Vision-based imitation learning has shown promising capabilities of endowing robots with
various motion skills given visual observation. However, current visuomotor policies fail to …

The ability to make educated predictions about their surroundings, and associate them with
certain confidence, is important for intelligent systems, like autonomous vehicles and robots …

This paper presents a framework for learning visual representations from unlabeled video
demonstrations captured from multiple viewpoints. We show that these representations are …

The ability to apply a previously-learned skill (eg, pushing) to a new task (context or object)
is an important requirement for new-age robots. An attempt is made to solve this problem in …

Learning to accomplish complex tasks may require a tight coupling among different levels of
cognitive functions or components, like perception, acting, planning, and self-explaining …

This paper presents a framework for learning visual representations from unlabeled video
demonstrations captured from multiple viewpoints. We show that these representations are …

Abstract In Activities of Daily Living (ADLs), humans perform thousands of arm and hand
object manipulation tasks, such as picking, pouring and drinking a drink. Interpreting such …