Balancing of 3D inverted cube using reaction wheels | |
| Author | Warat Tangnararatchakit |
| Call Number | AIT Thesis no.ISE-21-08 |
| Subject(s) | Robots--Motion PID controllers--Mathematics Three-dimensional printing |
| Note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Engineering in Mechatronics |
| Publisher | Asian Institute of Technology |
| Abstract | Reinforcement learning has become a powerful tool for tackling various problems in the past few years. It is well-establish that this method can solve complex problems in many fields of study. This thesis presents an aim to explore an alternate approach to balance the inverted cube structure. To test the hypothesis that reinforcement learning can balance a cube structure on its corner using three reaction wheels as actuators. Simultaneously, the control algorithm developed traditionally using the LQR method and alternatively using reinforcement learning. Additionally, the experiment result was compared to evaluate the reinforcement base control algorithm's performance and the LQR algorithm. The result showed that reinforcement learning could find good controller gain value to balance the inverted cube on its destinated corner. These results suggested that reinforcement learning can be an alternative method to solve the balance control problem. |
| Year | 2021 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Department of Industrial Systems Engineering (DISE) |
| Academic Program/FoS | Industrial Systems Engineering (ISE) |
| Chairperson(s) | Manukid Parnichkun |
| Examination Committee(s) | Mongkol Ekpanyapong;Pisut Koomsap |
| Scholarship Donor(s) | His Majesty the King's Scholarships (Thailand) |
| Degree | Thesis (M. Eng.) - Asian Institute of Technology, 2021 |