Towards Reliable and Deployable Learning-Based Robotic Systems

Conference on Robot Learning 2023, Atlanta, USA

Monday, Nov 6th, 2023

Full-day workshop

The field of robot learning has made substantial progress in endowing robots with greater capability, yet the large-scale real-world adoption of learning-based robotic systems remains limited. This workshop aims to dissect this phenomenon and to identify best practices that could lead to a paradigm shift in how we conceive and build reliable learning-based robotic systems.

We intend to guide our conversations with the following topics:

  1. What are the key challenges in deploying learning-based systems in the real world?
  2. What are the ingredients to ensure the reliability and robustness of learning-based robotic systems?
  3. How should we design learning algorithms that handle edge cases and unforeseen scenarios in the real world?
  4. What role does simulation play in the testing and verification of these systems?
  5. What are the key success stories and lessons learned from existing deployments of classical robotic systems?

Due to the interdisciplinary nature of this workshop, we encourage participants not only from the robot learning community, but equally importantly those from classical robotics and control systems, as well as industry practitioners with first-hand experience deploying such systems.

   

Call for papers

Important Dates:

  • Submission portal opens: 2023/09/01
  • Paper submission deadline: 2023/10/01 2023/10/05
  • Notification of acceptance: 2023/10/13 2023/10/23
  • Workshop date: 2023/11/06

See our Call for papers page for more details. Submission will be accepted through OpenReview.

   

Speakers

 

Xiaolong Wang
UC San Diego
Stefan Schaal
Intrinsic
Sergey Levine
UC Berkeley
Scott Kuindersma
Boston Dynamics
Russ Tedrake
MIT, Toyota Research Institute
Nicolas Heess
Deepmind
Emo Todorov
University of Washington
Dieter Fox
University of Washington, Nvidia
Chelsea Finn
Stanford University

 

Organizers

 

Jianlan Luo
UC Berkeley
Fangchen Liu
UC Berkeley
Tony Zhao
Stanford University
Huihan Liu
UT Austin
Lerrel Pinto
New York University
Yuke Zhu
UT Austin

Advisor

Pieter Abbeel
UC Berkeley