Roboticist argues full joint space is the wrong abstraction for high-level agents
KyleMorgenstein · x · 2026-11-20
In a discussion with Chen Tessler and Chris Paxton, KyleMorgenstein argues that full joint space is the wrong planning abstraction for higher-level agents: human motion data offers rich priors, but naive joint tracking may not be the right interface. Supporting evidence: many works need 10 future command frames for smooth joint tracking on hardware — a smell of poor formalism, he argues.
More from Embodied
- Kyle Morgenstein: full joint space is the wrong abstraction for high-level robot agents — KyleMorgenstein · 2026-11-20
- US Physical AI Runs on Private CAPEX, Frontier Models, and Energy Flexibility — ingliguori · 2026-11-20
- Skild AI open-sources code, ending speculation about its robotics work at CoRL — KyleMorgenstein · 2026-11-20
- Skild AI releases Steel 0.2 robot simulation platform with 81 environments and magnetic contacts — KyleMorgenstein · 2026-11-20
- STASIS (YC F26) launches smart glasses with 6 sensors tracking eye strain at 92% accuracy — LinusEkenstam · 2026-11-20
- NVIDIA's GR00T 2 Controls Real Dexterous Hands End to End, Fully Onboard — rsasaki0109 · 2026-11-20