Robotics researcher: foundation models cut cost but real progress needs performance gains

GlenBerseth · x · 2026-09-16

Robotics researcher Glen Berseth argues that Minsky's lab already had a robot arm using computer vision to see object geometry, plan paths, and assemble parts in the 1960s — today's foundation models are largely solving the same class of problem, just far cheaper and faster to set up. He contends progress should push performance up, not just the cost curve: more object variety, robustness to the wild, multi-robot/human-robot interaction, real-time closed-loop control, and better hardware — "human hands are still impressive." Self-driving cars show why: decades of effort remain hard because they need real-time closed-loop feedback, not just cheaper static perception plus planning.

Related event: Robotics researcher: foundation models only cut costs, performance is the real bottleneck(10 posts)→

Original post →

More from Embodied

Embodied channel →