening doors to further research for tasks that remain elusive with classical methods.