Embodiment Transfer Learning for Vision-Language-Action Models

TL;DR

This paper introduces ET-VLA, a transfer learning framework for vision-language-action models that uses synthetic data pretraining and graph-based task modeling to improve multi-robot collaboration, validated on real robots.

Contribution

The paper proposes a novel embodiment transfer learning framework with Synthetic Continued Pretraining and a Graph-of-Thought technique for multi-robot VLA models, reducing data needs and enhancing performance.

Findings

ET-VLA outperforms OpenVLA by over 53% on real-world tasks.

Synthetic pretraining enables effective transfer without real demonstrations.

The approach improves multi-robot collaboration in simulation and real robots.

Abstract

Vision-language-action (VLA) models have significantly advanced robotic learning, enabling training on large-scale, cross-embodiment data and fine-tuning for specific robots. However, state-of-the-art autoregressive VLAs struggle with multi-robot collaboration. We introduce embodiment transfer learning, denoted as ET-VLA, a novel framework for efficient and effective transfer of pre-trained VLAs to multi-robot. ET-VLA's core is Synthetic Continued Pretraining (SCP), which uses synthetically generated data to warm up the model for the new embodiment, bypassing the need for real human demonstrations and reducing data collection costs. SCP enables the model to learn correct actions and precise action token numbers. Following SCP, the model is fine-tuned on target embodiment data. To further enhance the model performance on multi-embodiment, we present the Embodied Graph-of-Thought technique, a novel approach that formulates each sub-task as a node, that allows the VLA model to distinguish the functionalities and roles of each embodiment during task execution. Our work considers bimanual robots, a simple version of multi-robot to verify our approaches. We validate the effectiveness of our method on both simulation benchmarks and real robots covering three different bimanual embodiments. In particular, our proposed ET-VLA \space can outperform OpenVLA on six real-world tasks over 53.2%. We will open-source all codes to support the community in advancing VLA models for robot learning.