Transfer learning is a conceptually-enticing paradigm in pursuit of truly intelligent embodied
agents. The core concept—reusing prior knowledge to learn in and from novel situations—is …

We study the problem of learning graph dynamics of deformable objects that generalizes to
unknown physical properties. Our key insight is to leverage a latent representation of elastic …

We present a virtual reality (VR) framework to automate the data collection process in cloth
folding tasks. The framework uses skeleton representations to help the user define the …

Kinodynamic motion planners allow robots to perform complex manipulation tasks under
dynamics constraints or with black-box models. However, they struggle to find high-quality …

In robotic deformable object manipulation (DOM) applications, constraints arise commonly
from environments and task-specific requirements. Enabling DOM with constraints is …

The robotic manipulation of deformable linear objects is a frontier problem with many
potential applications in diverse industries. However, most existing research in this area …

Visual action planning particularly excels in applications where the state of the system
cannot be computed explicitly, such as manipulation of deformable objects, as it enables …

Learning state representations enables robotic planning directly from raw observations such
as images. Several methods learn state representations by utilizing losses based on the …

Classical policy search algorithms for robotics typically require performing extensive
explorations, which are time-consuming and expensive to implement with real physical …

Robotic manipulation relies on analytical or learned models to simulate the system
dynamics. These models are often inaccurate and based on offline information, so that the …