Cross-Robot-Interface Teleoperation Framework towards Implementation-Friendly Human-Robot Collaboration

This paper presents a cross-robot and crossinterface teleoperation framework for versatile human-robot collaboration (HRC) tasks. HRC have recently collected attractions for designing a future society where people and robots live and work together. Teleoperation is a key technology to support HRC society, allowing human operators to remotely control robots. Transparent teleoperation system help the operators to intuitively and effectively perform various physical tasks as if they are doing by their own body. Besides to an application of manual remote work, teleoperation is recently utilized for collecting human demonstration data to train data-driven controllers, such as Vision-Language-Action models, for facilitating robust autonomous systems. From these background, the demand for implementation-friendly robotic teleoperation framework is rapidly growing. Especially, it is important to develop a framework that allows human operators to control various robots using various interfaces, since the appropriate robot and interface could depend on many factors such as the task contents, user's skill and affordable cost. In this study, we have been developing a framework achieving crossrobot-interface teleoperation, as a part of our open-source robot control library OpenHRC. The framework source codes can be accessed at https://github.com/OpenHRC/OpenHRC. git.