BreakShell Robotics Launches RoboAPI for Direct Physical World Control
一句指令，自己干活！「破壳机器人」发布RoboAPI！
BreakShell Robotics has launched RoboAPI, an embodied AI interface allowing developers to control robotic arms via simple prompts without prior data collection or model training. Accompanied by its self-developed Poke-Aurora world-action model, the system demonstrated success rates of 86.0% in object transfer and 87.7% in environment interaction during internal evaluations, outperforming several open-source models. Currently available free for non-commercial use, RoboAPI aims to validate model capabilities through real-world user testing rather than demonstration videos.
Source: Robotics — Chinese web 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
86%
View original evidence
支撑这套能力的Poke-Aurora，在破壳自建的规模化评测中，物品转移与整理、姿态与形状对齐、环境交互与工具使用三类任务的成功率分别做到86.0%、54.1%和87.7%，均高于参与对比的GPT6 Astra和两款开源具身模型，后两者的成绩都不到35%。
Open source S10Reported success rate
54.1%
View original evidence
支撑这套能力的Poke-Aurora，在破壳自建的规模化评测中，物品转移与整理、姿态与形状对齐、环境交互与工具使用三类任务的成功率分别做到86.0%、54.1%和87.7%，均高于参与对比的GPT6 Astra和两款开源具身模型，后两者的成绩都不到35%。
Open source S10Reported success rate
87.7%
View original evidence
支撑这套能力的Poke-Aurora，在破壳自建的规模化评测中，物品转移与整理、姿态与形状对齐、环境交互与工具使用三类任务的成功率分别做到86.0%、54.1%和87.7%，均高于参与对比的GPT6 Astra和两款开源具身模型，后两者的成绩都不到35%。
Open source S10human task completion time
20 seconds
View original evidence
数据显示，即便是GPT6 Astra这样的前沿通用大模型，直接控制机械臂完成任务的耗时，大约只有人类的百分之一，平均每项任务要花上约半小时，而人类只需要20秒。
Open source S20
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: 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.
支撑这套能力的Poke-Aurora，在破壳自建的规模化评测中，物品转移与整理、姿态与形状对齐、环境交互与工具使用三类任务的成功率分别做到86.0%、54.1%和87.7%，均高于参与对比的GPT6 Astra和两款开源具身模型，后两者的成绩都不到35%。
Open source S10
数据显示，即便是GPT6 Astra这样的前沿通用大模型，直接控制机械臂完成任务的耗时，大约只有人类的百分之一，平均每项任务要花上约半小时，而人类只需要20秒。
Open source S20
Source：Robotics — Chinese web discovery · robot.ofweek.com