Call for Papers

We invite researchers that work towards safe and robust autonomy of robots in the real world to share their results at our SAFE-ROL workshop at CoRL 2025. This includes contributions in all areas of robot learning, i.e., perception, prediction, planning, and control.

Topics that are in line with the workshop goals include but are not limited to:

• Data curation and generation

• Uncertainty quantification

• Out-of-distribution detection

• Interpretability

• Safety definition and modeling

• Safe learning

• Runtime monitoring

• Testing and coverage estimation

• Real-world safety

• Simulation for safety

Submissions are encouraged to present advancements in algorithms, theory, hardware, benchmarking tools such as datasets or simulators, or new viewpoints that enhance robotic safety and robustness when deployed to real-world scenarios.

Papers accepted for the workshop, along with any supplementary materials, will be accessible prior to the event and will remain available for later visitors. Please note that posting papers here is for informational purposes only and does not equate to official proceedings and is therefore non-archival.

Submission Guidlines

Submissions must be made via OpenReview and formatted according to the CoRL 2025 Conference Template. Papers are recommended to be 6 pages, with a maximum of 8 pages (excluding references, acknowledgments, and optional appendix). Authors are encouraged to include supplementary materials (e.g., videos, code, or datasets) either within a single ZIP file uploaded to OpenReview or via anonymized GitHub links.

The review process will be double blind and non-public. Only accepted papers will be made publicly available after the conclusion of the review process.

Important Dates