CO-MAN: Safe data-driven control for human-centric systems

The research project CO-MAN aims to develop a novel framework for user-adaptive data-driven control with performance guarantees in order to address the scientific challenges of high uncertainty andi ndividual user requirements.

Motivation

It is important for advances in technology to support human activities and interactions in the areas of healthcare, mobility and infrastructure systems. For instance, making healthcare more human requires digital interfaces to allow for more human interactions with the system. This is the goal of human-centric systems in which the human is both an element of the control system and a design criterion. The EU-funded CO-MAN project will develop a framework for user-adaptive data-driven control with performance guarantees. The biggest challenge will be to merge probabilistic non-parametric modelling techniques from statistical learning theory with novel risk-aware control methodologies while including active user modelling. The game changer is the current push towards reliable machine learning with novel results on theoretical bounds for learning behaviour.

Links

TUM team members

Selected publications

  • M. Omainska; J. Yamauchi; T. Beckers; T. Hatanaka; S. Hirche; M. Fujita: Gaussian process-based visual pursuit control with unknown target motion learning in three dimensions. SICE Journal of Control, Measurement, and System Integration 14 (1), 2021, 116-127 mehr… BibTeX
  • T. Beckers; S. Hirche: Prediction with Approximated Gaussian Process Dynamical Models. IEEE Transactions on Automatic Control , 2021 mehr… BibTeX
  • Yamauchi, Junya; Omainska, Marco; Beckers, Thomas; Hatanaka, Takeshi; Hirche, Sandra; Fujita, Masayuki: Cooperative Visual Pursuit Control with Learning of Position Dependent Target Motion via Gaussian Process. 2021 60th IEEE Conference on Decision and Control (CDC), IEEE, 2021 mehr… BibTeX
  • K. H. Degue; D. Efimov; J. Le Ny; S. Hirche: Novel_Interval_Observer_Hybrid_Systems_Final_Version. 2021 60th IEEE Conference on Decision and Control, 2021 mehr… BibTeX
  • Degue, Kwassi H.; Efimov, Denis; Le Ny, Jerome; Hirche, Sandra: Design of Interval Observers for Uncertain Linear Impulsive Systems. 2021 60th IEEE Conference on Decision and Control (CDC), IEEE, 2021 mehr… BibTeX
  • A. Lederer; A. J. Ordóñez Conejo; K. Maier; W. Xiao; J. Umlauft; S. Hirche: Gaussian Process-Based Real-Time Learning for Safety Critical Applications. Proceedings of the 38th International Conference on Machine Learning (Proceedings of Machine Learning Research 139), 2021, 6055-6064 mehr… BibTeX
  • A. Lederer; A. Capone; J. Umlauft; S. Hirche: How Training Data Impacts Performance in Learning-based Control. IEEE Control Systems Letters 5 (3), 2020, 905-910 mehr… BibTeX
  • Pfister, Franz M. J.; Um, Terry Taewoong; Pichler, Daniel C.; Goschenhofer, Jann; Abedinpour, Kian; Lang, Muriel; Endo, Satoshi; Ceballos-Baumann, Andres O.; Hirche, Sandra; Bischl, Bernd; Kulić, Dana; Fietzek, Urban M.: High-Resolution Motor State Detection in Parkinson's Disease Using Convolutional Neural Networks. Scientific Reports 10 (1), 2020, 5860 mehr… BibTeX
  • A. Capone; A. Lederer; J. Umlauft; S. Hirche: Data Selection for Multi-Task Learning Under Dynamic Constraints. IEEE Control Systems Letters 5 (3), 2020, 959-964 mehr… BibTeX
  • A. Capone; G.Noske; J. Umlauft; T. Beckers; A. Lederer; S. Hirche: Localized active learning of Gaussian process state space models. Learning for Dynamics & Control, 2020 mehr… BibTeX
  • J. Umlauft; T. Beckers; A. Capone; A. Lederer; S. Hirche: Smart Forgetting for Safe Online Learning with Gaussian Processes. Learning for Dynamics & Control, 2020 mehr… BibTeX