In today’s dynamic landscape, the interaction between humans and robots has become integral to various domains, reshaping industries and everyday life. Skill transfer, the ability for humans and machines to share expertise, stands at the forefront of this transformation. It signifes the bridge between human profciency and artifcial intelligence capabilities, encompassing knowledge transfer from humans to robots and vice versa. A fundamental aspect of the success of Human-Robot Skill Transfer (HRST) is the User Experience (UX), as the interplay between users and technology infuences acceptance and effectiveness. By examining current defnitions of HRST and assessing the state of UX research regarding this feld gaps in current research on the multifaceted interplay between users and technology in HRST are uncovered.
Current defnitions of HRST focus on combining Machine Learning with Learning from Demonstration approaches enabling human-like learning strategies, allowing humans to teach robots more human-like, thus enabling more intuitive human-to-robot skill transfer. Recent research also emphasizes the importance of Shared Autonomy for HRST in semi-autonomous robotic systems to distribute decision-making competence between humans and robots, and skill adaptation.
While there has been notable progress in UX research on Human-Robot Interaction generally, UX research in this feld is missing a common framework for HRST. Attention in creating such a framework needs to be directed toward implications introduced by Machine Learning and Shared Autonomy. Further, the users’ prepositions must be addressed for adapting and evaluating these systems.