Error mapping controller: a closed loop neuroprosthesis controlled by artificial neural networks
2006

Error Mapping Controller for Neuroprosthesis

publication Evidence: high

Author Information

Author(s): Alessandra Pedrocchi, Simona Ferrante, Elena De Momi, Giancarlo Ferrigno

Primary Institution: Politecnico di Milano

Hypothesis

Can an Error Mapping Controller (EMC) improve the performance of neuroprostheses in managing fatigue during knee flexion and extension?

Conclusion

The EMC outperforms traditional controllers by balancing tracking accuracy and managing fatigue, allowing for prolonged movement without overstressing muscles.

Supporting Evidence

  • The EMC showed improvements in tracking accuracy compared to traditional controllers.
  • It effectively managed fatigue, allowing for longer exercise durations.
  • The controller demonstrated robustness against mechanical disturbances.
  • Statistical tests indicated significant differences in performance between EMC and other controllers.

Takeaway

The EMC is like a smart helper for knee movements that learns how tired the muscles are and adjusts the help it gives, so you can move longer without getting too tired.

Methodology

The EMC uses artificial neural networks for both an inverse model and a feedback controller, validated through simulations and compared with traditional controllers.

Limitations

The study primarily focuses on knee flexion and extension, which may limit the generalizability to more complex movements.

Statistical Information

P-Value

p<0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1743-0003-3-25

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication