Holgercke Caesar on autonomous driving: scaling laws, end-to-end learning, and the gap

abursuc · x · 2026-09-18

At SSAD 2026, Holger Caesar — known for nuScenes and related perception datasets — gave the talk "Autonomous Driving at the crossroads: scaling laws, end to end learning, and the gap." He opened with the optimistic narrative that perception-oriented datasets have significantly improved perception, setting the stage for his analysis of where the field is headed.

Original post →

More from Embodied

Embodied channel →