Not The Shortest Way Home - But The Safest
Written by Lucy Black
Saturday, 22 September 2018

We talk a lot about how self-driving cars might save lives, but perhaps there are other ways of making things safer for drivers and pedestrians. Researchers from Cardiff University have been investigating how best to compute the safest way home.

Maps are everywhere and since maps moved to digital we have been able to do difficult things like compute the shortest route between two locations - but distance is not the only metric.

"Each year about 1.24 million deaths worldwide result from road traffic crashes, making this the eighth leading cause of death globally."

It is estimated that about 25% of all road traffic deaths are pedestrians. I don't know about you, but when I'm working out how to get from one place to another I often consider how difficult and dangerous a route is. Most of the time that consideration is unconscious - I just prefer one route to another and the preference sometimes isn't just for the quickest or shortest route. Avoiding dangerous roads, difficult crossings or reducing the number of crossings is also something to take into account. And yet when you ask Google Maps, say, for a route you get the shortest and not the safest.

In a new study, published in the journal Accident Analysis and Prevention, researchers have shown how a novel system for scoring the safety of an area can successfully predict the likely number of road casualties. The scoring of the routes is done automatically,

"We propose a novel linear model of pedestrian safety in urban areas with respect to road traffic crashes that considers a single independent variable of pedestrian path safety. This variable is estimated for a given urban area by sampling pedestrian paths from the population of such paths in that area and in turn estimating the mean safety of these paths. We argue that this independent variable directly models the factors contributing to pedestrian safety. This contrasts previous approaches, which, by considering multiple independent variables describing the environment, traffic and pedestrians themselves, indirectly model these factors. Using data about 15 UK cities, we demonstrate that the proposed model accurately estimates numbers of pedestrian casualties."

There are plans to turn the model into an app, but I'm not convinced how successful it would be. Will people actually take a longer but marginally safer route? It seems more likely that road planners and planners in general would be better placed to make use of the model to improve road safety and concentrate on pedestrian danger spots.

It does raise the idea of a whole class of apps however. What about safe bike routes and even safer car routes. The real question is would users value safety?

A computational model of pedestrian road safety: The long way round is the safe way home

Charlotte Hannah, Irena Spasić and Padraig Corcoran

(Shamefully the paper is behind a paywall)

#### Related Articles

Finding Beautiful Walking Routes

School Bus Optimization

DIY Streetview

The XY Traveling Salesman Problem Solved

The Physical Travelling Salesman Challenge

 Linux Foundation Launches Open Source COVID Group 29/07/2020The Linux Foundation has set up a group to bring together a number of open source projects that are working to fight COVID-19.  The Linux Foundation Public Health (LFPH) builds, secures, and sust [ ... ] + Full Story OpenCV AI Kit On Kickstarter22/07/2020To celebrate its 20th Anniversary OpenCV has announced its OpenCV AI Kit, affordable hardware and software for AI-powered Computer Vision, and initiated a Kickstarter Campaign.The funding goal of \$20, [ ... ] + Full Story More News