| Proj No. | A1005-251 |
| Title | Vision based Robot Control using Convolutional Neural Networks |
| Summary | In this project, a convolutional neural network (CNN) based robot control method for robots with fixed camera configuration and eye-in-hand camera configuration will be developed. An oriented object detector is first obtained by training a real-time CNN-based object detector such as you only look once (Yolo) and task variables are generated based on parameters of the oriented bounding box and a recurrent neural network such as Long short-term memory (LSTM) network. A CNN-based robot controller will be developed based on the task variables and implemented on an industrial robot with fixed camera configuration. |
| Supervisor | A/P Cheah Chien Chern (Loc:S1 > S1 B1B > S1 B1B 53, Ext: +65 67905385) |
| Co-Supervisor | - |
| RI Co-Supervisor | - |
| Lab | Robotics I (Loc: S2-B6a-01) |
| Single/Group: | Single |
| Area: | Intelligent Systems and Control Engineering |
| ISP/RI/SMP/SCP?: |