Altruistic Navigation

Recent advancements in computer vision, reinforcement learning and automated driving is allowing carmakers and scientists to steadily reach Level 5 automation. It is being positioned as a potential silver bullet for road safety and traffic congestion problems. While that seems to be the direction for automotive research especially with some developed countries already deploying their fleets, adoption in the developing world will take some time because of the difference in driving conditions, infrastructure readiness, skepticism, and ownership costs. Thus, our future roads will more likely be occupied by a heterogeneous mix of vehicles with varying levels of automation, or none at all. Government stakeholders will then have the daunting task of managing a more complex traffic flow, with the challenge of encouraging drivers who will only rely on some or no route guidance (no automation) to adopt sustainable routes and driving behaviors.

This research program explores novel navigation and wayfinding applications for connected drivers and commuters. The goal is to develop navigation and wayfinding solutions that can influence the mobility patterns of commuters and connected drivers towards more livable and sustainable cities. It is focused on three equally particular approaches:

  • understanding the practices of connected drivers and commuters, and the human factors behind their navigation and wayfinding decisions [CHI’19];
  • exploring novel and persuasive interaction techniques, data visualization, and information architecture that promotes altruistic, purposeful, and effective driving navigation and commuter wayfinding; and
  • creating agent-based models to understand how these designs and techniques can affect urban mobility and the system-wide performance of road networks.