Designing a Pedestrian Simulator for Autonomous Vehicles in Mixed Traffic

As autonomous vehicles are introduced to our roads, they will co-exist with vehicles of varying levels of autonomy, including those that are manually-driven or semi-autonomous. While manually-driven vehicles can communicate with pedestrians through cues such as eye contact and hand gestures, semi-autonomous and autonomous vehicles will not. To study this future interaction, we designed a pedestrian simulator in virtual reality (VR). We immersed participants in VR to evaluate how they could make safe crossing decisions when faced with vehicles of varying autonomy level. Our findings highlight the role interfaces play in communicating awareness and intent, across vehicles of all autonomy levels, and demonstrate the usefulness of immersive pedestrian simulators in designing autonomous vehicle interfaces.

Mahadevan, K., Sanoubari, E., Somanath, S., Young, J. E., & Sharlin, E. (2019, June). AV-Pedestrian Interaction Design Using a Pedestrian Mixed Traffic Simulator. In Proceedings of the 2019 on Designing Interactive Systems Conference (pp. 475-486). ACM.

Find the paper at: 

Pedestrian Simulator
Friday, October 19, 2018 - 10:45pm
Lab Member: 
Karthik Mahadevan

Communication of Awareness and Intent in Autonomous Vehicle-Pedestrian Interaction

In this project, we explored how we can build interfaces to suitably replace driver cues which pedestrians are used to receiving but will no longer receive as a result of introducing autonomous vehicles on our roads in the not-so-distant future.

Current vehicle-pedestrian interactions involve the vehicle communicating cues through its physical movement and through nonverbal cues from the driver. Our work studies vehicle-pedestrian interactions at a crosswalk in the presence of autonomous vehicles (without a driver) facilitated by the deployment of interfaces intended to replace missing driver cues. We created four prototype interfaces based on different modalities (such as visual, auditory, and physical) and locations (on the vehicle, on street infrastructure, on the pedestrian, or on a combination of the vehicle, street infrastructure, and the pedestrian). Our findings from two user studies indicate that interfaces which communicate awareness and intent can help pedestrians attempting to cross. We also find that interfaces are not limited to existing only on the vehicle.

Video Preview: 

Link to Paper: 

Pedestrian AV Interface
Monday, January 22, 2018 - 11:45am
Lab Member: 
Karthik Mahadevan