Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Optimizing and evaluating an FMG band for online control of a robotic hand orthosis
Despite the enormous potential of robotic assistive technologies in daily life applications and their remarkable technical advances in recent years, a major remaining challenge is the robust and reliable detection of the user’s intention to trigger the desired motion. One possible intention detection strategy is measuring the changes in the limb’s muscular stiffness pattern during muscle activations and relaxations, so-called force myography (FMG). However, the application of this technology to orthotics is still relatively rare. Thus, this project continues previous works on demonstrating the use of FMG signals collected through a wearable device to control a robotic hand orthosis, specifically the RELab tenoexo.
Keywords: force myography, electronic design, signal processing, machine learning, user studies
In the first phase of the project, you will optimize the design and the electronics of an existing armband incorporating multiple force-sensitive resistors (in the following just called “band”) to be able to read FMG signals from a human forearm or upper arm. Further, you will optimize signal processing steps and use machine learning algorithms for online-classification of the collected data in multiple hand gesture/movements, e.g. hand open, intent to close, hand closed, and intent to open.
For the second phase of the project, you will then integrate the band into the existing setup of the tenoexo for on-board data collection and processing to trigger its opening and closing. You will conclude the project with a study with participants to evaluate the performance of the band to trigger the tenoexo during selected activities of daily living.
In the first phase of the project, you will optimize the design and the electronics of an existing armband incorporating multiple force-sensitive resistors (in the following just called “band”) to be able to read FMG signals from a human forearm or upper arm. Further, you will optimize signal processing steps and use machine learning algorithms for online-classification of the collected data in multiple hand gesture/movements, e.g. hand open, intent to close, hand closed, and intent to open. For the second phase of the project, you will then integrate the band into the existing setup of the tenoexo for on-board data collection and processing to trigger its opening and closing. You will conclude the project with a study with participants to evaluate the performance of the band to trigger the tenoexo during selected activities of daily living.
The goal of the project is to assess and optimize the use of an FMG band to control a robotic hand orthosis in view of its application for people with neurological impairments.
The goal of the project is to assess and optimize the use of an FMG band to control a robotic hand orthosis in view of its application for people with neurological impairments.
- 15% Literature review and defining technical requirements
- 25% Optimizing the existing hardware and the signal processing pathway
- 15% Integration of the band into the existing tenoexo setup for on-board processing
- 30% Conduct a study to evaluate the feasibility and functionality of the combined setup (band and tenoexo) for participants with no impairments (and potentially such with neurological hand impairments)
- 15% Presentations and final report
- 15% Literature review and defining technical requirements - 25% Optimizing the existing hardware and the signal processing pathway - 15% Integration of the band into the existing tenoexo setup for on-board processing - 30% Conduct a study to evaluate the feasibility and functionality of the combined setup (band and tenoexo) for participants with no impairments (and potentially such with neurological hand impairments) - 15% Presentations and final report
- Enthusiasm for the multidisciplinary field of rehabilitation engineering
- Student with a technical background such as mechanical or electrical engineering, mechatronics, robotics, or computer science
- Strong experience in electrical engineering and soldering, microcontrollers, Python programming. Signal processing and machine learning.
- Enthusiasm for the multidisciplinary field of rehabilitation engineering - Student with a technical background such as mechanical or electrical engineering, mechatronics, robotics, or computer science - Strong experience in electrical engineering and soldering, microcontrollers, Python programming. Signal processing and machine learning.
If you are interested in pursuing the project or have any further questions, please send your motivation, CV, and transcript of records to both:
Jessica Gantenbein, Rehabilitation Engineering Laboratory, ETH Zurich
jessica.gantenbein@hest.ethz.ch
Dr. Chakaveh Ahmadizadeh, Biomedical and Mobile Health Technology Lab, ETH Zurich
chakaveh.ahmadizadeh@hest.ethz.ch
If you are interested in pursuing the project or have any further questions, please send your motivation, CV, and transcript of records to both:
Jessica Gantenbein, Rehabilitation Engineering Laboratory, ETH Zurich jessica.gantenbein@hest.ethz.ch
Dr. Chakaveh Ahmadizadeh, Biomedical and Mobile Health Technology Lab, ETH Zurich chakaveh.ahmadizadeh@hest.ethz.ch