The main goal of this workshop is to bring together pioneers in employing Model Predictive Control (MPC) and Reinforcement Learning (RL) to control legged robots to discuss the recent advances in the field and the potential ways to combine these two paradigms to have the best of both worlds. We believe that, given the recent advances in both fields, in this workshop we can provide the young researchers with a summary of the state of the art research in the area of legged locomotion control. The workshop is comprised of a series of talks, a poster&demo session and a panel discussion.
We invite interested researchers to participate to the poster and demo sessions by submitting an abstract. Abstract for posters would describe research relevant to the workshop (already published work or preliminary work is ok). Abstract for demos should describe the kind of live demonstrations that you would run virtually, its duration and time availability for the demonstration. Abstract can be submitted through the following page and should not exceed 2 pages in length:
https://easychair.org/conferences/?conf=mpcrl2021
Topics of interest are:
Model predictive control for legged locomotion
Reinforcement Learning applied to legged robots
Real-world realization of MPC or RL on legged robots
Proposition of live demonstration on the day of the workshop
The deadline for submission is April 30, 2021. Participants to the poster session will be asked to provide a teaser talk (around 2 min) to be uploaded in this website. On the day of the workshop, we will provide an interactive platform for the poster session and for the live demonstrations.
DeepMind
KAIST
Ubisoft
Apptronik
MPI
ETH
LAAS-CNRS
NYU & MPI