Maniskill2: A unified benchmark for generalizable manipulation skills
Generalizable manipulation skills, which can be composed to tackle long-horizon and
complex daily chores, are one of the cornerstones of Embodied AI. However, existing …
complex daily chores, are one of the cornerstones of Embodied AI. However, existing …
Dynamic visual reasoning by learning differentiable physics models from video and language
In this work, we propose a unified framework, called Visual Reasoning with Differ-entiable
Physics (VRDP), that can jointly learn visual concepts and infer physics models of objects …
Physics (VRDP), that can jointly learn visual concepts and infer physics models of objects …
Global planning for contact-rich manipulation via local smoothing of quasi-dynamic contact models
The empirical success of reinforcement learning (RL) in contact-rich manipulation leaves
much to be understood from a model-based perspective, where the key difficulties are often …
much to be understood from a model-based perspective, where the key difficulties are often …
RoboCraft: Learning to see, simulate, and shape elasto-plastic objects in 3D with graph networks
Modeling and manipulating elasto-plastic objects are essential capabilities for robots to
perform complex industrial and household interaction tasks (eg, stuffing dumplings, rolling …
perform complex industrial and household interaction tasks (eg, stuffing dumplings, rolling …
Robocook: Long-horizon elasto-plastic object manipulation with diverse tools
Humans excel in complex long-horizon soft body manipulation tasks via flexible tool use:
bread baking requires a knife to slice the dough and a rolling pin to flatten it. Often regarded …
bread baking requires a knife to slice the dough and a rolling pin to flatten it. Often regarded …
Accelerated policy learning with parallel differentiable simulation
Deep reinforcement learning can generate complex control policies, but requires large
amounts of training data to work effectively. Recent work has attempted to address this issue …
amounts of training data to work effectively. Recent work has attempted to address this issue …
An end-to-end differentiable framework for contact-aware robot design
The current dominant paradigm for robotic manipulation involves two separate stages:
manipulator design and control. Because the robot's morphology and how it can be …
manipulator design and control. Because the robot's morphology and how it can be …
Learning neural constitutive laws from motion observations for generalizable pde dynamics
We propose a hybrid neural network (NN) and PDE approach for learning generalizable
PDE dynamics from motion observations. Many NN approaches learn an end-to-end model …
PDE dynamics from motion observations. Many NN approaches learn an end-to-end model …
Pac-nerf: Physics augmented continuum neural radiance fields for geometry-agnostic system identification
Existing approaches to system identification (estimating the physical parameters of an
object) from videos assume known object geometries. This precludes their applicability in a …
object) from videos assume known object geometries. This precludes their applicability in a …
Learning foresightful dense visual affordance for deformable object manipulation
Understanding and manipulating deformable objects (eg, ropes and fabrics) is an essential
yet challenging task with broad applications. Difficulties come from complex states and …
yet challenging task with broad applications. Difficulties come from complex states and …