Imitation Learning and its Challenges in Robotics

NIPS workshop | Montreal, Canada | Dec 7, 2018

Description

Many animals including humans have the ability to acquire skills, knowledge, and social cues from a very young age. This ability to imitate by learning from demonstrations has inspired research across many disciplines like anthropology, neuroscience, psychology, and artificial intelligence. In AI, imitation learning (IL) serves as an essential tool for learning skills that are difficult to program by hand. The applicability of IL to robotics in particular, is useful when learning by trial and error (reinforcement learning) can be hazardous in the real world. Despite the many recent breakthroughs in IL, in the context of robotics there are several challenges to be addressed if robots are to operate freely and interact with humans in the real world.


Some important challenges include: 1) achieving good generalization and sample efficiency when the user can only provide a limited number of demonstrations with little to no feedback; 2) learning safe behaviors in human environments that require the least user intervention in terms of safety overrides without being overly conservative; and 3) leveraging data from multiple sources, including non-human sources, since limitations in hardware interfaces can often lead to poor quality demonstrations.


In this workshop, we aim to bring together researchers and experts in robotics, imitation and reinforcement learning, deep learning, and human robot interaction to

  • Formalize the representations and primary challenges in IL as they pertain to robotics
  • Delineate the key strengths and limitations of existing approaches with respect to these challenges
  • Establish common baselines, metrics, and benchmarks, and identify open questions

Invited Speakers

UT Austin

Georgia Tech

Oxford University

Caltech

Berkley / Waymo

Georgia Tech / NVIDIA

Important Dates

Oct 19

Oct 29

Nov 16

Dec 7

Submission deadline (AoE time)

Notification of acceptance

Camera ready deadline

Workshop

Call for Abstracts

We solicit up to 4 pages extended abstracts (excluding references) conforming to the NIPS style. Submissions can include archived or previously accepted work (please make a note of this in the submission). Reviewing will be single blind.

Submission link: https://easychair.org/conferences/?conf=nips18ilr

Topics of interest include, but are not limited to:

  • Sample efficiency in imitation learning
  • Learning from high dimensional demonstrations
  • Learning from observations
  • Learning with minimal demonstrator effort
  • Few shot imitation learning
  • Risk aware imitation learning
  • Learning to gain user trust
  • Learning from multi modal demonstrations
  • Learning with imperfect demonstrations

All accepted contributions will be presented in interactive poster sessions. A subset of accepted contributions will be featured in the workshop as spotlight presentations.

Travel Awards:

With the generous support of our sponsors, we are excited to offer a few travel awards intended to partly offset cost of attendance (registration + most of travel). Only presenting students/post-docs of accepted contributions will be eligible to receive these awards. Applications will be accepted alongside submissions. More details to be announced soon.

Schedule

Coming soon

Organizers

Georgia Tech

University of Washington

University of Washington

Sponsors