TY  - CPAPER
U1  - Konferenzveröffentlichung
A1  - Boribun, Wisanukorn
A1  - Heidmann, Frank
ED  - Staffa, Mariacarla
ED  - Cabibihan, John-John
ED  - Siciliano, Bruno
ED  - Sam Ge, Shuzhi
ED  - Bodenhagen, Leon
ED  - Tapus, Adriana
ED  - Rossi, Silvia
ED  - Cavallo, Filippo
ED  - Fiorini, Laura
ED  - Matarese, Marco
ED  - He, Hongsheng
T1  - Scaffolding Reflection, not Generation
BT  - Exploring Non-Directive Social Robot Interaction in Early-Stage Ideation
T2  - Social Robotics + AI : 17th International Conference, ICSR+AI 2025, Naples, Italy, September 10–12, 2025, Proceedings, Part I
N2  - In the context of design education, this study explores how a non-directive social robot (Furhat) can support early-stage idea generation. The robot was intentionally designed not to offer suggestions or solutions, distinguishing it from typical generative AI tools. Instead, it engaged students using metaphors, open-ended questions, and active listening. The aim was to examine how participants responded to a system that deliberately resisted the generative behavior commonly associated with tools like ChatGPT. Many participants appreciated the robot’s reflective role, noting that it helped them clarify and structure ideas without imposing direction. However, as the design process progressed, some expressed frustration and a desire for more proactive input—ranging from creative suggestions and emotional feedback to auditory elements, such as singing or whistling a melody. This mismatch between the robot’s expressive embodiment and its intentionally limited functionality led to moments of tension. Rather than viewing this as a shortcoming, we frame it as a deliberate design strategy: by withholding generative output, the robot fosters independent ideation. These findings contribute to broader discussions in human-robot interaction, particularly concerning creativity, user expectations, and the design of non-directive AI systems.
AB  - In the context of design education, this study explores how a non-directive social robot (Furhat) can support early-stage idea generation. The robot was intentionally designed not to offer suggestions or solutions, distinguishing it from typical generative AI tools. Instead, it engaged students using metaphors, open-ended questions, and active listening. The aim was to examine how participants responded to a system that deliberately resisted the generative behavior commonly associated with tools like ChatGPT. Many participants appreciated the robot’s reflective role, noting that it helped them clarify and structure ideas without imposing direction. However, as the design process progressed, some expressed frustration and a desire for more proactive input—ranging from creative suggestions and emotional feedback to auditory elements, such as singing or whistling a melody. This mismatch between the robot’s expressive embodiment and its intentionally limited functionality led to moments of tension. Rather than viewing this as a shortcoming, we frame it as a deliberate design strategy: by withholding generative output, the robot fosters independent ideation. These findings contribute to broader discussions in human-robot interaction, particularly concerning creativity, user expectations, and the design of non-directive AI systems.
KW  - Benutzererlebnis
KW  - Prompt Engineering
KW  - Soziale Robotik
Y1  - 2026
SN  - 978-981-95-2379-5
SB  - 978-981-95-2379-5
SN  - 0302-9743
SS  - 0302-9743
U6  - https://doi.org/10.1007/978-981-95-2379-5_36
DO  - https://doi.org/10.1007/978-981-95-2379-5_36
SP  - 482
EP  - 489
PB  - Springer Nature
CY  - Berlin
ER  -