NeurIPS 2021 Workshop on Deployable Decision Making in Embodied Systems (DDM)

The workshop will be virtual and will take place on December 14, 2021. We are currently inviting short paper/abstract submissions [call for papers]. The deadline for submission is October 15, 2021.

Overview

Embodied systems are playing an increasingly important role in our lives. Examples include, but are not limited to, autonomous driving, drone delivery, and service robots. In real-world deployments, the systems are required to safely learn and operate under the various sources of uncertainties. As noted in the Roadmap for US Robotics (2020), safe learning and adaptation is a key aspect of next-generation robotics. Learning is ingrained in all components of the robotics software stack including perception, planning, and control. While the safety and robustness of these components have been identified as critical aspects for real-world deployments, open issues and challenges are often discussed separately in the respective communities. In this workshop, we aim to bring together researchers from machine learning, computer vision, robotics, and control to facilitate interdisciplinary discussions on the topic of deployable decision making in embodied systems. Our workshop will feature two discussion themes:

  • Theme A: Deployable Learning Algorithms for Embodied Systems
  • Theme B: Safe Learning and Decision Making in Uncertain and Unstructured Environments

Call for Papers | Invited Speakers | Structure | Program | Organizers | Program Committee

Call for Papers

We are inviting researchers from different disciplines to share novel perspectives or ideas on related topics, which include but are not limited to:

  • Safety analysis and safety verification
  • Deployable decision making under uncertainty
  • Robust perception, planning and control
  • Safe reinforcement learning
  • Sim2real transfer
  • Embodied systems and safety-critical applications
  • Safe human-robot interaction
  • Explainability, transparency, and interpretability of learning
  • Uncertainty quantification
  • Deep learning theory
  • Probabilistic model learning
  • Safe (robot) learning dataset, simulators, and benchmarks¬†
  • Metrics for safe real-world deployments

Paper Format

Suggested Paper Length: 4 pages excluding references and appendices (longer papers are permitted)
Style Template: NeurIPS 2021 style files (anonymized)

Important Dates

Submission Deadline: October 8, 2021 October 15, 2021 (11:59 pm Anywhere on Earth)
Author Notification: October 20, 2021 October 23, 2021

Submission Website

https://cmt3.research.microsoft.com/DDM2021

Accepted submissions will be presented as either a spotlight talk or a poster. To further facilitate discussions, we will organize thematic discussion groups in our workshop that allow participants to connect and share ideas. To conform with the NeurIPS policy, submissions should be works that have not been presented at another conference. In case of any questions related to the submission or our workshop, please reach out to us at ddm2021neurips@gmail.com.

Also check out the NeurIPS 2021 workshop on Safe and Robust Control of Uncertain Systems!

Invited Speakers


Yarin Gal
University of Oxford

Shuran Song
Columbia University

Yisong Yue
Caltech
(Conditionally Confirmed)

Structure

We are committed to creating a diverse and inclusive online environment that allows researchers from different communities to exchange their views and ideas. Our workshop is designed to facilitate interdisciplinary exchange. We envision the workshop to be a full-day event consisting of

  1. lecture-style presentations given by the invited speakers to summarize their perspectives on the topic,
  2. moderated discussion panels facilitating discussions between the invited speakers and the audience, and
  3. a spotlight talks and poster session where junior members of the research community can share their ideas in thematic, interactive discussions.

To further foster open-ended discussions, we will leverage the virtual format and make an effort to connect researchers with different seniority and background for informal exchange and mentoring.

Program

Below is a tentative program of the workshop. Times are in Eastern Standard Time (EST).

Theme A: Deployable Learning Algorithms for Embodied Systems

10:00-10:10   Opening Remarks & Theme A Introduction
10:10-10:30   Invited Talk: Martin Riedmiller
10:30-10:50   Invited Talk: Shuran Song
10:50-11:10   Invited Talk: Nick Roy
11:10-11:30   Invited Talk: Aude Billard
11:30-11:35   Coffee Break
11:35-12:35   Panel Discussion
12:35-12:55   Invited Spotlight Talks
12:55-14:00   Poster Session

Theme B: Safe Learning and Decision Making in Uncertain and Unstructured Environments

14:00-14:10   Theme B Introduction
14:10-14:30   Invited Talk: Sandeep Neema
14:30-14:50   Invited Talk: Yarin Gal
14:50-15:10   Invited Talk: Yisong Yue
15:10-15:30   Invited Talk: Zico Kolter
15:30-15:45   Coffee Break
15:45-16:45   Panel Discussion
16:45-17:00   Concluding Remarks
17:00-18:00   Social Event

Organizers


Angela Schoellig
University of Toronto

Animesh Garg
University of Toronto

Somil Bansal
Waymo, USC

Melissa Greeff
University of Toronto

SiQi Zhou
University of Toronto

Program Committee

Sarah Dean, UC Berkeley
Gabriel Kalweit, University of Freiburg
Katie Kang, UC Berkeley
James Lucas, University of Toronto
Qiyang Li, UC Berkeley
Chris McKinnon, Applanix
Karime Pereida, Kindred
Mengye Ren, University of Toronto
Spencer Richards, Stanford
Guanya Shi, Caltech
Florian Shkurti, University of Toronto
Tim Tang, University of Oxford
Kyriakos Vamvoudakis, Georgia Tech
Zhaoming Xie, University of British Columbia

University of Toronto Institute for Aerospace Studies