@inproceedings{0cd4f02ae1514c2f99c515ee98e52381,
title = "Robust Sampling Based Model Predictive Control with Sparse Objective Information",
abstract = "We present an algorithmic framework for stochastic model predictive control that is able to optimize non-linear systems with cost functions that have sparse, discontinuous gradient information. The proposed framework combines the benefits of sampling-based model predictive control with linearization-based trajectory optimization methods. The resulting algorithm consists of a novel utilization of Tube-based model predictive control. We demonstrate robust algorithmic performance on a variety of simulated tasks, and on a real-world fast autonomous driving task.",
author = "Grady Williams and Brian Goldfain and Paul Drews and Kamil Saigol and Rehg, \{James M.\} and Theodorou, \{Evangelos A.\}",
note = "This work was made possible by the ARO award W911NF-12-1-0377, the Georgia Tech Vertical Lift Center of Excellence (VLCROE), and the Qualcomm Innovation Fellowship.; 14th Robotics: Science and Systems, RSS 2018 ; Conference date: 26-06-2018 Through 30-06-2018",
year = "2018",
doi = "10.15607/RSS.2018.XIV.042",
language = "English (US)",
isbn = "9780992374747",
series = "Robotics: Science and Systems",
publisher = "MIT Press Journals",
editor = "Hadas Kress-Gazit and Srinivasa, \{Siddhartha S.\} and Tom Howard and Nikolay Atanasov",
booktitle = "Robotics",
address = "United States",
}