Search Results for author:
Found 23 papers, 11 papers with code
DiffVL: Scaling Up Soft Body Manipulation using Vision-Language Driven Differentiable Physics
Combining gradient-based trajectory optimization with differentiable physics simulation is an efficient technique for solving soft-body manipulation problems.
Robo360: A 3D Omnispective Multi-Material Robotic Manipulation Dataset
Building robots that can automate labor-intensive tasks has long been the core motivation behind the advancements in computer vision and the robotics community.
Reparameterized Policy Learning for Multimodal Trajectory Optimization
We then present a practical model-based RL method, called Reparameterized Policy Gradient (RPG), which leverages the multimodal policy parameterization and learned world model to achieve strong exploration capabilities and high data efficiency.
Deductive Verification of Chain-of-Thought Reasoning
In light of this, we propose to decompose a reasoning verification process into a series of step-by-step subprocesses, each only receiving their necessary context and premises.
Chain-of-Thought Predictive Control
We study generalizable policy learning from demonstrations for complex low-level control tasks (e. g., contact-rich object manipulations).
DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physics
Reinforcement learning approaches for dexterous rigid object manipulation would struggle in this setting due to the complexity of physics interaction with deformable objects.
MovingParts: Motion-based 3D Part Discovery in Dynamic Radiance Field
Under the Lagrangian view, we parameterize the scene motion by tracking the trajectory of particles on objects.
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.
Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulation
Effective planning of long-horizon deformable object manipulation requires suitable abstractions at both the spatial and temporal levels.
Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization
In the abstract environment, complex dynamics such as physical manipulation are removed, making abstract trajectories easier to generate.
RoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects with Graph Networks
Our learned model-based planning framework is comparable to and sometimes better than human subjects on the tested tasks.
Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics
Extensive experimental results suggest that: 1) on multi-stage tasks that are infeasible for the vanilla differentiable physics solver, our approach discovers contact points that efficiently guide the solver to completion; 2) on tasks where the vanilla solver performs sub-optimally or near-optimally, our contact point discovery method performs better than or on par with the manipulation performance obtained with handcrafted contact points.
DiffSkill: Skill Abstraction from Differentiable Physics for Deformable Object Manipulations with Tools
We consider the problem of sequential robotic manipulation of deformable objects using tools.
Learning Multi-Object Dynamics with Compositional Neural Radiance Fields
We present a method to learn compositional multi-object dynamics models from image observations based on implicit object encoders, Neural Radiance Fields (NeRFs), and graph neural networks.
ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations
Here we propose SAPIEN Manipulation Skill Benchmark (ManiSkill) to benchmark manipulation skills over diverse objects in a full-physics simulator.
PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics
Experimental results suggest that 1) RL-based approaches struggle to solve most of the tasks efficiently; 2) gradient-based approaches, by optimizing open-loop control sequences with the built-in differentiable physics engine, can rapidly find a solution within tens of iterations, but still fall short on multi-stage tasks that require long-term planning.
Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous GNNs
Current graph neural networks (GNNs) lack generalizability with respect to scales (graph sizes, graph diameters, edge weights, etc..) when solving many graph analysis problems.
Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous Graph Neural Networks
Current graph neural networks (GNNs) lack generalizability with respect to scales (graph sizes, graph diameters, edge weights, etc..) when solving many graph analysis problems.
Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories
We address the problem of discovering 3D parts for objects in unseen categories.
Mapping State Space using Landmarks for Universal Goal Reaching
An agent that has well understood the environment should be able to apply its skills for any given goals, leading to the fundamental problem of learning the Universal Value Function Approximator (UVFA).
Object-Oriented Dynamics Predictor
Generalization has been one of the major challenges for learning dynamics models in model-based reinforcement learning.
Associative Embedding: End-to-End Learning for Joint Detection and Grouping
We introduce associative embedding, a novel method for supervising convolutional neural networks for the task of detection and grouping.
Ranked #5 on
Keypoint Detection
on OCHuman
Coarse-to-fine Face Alignment with Multi-Scale Local Patch Regression
Facial landmark localization plays an important role in face recognition and analysis applications.
