• Home
  • Bosch
  • Department of Corporate Research
  • Hanna Ziesche
Hanna Ziesche

Hanna Ziesche
Bosch · Department of Corporate Research

About

16
Publications
861
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
161
Citations

Publications

Publications (16)
Preprint
Full-text available
We present a novel meta-learning approach for 6D pose estimation on unknown objects. In contrast to "instance-level" pose estimation methods, our algorithm learns object representation in a category-agnostic way, which endows it with strong generalization capabilities within and across object categories. Specifically, we employ a conditional neural...
Preprint
Full-text available
Grasping inhomogeneous objects, practical use in real-world applications, remains a challenging task due to the unknown physical properties such as mass distribution and coefficient of friction. In this study, we propose a vision-based meta-learning algorithm to learn physical properties in an agnostic way. In particular, we employ Conditional Neur...
Preprint
Full-text available
Meta-learning is widely used in few-shot classification and function regression due to its ability to quickly adapt to unseen tasks. However, it has not yet been well explored on regression tasks with high dimensional inputs such as images. This paper makes two main contributions that help understand this barely explored area. \emph{First}, we desi...
Article
Automated vehicles require a comprehensive understanding of traffic situations to ensure safe and anticipatory driving. In this context, the prediction of pedestrians is particularly challenging as pedestrian behavior can be influenced by multiple factors. In this paper, we thoroughly analyze the requirements on pedestrian behavior prediction for a...
Preprint
Full-text available
Many possible fields of application of robots in real world settings hinge on the ability of robots to grasp objects. As a result, robot grasping has been an active field of research for many years. With our publication we contribute to the endeavor of enabling robots to grasp, with a particular focus on bin picking applications. Bin picking is esp...
Preprint
Full-text available
While classic control theory offers state of the art solutions in many problem scenarios, it is often desired to improve beyond the structure of such solutions and surpass their limitations. To this end, \emph{\gls{rpl}} offers a formulation to improve existing controllers with reinforcement learning (RL) by learning an additive "residual" to the o...
Preprint
Trust region methods are a popular tool in reinforcement learning as they yield robust policy updates in continuous and discrete action spaces. However, enforcing such trust regions in deep reinforcement learning is difficult. Hence, many approaches, such as Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), are based o...
Preprint
Full-text available
Automated vehicles require a comprehensive understanding of traffic situations to ensure safe and comfortable driving. In this context, the prediction of pedestrians is particularly challenging as pedestrian behavior can be influenced by multiple factors. In this paper, we thoroughly analyze the requirements on pedestrian behavior prediction for au...
Article
The detailed investigation of the Higgs sector at present and future colliders necessitates from the theory side as precise predictions as possible, including higher-order corrections. An important ingredient for the computation of higher-order corrections is the renormalization of the model parameters and fields. In this paper we complete the reno...
Article
Full-text available
The detailed investigation of the Higgs sector at present and future colliders necessitates from the theory side as precise predictions as possible, including higher order corrections. An important ingredient for the computation of higher order corrections is the renormalization of the model parameters and fields. In this paper we complete the reno...
Article
Full-text available
The 2-Higgs-Doublet Model (2HDM) belongs to the simplest extensions of the Standard Model (SM) Higgs sector that are in accordance with theoretical and experimental constraints. In order to be able to properly investigate the experimental Higgs data and, in the long term to distinguish between possible models beyond the SM, precise predictions for...
Article
A consistent interpretation of the Higgs data requires the same precision in the Higgs boson masses and in the trilinear Higgs self-couplings, which are related through their common origin from the Higgs potential. In this work we provide the two-loop corrections at O(αtαs) in the approximation of vanishing external momenta to the trilinear Higgs s...
Article
A consistent interpretation of the Higgs data requires the same precision in the Higgs boson masses and in the trilinear Higgs self-couplings, which are related through their common origin from the Higgs potential. In this work we provide the two-loop corrections at order ${\cal O}(\alpha_t \alpha_s)$ in the approximation of vanishing external mome...

Network

Cited By