Journal
IEEE ROBOTICS AND AUTOMATION LETTERS
Volume 6, Issue 3, Pages 4994-5001Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LRA.2021.3070305
Keywords
Learning for soft robots; calibration and identification; control; learning from experience; model learning for control; modeling
Categories
Funding
- NSF [EFRI-1830901]
- IARPA [2019-19020100001]
- DARPA [FA8750-20-C-0075]
Ask authors/readers for more resources
This method utilizes differentiable simulation and analytical hydrodynamic model for modeling and controlling underwater soft robots. By alternating between simulation and experiments with real data, it effectively reduces the simulation-to-reality gap and improves the performance of controllers in real experiments.
Underwater soft robots are challenging to model and control because of their high degrees of freedom and their intricate coupling with water. In this letter, we present a method that leverages the recent development in differentiable simulation coupled with a differentiable, analytical hydrodynamic model to assist with the modeling and control of an underwater soft robot. We apply this method to Starfish, a customized soft robot design that is easy to fabricate and intuitive to manipulate. Our method starts with data obtained from the real robot and alternates between simulation and experiments. Specifically, the simulation step uses gradients from a differentiable simulator to run system identification and trajectory optimization, and the experiment step executes the optimized trajectory on the robot to collect new data to be fed into simulation. Our demonstration on Starfish shows that proper usage of gradients from a differentiable simulator not only narrows down its simulation-to-reality gap but also improves the performance of an open-loop controller in real experiments.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available