Byte Bites with Andreea Bobu

Speaker: Andreea Bobu

Date: Tuesday, September 24, 2024

Time: 2:00 PM to 3:00 PM Note: all times are in the Eastern Time Zone

Public: Yes

Location:

Event Type: Seminar

Room Description: 32-370

Host: Matt Busekroos

Contact: Matthew Busekroos, 617-324-6745, mmbusekroos@csail.mit.edu

Relevant URL: https://mit.zoom.us/meeting/register/tJMqceihrjgjGdbhA_K1zMDKeqBE_9OGAwEy

Speaker URL: None

Speaker Photo:
None

Reminders to:

Reminder Subject: TALK: Byte Bites with Andreea Bobu

Title: Aligning Robot and Human Representations

Abstract: To perform tasks that humans want in the world, robots rely on a representation of salient task features; for example, to hand me a cup of coffee, the robot considers features like efficiency and cup orientation in its behavior. Prior methods try to learn both a representation and a downstream task jointly from data sets of human behavior, but this unfortunately picks up on spurious correlations and results in behaviors that do not generalize. In Andreea's view, what’s holding us back from successful human-robot interaction is that human and robot representations are often misaligned: for example, our assistive robot moved a cup inches away from my face -- which is technically collision-free behavior -- because it lacked an understanding of personal space. Instead of treating people as static data sources, Andreea's key insight is that robots must engage with humans in an interactive process for finding a shared representation for more efficient, transparent, and seamless downstream learning. In this talk, Andreea focuses on a divide and conquer approach: explicitly focus human input on teaching robots good representations before using them for learning downstream tasks. This means that instead of relying on inputs designed to teach the representation implicitly, we have the opportunity to design human input that is explicitly targeted at teaching the representation and can do so efficiently. Andreea introduces a new type of representation-specific input that lets the human teach new features, enables robots to reason about the uncertainty in their current representation and automatically detect misalignment, and proposes a novel human behavior model to learn robust behaviors on top of human-aligned representations. By explicitly tackling representation alignment, Andreea believe we can ultimately achieve seamless interaction with humans where each agent truly grasps why the other behaves the way they do.

Research Areas:
Human-Computer Interaction, Robotics

Impact Areas:

This event is not part of a series.

Created by Matthew Busekroos at Thursday, September 12, 2024 at 9:00 AM.