When a Robot Reaches for a Cup, It's Moved Away: LIBERO-MAX Uses 224,000 Simulations to Test Dynamic Reliability
机器人伸手时，杯子被挪走了：LIBERO-MAX用22.4万次仿真检验动态可靠性
LIBERO-MAX is a study that evaluates the adaptability of robots in dynamic environments by designing paired tasks and mid-task changes to assess the performance of different strategies under environmental changes. The study found that the success rates of all tested strategies decreased, and the impact of different types of changes on the models varied significantly, indicating that robots need more robust perception and planning mechanisms to handle uncertainties in real-world scenarios.
LIBERO-MAX is a study that evaluates the adaptability of robots in dynamic environments by designing paired tasks and mid-task changes to assess the performance of different strategies under environmental changes. The study found that the success rates of all tested strategies decreased, and the impact of different types of changes on the models varied significantly, indicating that robots need more robust perception and planning mechanisms to handle uncertainties in real-world scenarios.
Source: Machine Heart — Robotics on WeChat · 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.
- Environment
- SimulationOpen source S1Open source S21
Reported numbers
Reported success rate
66.9%
Reported success rate
65.7%
- paper: Available Artifact link Open source S15
- code: Available Artifact link Open source S15
- dataset: not_reported
What remains unknown
Not established in the collected evidence: 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.
机器人伸手时，杯子被挪走了：LIBERO-MAX用22.4万次仿真检验动态可靠性
Open source S1
每个策略完成 16,000 次执行，主评测累计 22.4 万次仿真 。
Open source S21
即使是动态条件下表现最好的 MolmoAct2 和 π₀.₅，成功率也分别只有 66.9%和 65.7%，丢失了不少原本能够完成的任务。
Open source S22
论文标题：LIBERO-MAX: Do Robot Policies Adapt When the World Changes? 作者：Yunbei Zhang*、Zijian Jin*、Yuanzhe Liu、Janet Wang、Xilun Zhang、Yuyou Zhang、Zhenyu Zhang、Daoan Zhang、Shuaicheng Niu、Gen Li、Jianfei Yang、Jihun Hamm、Ismini Lourentzou、Weirui Ye、Bo Liu、Peter Stone、Marco Pavone 论文链接：https://arxiv.org/abs/2609.36518 代码链接：https://github.com/liberomax/LIBERO-MAX 项目主页：https://liberomax.github.io/ 同一个机器人，两种后续 回到抓杯子的故事。
Open source S15
Source：Machine Heart — Robotics on WeChat · mp.weixin.qq.com