Robot Foundation Model via Simulation 

Abstract: Unlike natural language and image processing where internet data is easily available for training foundation models, data for robot learning is unavailable. I will discuss how simulators can be used to learn complex and generalizable sensorimotor skills in a manner that reduces human effort and is easily scaled to many tasks. I will elaborate using the following case studies:

(i) a dexterous manipulation system capable of re-orienting novel objects of complex shapes and peeling vegetables.
(ii) a quadruped robot capable of fast locomotion, manipulation, and whole-body control on diverse natural terrains.
(iii) a lifelong learning robotic agent that can request and learn new rigid-object manipulation skills in a few minutes. 

Next, I will discuss some algorithmic ideas aimed at mitigating human effort in reward design, hyper-parameter tuning and enabling seamless combination of learning signals from demonstrations, rewards, and the agent's self-exploration. The resulting framework provides a way to collect high-quality data for multiple tasks that can be used to train a robotic foundation model. 

Bio:  Pulkit Agrawal is an Assistant Professor in the Department of Electrical Engineering and Computer Science at MIT, where he directs the Improbable AI Lab. He is interested in robotics and learning methods for control. Pulkit's work received the Best Paper Award at the Conference on Robot Learning 2021 and the Best Student Paper Award at the Conference on Computer Supported Collaborative Learning 2011. He is a recipient of the Sony Faculty Research Award, Salesforce Research Award, Amazon Research Award, and a Fulbright fellowship. Before joining MIT, Pulkit received his Ph.D. from UC Berkeley and a Bachelor's degree from IIT Kanpur, where he was awarded the Directors Gold Medal.