Your self-driving car can keep you safe by predicting exactly when your 'human' brain is about to make a stupid mistake.
April 16, 2026
Original Paper
Adaptive Bounded-Rationality Modeling of Early-Stage Takeover in Shared-Control Driving
arXiv · 2604.10806
The Takeaway
When a semi-autonomous car needs the driver to take over, things often get dangerous because humans are 'irrational.' This study found that we can actually build a mathematical model of that irrationality to predict hazardous takeovers. By tracking real-time fluctuations in your cognitive state, the car's AI can sense when you’re too distracted or overwhelmed to drive safely before you even touch the wheel. We used to think human error was random, but it turns out our 'bounded rationality' is actually very predictable. This means the future of car safety isn't just better sensors on the road, but sensors that understand the messy rhythms of the human mind.
From the abstract
Human drivers' control quality in the first seconds after a handover is critical to shared-driving safety; potentially unsafe steering or pedal inputs therefore require detection and correction by the automated vehicle's safety-fallback system. Yet performance in this window is vulnerable because cognitive states fluctuate rapidly, causing purely rationality-driven, cognition-unaware models to miss early control dynamics. We present an interpretable driver model grounded in bounded rationality w