TY - GEN
T1 - A Recurrent Differentiable Engine for Modeling Tensegrity Robots Trainable with Low-Frequency Data
AU - Wang, Kun
AU - Aanjaneya, Mridul
AU - Bekris, Kostas
N1 - Funding Information:
The authors are with the Department of Computer Science, Rutgers University, NJ 08901, USA. Email: kun.wang2012, mridul.aanjaneya, kostas.bekris@rutgers.edu. This work has been partially supported by NSF award IIS 1956027, IIS-2132972, CCF-2110861 and the Rutgers University startup grant.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Tensegrity robots, composed of rigid rods and flexible cables, are difficult to accurately model and control given the presence of complex dynamics and high number of DoFs. Differentiable physics engines have been recently proposed as a data-driven approach for model identification of such complex robotic systems. These engines are often executed at a high-frequency to achieve accurate simulation. Ground truth trajectories for training differentiable engines, however, are not typically available at such high frequencies due to limitations of real-world sensors. The present work focuses on this frequency mismatch, which impacts the modeling accuracy. We proposed a recurrent structure for a differentiable physics engine of tensegrity robots, which can be trained effectively even with low-frequency trajectories. To train this new recurrent engine in a robust way, this work introduces relative to prior work: (i) a new implicit integration scheme, (ii) a progressive training pipeline, and (iii) a differentiable collision checker. A model of NASA's icosahedron SUPERballBot on MuJoCo is used as the ground truth system to collect training data. Simulated experiments show that once the recurrent differentiable engine has been trained given the low-frequency trajectories from MuJoCo, it is able to match the behavior of MuJoCo's system. The criterion for success is whether a locomotion strategy learned using the differentiable engine can be transferred back to the ground-truth system and result in a similar motion. Notably, the amount of ground truth data needed to train the differentiable engine, such that the policy is transferable to the ground truth system, is 1% of the data needed to train the policy directly on the ground-truth system.
AB - Tensegrity robots, composed of rigid rods and flexible cables, are difficult to accurately model and control given the presence of complex dynamics and high number of DoFs. Differentiable physics engines have been recently proposed as a data-driven approach for model identification of such complex robotic systems. These engines are often executed at a high-frequency to achieve accurate simulation. Ground truth trajectories for training differentiable engines, however, are not typically available at such high frequencies due to limitations of real-world sensors. The present work focuses on this frequency mismatch, which impacts the modeling accuracy. We proposed a recurrent structure for a differentiable physics engine of tensegrity robots, which can be trained effectively even with low-frequency trajectories. To train this new recurrent engine in a robust way, this work introduces relative to prior work: (i) a new implicit integration scheme, (ii) a progressive training pipeline, and (iii) a differentiable collision checker. A model of NASA's icosahedron SUPERballBot on MuJoCo is used as the ground truth system to collect training data. Simulated experiments show that once the recurrent differentiable engine has been trained given the low-frequency trajectories from MuJoCo, it is able to match the behavior of MuJoCo's system. The criterion for success is whether a locomotion strategy learned using the differentiable engine can be transferred back to the ground-truth system and result in a similar motion. Notably, the amount of ground truth data needed to train the differentiable engine, such that the policy is transferable to the ground truth system, is 1% of the data needed to train the policy directly on the ground-truth system.
UR - http://www.scopus.com/inward/record.url?scp=85131658560&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85131658560&partnerID=8YFLogxK
U2 - 10.1109/ICRA46639.2022.9812135
DO - 10.1109/ICRA46639.2022.9812135
M3 - Conference contribution
AN - SCOPUS:85131658560
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 3230
EP - 3237
BT - 2022 IEEE International Conference on Robotics and Automation, ICRA 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 39th IEEE International Conference on Robotics and Automation, ICRA 2022
Y2 - 23 May 2022 through 27 May 2022
ER -