D
Dave W. Oyler
Researcher at University of Michigan
Publications - 12
Citations - 467
Dave W. Oyler is an academic researcher from University of Michigan. The author has contributed to research in topics: Game theory & Control system. The author has an hindex of 7, co-authored 12 publications receiving 315 citations.
Papers
More filters
Journal ArticleDOI
Game Theoretic Modeling of Driver and Vehicle Interactions for Verification and Validation of Autonomous Vehicle Control Systems
TL;DR: In this article, the authors present a game theoretic traffic model that can be used to test and compare various autonomous vehicle decision and control systems and calibrate the parameters of an existing control system.
Journal ArticleDOI
Pursuit-evasion games in the presence of obstacles
TL;DR: The methods provided are used to determine dominance and solve the game, and a novel, multiplayer pursuit-evasion game is presented that features three players on two teams and can be used to model rescue scenarios and biological behaviors.
Proceedings ArticleDOI
Hierarchical reasoning game theory based approach for evaluation and testing of autonomous vehicle control systems
TL;DR: Two algorithms, based on Stackelberg policies and decision trees, are quantitatively compared in a traffic scenario where all the human-driven vehicles are modeled using the presented game theoretic approach.
Posted Content
Game-Theoretic Modeling of Driver and Vehicle Interactions for Verification and Validation of Autonomous Vehicle Control Systems
TL;DR: In this article, the authors present a game theoretic traffic model that can be used to test and compare various autonomous vehicle decision and control systems and calibrate the parameters of an existing control system.
Proceedings ArticleDOI
A game theoretical model of traffic with multiple interacting drivers for use in autonomous vehicle development
TL;DR: A computationally tractable solution to this problem is provided by employing hierarchical reasoning together with a suitable reinforcement learning algorithm, which demonstrate that the resulting driver models provide reasonable behavior for the given traffic scenarios.