Control of Flywheel Inverted Pendulum Using Reinforcement Learning / (Record no. 614608)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 01779nam a22001577a 4500 |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 629.8 |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Ahmad, Shakeel |
| 245 ## - TITLE STATEMENT | |
| Title | Control of Flywheel Inverted Pendulum Using Reinforcement Learning / |
| Statement of responsibility, etc. | Shakeel Ahmad |
| 264 ## - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE | |
| Place of production, publication, distribution, manufacture | Islamabad : |
| Name of producer, publisher, distributor, manufacturer | SMME- NUST; |
| Date of production, publication, distribution, manufacture, or copyright notice | 2025. |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 67p. |
| Other physical details | Soft Copy |
| Dimensions | 30cm |
| 500 ## - GENERAL NOTE | |
| General note | Balancing an inverted pendulum is a classic control problem that traditionally requires precise system modeling for effective controller design. Reinforcement Learning (RL) offers a model-free alternative but requires extensive training, which is impractical and risky when performed directly on physical hardware. Existing methods<br/>typically rely on simulation environments built on accurate models, which are often<br/>difficult to obtain. In this work, we use RL to balance flywheel inverted pendulum<br/>by constructing an approximate model of the system through parameter estimation.<br/>Despite its inaccuracies, the model proved sufficient for training RL agents in simulation. We developed a simulation environment based on the estimated model and<br/>trained agents using Deep Q-Network (DQN), Proximal Policy Optimization (PPO),<br/>and Discrete Soft Actor-Critic (SAC) algorithms. The trained policies were deployed<br/>on real hardware without any additional fine-tuning. All agents achieved successful swing-up and stabilization, with SAC achieving the fastest swing-up time (1.65<br/>s) and lowest steady-state error (0.0220 rad), demonstrating that RL can tolerate<br/>model imperfections and still perform effectively on real systems. |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | MS Robotics and Intelligent Machine Engineering |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Supervisor : Dr. Khawaja Fahad Iqbal |
| 856 ## - ELECTRONIC LOCATION AND ACCESS | |
| Uniform Resource Identifier | <a href="http://10.250.8.41:8080/xmlui/handle/123456789/54335">http://10.250.8.41:8080/xmlui/handle/123456789/54335</a> |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | |
| Koha item type | Thesis |
| Withdrawn status | Permanent Location | Current Location | Shelving location | Date acquired | Full call number | Barcode | Koha item type |
|---|---|---|---|---|---|---|---|
| School of Mechanical & Manufacturing Engineering (SMME) | School of Mechanical & Manufacturing Engineering (SMME) | E-Books | 09/01/2025 | 629.8 | SMME-TH-1146 | Thesis |