Differentiable visual computing for inverse problems and machine learning
A Spielberg, F Zhong, K Rematas… - Nature Machine …, 2023 - nature.com
Modern 3D computer graphics technologies are able to reproduce the dynamics and
appearance of real-world environments and phenomena, building on theoretical models in …
appearance of real-world environments and phenomena, building on theoretical models in …
A survey on physics informed reinforcement learning: Review and open problems
The inclusion of physical information in machine learning frameworks has revolutionized
many application areas. This involves enhancing the learning process by incorporating …
many application areas. This involves enhancing the learning process by incorporating …
Ppr: Physically plausible reconstruction from monocular videos
Given monocular videos, we build 3D models of articulated objects and environments
whose 3D configurations satisfy dynamics and contact constraints. At its core, our method …
whose 3D configurations satisfy dynamics and contact constraints. At its core, our method …
Grasp'd: Differentiable contact-rich grasp synthesis for multi-fingered hands
The study of hand-object interaction requires generating viable grasp poses for high-
dimensional multi-finger models, often relying on analytic grasp synthesis which tends to …
dimensional multi-finger models, often relying on analytic grasp synthesis which tends to …
Neuphysics: Editable neural geometry and physics from monocular videos
We present a method for learning 3D geometry and physics parameters of a dynamic scene
from only a monocular RGB video input. To decouple the learning of underlying scene …
from only a monocular RGB video input. To decouple the learning of underlying scene …
Efficient tactile simulation with differentiability for robotic manipulation
Efficient simulation of tactile sensors can unlock new opportunities for learning tactile-based
manipulation policies in simulation and then transferring the learned policy to real systems …
manipulation policies in simulation and then transferring the learned policy to real systems …
Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation
Abstract This paper introduces Hierarchical Diffusion Policy (HDP) a hierarchical agent for
multi-task robotic manipulation. HDP factorises a manipulation policy into a hierarchical …
multi-task robotic manipulation. HDP factorises a manipulation policy into a hierarchical …
Fluidlab: A differentiable environment for benchmarking complex fluid manipulation
Humans manipulate various kinds of fluids in their everyday life: creating latte art, scooping
floating objects from water, rolling an ice cream cone, etc. Using robots to augment or …
floating objects from water, rolling an ice cream cone, etc. Using robots to augment or …
Acting as inverse inverse planning
Great storytellers know how to take us on a journey. They direct characters to act—not
necessarily in the most rational way—but rather in a way that leads to interesting situations …
necessarily in the most rational way—but rather in a way that leads to interesting situations …
Roboninja: Learning an adaptive cutting policy for multi-material objects
We introduce RoboNinja, a learning-based cutting system for multi-material objects (ie, soft
objects with rigid cores such as avocados or mangos). In contrast to prior works using open …
objects with rigid cores such as avocados or mangos). In contrast to prior works using open …