Angela Schoellig

📰 COREnext Scientific Publication Alert! 📰 👉 Check out our #research paper titled "#Software-Defined CPU Modes." Authors: Michael Roitzsch, @Till Miemietz, Christian von Elm, Nils Asmussen 💡 This paper delves into the innovative concept of defining CPU modes entirely through software. Our researchers demonstrate how this design could function, highlighting the advantages it offers. By unifying all existing modes under a common design umbrella, this approach enforces a cleaner structure and greater control over exposed functionality. Additionally, the flexibility of #software-defined modes opens up exciting new use cases. 👉 Discover the future of #CPU design and its potential impact on computing! #Research #CPUModes #SoftwareDefined #Innovation #TechResearch #FutureOfComputing 🔗

2

We are happy to announce that our paper "SAUC: Sparsity-Aware Uncertainty Calibration for Spatiotemporal Prediction with Graph Neural Networks" has been accepted by ACM SIGSPATIAL 2024! 📜 Paper link: https://lnkd.in/efgH22K5 📑ArXiv: https://lnkd.in/evvjYd2A This paper addresses the challenge of uncertainty quantification in spatiotemporal deep learning, which is often overlooked in favor of deterministic predictions. Sparse, highly-granular spatiotemporal datasets pose additional difficulties. To tackle this, the authors propose the Sparsity-aware Uncertainty Calibration (SAUC) framework, which adjusts uncertainty for both zero and non-zero values. They first transform deterministic spatiotemporal Graph Neural Networks (ST-GNNs) into probabilistic models and then calibrate them using quantile methods. Experiments show that SAUC improves variance fitting and reduces calibration errors by 20% in sparse datasets like traffic accident and crime predictions, demonstrating its theoretical and practical value. We extend our heartfelt thanks to our esteemed collaborators: Dingyi Zhuang, Bu Yuheng, Guang Wang, Jinhua Zhao! #UncertaintyQuantification #SpatiotemporalData #GraphNeuralNetworks #DeepLearning #ACMSIGSPATIAL #AIResearch #DataScience #SparseData

12

#PaperAlert - Our work on "Acceptance and usability of a soft robotic, haptic feedback seat for autonomy level transitions in highly automated vehicles" has been accepted for publication in the IEEE Transactions on #Haptics. Link to paper: https://lnkd.in/evWNvGaX This work has been conducted in collaboration with Jan Peters, Johann Licher, Mats Wiese, and Prof. Annika Raatz from the Leibniz Universität Hannover and Prof. Helge A Wurdemann from UCL Mechanical Engineering and the UCL Robotics Institute. Related research started with my EPSRC "Engineering for a Prosperous Nation" grant (EP/R037795/1), awarded during my academic career at the University of Southampton. Many thanks again to the TRG group and, in particular, Prof. Tiina Roose for their excellent support. Follow-on support included the SAVE grant (https://lnkd.in/eWU4iYbv), funded by the UKRI Trustworthy Autonomous Systems (TAS) Hub (EP/V00784X/1), in collaboration with Dr Kate Devlin from King's College London and Dr Katie Plant from the University of Southampton as well as Ansible Motion, HORIBA MIRA and Reed Mobility (by Prof. Nick Reed). In 2021, I then secured equipment funding through an EPSRC Early Career Capital Equipment competition (EP/S01800X/1) to establish IM@UCL (http://im-ucl.com) - an advanced driving simulator at UCL PEARL in collaboration with Ansible Motion. Our work on take-over requests between human drivers and automated vehicles has resulted in a number of outputs including a Elsevier #Neurocomputing journal paper (https://lnkd.in/dGD3Pmf), co-authored by Dr Jan Luca Kästle and Dr Jakub Krol, an #IROS2020 paper (https://lnkd.in/eQw8zNvV) together with the Leibniz Universität Hannover and awards from an #IROS2020 workshop and the IEEE UK & Ireland RAS Conference. Building on this research, my IM@UCL team and I recently joined a collaborative project, led by 7th Sense Research UK Ltd., for the Department for Transport (DfT), United Kingdom, involving Loughborough University, aiming to answer critical questions about which #NDDTs, if any, can be safely performed during non-driving periods in cars with self-driving features. UCL Engineering UCL Dept of Civil, Environmental & Geomatic Engineering UCL Mechanical Engineering UCL Innovation & Enterprise

69

1 Kommentar