[robotics-worldwide] [Meetings] CfP: RSS Workshop on Learning from Demonstrations for High Level Robotics Tasks

ankurhanda handa.ankur at gmail.com
Wed Apr 11 10:08:14 PDT 2018

Call for Papers

RSS 2018 Workshop on
Learning from Demonstrations for High Level Robotics Tasks

Location: Pittsburgh, Pennsylvania, USA
Date: June 29/30, 2018
URL: https://urldefense.proofpoint.com/v2/url?u=https-3A__sites.google.com_view_learningfromdemonstrations_&d=DwICAg&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=bnilzfuZIu1sKwaUWMT9_B6dzfrZ0oWIyKwDtDHBlmE&s=xs0qZng8q0BRMaizQe5PfmGQsYQDPLJyBkHejRSVvcs&e=

Important Dates
May 25 - Submission deadline (AoE time)
May 30 - Notification of acceptance
June 8 - Camera ready deadline
June 29/30 - Workshop

Many real-world tasks require robots to solve complex decision making
problems and be capable of dexterous low level control to enable seamless
interaction with the surrounding environment. Learning from Demonstrations
(LfD) can greatly reduce the difficulty of learning in such settings by
making use of expert demonstrations. These demonstrations convey
near-optimal behaviours for these tasks and provide informed guidance to the
learning process without having to start from scratch. LfD has remained
popular in the past within robotics, neuroscience, behavioural psychology
and cognitive science, and has seen a resurgence recently in robotics,
particularly with the advent of deep learning techniques.

In this workshop, we plan to cover various techniques for LfD and invite a
discussion into the possible future of LfD in the context of robotics,
especially for solving long-time horizon tasks and tasks that require
hierarchical decision making from multi-modal input (e.g. visual, haptic,
language and auditory). We plan to invite well known researchers in machine
learning, cognitive science and robotics with the aim to encourage
collaboration and share new ideas across this multidisciplinary field. We
will cover topics focusing on, but not limited to, inverse optimal control,
inverse reinforcement learning, demonstrations within reinforcement
learning, and LfD with function approximators e.g. neural networks.

Invited Speakers
Chelsea Finn (UC, Berkeley)
Jeanette Bohg (Stanford)
Anca Dragan (UC, Berkeley)
Stefan Schaal (USC)
Jon Scholz (DeepMind)
Andrew Bagnell (CMU / Aurora)
Maya Cakmak (UW)

We solicit submissions conforming to the official RSS style guidelines.
Submissions can include arXived work or previously accepted work which has
not yet been presented. Reviewing will not be double blind, so please do not
anonymise the submission.

Submission link: https://urldefense.proofpoint.com/v2/url?u=https-3A__easychair.org_conferences_-3Fconf-3Drsswlfd18&d=DwICAg&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=bnilzfuZIu1sKwaUWMT9_B6dzfrZ0oWIyKwDtDHBlmE&s=frrZHa6CHJq3ZM1Zr8Xa5eBaeSNpPutDOqt-aVsh5XY&e=

Topics include but are not limited to:
- Planning with high-dimensional observations
- Imitation Learning in the real world
- Deep learning for planning
- Learning from high-dimensional demonstrations
- Predicting human behaviour from high-dimensional observations
- Deep Inverse Optimal Control

All accepted contributions will be presented in interactive poster sessions
and archived on the workshop website. All or a subset of accepted
contributions will be featured in the workshop as 3 minute spotlight

Ankur Handa
Feryal Behbahani
Arun Kumar Byravan
James Davidson
Dieter Fox

handa.ankur at gmail.com

Sent from: https://urldefense.proofpoint.com/v2/url?u=http-3A__robotics-2Dworldwide.1046236.n5.nabble.com_&d=DwICAg&c=clK7kQUTWtAVEOVIgvi0NU5BOUHhpN0H8p7CSfnc_gI&r=0w3solp5fswiyWF2RL6rSs8MCeFamFEPafDTOhgTfYI&m=bnilzfuZIu1sKwaUWMT9_B6dzfrZ0oWIyKwDtDHBlmE&s=TuhQjeAO1TYOGNb6TJ7gV7DKDd3Glou6LtVNkgBSbqQ&e=

More information about the robotics-worldwide mailing list