Robotics researcher Ryuichi Ueda: obsessing over measurement won't make autonomous robots smarter
4310sy · x · 2026-09-04
Ryuichi Ueda (Chiba Institute of Technology) presented "Autonomous Robots' Departure from Measurement" at the Robotics Society of Japan academic lecture.
- His core claim: no matter how refined measurement becomes, it can't serve high-level decision-making; obsessing over precise mapping and localization may keep autonomous robots from getting smarter.
- 2000s: factory robots relied on pre-planned, repetitive, precisely-measured motion — which fails outside factories, spawning probabilistic robotics that represent uncertainty as probability distributions.
- Two diverging paths: probabilistic robotics enabled both km-scale autonomous driving and fine mapping (the "precision route") and direct action selection from distributions (be cautious when uncertain). Ueda warns that conflating the two leads to misguided investment — expecting precision research to yield flexible robots, with budgets evaporating without results.
- 2020s trend: autonomous robots are moving away from measurement-centric approaches.
More from AGI Musings
- Richard Socher: AI could compress a century of scientific breakthroughs into a decade — RichardSocher · 2026-10-21
- Ethan Mollick: AI's work capacity doubled 8 times in 30 months, METR benchmark maxed out — One Useful Thing (Ethan Mollick) · 2026-10-20
- Time for Guardrails on Government Too: Rethinking Who AI Policy Constrains — neil_chilson · 2026-10-20
- Steam needs real quality control on AI slop, not an AI art ban, argues designer — AIandDesign · 2026-10-20
- Why personal AI agents fall into a retention dead zone between dopamine and infrastructure — signulll · 2026-10-20
- Scholar writes AI-assisted book on storytelling values, work nominated for EMNLP best paper — _akpiper · 2026-10-20