Laura Ferranti

@inproceedings{peters_learning_2022,
	title = {Learning {Mixed} {Strategies} in {Trajectory} {Games}},
	url = {paper=http://arxiv.org/abs/2205.00291 video=https://www.youtube.com/watch?v=gT52cKH9pvg website=https://lasse-peters.net/pub/lifted-games/ talk=https://www.youtube.com/watch?v=gT52cKH9pvg},
	abstract = {In multi-agent settings, game theory is a natural framework for describing the strategic interactions of agents whose objectives depend upon one another’s behavior. Trajectory games capture these complex effects by design. In competitive settings, this makes them a more faithful interaction model than traditional “predict then plan” approaches. However, current game-theoretic planning methods have important limitations. In this work, we propose two main contributions. First, we introduce an offline training phase which reduces the online computational burden of solving trajectory games. Second, we formulate a lifted game which allows players to optimize multiple candidate trajectories in unison and thereby construct more competitive “mixed” strategies. We validate our approach on a number of experiments using the pursuit-evasion game “tag.”},
	booktitle = {Robotics: {Science} and {Systems} ({RSS})},
	author = {Peters, L. and Fridovich-Keil, D. and Ferranti, L. and Stachniss, C. and Alonso-Mora, J. and Laine, F.},
	year = {2022},
	note = {Accepted for publication in the Proc. of RSS 2022},
	keywords = {key\_game\_theory, key\_multirobot, type\_conference},
}

In multi-agent settings, game theory is a natural framework for describing the strategic interactions of agents whose objectives depend upon one another’s behavior. Trajectory games capture these complex effects by design. In competitive settings, this makes them a more faithful interaction model than traditional “predict then plan” approaches. However, current game-theoretic planning methods have important limitations. In this work, we propose two main contributions. First, we introduce an offline training phase which reduces the online computational burden of solving trajectory games. Second, we formulate a lifted game which allows players to optimize multiple candidate trajectories in unison and thereby construct more competitive “mixed” strategies. We validate our approach on a number of experiments using the pursuit-evasion game “tag.”

@article{de_groot_scenario-based_2021,
	title = {Scenario-{Based} {Trajectory} {Optimization} in {Uncertain} {Dynamic} {Environments}},
	volume = {6},
	url = {paper=https://ieeexplore.ieee.org/document/9410362/ video=https://www.youtube.com/watch?v=YONmA4EGmtI},
	doi = {10.1109/LRA.2021.3074866},
	number = {3},
	journal = {IEEE Robotics and Automation Letters},
	author = {de Groot, O. and Brito, B. and Ferranti, L. and Gavrila, D. M. and Alonso-Mora, J.},
	month = jul,
	year = {2021},
	keywords = {key\_collision\_avoidance, key\_motion\_planning, key\_mpc, key\_scenario\_optimization, type\_journal},
	pages = {5389--5396},
}

@article{chowdhri_integrated_2021,
	title = {Integrated nonlinear model predictive control for automated driving},
	volume = {106},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0967066120302240},
	doi = {10.1016/j.conengprac.2020.104654},
	language = {en},
	journal = {Control Engineering Practice},
	author = {Chowdhri, N. and Ferranti, L. and Iribarren, F. S. and Shyrokau, B.},
	month = jan,
	year = {2021},
	note = {Feature Paper of Control Engineering Practice for June 2022},
	keywords = {key\_automotive, key\_evasive, key\_mpc, type\_journal},
	pages = {104654},
}

@article{pretagostini_survey_2020,
	title = {Survey on {Wheel} {Slip} {Control} {Design} {Strategies}, {Evaluation} and {Application} to {Antilock} {Braking} {Systems}},
	volume = {8},
	url = {https://ieeexplore.ieee.org/document/8955905/},
	doi = {10.1109/ACCESS.2020.2965644},
	journal = {IEEE Access},
	author = {Pretagostini, F. and Ferranti, L. and Berardo, G. and Ivanov, V. and Shyrokau, B.},
	year = {2020},
	keywords = {key\_automotive, key\_control, key\_mpc, key\_review, type\_journal},
	pages = {10951--10970},
}

@article{brito_model_2019,
	title = {Model {Predictive} {Contouring} {Control} for {Collision} {Avoidance} in {Unstructured} {Dynamic} {Environments}},
	volume = {4},
	url = {paper=https://ieeexplore.ieee.org/document/8768044/ video=https://www.youtube.com/watch?v=crGTsiiilHo},
	doi = {10.1109/LRA.2019.2929976},
	number = {4},
	journal = {IEEE Robotics and Automation Letters},
	author = {Brito, B. and Floor, B. and Ferranti, L. and Alonso-Mora, J.},
	month = oct,
	year = {2019},
	keywords = {key\_collision\_avoidance, key\_motion\_planning, key\_mpc, key\_robotics, type\_journal},
	pages = {4459--4466},
}

@inproceedings{ferranti_safevru_2019,
	address = {Paris, France},
	title = {{SafeVRU}: {A} {Research} {Platform} for the {Interaction} of {Self}-{Driving} {Vehicles} with {Vulnerable} {Road} {Users}},
	url = {paper=https://ieeexplore.ieee.org/document/8813899/ demo=https://www.youtube.com/watch?v=iISdbfPsR9g},
	doi = {10.1109/IVS.2019.8813899},
	booktitle = {2019 {IEEE} {Intelligent} {Vehicles} {Symposium} ({IV})},
	publisher = {IEEE},
	author = {Ferranti, L. and Brito, B. and Pool, E. and Zheng, Y. and Ensing, R. M. and Happee, R. and Shyrokau, B. and Kooij, J. F. P. and Alonso-Mora, J. and Gavrila, D. M.},
	month = jun,
	year = {2019},
	keywords = {key\_automotive, key\_experiments, key\_motion\_planning, key\_mpc, key\_perception, type\_conference},
	pages = {1660--1666},
}