Inertial measurement units (IMUs) are getting more and more incorporated into our lives due to their improving accuracy, lower cost and smaller sizes. Applications for inertial-based orientation estimation can already be found in the field of computer vision, aerospace engineering, robotics, navigation, biomechanics, health monitoring and sports. In order to enable non-intrusive, long-term tracking, this study addresses the problem of orientation estimation using a loosely attached IMU. To this end, a hybrid model is proposed combining
classical orientation methods with machine learning (ML) techniques. Previous works have focused only on parts of this task, which is why to date, there are little to no solutions to this problem. In this study, a model is designed containing three steps that are shown to be beneficial for reducing the estimation error. With the first step, the model becomes robust to a misaligned mounting of the loosely attached IMU and it allows to identify which part of the error can be contributed to the average misalignment. For the second step, two
algorithms are presented which make the model invariant to the absolute heading direction of the recorded data. In the third step, the data is prepared such that the size of the search space is reduced by a factor 2. Therefore, less data is required for learning the problem or, with an equal amount of data, a bigger part of the process can be discovered. Besides these steps, it is shown that the use of physics-based knowledge in the form of orientation estimates,
as opposed to raw inertial data as input features for the ML method, is beneficial.

This bachelor thesis is written as part of the curriculum for the bachelor Electrical Engineering at the Delft University of Technology. The thesis is part of the course EE3L11 - Bachelor Afstudeer Project and took place from April 2017 until July 2017.

This document describes the development of a system that is able to drive electric drum brakes, the brake control unit (BCU). The BCU is a subsystem of a larger project; a braking system that minimizes the force between a trailer and a car when braking. The ultimate goal is to let the trailer completely brake for itself.

To achieve this, two other subgroups have designed a control algorithm and a force sensor readout circuit that measures the force. The BCU receives a desired braking force from the control algorithm that should be exerted in order to eliminate the force between car and trailer.
This input force covers a certain range, so the BCU should be designed such that the braking force of the brakes can be regulated. For this purpose a power supply, current controller and lookup table are designed.

The developed power supply is able to provide a constant voltage to the solenoids inside the electric brakes. The power supply consists of a DC/DC converter, which is powered from a car battery. As a consequence, the input voltage of the DC/DC converter is dependent on the state of charge of the battery. Nevertheless, the output of the designed converter is able to provide a constant DC voltage with a maximum current of 8 A.

The designed current controller makes use of a PWM driven current source, which controls the output current of the DC/DC converter. Besides this source, an algorithm that estimates the duty cycle of the PWM signal is derived, based on the desired current through the solenoid.

Last, a lookup table is implemented that determines which current is needed for specific input forces. The table makes use of inter- and extrapolation between measured test results to calculate the right current for every input force.