DexTransfer: Real World Multi-fingered Dexterous Grasping with Minimal
Human Demonstrations
- URL: http://arxiv.org/abs/2209.14284v1
- Date: Wed, 28 Sep 2022 17:51:49 GMT
- Title: DexTransfer: Real World Multi-fingered Dexterous Grasping with Minimal
Human Demonstrations
- Authors: Zoey Qiuyu Chen, Karl Van Wyk, Yu-Wei Chao, Wei Yang, Arsalan
Mousavian, Abhishek Gupta, Dieter Fox
- Abstract summary: We propose a robot-learning system that can take a small number of human demonstrations and learn to grasp unseen object poses.
We train a dexterous grasping policy that takes the point clouds of the object as input and predicts continuous actions to grasp objects from different initial robot states.
The policy learned from our dataset can generalize well on unseen object poses in both simulation and the real world.
- Score: 51.87067543670535
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Teaching a multi-fingered dexterous robot to grasp objects in the real world
has been a challenging problem due to its high dimensional state and action
space. We propose a robot-learning system that can take a small number of human
demonstrations and learn to grasp unseen object poses given partially occluded
observations. Our system leverages a small motion capture dataset and generates
a large dataset with diverse and successful trajectories for a multi-fingered
robot gripper. By adding domain randomization, we show that our dataset
provides robust grasping trajectories that can be transferred to a policy
learner. We train a dexterous grasping policy that takes the point clouds of
the object as input and predicts continuous actions to grasp objects from
different initial robot states. We evaluate the effectiveness of our system on
a 22-DoF floating Allegro Hand in simulation and a 23-DoF Allegro robot hand
with a KUKA arm in real world. The policy learned from our dataset can
generalize well on unseen object poses in both simulation and the real world
Related papers
- Flow as the Cross-Domain Manipulation Interface [73.15952395641136]
Im2Flow2Act enables robots to acquire real-world manipulation skills without the need of real-world robot training data.
Im2Flow2Act comprises two components: a flow generation network and a flow-conditioned policy.
We demonstrate Im2Flow2Act's capabilities in a variety of real-world tasks, including the manipulation of rigid, articulated, and deformable objects.
arXiv Detail & Related papers (2024-07-21T16:15:02Z) - RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots [25.650235551519952]
We present RoboCasa, a large-scale simulation framework for training generalist robots in everyday environments.
We provide thousands of 3D assets across over 150 object categories and dozens of interactable furniture and appliances.
Our experiments show a clear scaling trend in using synthetically generated robot data for large-scale imitation learning.
arXiv Detail & Related papers (2024-06-04T17:41:31Z) - Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation [65.46610405509338]
We seek to learn a generalizable goal-conditioned policy that enables zero-shot robot manipulation.
Our framework,Track2Act predicts tracks of how points in an image should move in future time-steps based on a goal.
We show that this approach of combining scalably learned track prediction with a residual policy enables diverse generalizable robot manipulation.
arXiv Detail & Related papers (2024-05-02T17:56:55Z) - SynH2R: Synthesizing Hand-Object Motions for Learning Human-to-Robot
Handovers [37.49601724575655]
Vision-based human-to-robot handover is an important and challenging task in human-robot interaction.
We introduce a framework that can generate plausible human grasping motions suitable for training the robot.
This allows us to generate synthetic training and testing data with 100x more objects than previous work.
arXiv Detail & Related papers (2023-11-09T18:57:02Z) - Dynamic Handover: Throw and Catch with Bimanual Hands [30.206469112964033]
We design a system with two multi-finger hands attached to robot arms to solve this problem.
We train our system using Multi-Agent Reinforcement Learning in simulation and perform Sim2Real transfer to deploy on the real robots.
To overcome the Sim2Real gap, we provide multiple novel algorithm designs including learning a trajectory prediction model for the object.
arXiv Detail & Related papers (2023-09-11T17:49:25Z) - Robotic Learning the Sequence of Packing Irregular Objects from Human
Demonstrations [3.58439716487063]
We tackle the challenge of robotic bin packing with irregular objects, such as groceries.
Our approach is to learn directly from expert demonstrations in order to extract implicit task knowledge.
We rely on human demonstrations to learn a Markov chain for predicting the object packing sequence.
arXiv Detail & Related papers (2022-10-04T14:44:55Z) - FlowBot3D: Learning 3D Articulation Flow to Manipulate Articulated Objects [14.034256001448574]
We propose a vision-based system that learns to predict the potential motions of the parts of a variety of articulated objects.
We deploy an analytical motion planner based on this vector field to achieve a policy that yields maximum articulation.
Results show that our system achieves state-of-the-art performance in both simulated and real-world experiments.
arXiv Detail & Related papers (2022-05-09T15:35:33Z) - Learning Generalizable Robotic Reward Functions from "In-The-Wild" Human
Videos [59.58105314783289]
Domain-agnostic Video Discriminator (DVD) learns multitask reward functions by training a discriminator to classify whether two videos are performing the same task.
DVD can generalize by virtue of learning from a small amount of robot data with a broad dataset of human videos.
DVD can be combined with visual model predictive control to solve robotic manipulation tasks on a real WidowX200 robot in an unseen environment from a single human demo.
arXiv Detail & Related papers (2021-03-31T05:25:05Z) - Reactive Human-to-Robot Handovers of Arbitrary Objects [57.845894608577495]
We present a vision-based system that enables human-to-robot handovers of unknown objects.
Our approach combines closed-loop motion planning with real-time, temporally-consistent grasp generation.
We demonstrate the generalizability, usability, and robustness of our approach on a novel benchmark set of 26 diverse household objects.
arXiv Detail & Related papers (2020-11-17T21:52:22Z) - Learning Dexterous Grasping with Object-Centric Visual Affordances [86.49357517864937]
Dexterous robotic hands are appealing for their agility and human-like morphology.
We introduce an approach for learning dexterous grasping.
Our key idea is to embed an object-centric visual affordance model within a deep reinforcement learning loop.
arXiv Detail & Related papers (2020-09-03T04:00:40Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.