Abstract The Segway Loomo is a self-balancing segway robot, which is constantly balanced by an internal control system. A local path planning strategy was developed in advance for this robot. For local path planning, a motion model of the robot is needed to determine the effect of velocity commands on the robot’s pose. In the implemented local path planner, a simple motion model of the robot is used, which does not model the effect of the segway robot’s internal control on its motion.
Abstract Upon illumination of a sufficient amount of light, the chlorophyll molecules of a plant start to emit photons in the far red region of the light spectrum. This phenomenon is also known as chlorophyll fluorescence. In this thesis a classi- fier is built that serves as a benchmark for plant classification via chlorophyll a fluorescence. A data set of 2500 samples was acquired by illuminating a total of 500 leaves gathered from five different plants with seven LEDs.
Abstract Bayesian Optimization is a powerful method to optimize black-box derivative-free functions, with high evaluation costs. For instance, applications can be found in the context of robotics, animation design or molecular design. However, Bayesian Optimization is not able to scale into higher dimensions, equivalent to optimizing more than 20 parameters. This thesis introduces HIBO, a new hierarchical algorithm in the context of high dimensional Bayesian Optimization. The algorithm uses an automatic feature generation.
Abstract The focus of this work is on extending the functionality of the robot platform Loomo. Using cartography and navigation methods, the basis for an autonomous system is created. In addition, the recognition and storage of AR markers simplifies human-robot interaction by enabling targeted navigation to specific locations. The implementation of the used software components ROS, Movebase, RTAB-Map and ALVAR is described in detail and tested in an experimental setting.
Abstract The demand among the population for household robots continues to rise. These include in particular mobile cleaning and lawn mowing robots. These are usually very expensive and still very inefficient. Especially for lawn mowing robots, it is essential to have visited the entire working space in order to perform their task correctly. However, the current state of the art is still random walk algorithms, which are very unreliable and inefficient.
Abstract Based on the intention to build an autonomous lawn mower robot, this work examines the viability of a sensor and microprocessor for onboard plant clas- sification using machine learning. Usually, some sort of fencing is required to keep the robot in its intended processing area, so such a sensor would allow the robot to differentiate between grass and e.g. flowers. Also, the drive and blade speed can be adjusted for certain species or plant densities, etc.
Abstract This Bachelor thesis presents an approach for the complete coverage path planning (CCPP) problem which occurs for different robotic applications, such as autonomous lawn mowers or vaccuum cleaners. Methods used for localization [27], map representation [10] and planning [14] are discussed under consideration of sensor noise and uncertainty about the own position induced by the movement of the robot. An efficient method to solve the CCPP problem under uncertainty is proposed and evaluated due to simulations.
Abstract Medical interventions are often supported by imaging and position-determining procedures. In this thesis we investigate to what extent electromagnetic tracking systems can be used for accurate positioning. The focus is first on 2D, then on 3D systems.
Abstract To make it easier for people to work in the lawn care, there is a long list of robotic lawnmowers. The navigation is a big problem, since the application is usually limited by a perimeter wire. This process means a time as well as financial expense and must be changed. For this purpose, a new method for lawn detection was developed at the Institute of Robotics and Cognitive Systems.
Abstract The present bachelor thesis presents the necessary methods for an exact selflocalization by using an Inertial Mesurment Unit (IMU) and the odometry of an autonomous lawn mower. This self-localization shall be used in later work together with a localization of a particle filter. The required standard models [12] for the individual sensor systems were examined and the required parameters determined. Measurements were taken with the autonomous lawn mower to develop a Kalman filter [15] based on the data obtained.