Drivers can now guide a car using their eyes, not hands
get the car flowing again.
To demonstrate the car’s autonomy, Rojas at one point jumped in front of the car — which was at that moment driving at perhaps ten miles per hour — and the Dodge was immediately stopped by the cameras that had detected the obstacle. “I was lucky this time,” Rojas said jokingly.
While Rojas escaped, driver David Latotzky sat calmly on the passenger seat, wearing a bicycle helmet that is key to the functioning of the EyeDriver: One camera mounted on top of it monitors the street, a second one constantly keeps track of the driver’s eyes’ movements. “We chose a bicycle helmet because they’re the most ergonomic ones,” Rojas said. Selling that technology to customers, however, might be a tough call — it the driver look like he or she came straight out of a Star Wars movie.
If using your eyes for steering seems to tricky anyway, the researchers already have an alternative: Use your iPhone instead. In fall last year they presented a technology that allows to use Apple’s smart phone as remote control for the car. “Autonomous driving systems may considerably change our mobility in the future,” Rojas said.
Should the technology-packed vehicle have a major bug, there is still an old fashioned way of stopping it. Two big external emergency buttons at the rear of the car allow people outside to shut down all systems.
The software: EyeDrive
The eyeDriver software is a prototype application for steering the research vehicle Spirit of Berlin using eye movements. The software was designed by computer scientists at Freie Universität Berlin in collaboration with the company, SMI (SensoMotoric Instruments). The eye movements of the driver are collected and converted into control signals for the steering wheel. The speed is controlled separately and is not included in eyeDriver. The software shows that you can drive a vehicle alone with eye movements.
The HED4 solution by SMI is used for detecting and tracking the eye movements. It is a converted bicycle helmet equipped with two cameras and an infrared LED, as well as a laptop computer with special software. One of the cameras is pointed to the front in the same direction as the person wearing the helmet (scene camera), while the other camera films one eye of the wearer (eye camera). The infrared light supports the eye camera and is pointed to the eye under observation. A transparent mirror that reflects only the