Abstract
The ability to remotely control a free-floating object through surface flows on a fluid medium can facilitate numerous applications. Current studies on this problem have been limited to uni-directional motion control due to the challenging nature of the control problem. Analytical modelling of the object dynamics is difficult due to the high-dimensionality and mixing of the surface flows while the control problem is hard due to the nonlinear slow dynamics of the fluid medium, underactuation, and chaotic regions. This study presents a methodology for manipulation of free-floating objects using large-scale physical experimentation and recent advances in deep reinforcement learning. We demonstrate our methodology through the open-loop control of a free-floating object in water using a robotic arm. Our learned control policy is relatively quick to obtain, highly data efficient, and easily scalable to a higher-dimensional parameter space and/or experimental scenarios. Our results show the potential of data-driven approaches for solving and analyzing highly complex nonlinear control problems.
Highlights
The ability to remotely control a free-floating object through surface flows on a fluid medium can facilitate numerous applications
This trade-off between unrepeatabilities of the trajectory and the target angles is observed with the deep deterministic policy gradient (DDPG) controller, implying that this is a fundamental limitation of the system itself
This study shows that deep learning techniques combined with large scale robotic experimentation can be used to develop effective controllers in the face of nonlinearities, non-convexity, and environmental stochasticity
Summary
The ability to remotely control a free-floating object through surface flows on a fluid medium can facilitate numerous applications. Current studies on this problem have been limited to uni-directional motion control due to the challenging nature of the control problem. The control objective is to generate surface flows on the fluid surface by parametrically excited high-dimensional local wave sources These create two-dimensional horizontal velocity fields at the surface, known as Faraday flows, that have attributes of two-dimensional turbulence; characterised by surface vortices and local Lagrangian coherent s tructures[4,9,10,11]. This work extends the state-of-the-art to the two-dimensional control of a floating object in water driven by multi-periodic wave sources using recent advances in deep reinforcement learning (DRL). An electromagnet is used to reset the object to a new starting position—see Experimental Setup and Supplementary Video 1
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
