I get that the system is designed to follow the white line, and that in this nightmarish freeway design, the white line leads straight into the divider. But I thought that the whole point of LIDAR/whatever Tesla uses for object detection was to be able to detect upcoming objects. This seems to have been a problem in the Uber pedestrian crash as well - while it was clear from that video that a human driver probably couldn’t have seen the woman, a LIDAR equipped vehicle should have easily detected that she was there and avoided her (and that Uber vehicle had full LIDAR I believe).
So what is going on here? I’m not a radar expert. Is there some fundamental flaw with this technology that is preventing it from “seeing” all objects under all circumstances? Or does the problem arise from faulty driving logic...perhaps the object detection system reports the object, and for whatever reason the system interpreting that data ignores it?