Apple Research Team Discloses Progress on Robot 'Brain' System
苹果研究团队披露机器人“大脑”研究进展，大脑是具身智能从演示走向实用的核心变量之一，多家公司已布局机器人大脑领域
On November 4, Apple's research team submitted a preprint titled 'Perceptive Humanoid Motion from Simulation' to arXiv, detailing the HALO autonomous control system for humanoid robots. The system was validated on Unitree G1 robots, enabling actions learned in simulation to be executed in unfamiliar real-world environments. Industry analysts note that such 'embodied brains' are central to advancing embodied intelligence from demonstration to practical application.
Source: Chinese robotics — Robot learning research · Read original article ↗
English translation unavailable. Choose the original article to read it.
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
Reported success rate
98.3%
View original evidence
国内方面，智元 GO-3Preview 打通预训练、后训练与部署后全链路学习，手机包装成功率由 50.8% 升至 98.3%，首次在真实业务场景验证 PhysicalRSI。
Open source S13Reported success rate
50.8%
View original evidence
国内方面，智元 GO-3Preview 打通预训练、后训练与部署后全链路学习，手机包装成功率由 50.8% 升至 98.3%，首次在真实业务场景验证 PhysicalRSI。
Open source S13Reported success rate
85%
View original evidence
拓元智慧开源 4D 世界动作模型 E0.5，真机成功率 85.0%/88.3%，较 π 0.5 高 13.3/26.7 个百分点。
Open source S14Reported success rate
88.3%
View original evidence
拓元智慧开源 4D 世界动作模型 E0.5，真机成功率 85.0%/88.3%，较 π 0.5 高 13.3/26.7 个百分点。
Open source S14
- paper: not_reported
What remains unknown
Not established in the collected evidence: Environment, Control, Data origin.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
2026 年上半年国内具身智能赛道融资约 438 亿元，其中以具身大脑为核心业务的公司吸纳 222.53 亿元，占比 50.8%，而机器人本体整机公司同期融资仅 56 亿元，占比 12.8%。
Open source S10
国内方面，智元 GO-3Preview 打通预训练、后训练与部署后全链路学习，手机包装成功率由 50.8% 升至 98.3%，首次在真实业务场景验证 PhysicalRSI。
Open source S13
拓元智慧开源 4D 世界动作模型 E0.5，真机成功率 85.0%/88.3%，较 π 0.5 高 13.3/26.7 个百分点。
Open source S14
Source：Chinese robotics — Robot learning research · app.myzaker.com