In nonlinear tracking control, relevant to robotic applications, the knowledge on the system model may be not available and there is current need in model-free approaches to track a desired trajectory, regular or chaotic. The authors introduce here a framework that employs machine learning to control a two-arm robotic manipulator using only partially observed states.
- Zheng-Meng Zhai
- Mohammadamin Moradi
- Ying-Cheng Lai
