This paper provides a structured and practical roadmap for practitioners to integrate learning
from demonstration (LfD) into manufacturing tasks, with a specific focus on industrial …

Differentiable simulators continue to push the state of the art across a range of domains
including computational physics, robotics, and machine learning. Their main value is the …

Learning 3D human-object interaction relation is pivotal to embodied AI and interaction
modeling. Most existing methods approach the goal by learning to predict isolated …

In this work, we aim to learn a unified vision-based policy for multi-fingered robot hands to
manipulate a variety of objects in diverse poses. Though prior work has shown benefits of …

We present Jade, a differentiable physics engine for articulated rigid bodies. Jade models
contacts as the Linear Complementarity Problem (LCP). Compared to existing differentiable …

Recent rapid developments of dexterous robotic hands have greatly enhanced the
manipulative capabilities of robots, enabling them to perform industrial tasks in human-like …

We present an approach to learn general robot manipulation priors from 3D hand-object
interaction trajectories. We build a framework to use in-the-wild videos to generate …

Automating the assembly of objects from their parts is a complex problem with innumerable
applications in manufacturing, maintenance, and recycling. Unlike existing research, which …

The tie-knotting task is highly challenging due to the tie's high deformation and long-horizon
manipulation actions. This work presents TieBot, a Real-to-Sim-to-Real learning from visual …

Differentiable physics simulation provides an avenue to tackle previously intractable
challenges through gradient-based optimization, thereby greatly improving the efficiency of …