WASHINGTON: Route recommendations and warnings about traffic jams might be nearly always spot-on, but one of the biggest flaws in navigation software is that it can't tell you if and where a parking space is free near your destination.
To fix this glaring omission for urban drivers, a team at the Massachusetts Institute of Technology (MIT) has come up with a program that aims "to identify parking lots that offer the best balance of proximity to the desired location and likelihood of parking availability."
"Current navigation systems conflate time-to-drive with the true time-to-arrive by ignoring parking search duration and the final walking leg," the MIT team said in their paper, noting that "such underestimation can significantly affect user experience, mode choice, congestion and emissions."
The researchers believe that their more "adaptable method" – to direct drivers to the "optimal" parking area rather than their destination – would work better and reduce the frustrations caused by having to spend time driving around looking for a place to pull up after seeing that there is no room at a destination
The system is "a probability-aware approach that considers all possible public parking lots near a destination, the distance to drive there from a point of origin, the distance to walk from each lot to the destination, and the likelihood of parking success," the researchers said.
"In simulated tests with real-world traffic data from Seattle, this technique achieved time savings of up to 66% in the most congested settings," the researchers said.
Providing a clearer idea of how long it will take to drive and park means people will be less likely to be late for meetings or potentially make rash decisions as time pressures increase.
It could also encourage more people to opt for city buses, trams or trains as it becomes clearer that a 20-minute drive across town may actually take closer to an hour once parking and walking are factored in.
The next step, the researchers said, would be to develop a system to gather the data needed to make this a reality, likely involving a combination of data from car park operators and crowdsourced information from drivers. – dpa
