TY - GEN
T1 - Learning to Transfer Dynamic Models of Underactuated Soft Robotic Hands
AU - Schramm, Liam
AU - Sintov, Avishai
AU - Boularias, Abdeslam
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/5/1
Y1 - 2020/5/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85092692302&partnerID=8YFLogxK
U2 - 10.1109/ICRA40945.2020.9197300
DO - 10.1109/ICRA40945.2020.9197300
M3 - Conference contribution
AN - SCOPUS:85092692302
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 4579
EP - 4585
BT - 2020 IEEE International Conference on Robotics and Automation, ICRA 2020
PB - Institute of Electrical and Electronics Engineers
T2 - 2020 IEEE International Conference on Robotics and Automation, ICRA 2020
Y2 - 31 May 2020 through 31 August 2020
ER -