M
Matthias A. Müller
Researcher at Leibniz University of Hanover
Publications - 279
Citations - 6904
Matthias A. Müller is an academic researcher from Leibniz University of Hanover. The author has contributed to research in topics: Model predictive control & Computer science. The author has an hindex of 34, co-authored 232 publications receiving 4386 citations. Previous affiliations of Matthias A. Müller include Bosch Rexroth & ETH Zurich.
Papers
More filters
Proceedings ArticleDOI
DeepGCNs: Can GCNs Go As Deep As CNNs?
TL;DR: In this article, a very deep GCN architecture is proposed to solve the vanishing gradient problem in point cloud semantic segmentation, which is based on graph convolutional networks (GCNs).
Book ChapterDOI
TrackingNet: A Large-Scale Dataset and Benchmark for Object Tracking in the Wild
TL;DR: This work presents TrackingNet, the first large-scale dataset and benchmark for object tracking in the wild, which covers a wide selection of object classes in broad and diverse context and provides an extensive benchmark on TrackingNet by evaluating more than 20 trackers.
Posted Content
DeepGCNs: Can GCNs Go as Deep as CNNs?
TL;DR: This work presents new ways to successfully train very deep GCNs by borrowing concepts from CNNs, specifically residual/dense connections and dilated convolutions, and adapting them to GCN architectures, and building a very deep 56-layer GCN.
Journal ArticleDOI
Data-Driven Model Predictive Control With Stability and Robustness Guarantees
TL;DR: The presented results provide the first (theoretical) analysis of closed-loop properties, resulting from a simple, purely data-driven MPC scheme, including a slack variable with regularization in the cost.
Driving Policy Transfer via Modularity and Abstraction.
TL;DR: In this article, the authors present an approach to transfer driving policies from simulation to reality via modularity and abstraction, inspired by classic driving systems and aiming to combine the benefits of modular architectures and end-to-end deep learning approaches.