Publications

Data-Driven Modelling for Health Estimation of High-Voltage Battery Systems

Published in Chalmers Open Digital Repository, 2020

Short abstract - An accurate determination of battery health and life prediction is essential to ensure reliable, efficient and durable battery performance along the full lifetime of a vehicle. This thesis builds on achievements with data-driven modelling to determine the behaviour of complex dynamical systems through machine learning techniques. The conducted survey over a range of model techniques, from standard baseline up to state-of-the-art approaches, indicates the power and flexibility of data-driven models in the directions of per vehicle and fleet use cases.

Download here

Usable surface detection on top-view camera data using automatic ground truth generation for binary semantic segmentation

Published in None, 2020

Short abstract - This project aims to solve the problem to detect drivable areas of a factory floor, using a workflow consisting of background subtraction to generate a ground truth, that is then used to train a neural network. The output could potentially be used as a mapping for which a scheduler or robot control system could work upon to avoid collisions and problems with dynamic obstacles.

Download here

Developement of a Service Store for an Augmented Reality Machine Window

Published in None, 2018

Short abstract - The aim of this Bachelor Thesis was to develop a distribution concept for the value-added services of the AR machine window, the so-called iWindow.