A talk about a low-cost mowing area detector
A talk about how hierarchical acquisition functions can improve the performance of Bayesian Optimization on complex problems.
A workshop talk about how meta-parameters, required for most mapping algorithms, can be learned.
Learning control policies in robotic tasks requires a large number of interactions due to small learning rates, bounds on the updates or unknown constraints. In contrast humans can infer protective and safe solutions after a single failure or …
Tuning parameters is crucial for the performance of localization and mapping algorithms. In general, the tuning of the parameters requires expert knowledge and is sensitive to information about the structure of the environment. In order to design …
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.
Gradient-free reinforcement learning algorithms often fail to scale to high dimensions and require a large number of rollouts. In this paper, we propose learning a predictor model that allows simulated rollouts in a rank-based black-box optimizer …
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 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.