Distracted Driving & Voice-to-Text Overview Christine Yager Texas A&M Transportation Institute
Definition Driver distraction is a diversion of attention away from activities critical for safe driving toward a competing activity. - Regan, Lee, and Young (2009)
Types of Distraction Manual Visual Cognitive
Distraction is a Safety Issue
Distraction is a Safety Issue Prevalence o January 2013: Nearly 35% of drivers admitted reading a text or email while driving in the past month, and over 26% admitted typing one. (AAA Foundation for Traffic Safety) o In 2012, the average number of text messages sent in the U.S. Risk o Drivers who use hand-held devices are four times as likely to get into crashes serious enough to injure per themselves. day was (Monash 6.1 University) billion. (Cellular Telecommunications Industry o Using a cell phone use while driving, whether it s hand-held or hands-free, delays a driver's reactions Association) as much as having a blood alcohol concentration at the legal limit of.08 percent. (University of Utah) o Driving while using a cell phone reduces the amount of brain activity associated with driving by 37%. (Carnegie Mellon) o Text messaging creates a crash risk 23 times worse than driving while not distracted. (VTTI) o Sending or receiving a text takes a driver's eyes from the road for an average of 4.6 seconds, the equivalent-at 55 mph-of driving the length of an entire football field, blind. (VTTI) Outcome o 18% of injury crashes in 2010 involved reports of distracted driving. (NHTSA) o During NHTSA s 100-Car Naturalistic Driving Study, driver involvement in secondary tasks contributed to more than 22% of all crashes and near-crashes recorded during the study period. o This safety issue extends to professional drivers of buses, trucks, and trains: A 2008 commuter train crash in Los Angeles that killed 25 people was caused by the conductor who missed a red light because he was texting.
Distraction is a Safety Issue Prevalence o Risk May 2012: Nearly 70% of drivers reported talking on their cellphone while driving, and more than 30% admitted to reading a text or email while driving in the past month. (AAA Foundation for Traffic Safety) o Drivers who use hand-held devices are four times as likely to get into o In crashes 2011, the serious average number enough of text to messages injure sent themselves. in U.S. per (Monash day was 6.6 billion. University) (Cellular Telecommunications Industry Association) o Using a cell phone use while driving, whether it s hand-held or handsfree, delays a driver's reactions as much as having a blood alcohol concentration at the legal limit of.08 percent. (University of Utah) o Driving while using a cell phone reduces the amount of brain activity associated with driving by 37%. (Carnegie Mellon) o Text messaging creates a crash risk 23 times worse than driving while Outcome o 18% not of distracted. injury crashes in (VTTI) 2010 involved reports of distracted driving. (NHTSA) During NHTSA s 100-Car Naturalistic Driving Study, driver involvement in secondary tasks o contributed Sending to or more receiving than 22% a of text all crashes takes and a near-crashes driver's recorded eyes from during the study road period. for an o This safety issue extends to professional drivers of buses, trucks, and trains: A 2008 commuter train crash in Los Angeles that killed 25 people was caused by the conductor who missed a red light because of an entire football field, blind. (VTTI) he was texting. average of 4.6 seconds, the equivalent-at 55 mph-of driving the length
Distraction is a Safety Issue Prevalence Outcome May 2012: Nearly 70% of drivers reported talking on their cellphone while driving, and more than o 30% In the admitted U.S.: to 10% reading a of text fatal or email crashes while driving and in 17% the past of month. injury (AAA crashes Foundation for in Traffic 2011 Safety) involved reports of distracted driving. (NHTSA) In 2011, the average number of text messages sent in the U.S. per day was 6.6 billion. (Cellular o Telecommunications In Texas: In 2012, Industry more Association) than 90,000 crashes - 453 of which were Risk fatal - involved driver distraction. Nearly 1 in 4 crashes involve o Drivers who use hand-held devices are four times as likely to get into crashes serious enough to injure distracted driving. (TxDOT) themselves. (Monash University) o Using During a cell phone NHTSA s use while 100-Car driving, whether Naturalistic it s hand-held or Driving hands-free, delays Study, a driver's driver reactions as much as having a blood alcohol concentration at the legal limit of.08 percent. (University of Utah) involvement in secondary tasks contributed to more than 22% of o Driving while using a cell phone reduces the amount of brain activity associated with driving by 37%. all (Carnegie crashes Mellon) and near-crashes recorded during the study period. o Text messaging creates a crash risk 23 times worse than driving while not distracted. (VTTI) o Sending or receiving a text takes a driver's eyes from the road for an average of 4.6 seconds, the equivalent-at 55 mph-of driving the length of an entire football field, blind. (VTTI) o This safety issue extends to professional drivers of buses, trucks, and trains: A 2008 commuter train crash in Los Angeles that killed 25 people was caused by the conductor who missed a red light because he was texting.
