The DesignCore sensor interface card for the Nvidia Jetson AGX Xavier developer kit allows engineers to quickly connect multiple cameras or sensors.

Accepting up to 16 streams of input data accelerates development of advanced artificial intelligence (AI) robotics and autonomous applications. Sensor data is delivered via a serial link and de-serialized into MIPI CSI-2 data for consumption on the Jetson AGX Xavier developer kit. This allows the sensors to be placed up to 15m away from the processing unit. GPIO and I2C control are available for configuration and reset. An on-board FPGA provides hardware-level synchronization capability.

D3 Engineering

Automated cars, operators fail to detect dangers

Automated cars are becoming more common, but still require drivers to react to dangers undetected by an automated system. Research from two Texas schools, Rice University in Houston and Texas Tech University in Lubbock, found drivers often fail to spot hazards missed by automated vehicles, and it only gets worse the longer drivers ride in them.

Researchers examined the behavior of 60 licensed drivers operating an automated car in a simulator. Participants were told that due to the automation, they would not need to operate the steering wheel, brake pedal, or accelerator pedal. They were instructed to monitor the roadway for vehicles that were stopped dangerously at intersections and intruding into the driver’s lane, which constituted a hazard the automated vehicle could not detect. Participants also had to distinguish between vehicles safely stopped and dangerously stopped at intersections.

Driver accuracy dropped between 7% and 21% throughout the 40-minute simulation. Within the first 10 minutes the success rate was, at best, close to 88%, suggesting that all drivers missed at least some hazards.

Pat DeLucia, a professor of psychological sciences at Rice and the study’s co-author, says people might get used to cars doing the driving and become complacent. Previous research indicates that people are terrible at monitoring for occasional hazards, so the new research “suggests that this phenomenon of difficulty monitoring effectively throughout time extends to monitoring an automated car.”

Texas Tech Psychology Sciences Professor Eric Greenlee, the study’s lead author, adds, “The bottom line is, until automated driving systems are completely reliable and can respond in all situations, the driver must stay alert and be prepared to take over. And this research clearly shows that is not happening and gets worse as time passes.”

The study was co-authored by David Newton, a graduate student at Texas Tech.

Rice University

Texas Tech University