A generic haptic teleoperation architecture integrating Dobot X-Trainer controllers across YARP and ROS 2

Abstract

We extend our previously published hardware- and middleware-agnostic generic teleoperation architecture to integrate the Dobot X-Trainer input controllers, adding haptic feedback to the overall control scheme. YARP and ROS 2 middleware frameworks are leveraged to enable seamless cross-middleware interoperability across diverse robotic platforms and their simulated environments and models, such as those evaluated in this work: the TEO humanoid, the ABB CRB 15000-5 “GoFa” industrial cobot, and Dobot collaborative arms. Haptic feedback is achieved by converting external force-torque measurements into motor command adjustments on the position-controlled X-Trainer input hardware. The architecture’s flexibility and performance are validated across simulated environments and physical systems.

Publication
In 2026 International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI)
Accepted for IEEE RICAI 2026 (Shenzhen, China, November 2026). The accepted manuscript is available as a PDF on this page; the DOI and official proceedings link will be added when they become available.
Qiang Li
Qiang Li
Professor and header of AG

My research interests include underwater robot, collaborative robots, humanoid robots.