[robotics-worldwide] [meetings][cfp] 1st RSS Workshop on Social Robot Navigation

Chris Mavrogiannis cmavro at cs.washington.edu
Sun Mar 15 15:11:49 PDT 2020

Call for Papers

1st RSS 2020 Workshop on Social Robot Navigation
RSS 2020 Workshop, Sunday July 12th, 2020 
Location: Oregon State University, Corvallis OR, USA

URL: https://urldefense.com/v3/__https://socialrobotnavigation.github.io__;!!LIr3w8kk_Xxm!8Q-o39jau4rXApbSg7iwUG0o0raNjWQ-P6qHyBfTSLK_bvdooYnaE8ND7-y0OlYF50YYGc1n$ 

Workshop organizers: 
* Chris Mavrogiannis, University of Washington
* Pete Trautman, Honda Research Institute USA 
* Leila Takayama, University of California Santa Cruz
* Siddhartha Srinivasa, University of Washington 

Important Dates 
* April 9th 2020 - Deadline for paper submissions 
* April 16th 2020 - Notification of acceptance
* July 12th 2020 - Workshop 

Scope, Motivation, and Format 
The social robot navigation and trajectory prediction community has reached
a crucial point. Despite the large volume of publications, we lack a “common
language.” Broadly speaking, we have yet to reach consensus about:

• The most meaningful skills, capabilities, and behaviors that a social
robot navigation system should have.

• Validation standards. Practitioners adopt different scenarios,
experimental setups, robot platforms, baselines, and metrics.

• The abstractions best suited for the challenges of social navigation.

• What constitutes a good social navigation dataset and how to best use a
given dataset (e.g., for training or validation).

Motivated by these observations, we would like to call a diverse,
multidisciplinary audience to participate in an interactive,
discussion-oriented workshop. We would like to hear from roboticists, social
scientists, and designers about how to develop best practices for social
robot navigation research. The workshop will be organized around focus
topics, which are narrow “common language” challenges. After our invited
speakers present short, provocative talks about a focus topic, workshop
participants will break off into multiple workgroups. These workgroups will
be comprised of the invited speakers, the organizers, and the workshop

Ultimately, we want the community to drive the conversation around the focus

Focus topic 1. What are the most important variables that influence social
robot navigation performance? In other words, what levers should we be

Focus topic 2: What are the best abstractions for social robot navigation
from the perspective of perception, planning, and control?

Focus topic 3: How should we collect (or generate) and use data for social
robot navigation?

(Please see https://urldefense.com/v3/__https://socialrobotnavigation.github.io__;!!LIr3w8kk_Xxm!8Q-o39jau4rXApbSg7iwUG0o0raNjWQ-P6qHyBfTSLK_bvdooYnaE8ND7-y0OlYF50YYGc1n$  for additional detail
about the focus topics.)

Confirmed Speakers 

* Anca Dragan (UC Berkeley) 

* Jonathan How (Massachusetts Institute of Technology)

* Wendy Ju (Cornell University)

* Takayuki Kanda (Kyoto University)

* Ross A. Knepper (Cornell University)

* Benjamin Kuipers (University of Michigan)

* Reid Simmons (Carnegie Mellon University)

We invite short papers (max 4 pages, excluding citations) on topics related
to social robot navigation or social trajectory prediction in standard RSS
paper format. All accepted papers will be presented as posters and
introduced via lightning talks. The papers are encouraged (but are not
required to) address the workshop’s focus topics and the following themes of

Themes of Interest 

Design and experiments
-What robot behaviors will enable untrained pedestrians to navigate
effectively around robots? 
-How do we design user studies to address and get beyond novelty effects?
-How do we measure the performance of a social robot navigation system? 
-How do we deal with uncontrollable variables in experimental settings?
-What are appropriate benchmarking experiments and baselines? 
-How do we ensure these benchmarks are accessible to the community?
-What is the role of simulation in social robot navigation research? What
aspects of human behavior can and should be simulated?

Social robot navigation formalisms
-What are appropriate representations for capturing important properties of
crowd behavior?
-What are appropriate context models? What is the right level of context
detail and how should it change depending on experimental settings?
-How do we encode behavior specifications into objective or reward
-Should robots try to “mimic” human behavior? What behavior models and
interaction metaphors are most effective for enabling smooth robot
-How do we verify that a robot navigation framework is correct and safe? 
-How do we manage and deploy a safety-critical system without safety

Datasets and data-driven approaches
-What properties and variables should a social navigation dataset capture? 
-What is the role of human navigation datasets in social robot navigation
-How do we verify that we have not learned dataset-specific artifacts? How
do we account for “distribution shift” in social navigation settings?
-What is the role of learning (e.g., deep, imitation) in social robot
-How do simulation datasets limit learning-based approaches? How can we
ensure smooth transfer to real-world settings?
-Can we extract performance boundaries in sim2real transfer?

Papers may be submitted in PDF format via email to the address: 
socialrobotnavigation at gmail.com
Submissions need *not* be anonymized.

Christoforos Mavrogiannis, Ph.D.
Postdoctoral Research Associate
Paul G. Allen School of Computer Science & Engineering
University of Washington
Sent from: https://urldefense.com/v3/__http://robotics-worldwide.1046236.n5.nabble.com/__;!!LIr3w8kk_Xxm!8Q-o39jau4rXApbSg7iwUG0o0raNjWQ-P6qHyBfTSLK_bvdooYnaE8ND7-y0OlYF5zBMXpuJ$ 

More information about the robotics-worldwide mailing list