Robot learns cornhole by building its own sim, succeeds on real hardware in 6 trials
ki_ki_ki1 · x · 2026-10-14
A workflow demo where a robot plays Cornhole: it watches a human play, records the video, builds a simulation scene, and optimizes the motion in sim — when asked for dynamic stability it starts checking ZMP and optimizes accordingly. Iterating on the real robot, it shows strong spatial understanding and succeeds after only 6 real-world trials.
Related event: Robot Masters Cornhole in Just 6 Real-World Trials via Simulation(3 posts)→
More from coding & agent
- Everyone shipped their own harness, now everyone is shipping their own GitHub — tekbog · 2026-10-14
- Microsoft's TeleTune turns offline telemetry into agent skills, cutting tokens up to 75x — EliasEskin · 2026-10-14
- "AI is still dumb at architecture": devs swap war stories of bad model advice — teropa · 2026-10-14
- "Coding isn't solved—you just stopped reading the code" — prasenx · 2026-10-14
- Superhuman coding agents are here, yet we still build the same web apps as 5 years ago — mhmazur · 2026-10-14
- FrontierML benchmark tests whether agents can spend money to scale ML performance — akbirthko · 2026-10-14