Learning to Transfer Dynamic Models of Underactuated Soft Robotic Hands

TL;DR

This paper explores transfer learning for dynamic models of underactuated soft robotic hands, identifying issues with fine-tuning and proposing methods to improve transfer performance based on model stability insights.

Contribution

It introduces a stability-based approach to transfer learning in robotic dynamics, addressing divergence issues in small data regimes and demonstrating improved transfer methods.

Findings

Transfer learning can significantly reduce data needs in soft robotics.

Traditional fine-tuning may worsen model performance due to chaotic behavior.

Proposed methods improve transfer accuracy and stability in experiments.

Abstract

Transfer learning is a popular approach to bypassing data limitations in one domain by leveraging data from another domain. This is especially useful in robotics, as it allows practitioners to reduce data collection with physical robots, which can be time-consuming and cause wear and tear. The most common way of doing this with neural networks is to take an existing neural network, and simply train it more with new data. However, we show that in some situations this can lead to significantly worse performance than simply using the transferred model without adaptation. We find that a major cause of these problems is that models trained on small amounts of data can have chaotic or divergent behavior in some regions. We derive an upper bound on the Lyapunov exponent of a trained transition model, and demonstrate two approaches that make use of this insight. Both show significant improvement over traditional fine-tuning. Experiments performed on real underactuated soft robotic hands clearly demonstrate the capability to transfer a dynamic model from one hand to another.