MetaMorph: Learning Universal Controllers with Transformers

• URL: http://arxiv.org/abs/2203.11931v1
• Date: Tue, 22 Mar 2022 17:58:31 GMT
• Title: MetaMorph: Learning Universal Controllers with Transformers
• Authors: Agrim Gupta, Linxi Fan, Surya Ganguli, Li Fei-Fei
• Abstract summary: In robotics we primarily train a single robot for a single task. modular robot systems now allow for the flexible combination of general-purpose building blocks into task optimized morphologies. We propose MetaMorph, a Transformer based approach to learn a universal controller over a modular robot design space.
• Score: 45.478223199658785
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multiple domains like vision, natural language, and audio are witnessing tremendous progress by leveraging Transformers for large scale pre-training followed by task specific fine tuning. In contrast, in robotics we primarily train a single robot for a single task. However, modular robot systems now allow for the flexible combination of general-purpose building blocks into task optimized morphologies. However, given the exponentially large number of possible robot morphologies, training a controller for each new design is impractical. In this work, we propose MetaMorph, a Transformer based approach to learn a universal controller over a modular robot design space. MetaMorph is based on the insight that robot morphology is just another modality on which we can condition the output of a Transformer. Through extensive experiments we demonstrate that large scale pre-training on a variety of robot morphologies results in policies with combinatorial generalization capabilities, including zero shot generalization to unseen robot morphologies. We further demonstrate that our pre-trained policy can be used for sample-efficient transfer to completely new robot morphologies and tasks.

Related papers

• One Policy to Run Them All: an End-to-end Learning Approach to Multi-Embodiment Locomotion [18.556470359899855]
  We introduce URMA, the Unified Robot Morphology Architecture. Our framework brings the end-to-end Multi-Task Reinforcement Learning approach to the realm of legged robots. We show that URMA can learn a locomotion policy on multiple embodiments that can be easily transferred to unseen robot platforms.
  arXiv  Detail & Related papers  (2024-09-10T09:44:15Z)
• Body Transformer: Leveraging Robot Embodiment for Policy Learning [51.531793239586165]
  Body Transformer (BoT) is an architecture that leverages the robot embodiment by providing an inductive bias that guides the learning process. We represent the robot body as a graph of sensors and actuators, and rely on masked attention to pool information throughout the architecture. The resulting architecture outperforms the vanilla transformer, as well as the classical multilayer perceptron, in terms of task completion, scaling properties, and computational efficiency.
  arXiv  Detail & Related papers  (2024-08-12T17:31:28Z)
• RoboMorph: Evolving Robot Morphology using Large Language Models [0.5812095716568273]
  We introduce RoboMorph, an automated approach for generating and optimizing modular robot designs. By integrating automatic prompt design and a reinforcement learning based control algorithm, RoboMorph iteratively improves robot designs through feedback loops.
  arXiv  Detail & Related papers  (2024-07-11T16:05:56Z)
• RoboScript: Code Generation for Free-Form Manipulation Tasks across Real and Simulation [77.41969287400977]
  This paper presents textbfRobotScript, a platform for a deployable robot manipulation pipeline powered by code generation. We also present a benchmark for a code generation benchmark for robot manipulation tasks in free-form natural language. We demonstrate the adaptability of our code generation framework across multiple robot embodiments, including the Franka and UR5 robot arms.
  arXiv  Detail & Related papers  (2024-02-22T15:12:00Z)
• DittoGym: Learning to Control Soft Shape-Shifting Robots [30.287452037945542]
  We explore the novel reconfigurable robots, defined as robots that can change their morphology within their lifetime. We formalize control of reconfigurable soft robots as a high-dimensional reinforcement learning (RL) problem. We introduce DittoGym, a comprehensive RL benchmark for reconfigurable soft robots that require fine-grained morphology changes.
  arXiv  Detail & Related papers  (2024-01-24T05:03:05Z)
• RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation [33.10577695383743]
  We propose a multi-embodiment, multi-task generalist agent for robotic manipulation called RoboCat. This data spans a large repertoire of motor control skills from simulated and real robotic arms with varying sets of observations and actions. With RoboCat, we demonstrate the ability to generalise to new tasks and robots, both zero-shot as well as through adaptation using only 100-1000 examples.
  arXiv  Detail & Related papers  (2023-06-20T17:35:20Z)
• Universal Morphology Control via Contextual Modulation [52.742056836818136]
  Learning a universal policy across different robot morphologies can significantly improve learning efficiency and generalization in continuous control. Existing methods utilize graph neural networks or transformers to handle heterogeneous state and action spaces across different morphologies. We propose a hierarchical architecture to better model this dependency via contextual modulation.
  arXiv  Detail & Related papers  (2023-02-22T00:04:12Z)
• GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots [87.32145104894754]
  We introduce a framework for training generalized locomotion (GenLoco) controllers for quadrupedal robots. Our framework synthesizes general-purpose locomotion controllers that can be deployed on a large variety of quadrupedal robots. We show that our models acquire more general control strategies that can be directly transferred to novel simulated and real-world robots.
  arXiv  Detail & Related papers  (2022-09-12T15:14:32Z)
• REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer [57.045140028275036]
  We consider the problem of transferring a policy across two different robots with significantly different parameters such as kinematics and morphology. Existing approaches that train a new policy by matching the action or state transition distribution, including imitation learning methods, fail due to optimal action and/or state distribution being mismatched in different robots. We propose a novel method named $REvolveR$ of using continuous evolutionary models for robotic policy transfer implemented in a physics simulator.
  arXiv  Detail & Related papers  (2022-02-10T18:50:25Z)

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.