One perspective asserts that lidar and radar can increase autonomous vehicle danger because sensor disagreement with cameras creates contention and ambiguity that heightens risk. Evidence cited includes safety improvements after disabling radar and focusing on camera-only (vision) systems. A contrasting perspective asserts that combining camera, radar, and LiDAR achieves superhuman safety, noting that solid-state LiDAR can cost about $500 and that many partners employ multi-sensor stacks. The central issue is whether sensor redundancy reduces risk through corroboration or increases risk through conflicting inputs and decision ambiguity.
Solid state LiDAR is $500. Why not include lidar as well in order to achieve super human safety. All of our partners are using a combination of camera, radar and LiDAR, and I personally think that's the right solution, but I could be proven wrong,
Lidar and radar reduce safety due to sensor contention. If lidars/radars disagree with cameras, which one wins? This sensor ambiguity causes increased, not decreased, risk. That's why Waymos can't drive on highways.We turned off the radars in Teslas to increase safety....- Elon Musk (@elonmusk) August 25, 2025
Collection
[
|
...
]