For a robot to personalize physical assistance effectively, it must lear...
When humans perform contact-rich manipulation tasks, customized tools ar...
Manipulation of objects in-hand without an object model is a foundationa...
Differentiable simulation is a promising toolkit for fast gradient-based...
Research in manipulation of deformable objects is typically conducted on...
Deformable object manipulation remains a challenging task in robotics
re...
We develop a method for learning periodic tasks from visual demonstratio...
BayesSim is a statistical technique for domain randomization in reinforc...
Deformable objects present a formidable challenge for robotic manipulati...
We address the problem of learning reusable state representations from
s...
Data-efficiency is crucial for autonomous robots to adapt to new tasks a...
We develop an approach that benefits from large simulated datasets and t...
Learning for control can acquire controllers for novel robotic tasks, pa...