Thesis Defense: Compositional Robot Learning for Generalizable Interactions

Speaker: Yen-Ling Kuo , MIT CSAIL

Date: Friday, May 06, 2022

Time: 3:00 PM to 4:00 PM Note: all times are in the Eastern Time Zone

Public: Yes

Location: 32-G882 (Hewlett Room), https://mit.zoom.us/j/99850893101

Event Type: Thesis Defense

Room Description:

Host: Boris Katz

Contact: Yen-Ling Kuo, ylkuo@mit.edu

Relevant URL:

Speaker URL: None

Speaker Photo:
None

Reminders to: seminars@csail.mit.edu

Reminder Subject: TALK: Thesis Defense: Compositional Robot Learning for Generalizable Interactions

Abstract:

To understand environments effectively and to interact safely with humans, robots must generalize their learned models to scenarios they have never been trained on before, such as new commands and new agents. Humans have shown a remarkable ability to compose concepts they have learned before in order to interpret and to act in a novel environment. In contrast, many deep-learning based methods fail at compositional generalization, i.e., an ability to generalize to novel combinations of concepts that have not been seen before in training.

In this talk, I will present several learning-based approaches that leverage compositionality to enable generalization in various reasoning skills. First, I will show how compositional linguistic structure can be incorporated into robotic models to enable robots to follow novel commands and act rationally in new scenarios. Then I will show how recursive reward estimation can enable robots to reason about sequences of actions and about novel social interactions. Finally, I will show how we can incorporate compositionality into trajectory prediction by using language as an intermediate representation.

Thesis Committee: Boris Katz, Andrei Barbu, Leslie Kaelbling, and Nicholas Roy

Research Areas:
AI & Machine Learning

Impact Areas:

This event is not part of a series.

Created by Yen-Ling Kuo Email at Friday, April 29, 2022 at 4:09 PM.