Lidar Supplier Velodyne 'Baffled' at Fatal Uber Crash
The car's lidar system should have detected the pedestrian, says the President of Velodyne Lidar, Inc.
A pedestrian jaywalking across a dark Arizona road should have been detected by the autonomous Uber car that fatally struck her on Sunday. So says Marta Thoma Hall, president of Velodyne Lidar Inc., reports Bloomberg.
"We are as baffled as anyone else," Thoma Hall told Bloomberg. "Certainly, our Lidar is capable of clearly imaging Elaine [Herzberg] and her bicycle in this situation. However, our Lidar doesn’t make the decision to put on the brakes or get out of her way."
Indeed, Thoma Hall agrees with The Drive's Alex Roy, who said the lidar should have detected Elaine Herzberg beyond line-of-sight as she pushed her bike across a dark road in Tempe, Arizona. Lidar, or "laser radar," quite literally makes its own light by shooting a laser down the road and detecting any reflections that bounce off obstructions. The distance between the sensor and the obstruction can be calculated by comparing the speed of light to the time between the laser transmission and receipt of the reflection.
"In addition to Lidar, autonomous systems typically have several sensors, including camera and radar to make decisions,” Thoma Hall told Bloomberg. "We don’t know what sensors were on the Uber car that evening, if they were working, or how they were being used." Even if the camera did not see Herzberg in the dark, the radar and lidar should have, particularly since she and her bicycle were perpendicular to the road, presenting a larger cross-section to reflect these signals. It is highly unlikely that both of these systems failed, which may indicate a problem in how the autonomous software interpreted their input.
"We at Velodyne are very sad, and sorry about the recent Uber car accident which took a life,” Thoma Hall told Bloomberg. "David Hall, company CEO, inventor and founder, believes the accident was not caused by Lidar. The problem lies elsewhere."