Date: February 25, 2026
Speaker: Shivam Vats, Postdoctoral Researcher, Brown University
Title: Resource-Rational Robot Planning and Learning
Abstract: While robotics has seen remarkable progress in many domains, we see very few robots actually helping us in our daily lives. This gap stems from fundamental constraints of real-world deployment that are often overlooked in controlled demonstrations: robots have only seconds to plan and cannot pretrain for every possible scenario. These realities demand a tight integration of planning and learning that makes the most effective use of available resources. I will present a framework for resource-rational robotics that treats time, data, and computation as resources with explicit costs and budgets that must be allocated intelligently. I will introduce metareasoning algorithms that decide what and how to learn at deployment time, enabling robots in factories and homes to provably maximize their performance under operational constraints. I will then present hybrid policies, which combine the complementary strengths of different learning and planning paradigms. These policies enable robots to acquire contact-rich tasks, such as pipe assembly, through a few hours of unsupervised practice, and to coordinate dozens of robots in complex warehouses without any multi-robot data. Together, these results chart a path towards robots that act reliably and learn rapidly under real-world constraints, bringing us closer to long-term autonomy.
Bio: Shivam Vats is a postdoctoral researcher in the Department of Computer Science at Brown University, where he works with George Konidaris on developing planning algorithms that continually learn from experience. His research on manipulation, human-robot teaming and multi-robot systems has been recognized with an Outstanding HRI Paper Finalist Award at ICRA 2022 and a Spotlight presentation at ICLR 2025. He earned his PhD in robotics from Carnegie Mellon University, where he was co-advised by Maxim Likhachev and Oliver Kroemer. Shivam also holds a BSc and an MSc in Mathematics and Computing from IIT Kharagpur.