GET-Zero: Graph Embodiment Transformer for Zero-shot Embodiment Generalization

This paper introduces GET-Zero, a model architecture and training procedure for learning an embodiment-aware control policy that can immediately adapt to new hardware changes without retraining.

To do so, we present Graph Embodiment Transformer (GET), a transformer model that leverages the embodiment graph connectivity as a learned structural bias in the attention mechanism.

We use behavior cloning to distill demonstration data from embodiment-specific expert policies into an embodiment-aware GET model that conditions on the hardware configuration of the robot to make control decisions.

We conduct a case study on a dexterous in-hand object rotation task using different configurations of a four-fingered robot hand with joints removed and with link length extensions.

Using the GET model along with a self-modeling loss enables GET-Zero to zero-shot generalize to unseen variation in graph structure and link length, yielding a 20% improvement over baseline methods.

All code and qualitative video results are on https://get-zero-paper.github.io ;Comment: 8 pages, 5 figures, 3 tables, website https://get-zero-paper.github.io