An “ensemble” approach to decision-making involves aggregating the results from different
decision makers solving the same problem (ie, a division of labor without specialization). We …

In contact-rich tasks, like dexterous manipulation, the hybrid nature of making and breaking
contact creates challenges for model representation and control. For example, choosing and …

This paper investigates the learning, or system identification, of a class of piecewise-affine
dynamical systems known as linear complementarity systems (LCSs). We propose a …

Robotic manipulation can greatly benefit from the data efficiency, robustness, and
predictability of model-based methods if robots can quickly generate models of novel objects …

In contact-rich tasks, the hybrid, multi-modal nature of contact dynamics poses great
challenges in model representation, planning, and control. Recent efforts have attempted to …

The hybrid nature of multi-contact robotic systems, due to making and breaking contact with
the environment, creates significant challenges for high-quality control. Existing model …

Imperfect, useful dynamical models have enabled significant progress in planning and
controlling robotic locomotion and manipulation. Traditionally, these models have been …

It is well-known that a neural network learning process—along with its connections to fitting,
compression, and generalization—is not yet well understood. In this paper, we propose a …

One key area of research in Human-Robot Interaction is solving the human-robot
correspondence problem, which asks how a robot can learn to reproduce a human motion …

We present a new class of structured reinforcement learning policy-architectures, Implicit
Two-Tower (ITT) policies, where the actions are chosen based on the attention scores of …