This thesis will focus on how to apply Reinforcement Learning methods for solving deformable object manipulation tasks.
In this thesis, an extensive investigation of constrained DDP methods will be performed and the major selected ones will be implemented in simulation environment for trajectory optimizations of different robots such as a simple point robot, 2D car-like robot, 3D quadrotor robot and cart-pole system. In this context, the methods will be compared in terms of convergence speed, computational complexity, sensitivity to initializations and parameter selections.
This thesis will focus on proposing principled ways to increase the fidelity of cloth simulations using real-world observations from different types/sizes of cloths.
In this thesis, model predictive control-based emergency corridor building algorithms will be developed for autonomous vehicles in simulation. In this context, the thesis is expected to include varying simulated scenarios in terms of lane numbers, autonomous/human drivers amount, road types, traffic densities.
Safe Model Predictive Control (Safe MPC) aims to ensure that a physical system’s safety constraints are satisfied with high probability. Our research is on extending constrained MPC methods to cope with probabilistic safety constraints. We further research modeling uncertainty of dynamics to ensure safe exploration when combined with safety constraints learned in simulation, and learning powerful data-efficient surrogate models for complex dynamics.
Robotic tasks in real-world applications generally involve uncertain, stochastic and dynamic environments. Pre-programming based solutions either do not work or give unsatisfactory results in such environments. This requires to generate cautious control strategies that provide optimum actions to perform the desired task while considering the effects of the uncertainties in the environment. Robot control aims […]