LPVcore toolbox:
LPVcore contains implementations of state-of-the-art algorithms in LPV system identification and control synthesis. The toolbox is continuously expanding. The toolbox is free to use. However, if you apply it in your work or research, please reference the paper below:
P. den Boef, P. B. Cox and R. Tóth: LPVcore: MATLAB Toolbox for LPV Modelling, Identification and Control of Non-Linear Systems, Proc. of the 19th IFAC Symposium System Identification: learning models for decision and control, (2021), Padova, Italy. (Published version, arXiv link)
Deep-learning-based system identification (DeepSI toolbox):
https://github.com/GerbenBeintema/deepSI
DeepSI offers a powerful Python toolbox to perform Deep System Identification (DeepSI) with a wide range of tools and methods. The deepSI Python module aims to offer an intuitive machine learning for system identification environment without the need for deep expert knowledge. Implementing a system identification task often requires effectively no more than 10 lines of code. Coding examples can be found on the GitHub page of the toolbox. If you apply it in your work or research, please reference the paper below:
Gerben Beintema, Roland Toth, Maarten Schoukens. Nonlinear State-Space Identification using Deep Encoder Networks; Proceedings of the 3rd Conference on Learning for Dynamics and Control, PMLR 144:241-250, 2021. (Github, Published version)
Single-Stage Monocular 3D Object Detection via Keypoint Estimation (SMOKE):
https://github.com/lzccccc/SMOKE
SMOKE is a real-time monocular 3D object detector for autonomous driving. The runtime on a single NVIDIA TITAN XP GPU is ~30ms.
Matlab Examples (from papers)
- Randomly generated LPV-SS model (IO dimension: 2×2, order 4, scheduling dimension 5) for comparing state-space identification approaches: sys_data.mat.