Year: 2023
Type: dissertation
Abstract: This thesis focused on the development of a novel embedded sensor for the existing continuum actuator for the Honda Haru robot. The newly developed sensor will enable the sensing to Roll and Pitch without modifying the actuator’s external geometry. The sensor will serve as a basis for future dynamic load sensing capabilities for the robot. After development the sensor was embedded to the actuator of the robot. The newly developed sensor was thoroughly modeled and provides Roll and Pitch sensing capabilities on Simulink. Linear models and neural network models were developed to enable the use of sensors in different scenarios. With continual learning, the newly developed sensor array model can dynamically evolve while providing an accurate model with respect to ground truth.An incremental learning model is also developed to enable future expansion of capability of the sensor with Python.
Author: Chuen Hau, Pak
Institution: KTH Royal Institute of Technology
Language: English
Subfield: Biomedical Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7065038481
