Learning Generalizable Tool Use with Non-rigid Grasp-pose Registration
- URL: http://arxiv.org/abs/2307.16499v2
- Date: Tue, 1 Aug 2023 16:54:23 GMT
- Title: Learning Generalizable Tool Use with Non-rigid Grasp-pose Registration
- Authors: Malte Mosbach and Sven Behnke
- Abstract summary: We present a novel method to enable reinforcement learning of tool use behaviors.
Our approach provides a scalable way to learn the operation of tools in a new category using only a single demonstration.
The learned policies solve complex tool use tasks and generalize to unseen tools at test time.
- Score: 29.998917158604694
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Tool use, a hallmark feature of human intelligence, remains a challenging
problem in robotics due the complex contacts and high-dimensional action space.
In this work, we present a novel method to enable reinforcement learning of
tool use behaviors. Our approach provides a scalable way to learn the operation
of tools in a new category using only a single demonstration. To this end, we
propose a new method for generalizing grasping configurations of multi-fingered
robotic hands to novel objects. This is used to guide the policy search via
favorable initializations and a shaped reward signal. The learned policies
solve complex tool use tasks and generalize to unseen tools at test time.
Visualizations and videos of the trained policies are available at
https://maltemosbach.github.io/generalizable_tool_use.
Related papers
- Dreamitate: Real-World Visuomotor Policy Learning via Video Generation [49.03287909942888]
We propose a visuomotor policy learning framework that fine-tunes a video diffusion model on human demonstrations of a given task.
We generate an example of an execution of the task conditioned on images of a novel scene, and use this synthesized execution directly to control the robot.
arXiv Detail & Related papers (2024-06-24T17:59:45Z) - Learning Reusable Manipulation Strategies [86.07442931141634]
Humans demonstrate an impressive ability to acquire and generalize manipulation "tricks"
We present a framework that enables machines to acquire such manipulation skills through a single demonstration and self-play.
These learned mechanisms and samplers can be seamlessly integrated into standard task and motion planners.
arXiv Detail & Related papers (2023-11-06T17:35:42Z) - Learning to Design and Use Tools for Robotic Manipulation [21.18538869008642]
Recent techniques for jointly optimizing morphology and control via deep learning are effective at designing locomotion agents.
We propose learning a designer policy, rather than a single design.
We show that this framework is more sample efficient than prior methods in multi-goal or multi-variant settings.
arXiv Detail & Related papers (2023-11-01T18:00:10Z) - Learning Generalizable Tool-use Skills through Trajectory Generation [13.879860388944214]
We train a single model on four different deformable object manipulation tasks.
The model generalizes to various novel tools, significantly outperforming baselines.
We further test our trained policy in the real world with unseen tools, where it achieves the performance comparable to human.
arXiv Detail & Related papers (2023-09-29T21:32:42Z) - Silver-Bullet-3D at ManiSkill 2021: Learning-from-Demonstrations and
Heuristic Rule-based Methods for Object Manipulation [118.27432851053335]
This paper presents an overview and comparative analysis of our systems designed for the following two tracks in SAPIEN ManiSkill Challenge 2021: No Interaction Track.
The No Interaction track targets for learning policies from pre-collected demonstration trajectories.
In this track, we design a Heuristic Rule-based Method (HRM) to trigger high-quality object manipulation by decomposing the task into a series of sub-tasks.
For each sub-task, the simple rule-based controlling strategies are adopted to predict actions that can be applied to robotic arms.
arXiv Detail & Related papers (2022-06-13T16:20:42Z) - Learning Generalizable Dexterous Manipulation from Human Grasp
Affordance [11.060931225148936]
Dexterous manipulation with a multi-finger hand is one of the most challenging problems in robotics.
Recent progress in imitation learning has largely improved the sample efficiency compared to Reinforcement Learning.
We propose to learn dexterous manipulation using large-scale demonstrations with diverse 3D objects in a category.
arXiv Detail & Related papers (2022-04-05T16:26:22Z) - Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task
Learning [108.08083976908195]
We show that policies learned by existing reinforcement learning algorithms can in fact be generalist.
We show that a single generalist policy can perform in-hand manipulation of over 100 geometrically-diverse real-world objects.
Interestingly, we find that multi-task learning with object point cloud representations not only generalizes better but even outperforms single-object specialist policies.
arXiv Detail & Related papers (2021-11-04T17:59:56Z) - TANGO: Commonsense Generalization in Predicting Tool Interactions for
Mobile Manipulators [15.61285199988595]
We introduce TANGO, a novel neural model for predicting task-specific tool interactions.
TANGO encodes the world state comprising of objects and symbolic relationships between them using a graph neural network.
We show that by augmenting the representation of the environment with pre-trained embeddings derived from a knowledge-base, the model can generalize effectively to novel environments.
arXiv Detail & Related papers (2021-05-05T18:11:57Z) - 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) - Visual Imitation Made Easy [102.36509665008732]
We present an alternate interface for imitation that simplifies the data collection process while allowing for easy transfer to robots.
We use commercially available reacher-grabber assistive tools both as a data collection device and as the robot's end-effector.
We experimentally evaluate on two challenging tasks: non-prehensile pushing and prehensile stacking, with 1000 diverse demonstrations for each task.
arXiv Detail & Related papers (2020-08-11T17:58:50Z)
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.