Cortex Framework Bridges High-Level Planning and Low-Level Skills for Robots
jiqizhixin · x · 2026-07-31
Tsinghua University and Shanghai AI Lab introduced Cortex, a framework designed to bridge the gap between high-level planning and low-level motor skills in embodied AI, enabling robots to execute long-horizon tasks.
- Core Mechanism: Breaks down complex tasks into 32 standardized skill primitives for bidirectional alignment.
- Performance: Outperforms existing monolithic models by 3.1% on Libero-long and 4.1% on RoboTwin.
- Zero-shot: Achieves zero-shot completion of unseen real-world long-horizon tasks like multi-stage chemistry experiments.
More from Embodied
- Physical Intelligence Clarifies Strategy: Solving Physical Intelligence by Any Means Necessary — ZeYanjie · 2026-07-31
- Live Footage: Grinding of a Large Motor Shaft — MatthewChang · 2026-07-31
- M5Stack Workshop: Training Self-Balancing Robots with RL from Sim to Hardware — ShawnHymel · 2026-07-31
- Kunlun Wanwei Unveils AI Hardware Family: From Recorders to Smart Rings — 昆仑万维集团 · 2026-07-31
- Real-World 3D Data: Powering Real2Sim Simulation for Embodied AI Deployment — 机器之心 · 2026-07-31
- Cheffy Launches Eggor, an Automated Egg-Cooking Robot, Priced at $349 — kscottz · 2026-07-31