Medical exoskeletons are an important topic, e.g. for the medical rehabilitation of stroke patients. One challenge is to identify what kind of movement a user wants to perform, e.g. lifting an arm. This can be supported by analysing biosignals such as EEG (i.e. neuron activity in the brain) or EMG (i.e. muscle activity). In this project, we will investigate how machine learning can be used for embedded systems to realise better exoskeletons through such bio-signal analysis.

We offer this project in collaboration with Prof. Elsa Kircher's medical engineering department. She is working on medical exoskeletons and provides us with access to an existing system that we will use as a starting point and comparison system.

In addition, the project will be carried out in parallel with a medical technology project that will provide contributions to bio-signal analysis. Project members will

• investigate the state of the art of biosignal analysis for the control of exoskeletons
• develop and train machine learning (ML) algorithms for the analysis of biosignals (EEG, EMG)
• use an existing toolchain to implement embedded accelerators for such ML algorithms
• evaluate the developed system with real experiments

The project is planned as the first part of a one-year (two-semester) project. Experience with C/C++ programming is required. Additional skills might be useful:

• Knowledge of in time series analysis and/or digital signal processing
• Experience with the design/training of machine learning solutions
• Experience with the development of embedded systems
• Experience with Python or VHDL programming

The project is about improving an existing drink-mixing machine. The aim is to give students an insight into cyber-physical systems by working on hardware, software and electronics.

The project members will

• deal with sensor and actuator technology
• plan and implement a pump system
• develop controls systems
• edit a user interface
• in certain circumstances, use machine learning for the control technology used

The project is planned as the first part of a one-year (two-semester) project.

Experience with either hardware, software or electronics is required. Additional experience in the following areas is advantageous:

• sensors and actuators
• automation technology
• circuit design
• Embedded Systems development
• control engineering
• user interface design