Learning, Hierarchies, and Reduced Order Models

with Steve Heim, Research Scientist
Biomimetic Robotics Lab
Massachusetts Institute of Technology

Thursday, January 30th, 10:00-11:00 am
310 Kelly Hall

With the advent of ever more powerful compute and learning pipelines that offer robust end-to-end performance, are hierarchical control frameworks with different levels of abstraction still useful? Hierarchical frameworks with reduced-order models (ROMs) have been commonplace in modelbased control for robots, primarily to make long-horizon reasoning computationally tractable. I will discuss some of the other advantages of hierarchies, why we want ROMs and not simply latent spaces, and the importance of matching the time scale to each level of the hierarchy. I will show some results in learning for legged robots using ROMs with cyclic inductive bias, with both handdesigned and data-driven ROMs. I will also discuss using viability measures to estimate the intuitive notion of “how confident/safe is this action” and why this is only useful at the right level of abstraction.

Steve Heim is a research scientist with the Biomimetic Robotics Lab at Massachusetts Institute of Technology (MIT). He is interested in understanding dynamics in natural systems, especially how and why animals (learn to) move the way they do. Previously, Steve was at the Max Planck Institute for Intelligent Systems (Germany), where he completed a postdoc with the Intelligent Control Systems Group and his PhD with the Dynamic Locomotion Group. He obtained his MSc and BSc from ETH Zurich, with stays at Tohoku University (Japan), EPFL (Switzerland), and TU Delft (Netherlands).

Host: Dylan Losey