Your comments on sensor fusion seem to describe the weird results of 2 informal ADAS (lidar, vision, lidar + vision, lidar + vision + 4d imaging radar, etc.) “tournaments” conducted earlier this year. There was an earlier HN post about it <https://news.ycombinator.com/item?id=44694891> with a comment noting “there was a wide range of crash avoidance behavior even between the same car likely due to the machine learning, and that also makes explaining the differences hard. Hopefully someone with more background on ADAS systems can watch and post what they think.”

Notably, sensor confusion is also an “unsolved” problem in humans, eg vision and vestibular (inner ear) conflicts possibly explaining motion sickness/vertigo <https://www.nature.com/articles/s44172-025-00417-2>

The results of both tournaments: <https://carnewschina.com/2025/07/24/chinas-massive-adas-test...> Counterintuitively, vision scored best (Tesla Model X)

The videos are fascinating to watch (subtitles are available): Tournament 1 (36 cars, 6 Highway Scenarios): <https://www.youtube.com/watch?v=0xumyEf-WRI> Tournament 2 (26 cars, 9 Urban Scenarios): <https://www.youtube.com/watch?v=GcJnNbm-jUI>

Highway Scenarios: “tests...included other active vehicles nearby to increase complexity and realism”: <https://electrek.co/2025/07/26/a-chinese-real-world-self-dri...>

Urban Scenarios: “a massive, complex roundabout and another segment of road with a few unsignaled intersections and a long straight...The first four tests incorporated portions of this huge roundabout, which would be complex for human drivers, but in situations for which there is quite an obvious solution: don’t hit that car/pedestrian in front of you” <https://electrek.co/2025/07/29/another-huge-chinese-self-dri...>