The Role of Frustration in Human–Robot Interaction – What Is Needed for a Successful Collaboration?

Abstract

To realize a successful and collaborative interaction between human and robots remains a big challenge. Emotional reactions of the user provide crucial information for a successful interaction. These reactions carry key factors to prevent errors and fatal bidirectional misunderstanding. In cases where human–machine interaction does not proceed as expected, negative emotions, like frustration, can arise. Therefore, it is important to identify frustration in a human–machine interaction and to investigate its impact on other influencing factors such as dominance, sense of control and task performance. This paper presents a study that investigates a close cooperative work situation between human and robot, and explore the influence frustration has on the interaction. The task for the participants was to hand over colored balls to two different robot systems (an anthropomorphic robot and a robotic arm). The robot systems had to throw the balls into appropriate baskets. The coordination between human and robot was controlled by various gestures and words by means of trial and error. Participants were divided into two groups, a frustration- (FRUST) and a no frustration- (NOFRUST) group. Frustration was induced by the behavior of the robotic systems which made errors during the ball handover. Subjective and objective methods were used. The sample size of participants was N = 30 and the study was conducted in a between-subject design. Results show clear differences in perceived frustration in the two condition groups and different behavioral interactions were shown by the participants. Furthermore, frustration has a negative influence on interaction factors such as dominance and sense of control. The study provides important information concerning the influence of frustration on human–robot interaction (HRI) for the requirements of a successful, natural, and social HRI. The results (qualitative and quantitative) are discussed in favor of how a successful und effortless interaction between human and robot can be realized and what relevant factors, like appearance of the robot and influence of frustration on sense of control, have to be regarded.

Multi-modal Affect Detection Using Thermal Imaging in a Gamified Exercise

“…Multi-modal approaches focus on detecting multiple affective states, nonetheless, one of the most commonly experienced affective states in HRI is frustration [23]. Therefore, several approaches have been focused on detecting it.…”

A Vision of Future Healthcare: Potential Opportunities and Risks of Systems Medicine from a Citizen and Patient Perspective—Results of a Qualitative Study

“…When employees are overwhelmed with the use of innovative technologies, this triggers work-related stress, which, among other factors, negatively affects psychosocial health [80]. Weidemann and Rußwinkel (2021) described what happens when problems occur in the interaction between humans and robots. When robotic systems display erroneous behavior, it triggers counterproductive emotional states in users, such as frustration, feelings of inferiority to technology, and loss of control [81].…”

“…Weidemann and Rußwinkel (2021) described what happens when problems occur in the interaction between humans and robots. When robotic systems display erroneous behavior, it triggers counterproductive emotional states in users, such as frustration, feelings of inferiority to technology, and loss of control [81]. As for a well-functioning human-machine interaction, the concerns, expectations, and capabilities of users regarding new key technologies should be considered when implementing systems medicine.…”

Expect the Unexpected: Leveraging the Human-Robot Ecosystem to Handle Unexpected Robot Failures

“…2021) Develop mechanisms for robots to understand and react to emotions, like pain, fear, panic, confusion, and distress, to correctly identify warning conditions requiring a reaction. Kulic and Croft (2007), Leite et al (2013), Le andLee (2014), Jung (2017), Bagheri et al (2020), de Kervenoael et al (2020, Spezialetti et al (2020), Weidemann and Rußwinkel (2021) Perform task analysis, communication analysis, workflow analysis, and usability studies of robot interactions with people in the HRE (users, bystanders, customer service agents, etc.). Test in real-world environments, under normal and degraded conditions, to identify challenges, potential degraded states, and conflicts originating from interactions within the HRE.…”