Loading Events

« All Events

  • This event has passed.

Animesh Garg: “Towards Generalizable Imitation in Robotics”

November 1 @ 11:00 am - 12:00 pm

Abstract: Robotics and AI are experiencing a radical growth, fueled by innovations in data-driven learning paradigms coupled with novel device design, in applications such as healthcare, manufacturing and service robotics. The challenges of advanced robotics and intelligent decision cannot be addressed by developing new learning algorithms or designs in isolation. The aim of my research is to bridge this gap and enable generalizable imitation for robot autonomy. I am interested enabling learning from imprecise information for performing a range of tasks with independence and flexibility. This involves coupled algorithms in reinforcement learning, control theoretic planning, semantic scene & video understanding, and design.

In this talk, I will present specific instances of my research in robotics spanning these areas: Hierarchical RL and Meta-Learning, Safe Policy Learning, and Video understanding. I will first describe algorithmic paradigm towards enabling complex multi-step sequential tasks. I will also discuss one-shot imitation learning for hierarchical tasks. Then I will discuss methods for robust policy learning to handle generalization across dynamics. Finally, I will discuss reference resolution algorithms towards task-level understanding from videos. The algorithms and techniques introduced are applicable across domains in robotics; in this talk, I will exemplify these ideas through my work on medical and personal robotics.

Bio: Animesh is a Postdoctoral Researcher at Stanford University AI lab. Animesh is interested in problems at the intersection of optimization, machine learning, and design. He studies the interaction of data-driven Learning for autonomy and Design for automation for human skill-augmentation and decision support. Animesh received his Ph.D. from the University of California, Berkeley where he was a part of the Berkeley AI Research center and the Automation Science Lab. His research has been recognized with Best Applications Paper Award at IEEE CASE, Best Video at Hamlyn Symposium on Surgical Robotics, and Best Paper Nomination at IEEE ICRA 2015.  And his work has also featured in press outlets such as New York Times, UC Health, UC CITRIS News, and BBC Click.
Host: Ron Alterovitz

Details

Date:
November 1
Time:
11:00 am - 12:00 pm
Event Category:

Venue

141 Brooks Building (FB141)
Brooks Computer Science Building, S. Columbia St.
Chapel Hill, NC 27599 United States
+ Google Map