Any-ttach: Quick End-effector Swapping Enables Manipulation Dexterity with Simplicity
Any-ttach: Quick End-effector Swapping Enables Manipulation Dexterity with Simplicity
This research presents Any-ttach, a tool-centric manipulation system that leverages mechanical modularity to enable autonomous end-effector swapping. The system supports 15 heterogeneous modules ranging from robotic fingers to articulated tools like scissors through a unified object-centric framework. Experiments demonstrate reliable autonomous swapping, automatic integration of new tools, and broad manipulation capabilities across different skill sources, including multi-tool long-horizon tasks.
The paper introduces Any-ttach, a modular robotic manipulation system that enables autonomous swapping of 15 heterogeneous end-effector modules via a low-cost standardized interface, demonstrating reliable integration and task execution across different tools and skill sources.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Control
- Reported autonomousOpen source S4
Reported numbers
tool-skill steps
7
Reported trials
View original evidence
atic integration to new tools, and broad manipulation capability across different skill sources. Two multi-tool application demonstrations, comprising seven tool--skill steps across two tasks, further illustrate the autonomous composition of end-effector exchange and heterogeneous manipulation skills. These results show that end-effector swapping can expand manipulation capability without concentrating increasing com
Open source S5tasks
2
Reported trials
View original evidence
atic integration to new tools, and broad manipulation capability across different skill sources. Two multi-tool application demonstrations, comprising seven tool--skill steps across two tasks, further illustrate the autonomous composition of end-effector exchange and heterogeneous manipulation skills. These results show that end-effector swapping can expand manipulation capability without concentrating increasing com
Open source S5
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
olicy learning; and 3) hierarchical planning and execution system for tools and skills for multi-tool long-horizon tasks. We demonstrated 15 heterogeneous end-effector modules supported by our system, spanning different robotic fingers, everyday tools (including articulated tools such as scissors), and unconventional end-effectors through the same interface. Experiments demonstrate reliable autonomous swapping, autom
Open source S4
atic integration to new tools, and broad manipulation capability across different skill sources. Two multi-tool application demonstrations, comprising seven tool--skill steps across two tasks, further illustrate the autonomous composition of end-effector exchange and heterogeneous manipulation skills. These results show that end-effector swapping can expand manipulation capability without concentrating increasing com
Open source S5
plexity entirely in a single end-effector. More details and videos are available at https://any-ttach.github.io/.
Open source S6
Source：arXiv Robotics — research abstracts · arxiv.org