MetaMorph: Learning Universal Controllers with Transformers

Agrim Gupta, Linxi Fan, Surya Ganguli, Li Fei-Fei

Keywords: RL, Modular Robots, Transformers

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.

One-sentence Summary: We learn a transformer based general purpose controller for a modular robot design space which can zero-shot generalize to unseen variations in dynamics, kinematics, new morphologies and tasks.

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:2203.11931/code)