Výsledky vyhledávání - "Nishiyama, Daisuke"

Report

Discovering Avoidable Planner Failures of Autonomous Vehicles using Counterfactual Analysis in Behaviorally Diverse Simulation

Autor: Nishiyama, Daisuke, Castro, Mario Ynocente, Maruyama, Shirou, Shiroshita, Shinya, Hamzaoui, Karim, Ouyang, Yi, Rosman, Guy, DeCastro, Jonathan, Lee, Kuan-Hui, Gaidon, Adrien

Publikováno v: The 23rd IEEE International Conference on Intelligent Transportation Systems (ITSC2020)

Automated Vehicles require exhaustive testing in simulation to detect as many safety-critical failures as possible before deployment on public roads. In this work, we focus on the core decision-making component of autonomous robots: their planning al

Externí odkaz: http://arxiv.org/abs/2011.11991

Zobrazit plný text záznamu

Report

Behaviorally Diverse Traffic Simulation via Reinforcement Learning

Autor: Shiroshita, Shinya, Maruyama, Shirou, Nishiyama, Daisuke, Castro, Mario Ynocente, Hamzaoui, Karim, Rosman, Guy, DeCastro, Jonathan, Lee, Kuan-Hui, Gaidon, Adrien

Publikováno v: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020, pp. 2103-2110

Traffic simulators are important tools in autonomous driving development. While continuous progress has been made to provide developers more options for modeling various traffic participants, tuning these models to increase their behavioral diversity

Externí odkaz: http://arxiv.org/abs/2011.05741

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Report

Asymmetric Cloaking Theory Based on Finsler Geometry ~ How to design Harry Potter's invisibility cloak with a scientific method ~

Autor: Amemiya, Tomohiro, Nishiyama, Daisuke, Taki, Masato

Is it possible to actually make Harry's invisibility cloaks? The most promising approach for realizing such magical cloaking in our real world would be to use transformation optics, where an empty space with a distorted geometry is imitated with a no

Externí odkaz: http://arxiv.org/abs/1211.3040

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Akademický článek

Feature selection to classify lameness using a smartphone-based inertial measurement unit.

Autor: Arita, Satoshi¹ (AUTHOR), Nishiyama, Daisuke¹ (AUTHOR) dnishiya@wakayama-med.ac.jp, Taniguchi, Takaya¹ (AUTHOR), Fukui, Daisuke¹ (AUTHOR), Yamanaka, Manabu¹ (AUTHOR), Yamada, Hiroshi¹ (AUTHOR)

Publikováno v: PLoS ONE. 9/30/2021, Vol. 16 Issue 9, p1-9. 9p.

Zobrazit plný text záznamu

Plný text ve formátu HTML