TTI s Activities in this Area Driver Perceptions of Risks of Distraction Distraction due to in-vehicle information and warning systems Effects of reading and writing text-based messages Testimony to Texas legislature Presentations at various conferences in the U.S. Effects of voice-to-text technologies while driving
Manual vs. Voice-to-Text Mobile Apps Sponsored by the Southwest Region University Transportation Center (SWUTC) The purpose of this research was to evaluate the impacts of using voice-to-text mobile applications to send and receive text messages while driving and was driven by three primary research questions: 1. When texting using a voice-to-text application, does driving impairment improve, remain the same, or increase when compared to manual-entry texting and the baseline? 2. Are there any significant differences in performance between the two types of voice-to-text applications that were tested? 3. How do driver perceptions toward texting while driving compare to their actual performance?
Methodology 43 participants drove an instrumented vehicle on a closed course (23 females/20 males) Ages ranged from 16-63 Had to be very familiar with texting on a smartphone Four experimental conditions: o Baseline o Manual texting o Texting with Siri o Texting with Vlingo
Methodology
Methodology 3.8-mile long course Text messaging tasks were initiated at the same physical locations for each condition o Task 1: Send Only o Tasks 2-4: Read & Reply o Task 5: Read Only Content: Same short-phrased script for each condition
U-turn Start/End Task 3 Task 1 Task 5 Task 2 Task 4
Methodology Performance metrics recorded: o Driver response times o Speed o GPS o Gaze tracking o Accuracy of and length of time to complete text messaging tasks o Self-performance ratings and comments
Methodology Performance metrics recorded: o Driver response times o Speed o GPS (used to measure changes in lateral lane position) o Gaze tracking o Accuracy of and length of time to complete text messaging tasks o Self-performance ratings and comments
Methodology Performance metrics recorded: o Driver response times o Speed o GPS (used to measure changes in lateral lane position) o Gaze tracking o Accuracy of and length of time to complete text messaging tasks o Self-performance ratings and comments
Key Findings Reaction times were nearly two times slower no matter which texting method was used
Key Findings Mean Response Times 3.0 2.5 2.0 Seconds 1.5 1.0 0.5 0.0 Baseline Manual Siri Vlingo
Key Findings Reaction times were nearly two times slower no matter which texting method was used The percentage of time drivers spent looking at the forward roadway significantly decreased in any of the three texting conditions compared to the baseline.
Key Findings
Key Findings Reaction times were nearly two times slower no matter which texting method was used The percentage of time drivers spent looking at the forward roadway significantly decreased in any of the three texting conditions compared to the baseline. Task accuracy: Siri produced fewest typographical errors compared to manual and Vlingo Task Completion Times: Send Only: each method took approximately the same length of time Read & Reply, Read Only: manual-texting took least amount of time Self-performance Ratings: Participants rated Siri as much safer to use while driving than manual or Vlingo
Key Findings Self-Assessment Ratings During Experiment Baseline 6 37 Manual 11 16 9 Siri 11 17 3 Vlingo 4 18 10 50 40 30 20 10 0 10 20 30 40 50 Perception Very Unsafe Unsafe Safe Very Safe
Key Findings Are Assisted Forms of Texting Safer than Manual Texting? Voice-to-Text Mobile Apps 2 58 26 100 50 0 50 100 Percentage of drivers who view assisted texting as less safe (left of zero) and safer (right of zero) than manual texting. Perception Considerably Less Safe Somewhat Less Safe Somewhat Safer Considerably Safer