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.
More from Embodied
- Drone-captured 400-ft guyed tower rebuilt as 3DGS via Metashape and LichtFeld Studio — janusch_patas · 2026-11-02
- Physical AI's real story: a 4-layer map of 15 companies behind humanoid robots — pdamodaran · 2026-11-02
- Autonomous's Harness Pro uses an ESP32-P4, not a mini PC, to monitor AI coding agents — dee_hw · 2026-11-02
- KAIST's QCP lets robot policies control execution quality in real time — kaist-ai · 2026-11-02
- ANYbotics begins customer deliveries of ANYmal X, first legged robot certified for explosive atmospheres — lukas_m_ziegler · 2026-11-02
- InSpatio opens China's first embodied simulation data center targeting 1M hours/month — 智东西 · 2026-11-02