Silvério, J., Clivaz, G. and Calinon, S. (2021)
A Laser-based Dual-Arm System for Precise Control of Collaborative Robots
In Proc. IEEE Intl Conf. on Robotics and Automation (ICRA), pp. 9183-9189.
Abstract
Collaborative robots offer increased interaction capabilities at relatively low cost, but in contrast to their industrial counterparts, they inevitably lack precision. In addition, modeling errors rapidly accumulate as tasks change and robots are re-programmed, which adds to the robots' own kinematic and dynamic errors, often requiring time-consuming calibrations to be performed regularly. These aspects strongly limit the application of collaborative robots in tasks requiring high precision such as surgery or watch-making. We address this problem by relying on a dual-arm system with laser-based sensing to measure relative poses between objects of interest and compensate for pose errors coming from robot proprioception. Our approach leverages previous knowledge of the object 3D models in combination with point cloud registration to efficiently extract relevant poses and compute corrective trajectories. This results in high-precision assembly behaviors. The approach is validated in needle threading and USB insertion tasks using two 7-axis Panda robots.
Bibtex reference
@inproceedings{Silverio21ICRA,
author="Silv\'erio, J. and Clivaz, G. and Calinon, S.",
title="A Laser-based Dual-Arm System for Precise Control of Collaborative Robots",
booktitle="Proc.\ {IEEE} Intl Conf.\ on Robotics and Automation ({ICRA})",
year="2021",
pages="9183--9189"
}
Video
Related publication: Silvério, J., Clivaz, G. and Calinon, S. (2021). A Laser-based Dual-arm System for Precise Control of Collaborative Robots. In Proc. IEEE Intl Conf. on Robotics and Automation (ICRA).