The integration of brain–computer interfaces (BCIs) with robotics offers a promising pathway toward intuitive and natural human–robot interaction. This thesis explores the use of electroencephalography (EEG) signals for decoding human motion intention and predicting corresponding movement trajectories. EEG provides a non-invasive method into cortical activity, reflecting motor planning and motor imagery processes before actual muscle activation. By extracting discriminative features from EEG recordings, the system aims to recognize different motion intentions—such as grasping, lifting, or reaching—and further predict the spatial trajectory of the motion. The study combines neural decoding and motion estimation to translate the human intention. The results are expected to contribute to the development of intuitive BCI systems that enable users to interact with robotic devices in the future through the “mind-driven” motion control.
1, You will learn how to process the EEG signal.
2, You will develop the self-adaptive prediction system using the EEG signal.
3, You will use the features of EEG to predict the intended motion.
References:
1, Dangi, S., Orsborn, A. L., Moorman, H. G., & Carmena, J. M. (2013). Design and analysis of closed-loop decoder adaptation algorithms for brain-machine interfaces. Neural computation, 25(7), 1693-1731.
2, Lawhern, V. J., Solon, A. J., Waytowich, N. R., Gordon, S. M., Hung, C. P., & Lance, B. J. (2018). EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces. Journal of neural engineering, 15(5), 056013.
3, Orsborn, A. L., Moorman, H. G., Overduin, S. A., Shanechi, M. M., Dimitrov, D. F., & Carmena, J. M. (2014). Closed-loop decoder adaptation shapes neural plasticity for skillful neuroprosthetic control. Neuron, 82(6), 1380-1393.
4, Silversmith, D. B., Abiri, R., Hardy, N. F., Natraj, N., Tu-Chan, A., Chang, E. F., & Ganguly, K. (2021). Plug-and-play control of a brain–computer interface through neural map stabilization. Nature biotechnology, 39(3), 326-335.
5, Schulman, J., Wolski, F., Dhariwal, P., Radford, A. & Klimov, O. Proximal policy optimization algorithms. Preprint at https://arxiv.org/abs/1707.06347 (2017).
6, Pfurtscheller, G. & Da Silva, F. L. Event-related EEG/MEG synchronization and desynchronization: basic principles. Clin. Neurophysiol. 110, 1842–1857 (1999).
7, Olsen, S. et al. An artificial intelligence that increases simulated brain–computer interface performance. J. Neural Eng. 18, 046053 (2021).
8, https://github.com/kaolab-research/bci_raspy