Smart Goggles for Visual In-Action Feedback in Ski Jumping (1 M 1-2B/S)
From iis-projects
Contents
Short Description
In ski jumping, low repetition rates of jumps limit effectiveness of training. Thus, increasing learning rate within every single jump is key to success. A critical element of athlete training is motor learning, which has been shown to be accelerated using feedback methods. Today, coach’s training feedback is mainly verbal and based on recorded video data. Video data provides good insight into the entire jump, however for an athlete to convert post-action video and speech information into actual motor control during action is difficult. Therefore, we aim to develop a system that translates sensor data into simple, motor-transferable information online and displays this to jumpers (e.g. via LEDs) during the execution of the jump.
Status: Available
- Students will be co-supervised by the Center of Project Based Learning.
- Looking for 1-2 Bachelor or Semester students / 1 Master student
- Contact: Christoph Leitner, Lukas Schulthess (PBL)
Prerequisites
- Embedded systems and PCB design
- Microcontrollers
Character
- 40% Hardware and PCB Design
- 30% Firmware Development
- 20% Hardware evaluation and integration
- 10% Data analyses and documentation
Professor
Detailed Task Description
The main goal of this thesis is to design, build and test an intelligent ski goggle that provides in-action feedback to athletes. Goggles should inform athletes about their center of gravity positioning druing the in-run. For this purpose, sensor data is collected from the insole of ski boots and processed with a tinyML model. The extracted feedback information is displayed over a LED display inside the glasses. According to the level of the student and the chosen thesis type (BT/ST/MT) the work will include some or all following tasks:
Goals
Hardware and PCB Design
- Creation of design proposals for the integration of a visual biofeedback in ski goggles.
- Development of a benchtop prototype using a nRF52 development kit (Nordic Semiconductor)
Firmware Development
- Implementation of biofeedback data transmission via BLE using two nRF52 microcontrollers (on the sensor node and in the glasses).
- Conversion of tinyML outputs into visual feedback.
Testing
- Analyses of data transfer quality using BLE (e.g., identification of losses, delay times,..)
- Testing in lab conditions and in a real world scenario
Practical Details
