Learning to Trust Autonomy Workshop
Research on autonomous systems has seen a rapid advance of learning-based and data-driven approaches, especially for systems that move in the real world (e.g., during navigation, manipulation, and multi-agent coordination). These methods can tackle problems that seemed out of reach just a few years ago. However, their robustness is typically limited to the training scenarios, leaving a challenge when facing the unpredictability of the real world. The goal of the workshop is to foster discussion among researchers, practitioners, and industry stakeholders to answer the critical question:What will it take to trust and invest in learning-based systems when training data can’t cover every real-world scenario?
Sponsored by the BU Center for Information & Systems Engineering
