.png){kind=icon}
.png){kind=icon}
Return
An Emotional BDI Framework for Affective Decision Making Based on Action Tendency
.png){kind=icon}
OA
AI
J
S
DOI：10.3390/electronics15081691.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
As social robots are increasingly deployed in domains such as healthcare, education, and entertainment, there is growing demand for affective agents that can interpret users’ affective states and respond in contextually appropriate ways. Existing work has established strong foundations for emotion generation and appraisal, but the step that connects generated emotion to behavioral execution still relies heavily on model-specific rules or implicit links. We frame this issue as a Mechanism Gap and propose an Emotional BDI framework that introduces Frijda’s action tendency as an intermediate representation layer between the Affective Core and the Belief–Desire–Intention (BDI) Executor. Rather than mapping emotion directly to concrete behavior, the framework first transforms affective state into a directional action tendency and then lets BDI reasoning realize that tendency according to role and context. This creates an explicit emotion-to-behavior mediation structure through which the same emotion can be expressed differently across situations and roles. In an exploratory user evaluation with 26 participants, the proposed model received more favorable ratings than an Emotion-Driven Agent in satisfaction ( p = 0.010 ) and appropriateness ( p = 0.002 ). Compared with a Cooperative Agent, the proposed model showed a significant advantage only in satisfaction ( p = 0.030 ). These findings suggest that the proposed framework offers a useful architectural direction for affective decision making beyond direct mapping or unconditional compliance.
Keywords:
emotional BDI
action tendency
affective computing
social robotics
cognitive architecture
Mechanism Gap
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
2.6
Papers:
9.3K
Citations:
4.7W