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 多家公司已布局机器人大脑领域
On November 4, Apple's research team submitted a preprint to arXiv detailing the HALO autonomous control system for humanoid robots. The system was validated on Unitree G1 units, enabling transfer of skills learned in simulation to real-world environments. Industry analysis notes that robot 'brains' are central to advancing embodied intelligence from demonstration to practical use.
Source: Chinese robotics — Company news discovery · 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 S16Reported 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 S16Reported success rate
85%
Reported success rate
88.3%
- 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 S13
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 S16
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π0.5高13.3/26.7个百分点。
Open source S17
国外方面，PhysicalIntelligence已获200亿美元估值，Physical Intelligence（简称 PI或 π ）由UC Berkeley、斯坦福大学教授团队和谷歌科学家等科研和技术大牛于2024年3月成立，公司致力于创建可以为各种机器人和机器增添高级智能的软件，最终目标是创建一种作为通用机器人系统的AI模型（机器人通用大脑）。
Open source S14
Source：Chinese robotics — Company news discovery · fund.eastmoney.com