[Paper] Real-time Nonlinear MPC Strategy with Full Vehicle Validation for Autonomous Driving

We present the development and deployment of an embedded optimal control strategy for autonomous driving applications on a Ford Focus road vehicle.Non-linear model predictive control (NMPC) is designed and deployed on a system with hard real-time constraints. We show the properties of sequential quadratic programming (SQP) optimization solvers that are suitable for driving tasks

[Paper] Real-time Nonlinear MPC Strategy with Full Vehicle Validation for Autonomous Driving

arXiv link: https://lnkd.in/d7Udbi_6  Collaborators: Jean Pierre, Herman Van der Auweraer (Siemens), Peter Listov, Colin Jones (EPFL)

Another paper on similar track that we just published on ITSC2021 using physical highway driving data for human-like safe imitation learning, then validation using digital twin. arXiv link: https://lnkd.in/dJ4d2Rdh Collaborators: Flavia Sofia Acerbo, Mohsen Alirezaei, Herman Van der Auweraer (Siemens)

Since there are not many papers published from the automotive industry on testing advanced control in full vehicle, I would also suggest you checking the recent paper that I found very interesting, from Renault ADAS on LPV control for collision avoidance (main author: Anh Lam Do, PhD, a friend of mine :). 

Link: https://lnkd.in/dUAhdXNy