Human hand control involves many biomechanical degrees of freedom, making direct EMG-based control of robotic and prosthetic hands difficult. Previous work has therefore investigated continuous decoding of hand and finger kinematics from surface EMG signals using regression models and neural networks [1]. In parallel, research on muscle and kinematic synergies has shown that hand movements can be represented in a low-dimensional latent space rather than through independent control of each joint. Early studies by Santello et al. demonstrated that natural grasp postures can be reconstructed using only a few principal components [2]. More recent work combines EMG decoding with latent-space and deep-learning approaches to enable smoother and more biologically plausible continuous prosthetic hand control [3].
Building on these developments, this thesis investigates continuous EMG-driven robotic hand control through a low-dimensional synergy representation.
Project goals
- Conduct a literature review on continuous robotic hand control
- Design a pipeline which reconstructs finger joint angles from forearm emg signals using muscle and kinematic synergies
- Implement a controller for a robotic hand that uses the developed pipeline and produces realistic motion
- Test in simulation and on real robotic hand and evaluate motion reconstruction accuracy
Requirements
- Student of Medical Engineering, Mechatronics, Autonomy Technology, Electrical Engineering or Computational Engineering
- Programming skills in Python
- Understanding of robotic hand kinematics and biosignal processing
- Interest in robotic hands and human motor control
References
[1] R. J. Smith et al., “Continuous decoding of finger position from surface EMG signals for the control of powered prostheses,” Proc. IEEE EMBS, pp. 197–200, 2008.
[2] M. Santello, M. Flanders, and J. F. Soechting, “Postural hand synergies for tool use,” Journal of Neuroscience, vol. 18, no. 23, pp. 10105–10115, 1998.
[3] E. Krasoulis, S. Vijayakumar, and K. Nazarpour, “Effect of user practice on prosthetic finger control with an intuitive myoelectric decoder,” Frontiers in Neuroscience, vol. 13, 2019.
Contact
marius.kindermann@fau.de