PhD Defense: Sardor Israilov

  • Research
Published on January 24, 2024 Updated on January 24, 2024

on the January 30, 2024

Institut de Physique de Nice
Salle des séminaires

From learning-based identification to model-based control of robotic systems

Fish swimming remains a complex subject that is not yet fully understood due to the intersection of biology and fluid dynamics. Through years of evolution, organisms in nature have perfected their biological mechanisms to navigate efficiently in their environment and adapt to particular situations. Throughout history, mankind has been inspired by nature to innovate and develop nature-like systems. Biomimetic robotic fish, in particular, has a number of applications in the real world and its control is yet to be optimized. Deep Reinforcement Learning showed  excellent results in control of robotic systems, where dynamics is too complex to be fully modeled and analyzed. In this thesis, we explored new venues of control of a biomimetic fish via reinforcement learning to effectively maximize the thrust and speed. However, to fully comprehend the newly-emerged data-based algorithms, we first studied the  application of these methods on a standard benchmark of a control theory, the inverted pendulum with a cart. We demonstrated that deep Reinforcement Learning could control the system without any prior knowledge of the system, achieving performance comparable to traditional model-based control theory methods. In the third chapter, we focus on the undulatory swimming of a robotic fish, exploring various objectives and information sources for control. Our studies indicate that the thrust force of a robotic fish can be optimized using inputs from both force sensors and cameras as feedback for control. Our findings demonstrate that a square wave control with a particular frequency maximizes the thrust and we rationalize it using Pontryagin Maximum Principle. An appropriate model is established that shows an excellent  agreement between simulation and experimental results. Subsequently, we concentrate on the speed maximization of a robotic fish both in several  virtual environments and experiments using visual data. Once again, we find that deep Reinforcement Learning can find an excellent swimming gait with a square wave control that maximizes the swimming speed.