Document Type
Conference Proceeding
Publication Date
2021
Abstract
We propose a novel data-driven procedure to train a neural network for the swing-up control of underactuated robotic systems. Our approach is inspired by several recent developments ranging from nonlinear control theory to machine learning. We embed a neural network indirectly into the equations of motion of the robotic manipulator as its control input. Using familiar results from passivity-based and energy-shaping control literature, this control function is determined by the appropriate gradients of a neural network, acting as an energy-like (Lyapunov) function. We encode the task of swinging-up robotic systems through the use of transverse coordinates and goal sets; which drastically accelerates the rate of learning by providing a concise target for the neural network. We demonstrate the efficacy of the algorithm with both numerical simulations and experiments.
Copyright Statement
This version of the article has been accepted for publication and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-030-71151-1_29
Publication Information
Sirichotiyakul, Wankun and Satici, Aykut C. (2021). "Data-Driven Design of Energy-Shaping Controllers for Swing-Up Control of Underactuated Robots". In B. Siciliano, C. Laschi, and O. Khatib (Eds.), ISER 2020: Experimental Robotics (Springer Proceedings in Advanced Robotics series, Volume 19, pp. 323-333). Springer. https://doi.org/10.1007/978-3-030-71151-1_29
Comments
ISER 2020: Experimental Robotics is volume 19 of the Springer Proceedings in Advanced Robotics book series.