Robotics researcher: AI progress is cost-only, closed-loop control remains unsolved
GlenBerseth · x · 2026-09-16
Robotics researcher Glen Berseth argues recent embodied-AI progress is real but confined to one axis: cost.
- Foundation models make robotic tasks far cheaper and faster to set up, but performance itself hasn't broken through.
- Self-driving cars remain the clearest example: decades of effort, still hard, because they demand real-time closed-loop feedback rather than cheaper static perception plus planning.
- He points to Minsky's 1960s robot arm—vision-based geometry, path planning, assembly—noting today's foundation models are largely still solving the same class of problem, just much cheaper.
More from Embodied
- First M5 Ultra Geekbench leak: 52,516 multi-core, ~35% faster than M3 Ultra — jedisct1 · 2026-09-16
- Fei-Fei Li's World Labs is hiring robot learning researchers to scale world models — YunzhuLiYZ · 2026-09-16
- Figure CEO Brett Adcock Shows Off New F.03 Humanoid Robot at Dreamforce — adcock_brett · 2026-09-16
- Berseth: Self-driving shows cost cuts aren't enough — real-time closed-loop control is the hard part — GlenBerseth · 2026-09-16
- Light-Loco-Parkour shows humanoid robots zero-shot navigating complex terrain on onboard compute — chris_j_paxton · 2026-09-16
- Einride and Lidl put first cab-less Level 4 autonomous truck into daily operation on German public road — FlorianGallwitz · 2026-09-16