Safety

This paper describes a general method to generate warnings for the driver of a vehicle. The
method takes into account the current measured state of the own vehicle and observed objects, the uncertainties of these measurements, models of driver, vehicle, and object behavior, and information about the environment, especially how it influences the driver and the observed object. This method is designed to work in two dimensions. It is being implemented into a side collision warning system for transit buses.

Robotics Institute, Carnegie Mellon University

Presented at the ITS America Annual Conference and Exposition, April 26 - 28, 2004 San Antonio, Texas

A discrete-time model, which characterizes a driver’s braking behavior, is developed. According to the proposed model, the amount of braking depends on the current vehicle speed and the required stopping distance. The model is used to simulate the performance of the NHTSA (National Highway Traffic Safety Administration) Alert Algorithm. The simulation results indicate that, in the situation where an inattentive driver is approaching a stopped lead vehicle at 60 mph, the probability of collision is less than 17.6% when the NHTSA Alert Algorithm is in minimum sensitivity mode. In maximum sensitivity mode, the probability of collision is less than 3.2%.

The Johns Hopkins University - Applied Physics Laboratory

Presented at the ITS America Annual Conference and Exposition, April 29 –May 2, 2002 Long Beach, California

A discrete-time model, which characterizes a driver’s braking behavior, is
developed. According to the proposed model, the amount of braking depends on the
current vehicle speed and the required stopping distance. The model is used to simulate
the performance of the NHTSA (National Highway Traffic Safety Administration) Alert
Algorithm. The simulation results indicate that, in the situation where an inattentive
driver is approaching a stopped lead vehicle at 60 mph, the probability of collision is less
than 17.6% when the NHTSA Alert Algorithm is in minimum sensitivity mode. In
maximum sensitivity mode, the probability of collision is less than 3.2%.

The Johns Hopkins University

Presented at the ITS America Annual Conference and Exposition, April 29-May 2, 2002, Long Beach, California

We describe a computational architecture of a collision early warning system for ve-
hicles and other principals. Early warnings allow drivers to make good judgments and
to avoid emergency stopping or dangerous maneuvering. With many principals (vehicles,
pedestrians, bicyclists, etc) coexisting in a dense intersection, it is difficult to predict even
a few seconds in advance, since there are an enormous number of possible scenarios. It is a
major challenge to manage computational resources and human resources so that only the
more plausible collisions are tracked and of those, only the most critical collisions prompt
warnings to drivers. In this paper, we propose a two-stage collision risk assessment process,
including (1) a preliminary assessment via simple efficient geometric computations which
throughly considers surrounding principals and identifies likely potential accidents, and (2)
a specialized assessment which computes more accurate collision probabilities via sophis-
ticated statistical inference. The whole process delivers an expected utility assessment to
available user-interfaces, allowing the user interfaces make discriminating choices of when
to warn drivers or other principals.

Palo Alto Research Center

Fujitsu Limited

Presented at the 15th World Congress on Intelligent Transport Systems, November 16-20, 2008, New York, New York

The current emergency evacuations practices are mainly focused on two levels: either in a relatively larger scale of urban or state area; or in a small-scale like a building and elevators. In this paper, a microscope simulation framework is proposed to develop suitable transportation evacuation plans for Multi-Institutional Centers (MIC). VISSIM is selected as the simulation tool, while the Genetic Algorithm (GA) is used to calibrate driving behavior parameters for VISSIM. As a case study, the Texas Medical Center (TMC) network is modeled and the evacuation plans are developed and evaluated. Results show that the proposed framework is a good and practical tool for developing and evaluating appropriate evacuation plans under similar instances.

Texas Southern University

KOA Corporation

Presented at the ITS America Annual Conference and Exposition, May 3-5, 2010, Houston, Texas