A team of researchers is developing a dataset to fill a critical gap in self-driving cars’ learning models.

Researchers at the University of Maryland are working to make autonomous vehicles safer for blind pedestrians, reports Laurie Robinson in Maryland Today. According to the researchers, autonomous cars lack “solid data” for how blind pedestrians move and navigate streets and sidewalks.
“The oversight can hinder the ability of autonomous vehicles to safely predict the movements of blind pedestrians, whose behaviors, such as using a cane to feel the curbs or veering, might confuse current models, leading to potentially dangerous errors.” The research team is creating a dataset called BlindWays that uses real-world 3D motion-capture data to help the systems understand blind pedestrians more effectively.
In testing, the model reduced prediction errors by over 80 percent in some cases. “To enhance and expand the BlindWays dataset, the researchers plan to collaborate with organizations specializing in disability rights, mobility training and urban planning. These partnerships aim to diversify participants, locations and scenarios in the dataset.”
FULL STORY: Autonomous Cars Don’t Understand How Blind People Move Around. A Research Team Is Trying to Boost Safety.

Alabama: Trump Terminates Settlements for Black Communities Harmed By Raw Sewage
Trump deemed the landmark civil rights agreement “illegal DEI and environmental justice policy.”

Study: Maui’s Plan to Convert Vacation Rentals to Long-Term Housing Could Cause Nearly $1 Billion Economic Loss
The plan would reduce visitor accommodation by 25% resulting in 1,900 jobs lost.

Why Should We Subsidize Public Transportation?
Many public transit agencies face financial stress due to rising costs, declining fare revenue, and declining subsidies. Transit advocates must provide a strong business case for increasing public transit funding.

Paris Bike Boom Leads to Steep Drop in Air Pollution
The French city’s air quality has improved dramatically in the past 20 years, coinciding with a growth in cycling.

Why Housing Costs More to Build in California Than in Texas
Hard costs like labor and materials combined with ‘soft’ costs such as permitting make building in the San Francisco Bay Area almost three times as costly as in Texas cities.

San Diego County Sees a Rise in Urban Coyotes
San Diego County experiences a rise in urban coyotes, as sightings become prevalent throughout its urban neighbourhoods and surrounding areas.
Urban Design for Planners 1: Software Tools
This six-course series explores essential urban design concepts using open source software and equips planners with the tools they need to participate fully in the urban design process.
Planning for Universal Design
Learn the tools for implementing Universal Design in planning regulations.
Smith Gee Studio
Alamo Area Metropolitan Planning Organization
City of Santa Clarita
Institute for Housing and Urban Development Studies (IHS)
City of Grandview
Harvard GSD Executive Education
Toledo-Lucas County Plan Commissions
Salt Lake City
NYU Wagner Graduate School of Public Service