Call for Papers

Update: We have extended the deadline to October 11, AOE!

In the CoRL 2023 Workshop on Reliable Out-of-Distribution Generalization in Robot Learning, we invite researchers working with data-driven robotic systems to share their findings with the community. Since data-driven methods are now pervasive throughout robotics practice, we are soliciting contributions at all levels of robotic deployment (individual components, full systems, or fleets thereof) aimed at improving generalization and reliability. Topics that intersect with this workshop's research objectives as detailed on the home page include but are not limited to:

• Distributionally robust robot learning,

• Detecting distributional shifts,

• Fault detection, isolation, and recovery,

• Model calibration and (epistemic) uncertainty quantification,

• Self-supervised (pre-)training,

• Domain adaptation and generalization,

• Continual/lifelong learning,

• Multi-task learning,

• Offline reinforcement learning,

• Risk-aware decision-making,

• Data augmentation and coverage estimation,

• Assessing generalization performance.

Contributions should make some novel algorithmic, theoretical, hardware, benchmarking (e.g., dataset, simulator), or perspective advancement that promotes increased robot reliability under distributional shifts or within the long tail of rare events in the real world. Additionally, contributions may be on-going, under review, or recently published work.

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.

Submission Guidelines