Real-time Safe Semi-Autonomous Control with Driver Modeling

Victor Shia

EECS Department
University of California, Berkeley
Technical Report No. UCB/EECS-2014-41
May 1, 2014

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2014/EECS-2014-41.pdf

Distracted driving is still a major concern on roadways today. According to the US Department of Transportation, in 2011, 387,000 people were injured in crashes involving a distracted driver. While there has been tremendous work in vehicular safety systems, as the velocity of the vehicle increases, threat assessment becomes more difficult to predict. In this regime, understanding how the driver behaves is critical in determining the safety of the vehicle. This work presents a framework for incorporating human driver modeling with a controller to provide a semi-autonomous system for vehicle safety. We describe how the system is built, present metrics to evaluate its utility and conduct real-time experiments with a safety controller to verify the utility of incorporating the driver’s behavior while designing a semi-autonomous system.

Advisor: Ruzena Bajcsy


BibTeX citation:

@mastersthesis{Shia:EECS-2014-41,
    Author = {Shia, Victor},
    Title = {Real-time Safe Semi-Autonomous Control with Driver Modeling},
    School = {EECS Department, University of California, Berkeley},
    Year = {2014},
    Month = {May},
    URL = {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2014/EECS-2014-41.html},
    Number = {UCB/EECS-2014-41},
    Abstract = {Distracted driving is still a major concern on roadways today. According to the US Department of Transportation, in 2011, 387,000 people were injured in crashes involving a distracted driver. While there has been tremendous work in vehicular safety systems, as the velocity of the vehicle increases, threat assessment becomes more difficult to predict. In this regime, understanding how the driver behaves is critical in determining the safety of the vehicle. This work presents a framework for incorporating human driver modeling with a controller to provide a semi-autonomous system for vehicle safety. We describe how the system is built, present metrics to evaluate its utility and conduct real-time experiments with a safety controller to verify the utility of incorporating the driver’s behavior while designing a semi-autonomous system.}
}

EndNote citation:

%0 Thesis
%A Shia, Victor
%T Real-time Safe Semi-Autonomous Control with Driver Modeling
%I EECS Department, University of California, Berkeley
%D 2014
%8 May 1
%@ UCB/EECS-2014-41
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2014/EECS-2014-41.html
%F Shia:EECS-2014-41