Nowadays, robots are increasingly integrated into our daily life, from industrial Human-Robot collaboration settings (Matheson et al., 2019) to robots assigned to household chores or companion robots that are expected to emotionally and cognitively understand and interact with their users. They are transitioning from being seen as simple tools to being seen as interactive collaborators. This deeply changes the synergy between humans and robots. Understanding this dynamic of human-robot interaction (HRI) is a continuously evolving research topic.

Human-robot interaction studies provide leads to the design of robots that seamlessly integrate into human environments. By understanding how humans perceive and interact with robots, researchers can develop robotic frameworks and behaviors that facilitate smooth collaboration, nurture long-term use of the robot, simplify usability, improve the efficiency of the interactions and more. Several key elements contribute to the quality of HRI:

– Trust: It is a fundamental aspect of any interaction, influencing how individuals perceive and engage with one another. It can be defined as the willingness to accept vulnerability, thus implying a notion of accepted risk in expectation of a positive outcome (Hannibal, 2021; Weiss et al., 2021). In the context of HRI, trust can be divided into two components: cognitive trust and affective trust (Lee & See, 2004). Cognitive trust is associated with rational assessments of a robot’s competencies, and reliability , and affective trust is associated with emotions and feelings, it relates to how the robot is perceived as moral, specifically ethical, transparent and benevolent (Ullman & Malle, 2019) :

Robots ambivalence between inanimate objects and sentient beings, are subjects to a complex mixture of cognitive and affective trust (Coeckelbergh, 2012).

– Involvement: This is the degree to which individuals actively engage with and participate in the interaction with the robot. Higher levels of involvement lead to increased satisfaction and effectiveness of the interaction.

– Psychological Ownership (PO) (Delgosha & Hajiheydari, 2021) : It is the sense of possession and attachment that individuals develop towards robots. This includes when users perceive the robot as an extension of themselves or as possessing certain characteristics that are similar with their own.

– Anthropomorphism (Gray et al., 2007): Humans have a tendency to attribute human-like qualities to non-human entities, including robots. Anthropomorphism influences the user’s  expectation/prediction of the robot’s gestures and behaviors.

– Perceived Autonomy: It is the extent to which users perceive the robot as autonomous, capable of independent decision-making, and adaptable to various situations.

One promising approach to permit intuitive robot skills management is learning by demonstration, inspired by imitation learning observed in nature. Learning by demonstration involves robots acquiring skills or behaviors by observing and imitating human actions. Kinesthetic teaching (KT) is a way of learning by demonstration that focuses on physical interaction and guidance from the user (Kormushev et al., 2012). In kinesthetic teaching, humans provide direct physical guidance to the robot, facilitating the learning process through tactile feedback. Moreover it fosters a deep understanding of the task context, and limitations which improves the transparency of the interaction and of the robot actions and thus their understandability. KT can also be seen as a way of personalization of the robot where the end-user can teach their robot what to do or parameterize pre-taught skills to their preferences. Thus, KT should bring the same advantages as personalization for HRI. In particular, robots can adapt their behavior to suit the preferences and needs of their users, thus enhancing involvement, but also trust (Schneider & Kummert, 2021). In addition, by allowing the user to directly teach the robot motions and behaviors, it involves the user in the robot functioning and increases the ownership over the robot as one would feel like possessing the robot’s motions that, by construction, encapsulate some motion characteristics of their teacher.  Moreover, KT can also impact the interaction quality as physical guidance fosters a human sense of collaboration and mutual understanding with the robots, thus, potentially strengthening both cognitive and affective trust. Finally physical interactions and teaching encourages active participation and involvement from the users.

In conclusion, as robots become more used alongside humans, understanding and optimizing human-robot interaction becomes critical. Specifically, studying the impact of different methods of control and interactions on the HRI quality is essential. By evaluating the impact of KT on user involvement, perceived autonomy, PO, anthropomorphism, and trust, we can create robots that are intuitive to use and can be personalized, while ensuring a good interaction quality with the users.

Coeckelbergh, M. (2012). Can we trust robots? Ethics and Information Technology, 14(1), 53–60.

Delgosha, M. S., & Hajiheydari, N. (2021). How human users engage with consumer robots? A dual model of psychological ownership and trust to explain post-adoption behaviours. Computers in Human Behavior, 117, 106660.

Gray, H., Gray, K., & Wegner, D. (2007). Dimensions of Mind Perception. Science (New York, N.Y.), 315, 619.

Hannibal, G. (2021). Focusing on the Vulnerabilities of Robots through Expert Interviews for Trust in Human-Robot Interaction. Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction, 288–293.

Kormushev, P., Calinon, S., & Caldwell, D. G. (2012). Imitation Learning of Positional and Force Skills Demonstrated via Kinesthetic Teaching and Haptic Input. Advanced Robotics.

Lee, J. D., & See, K. A. (2004). Trust in Automation: Designing for Appropriate Reliance. Human Factors, 46(1), 50–80.

Matheson, E., Minto, R., Zampieri, E. G. G., Faccio, M., & Rosati, G. (2019). Human–Robot Collaboration in Manufacturing Applications: A Review. Robotics, 8(4), Article 4.

Schneider, S., & Kummert, F. (2021). Comparing Robot and Human guided Personalization: Adaptive Exercise Robots are Perceived as more Competent and Trustworthy. International Journal of Social Robotics, 13(2), 169–185.

Ullman, D., & Malle, B. F. (2019). Measuring Gains and Losses in Human-Robot Trust: Evidence for Differentiable Components of Trust. 2019 14th ACM/IEEE International Conference on Human-Robot Interaction (HRI), 618–619.

Weiss, A., Michels, C., Burgmer, P., Mussweiler, T., Ockenfels, A., & Hofmann, W. (2021). Trust in everyday life. Journal of Personality and Social Psychology, 121(1), 95–114.