The base paper deals with an intelligent human-robot interaction system. The problem of finding the optimal parameters of the model is transformed into an LQR problem which minimizes the human effort and optimizes the closed-loop behavior. As the human model is difficult to estimate, Reinforcement learning is used in the paper to solve the LQR problem. The plan for the project consisted of two tasks.
- The first part was the application of integral reinforcement learning
- the second part was using a neural network to find the optimal solution for LQR.