Call for Papers / Videos

Call for Videos --- Safety Failure Track  

Submissions for the Safety Failure track is now open here!
Those submitting videos need-not attend the workshop in-person. The organizers will use the videos to guide discussions on the subjective nature of safety during the workshop! We will offer a zoom link for those unable to travel to Australia. 

We are soliciting video submissions of robot safety failures, broadly defined, along with contextual information (task description, failure reason) that have been encountered in your research. As researchers, we believe showcasing the limitations/failure modes of state-of-the-art methods is just as important as positive results. We hope that these submissions can serve as motivation for future research in robot safety. 

Call for Papers

Submission on OpenReview is now open!
We ask that each paper accepted to the workshop as at least one author present in-person at the workshop to present their poster.

We welcome 4 page submissions which highlight new or in-progress ideas, and discourage submissions of work presented in the main RSS conference or a prior conference. The requested format is the RSS template with 4+n page limit. Accepted papers and supplementary material will be made available on this workshop website both before the workshop date and subsequently for future visitors unless otherwise requested by authors. Sharing papers in this way does not constitute formal proceedings, i.e., this workshop is a non-archival venue that will not restrict later renditions of the work from being published in archival conferences or journals. Topics that align with this workshop include, but are not limited to:

• Safety guardrails for generalist policies

• Benchmarks / evaluation for safety

• Safety and alignment during pre-training and/or post-training  

• Learning safety concepts from data

• Robot jailbreaking

• Preventing adversarial attacks 

• Out-of-distribution detection

• Safe exploration during learning

• Safe physical human-robot-interaction

• Perceptions of safety in human-robot-interaction

• Privacy-preserving robotics