Interactive Robot Task Learning: Human Teaching Proficiency With Different Feedback Approaches

Abstract

The deployment of versatile robot systems in diverse environments requires intuitive approaches for humans to flexibly teach them new skills. In our present work, we investigate different user feedback types to teach a real robot a new movement skill. We compare feedback as star ratings on an absolute scale for single roll-outs versus preference-based feedback for pairwise comparisons with respective optimization algorithms (i.e., a variation of co-variance matrix adaptationevolution strategy (CMA-ES) and random optimization) to teach the robot the game of skill cup-and-ball. In an experimental investigation with users, we investigated the influence of the feedback type on the user experience of interacting with the different interfaces and the performance of the learning systems. While there is no significant difference for the subjective user experience between the conditions, there is a significant difference in learning performance. The preference-based system learned the task quicker, but this did not influence the users' evaluation of it. In a follow-up study, we confirmed that the difference in learning performance indeed can be attributed to the human users' performance.

Design and Quantitative Assessment of Teleoperation-Based Human–Robot Collaboration Method for Robot-Assisted Sonography

“…However, most of the work focuses on tracking control, communication delay and data loss, transparency and stability of the teleoperation system. Human-robot interaction and collaboration through teleoperation, such as robot-assisted telediagnostics and telemedicine, have attained increasing attention, and a number of research efforts related to these topics have been investigated, especially since the COVID-19 pandemic [9], [15]. For example, a range of human-robot collaboration interfaces through teleoperation 1 and shared control frameworks are developed to achieve human-robot collaboration tasks.…”

“…Because humanrobot collaboration provides an effective approach to combining human intelligence and the autonomy of robots, it could improve the safety and efficiency of the robot performing dexterous manipulation tasks. In addition, the intuitive and natural human-robot interface is vital for robot skill learning, such as learning from human demonstration [16], human-inthe-loop robot skill learning, and interactive learning [15] etc. More recently, brain-inspired or human-inspired methods have been proposed to design intelligent robotic systems from the behaviour and neural-inspired aspect [17], [18].…”