S
Stephanie Lefevre
Researcher at University of California, Berkeley
Publications - 29
Citations - 2625
Stephanie Lefevre is an academic researcher from University of California, Berkeley. The author has contributed to research in topics: Advanced driver assistance systems & Intersection. The author has an hindex of 18, co-authored 29 publications receiving 1999 citations. Previous affiliations of Stephanie Lefevre include Institut national des sciences appliquées & Renault.
Papers
More filters
Journal ArticleDOI
A survey on motion prediction and risk assessment for intelligent vehicles
TL;DR: This paper points out the tradeoff between model completeness and real-time constraints, and the fact that the choice of a risk assessment method is influenced by the selected motion model.
Proceedings ArticleDOI
Learning-based approach for online lane change intention prediction
TL;DR: A novel approach based on Support Vector Machine and Bayesian filtering is proposed for online lane change intention prediction that is able to predict driver intention to change lanes on average 1.3 seconds in advance, with a maximum prediction horizon of 3.29 seconds.
Journal ArticleDOI
A Learning-Based Framework for Velocity Control in Autonomous Driving
TL;DR: A framework for autonomous driving which can learn from human demonstrations, and it is applied to the longitudinal control of an autonomous car to handle cases where the training data used to learn the driver model does not provide sufficient information about how a human driver would handle the current driving situation.
Journal ArticleDOI
Automated Driving The Role of Forecasts and Uncertainty - A Control Perspective
TL;DR: An overview of the research on control design methods which systematically handle uncertain forecasts for autonomous and semi-autonomous vehicles and relevant aspects of the recent results are presented.
Proceedings ArticleDOI
Comparison of parametric and non-parametric approaches for vehicle speed prediction
TL;DR: A comparative evaluation of parametric and non-parametric approaches for speed prediction during highway driving shows that the relative performance of the different models vary strongly with the prediction horizon, taking into account when selecting a prediction model for a given ITS application.