Global First Robot Task Native 3D World Model: Cross-Dimensional UNITAS Enables Robots to Learn Physical Intuition, Sweeping Multiple Benchmarks
全球首个机器人任务原生3D世界模型:跨维UNITAS让机器人学会物理直觉,横扫多个榜单
UNITAS is the world's first robot task-native 3D world model, achieving cross-perspective and cross-body generalization capabilities by unifying observation, action, and environmental changes within a three-dimensional physical space. The model performs exceptionally well in multiple benchmark tests, including LIBERO, LIBERO-Plus, and RoboTwin 2.0. With just 1.7B parameters, it outperforms larger parameter models such as Fast-WAM (6B) and Motus (8B).
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.
Reported numbers
Reported success rate
89.1%
View original evidence
这不仅是一个技术思路,UNITAS 已在多项机器人操作评测中展现出 “ 屠榜 ” 实力:仅凭 1.7B (17 亿)参数,在 LIBERO 上取得 99.8% 的平均成功率、在 LIBERO-Plus 上达到 89.1% ,并在 RoboTwin 2.0 双臂操作的 Clean 与 Randomized 设置中分别取得 92.94% 和 93.04% 的成功率,超越参数规模达 6B(60 亿) 的 Fast-WAM、 8B(80 亿) 的 Motus,以及 π0.5、LingBot-VA、PointWorld 等模型, 在多项基准测试中全面夺冠, 进一步 在真实机器人操作执行 上同样表现突出, 任务平均成功率达到 85% !
Open source S9Reported success rate
85%
View original evidence
这不仅是一个技术思路,UNITAS 已在多项机器人操作评测中展现出 “ 屠榜 ” 实力:仅凭 1.7B (17 亿)参数,在 LIBERO 上取得 99.8% 的平均成功率、在 LIBERO-Plus 上达到 89.1% ,并在 RoboTwin 2.0 双臂操作的 Clean 与 Randomized 设置中分别取得 92.94% 和 93.04% 的成功率,超越参数规模达 6B(60 亿) 的 Fast-WAM、 8B(80 亿) 的 Motus,以及 π0.5、LingBot-VA、PointWorld 等模型, 在多项基准测试中全面夺冠, 进一步 在真实机器人操作执行 上同样表现突出, 任务平均成功率达到 85% !
Open source S9
- 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.
这不仅是一个技术思路,UNITAS 已在多项机器人操作评测中展现出 “ 屠榜 ” 实力:仅凭 1.7B (17 亿)参数,在 LIBERO 上取得 99.8% 的平均成功率、在 LIBERO-Plus 上达到 89.1% ,并在 RoboTwin 2.0 双臂操作的 Clean 与 Randomized 设置中分别取得 92.94% 和 93.04% 的成功率,超越参数规模达 6B(60 亿) 的 Fast-WAM、 8B(80 亿) 的 Motus,以及 π0.5、LingBot-VA、PointWorld 等模型, 在多项基准测试中全面夺冠, 进一步 在真实机器人操作执行 上同样表现突出, 任务平均成功率达到 85% !
Open source S9
Source:Machine Heart — Robotics on WeChat · mp.weixin.qq.com