Tag
This paper audits graph neural network-based road-level crash prediction by replicating a recent uncertainty-aware model across three London boroughs, finding that most reported design effects fail to replicate or even reverse sign. The authors show that a parameter-free baseline ranking road segments by past crash counts matches or beats the GNN models at horizon-matched lookbacks, arguing reported gains are largely an artefact of short-horizon baselines and calling for horizon-matched baselines and multi-seed reporting.
Volvo is updating its electric vehicles with new connected safety features that alert drivers to hazards like animals and cyclists by sharing real-time data between vehicles.
This study uses connected vehicle telemetry data from Sydney to predict high-risk driving hotspots, benchmarking machine learning and time-series models for proactive road safety interventions.
A study in Current Biology finds that cougars reduce deer-vehicle collisions by up to 76% in areas with healthy cougar populations, as deer avoid habitats near roads where the big cats hunt.
Starting July 1, all new vehicles sold in the European Union must include a preinstalled interface for connecting a breathalyzer lock, as part of the EU's Vision Zero program to reduce alcohol-related traffic fatalities.
A company called LED Truck Media has launched a truck with curved LED panels that display 3D anamorphic ads on roads, raising safety concerns about driver distraction.