| Proj No. | A1096-251 |
| Title | Quadruped Robot Control via Natural Human Commands |
| Summary | Quadruped robots possess special locomotive and agility features that can provide great assistance to human. This project seeks to explore the ability of quadruped robots to move and manipulate objects using verbal commands or gestures. In terms of technique, the project shall first explore solutions to detect objects and human gestures based on image, audio, or 3D depth sensors, along with reinforcement learning to help the robot learn the correct behavior. In terms of software, simulation platforms such as Isaac Sim, and Mujoco will be used to model the environments and the robots before transferring to real-world robot. This topic is recommended for student with the following qualities: ● Strong passion for machine learning and robotics. ● Self-driven, capable of studying from public websites, youtube, books and know how to employ ChatGPT in meaningful ways. ● Good python programming skills. Knowledge on C programming is also necessary in some parts. ● Good technical communication skills, capable of elaborating problems and ideas to mentors and colleagues. |
| Supervisor | Prof Xie Lihua (Loc:S2 > S2 B2C > S2 B2C 94, Ext: +65 67904524) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Internet of Things Laboratory (Loc: S1-B4c-14, ext: 5470/5475) |
| Single/Group: | Single |
| Area: | Intelligent Systems and Control Engineering |
| ISP/RI/SMP/SCP?: |