Evaluate, Detect, Adapt: Trustworthy Deployment of Large Behavior Models
Research Lead and Manager, Toyota Research Institute
Attendance Link: https://docs.google.com/forms/d/e/1FAIpQLSdzU9VehavfTCy6zZk7vXcXHEx-FtcWxWNqa091cx10YlUvSQ/closedform
Abstract
Large-scale robot learning, such as using large behavior models (LBMs), has increasingly become the norm in robot learning literature. Nevertheless, many questions remain about how to deploy these embodied learning-based systems in the real world. First, we need a rigorous and efficient means to evaluate candidate robot learning models with statistical guarantees. Second, to deploy these models in human environments, they should be equipped with reliable failure detection systems despite the challenge posed by countless and often unforeseeable 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 along these research directions as part of the Trustworthy Learning under Uncertainty (TLU) team at TRI, focusing on rigorous and fast sequential evaluation, detecting failures on the fly, and adapting large behavior models to new tasks during deployment. These research lines aim to spur algorithmic development for robust and reliable deployment of embodied foundation models in human environments. To learn more about our work, visit: https://www.tri.global/trustworthy-learning-under-uncertainty-tlu.
Bio:
I am a roboticist. I work on helping robots understand the world around them. My interests lie in uncertainty-aware machine learning algorithms for embodied systems. I am a Research Lead and Manager at the Toyota Research Institute (TRI) where I co-lead the Trustworthy Learning under Uncertainty (TLU) research direction in the context of Large Behavior Models (LBMs). We are currently researching statistical robot evaluation, failure detection, recovery, and mitigation, as well as (inter)active and continual learning. To see my latest research, here is my Google Scholar.
Previously, as part of the Stanford Intelligent Systems Laboratory (SISL), my research focused on spatiotemporal perception for self-driving cars. I built perception systems that robustly predicted the evolution of the dynamic environment and made inference into spatially occluded regions, while taking into account uncertainty, in order to intelligently inform autonomous decision making
Please visit https://stanfordasl.github.io/robotics_seminar/for this quarter’s lineup of speakers. Although we encourage live in-person attendance, recordings of talks will be posted also.