Multi-embodiment Legged Robot Control as a Sequence Modeling Problem

by   Chen Yu, et al.

Robots are traditionally bounded by a fixed embodiment during their operational lifetime, which limits their ability to adapt to their surroundings. Co-optimizing control and morphology of a robot, however, is often inefficient due to the complex interplay between the controller and morphology. In this paper, we propose a learning-based control method that can inherently take morphology into consideration such that once the control policy is trained in the simulator, it can be easily deployed to robots with different embodiments in the real world. In particular, we present the Embodiment-aware Transformer (EAT), an architecture that casts this control problem as conditional sequence modeling. EAT outputs the optimal actions by leveraging a causally masked Transformer. By conditioning an autoregressive model on the desired robot embodiment, past states, and actions, our EAT model can generate future actions that best fit the current robot embodiment. Experimental results show that EAT can outperform all other alternatives in embodiment-varying tasks, and succeed in an example of real-world evolution tasks: stepping down a stair through updating the morphology alone. We hope that EAT will inspire a new push toward real-world evolution across many domains, where algorithms like EAT can blaze a trail by bridging the field of evolutionary robotics and big data sequence modeling.


page 1

page 3

page 4

page 5

page 6


Real-World Evolution Adapts Robot Morphology and Control to Hardware Limitations

For robots to handle the numerous factors that can affect them in the re...

Environmental Adaptation of Robot Morphology and Control through Real-world Evolution

Robots operating in the real world will experience a range of different ...

Universal Morphology Control via Contextual Modulation

Learning a universal policy across different robot morphologies can sign...

Scalable Co-Optimization of Morphology and Control in Embodied Machines

Evolution sculpts both the body plans and nervous systems of agents toge...

Lessons Learned from Real-World Experiments with DyRET: the Dynamic Robot for Embodied Testing

Robots are used in more and more complex environments, and are expected ...

Controlling Robot Morphology from Incomplete Measurements

Mobile robots with complex morphology are essential for traversing rough...

REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer

A popular paradigm in robotic learning is to train a policy from scratch...

Please sign up or login with your details

Forgot password? Click here to reset