Include pedestrian collision warnings on in-vehicle heads-up displays to reduce reaction time, maximum deceleration, and, in some cases, stopping distance and braking time.
Study performed with sixteen drivers with actual pedestrians in a parking lot environment evaluated a display showing the word “BRAKE” and a virtual shadow that changes size as the vehicle gets closers to the pedestrian.
Made Public Date
01/08/2018

13

Nationwide
United States
TwitterLinkedInFacebook
Identifier
2017-00775

Look at Me: Augmented Reality Pedestrian Warning System Using an In-vehicle Volumetric Head Up Display

Background

Pedestrian collision warning systems in vehicles generally work by warning drivers through auditory or visual alerts when pedestrians are detected in the vehicle path. However, these warnings often lack spatial information, so drivers need to further localize (i.e., recognize direction and distance of) approaching pedestrians to appropriately react. This study uses augmented reality (AR) heads up displays (HUDs) to answer two questions: (1) Can visual warnings on HUDs improve driver performance? (2) Can spatial information provided by AR HUDs change braking behavior?

Sixteen drivers were asked to drive a test vehicle in a parking lot and brake for crossing pedestrians with three pedestrian collision warning interface designs (no warning, HUD "BRAKE" sign, HUD virtual shadow enlarging as the vehicle approaches the pedestrian) and two levels of distance to pedestrians (near – 2.5 sec time to collision, far – 5 sec time to collision). The first runs used no warning signs to establish a baseline, the remaining conditions were then completed in an order to minimize learning effects. The location of road events was randomized and "no event" trials were randomly added to minimize anticipation of pedestrians.

The study analyzed deceleration profiles during each braking maneuver with dependent variables as reaction time, braking time, time to stop, maximum deceleration, and stopping distance. Data from 14 of the participants was analyzed using two-way repeated measure analysis of variance (ANOVA) to examine the effect of interface design and target distance.

Lessons Learned

Include pedestrian collision warnings on in-vehicle heads-up displays to reduce reaction time, maximum deceleration, and, in some cases, stopping distance and braking time.

  • Reaction, Braking Time, and Time to Stop: Post-hoc tests found the virtual shadow reduced reaction time while increasing braking time, resulting in the same time to stop as the baseline for near and far targets. The brake sign warning reduced reaction and braking times, resulting in reduced time to stop, target distance did not affect reaction time.
  • Maximum Deceleration: For the near targets, both interface designs reduced maximum deceleration. For the far targets, the traditional warning showed even higher maximum deceleration than the baseline.
  • Stopping Distance and Gap: For far targets, both HUD interfaces reduced stopping distance, which resulted in larger gaps leading up to the pedestrians. There was no improvement for the near target.

The proposed design and findings can be extended to other use-cases such as cross traffic alerts to avoid collision with vehicles backing up in parking lots, given that high performance object detection and localization technology is available.

Look at Me: Augmented Reality Pedestrian Warning System Using an In-vehicle Volumetric Head Up Display

Look at Me: Augmented Reality Pedestrian Warning System Using an In-vehicle Volumetric Head Up Display
Publication Sort Date
03/07/2016
Author
Kim, Hyungil, et.al.
Publisher
ACM International Conference on Intelligent User Interfaces

(Our website has many links to other organizations. While we offer these electronic linkages for your convenience in accessing transportation-related information, please be aware that when you exit our website, the privacy and accessibility policies stated on our website may not be the same as that on other websites.)

Goal Areas
System Engineering Elements

Focus Areas Taxonomy: