Many have speculated that Tesla could have prevented the Autopilot-related Florida crash if its cars had lidar (visible light detection and ranging) to better understand the world around them, not just cameras and radar. However, Tesla might have a way to improve its semi-autonomous driving without grafting on new equipment. Elon Musk explains that his company hopes to adapt its existing radar systems to produce a lidar-like map of the surrounding environment with the help of “temporal smoothing” that compares object positions over time. The current hardware should produce a high-enough resolution for this to work, he adds. And unlike lidar, it can see through dust, rain and snow.
Musk doesn’t have a timetable for when this radar upgrade could happen, but he believes that it would produce at least “moderate” improvements in Autopilot (if not major ones) without requiring brand new hardware.
Tesla has a strong financial motivation to pursue this strategy, as you might guess. It’d have to spend a lot to add lidar to cars, not the least of which might be significant redesigns to accommodate the sensor tech. If this goes forward, though, it could be a big deal. It still wouldn’t make Autopilot foolproof, but it might mitigate (or even eliminate) a key weak point and make the hands-off system that much more trustworthy.
Working on using existing Tesla radar by itself (decoupled from camera) w temporal smoothing to create a coarse point cloud, like lidar
— Elon Musk (@elonmusk) July 15, 2016