Date: November 21, 2025
Speaker: Masha Itkina, Research Lead and Manager in the Large Behavior Model (LBM) division, Toyota Research Institute (TRI)
Title: Evaluation and Uncertainty in the Age of Robot Learning
Abstract: Large-scale robot learning, such as through Large Behavior Models (LBMs), has become increasingly the norm in robot learning literature since the success of ChatGPT. Nevertheless, there are many questions that remain surrounding how we should go about deploying these embodied learning-based systems in the real world. First, we need a rigorous means to evaluate candidate robot learning models supported with statistical guarantees. To deploy these models in human environments, they should be equipped with reliable failure detection systems despite the challenge of immeasurable failure types and conditions during deployment. Lastly, these models should have the capacity to explore and adapt to new environments, preferences, and tasks. In this talk, I will overview our work as part of the Trustworthy Learning under Uncertainty (TLU) team at TRI along a few of these research directions, focussing on evaluation and failure detection. Then, I will briefly mention how we can adapt available training data through curation to best suit a deployment environment.
Bio: Masha Itkina is a Research Lead and Manager in the Large Behavior Model (LBM) division at the Toyota Research Institute (TRI). At TRI, she co-leads the Trustworthy Learning under Uncertainty (TLU) effort in the context of robotic manipulation. Her research focuses on policy evaluation, failure detection and mitigation, and active learning. Previously, she completed her PhD at the Stanford Intelligent Systems Lab (SISL) on uncertainty-aware perception for self-driving cars. Masha has been invited to speak on her TLU work in top-tier robotics and machine learning conferences, including RSS, CoRL, ICRA, and NeurIPS.