Relative Contact Velocity-Controlled Hand-Object Mechanism for Dexterous Tool Manipulation
Relative Contact Velocity-Controlled Hand-Object Mechanism for Dexterous Tool Manipulation
This work proposes a unified hand-object mechanism (HOM) framework to enable general multi-finger robotic hands to perform complete tool manipulation, including picking up tools, loading them into suitable poses, and wielding them. By modeling the hand and tool as sub-assemblies with relative contact velocity and force constraints, the authors developed a lightweight motion planning and contact estimation framework using least squares and a complementary filter. Evaluated in simulation via teleoperation of five different robotic hands, the framework successfully enabled all hands to execute the complete tool manipulation process from simple reference trajectories, demonstrating adaptability across different hands, tools, and tasks.
The authors present a unified hand-object mechanism framework that enables five distinct robotic hands to execute complete tool manipulation tasks via teleoperation in simulation, relying on least squares and complementary filtering for motion planning and contact estimation.
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.
- Environment
- SimulationOpen source S4
- Control
- TeleoperatedOpen source S4
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
ons, we developed a lightweight and physically interpretable motion planning and contact estimation framework using least squares and a complementary filter. We evaluated our framework in simulation by teleoperating five different robotic hands. The results show that our framework enabled all five hands to execute the complete tool manipulation process, achieving dexterous behaviors even from identical, simple refere
Open source S4
nce trajectories. Furthermore, the results showcase our framework's adaptability to different hands, tools, and tasks, enabled by its kinematic and geometric foundation. Please visit website for videos: \href{https://sunyuw.github.io/hom-sim/}{https://sunyuw.github.io/hom-sim/}
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org