Feijie Kesi Releases Fysiverse-UniWAM Unified World Action Model with Fudan University's CITLab
让机器人既会认路又能干活 飞捷科思发布统一世界动作模型Fysiverse-UniWAM
Feijie Kesi, in collaboration with Fudan University's Cognitive and Intelligent Technology Laboratory (CITLab), has released the Fysiverse-UniWAM unified world action model. Unlike traditional approaches that concatenate navigation and operation models, UniWAM learns navigation, stopping positions, and manipulation actions within a single framework. Key innovations include the Manipulation Anchor Pose (MAP) for precise docking and a Mixed-Stream architecture sharing video/action backbones while maintaining separate input/output heads. The model achieves state-of-the-art results on MAP-Bench benchmarks, outperforming models like GR00T and π0.5 in navigation accuracy and manipulation success rates. It demonstrates effective sim-to-real transfer without requiring expensive robot pretraining, with open-source code and data available.
Source: Chinese robotics — Research 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.
- Control
- Reported autonomousOpen source S18
Reported numbers
MAP-Bench trajectories
>1,500,000 trajectories
Trajectory count
MAP-Data hours
≈7,500 hours
navigation tasks
13
Reported trials
View original evidence
综合真机评测覆盖四类机器人平台、13项MAP导航任务、4项移动操作任务和7项固定工位操作任务，共计24项：其中13项导航任务位置误差全部领先、多数任务朝向误差领先；固定工位操作在多项分拣与放置任务上优于π0.5，整体表现已接近这一当前最强基线。
Open source S23mobile manipulation tasks
4
Reported trials
View original evidence
综合真机评测覆盖四类机器人平台、13项MAP导航任务、4项移动操作任务和7项固定工位操作任务，共计24项：其中13项导航任务位置误差全部领先、多数任务朝向误差领先；固定工位操作在多项分拣与放置任务上优于π0.5，整体表现已接近这一当前最强基线。
Open source S23fixed station operation tasks
7
Reported trials
View original evidence
综合真机评测覆盖四类机器人平台、13项MAP导航任务、4项移动操作任务和7项固定工位操作任务，共计24项：其中13项导航任务位置误差全部领先、多数任务朝向误差领先；固定工位操作在多项分拣与放置任务上优于π0.5，整体表现已接近这一当前最强基线。
Open source S23total evaluation tasks
24
Reported trials
View original evidence
综合真机评测覆盖四类机器人平台、13项MAP导航任务、4项移动操作任务和7项固定工位操作任务，共计24项：其中13项导航任务位置误差全部领先、多数任务朝向误差领先；固定工位操作在多项分拣与放置任务上优于π0.5，整体表现已接近这一当前最强基线。
Open source S23
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
机器人自主环顾四周、规划路线、修正底盘，停在机械臂可及的位置，再把桌上的杯子逐个收进托盘。
Open source S18
完整的MAP-Data包含超过150万条轨迹、约7500小时数据。
Open source S12
综合真机评测覆盖四类机器人平台、13项MAP导航任务、4项移动操作任务和7项固定工位操作任务，共计24项：其中13项导航任务位置误差全部领先、多数任务朝向误差领先；固定工位操作在多项分拣与放置任务上优于π0.5，整体表现已接近这一当前最强基线。
Open source S23
Source：Chinese robotics — Research news discovery · sohu.com