SLIDE 1:
Drowsy Driver Detection and Warning System For Commercial Vehicle Drivers:Field Operational Test Design, Analysis, and Progress

Dr. Paul Rau
Office of Vehicle Safety Research
Heavy Vehicle/Driver Interaction Division

SAE Government / Industry Meeting
Washington, DC
May 11, 2005


SLIDE 2:
Estimated Total Problem Size

 - Approximately 100,000 drowsy-related crashes per year.

 - Approximately 1,357 drowsy-related fatal crashes resulting in 1,544 fatalities.
 
 - Approximately 71,000 drowsy-related crashes involved non-fatal injuries.

 - Estimated annual monetary loss is about $12.5 Billion.



SLIDE 3:
DROWSY DRIVER TECHNOLOGY PROGRAM
Program Size

Total Est Drowsy Crashes
	Passenger Vehicles	96,000
	Heavy Trucks		3,300

Total Est Involvement
	Passenger Vehicles	95.9%
	Heavy Trucks		3.3%

Drowsy Related Fatalities
	Passenger Vehicles	1,429
	Heavy Trucks		   84

Fatalities Outside Vehicle
	Passenger Vehicles	12%
	Heavy Trucks		37%

Drowsiness Cited by Police
	Passenger Vehicles	.52%
	Heavy Trucks		.82%

Miles/Year Exposure
	Passenger Vehicles	11k
	Heavy Trucks		60k

Years Opeational Life
	Passenger Vehicles	13
	Heavy Trucks		15

Primary Driving Period
	Passenger Vehicles	day
	Heavy Trucks		night

* estimates based on 5-year period 1989-1993 (Knipling & Wang, 1995)


SLIDE 4:
Program Justification

* Previous trucking summit meetings identify drowsiness as the #1 driving problem.

* Drivers are often unaware of their deteriorating condition.

* Drivers are often motivated to keep driving.

* Incipient drowsiness can be observed and measured.



SLIDE 5:
Program Objectives

* Reduce the injuries, deaths, and costs associated with drowsiness.

* Develop, test, and evaluate a prototype continuous/drowsiness detection and warning system for commercial vehicle drivers. 


SLIDE 6:
The Copilot
[uncaptioned photos]


SLIDE 7:
Coherence over bouts between 20 minute visual PVT lapse duration and PERCLOS 1 score (subject 6109)


SLIDE 8:
Field Operational Test

 * Performance Period: October 2002 – October 2005.

 * FOT Conductor – Virginia Tech. Transportation Institute (VTTI).

 * FOT Independent Evaluator – Volpe Center.


SLIDE 9:
Research Questions

1. What is the distribution of drowsiness in the population of heavy vehicle drivers, and how do these groups differ in their performance w/ or w/o the warning system?

2. What are the effects of independent factors such as driver age, health, sleep patterns, road conditions, and type of trucking operation?

3. What is the effect of the warning system and independent factors on conflict driving, near collisions and severe near collisions?


4. What are the fleet acceptance and deployment prospects?



SLIDE 10:
Experimental Design

Subjects

- 102 drivers, 34 single-unit  heavy trucks.

- Long haul operations:
	* Howell’s Trucking Company – 51 drivers.

- Overnight express operations:
	* Pitt-Ohio Express (PA Turnpike) - 6 drivers.
	* J.B. Hunt (Virginia Interstate) – 45 drivers.



SLIDE 11:
Experimental Design
	Alert Enabled
	Alert Disabled
______    _____________________
A  A  A  B  B  B  B  B  B  B  B  B  

  * Experimental Group
  * 34 Drivers/ Op.Type


A  A  A  A  A  A  A  A  A  A  A  A  
____________________________________   
1  2  3  4  5  6  7  8  9 10 11 12 

	     Week

  * Control Group
  * 17 Drivers/ Op.Type
SLIDE 12:
Analysis

Safety Benefits

- DDWS Effect on Drowsiness
  * Drowsy level w/ or w/o the DDWS.
  * Drowsiness varying by independent factors – age, health, sleep patterns, road conditions, type of trucking operation, etc.

- Driving Performance
  * Performance level w/ or w/o the DDWS.
  * Performance varying by independent factors – age, health, sleep patterns, road conditions, type of trucking operation, etc.



SLIDE 13:
Analysis

- Conflict Driving
  * Conflict level w/ or w/o the DDWS.
  * Conflicts varying by independent factors – age, health, sleep patterns, road conditions, type of trucking operation, etc.

- Causal Analysis
  * Video Coding – Intervening variables.

- Crash Estimation
  * Monte Carlo Simulation


SLIDE 14:
Status

Whereas, the process of data collection, reduction, and transfer has begun, there are no results to report at this time.

The final report is due October 30, 2005. 



SLIDE 15:	
Further Information:

Paul S. Rau, Ph.D., CPE
National Highway Traffic Safety Administration
Office of Vehicle Safety Research
400 Seventh Street, S.W. Room 6220
Washington, D.C. 20590

	Voice : (202) 366-0418
	Fax    : (202) 366-7237
	E-mail: prau@nhtsa.dot.gov