RL robot running form hailed as potential 'Move 37' of biomechanics
rohanpaul_ai · x · 2026-08-30
A post showcases a video of a robot mimicking human running form, comparing it to AlphaGo's 'Move 37' and suggesting it could be a milestone in biomechanics. Comments explain that reinforcement learning helped the robot maintain a posture superior to human form: humans swing arms to counter torso rotation from leg strides, while robots using motors and gears generate high torque; the forward lean shifts the center of mass, reducing effort to stay upright and increasing forward motion efficiency.
Related event: Reinforcement Learning Enables Humanoid Robots to Run Like Humans(2 posts)→
More from Embodied
- Berkeley researchers sample humanoid robot policies directly from weight space with diffusion — berkeley_ai · 2026-10-16
- OneWM: unified causal training shows world and action modeling improve each other — IAAI233 · 2026-10-16
- Tesla's hover car isn't a flying car — compressed air can't sustain flight — tinyfool · 2026-10-16
- Scobleizer relays claim that Optimus demo will be even more mind-blowing than the road-flipping Roadster — Scobleizer · 2026-10-16
- Indie dev's AI PASSPORT wearable firmware hits 1,200+ downloads in days — ezshine · 2026-10-16
- 1X Opens California Factory for Mass Production of NEO Humanoid Robots — emmanuelvivier · 2026-10-16