[论文解读] A Computational Study on Emotions and Temperament in Multi-Agent Systems

Luís Paulo Reis, Daria Barteneva+1 more|ArXiv.org|Sep 27, 2008

Social Robot Interaction and HRI参考文献 26被引用 8

一句话总结

本文提出了一种模块化、可扩展的情绪与气质计算模型，应用于多智能体系统，受神经生物学和气质理论启发，以增强自主智能体的决策能力。研究证明，情绪状态和气质类型显著影响个体与团队的表现，验证了该方法在建模机器人与人工智能系统中情感智能行为方面的有效性。

ABSTRACT

Recent advances in neurosciences and psychology have provided evidence that affective phenomena pervade intelligence at many levels, being inseparable from the cognitionaction loop. Perception, attention, memory, learning, decisionmaking, adaptation, communication and social interaction are some of the aspects influenced by them. This work draws its inspirations from neurobiology, psychophysics and sociology to approach the problem of building autonomous robots capable of interacting with each other and building strategies based on temperamental decision mechanism. Modelling emotions is a relatively recent focus in artificial intelligence and cognitive modelling. Such models can ideally inform our understanding of human behavior. We may see the development of computational models of emotion as a core research focus that will facilitate advances in the large array of computational systems that model, interpret or influence human behavior. We propose a model based on a scalable, flexible and modular approach to emotion which allows runtime evaluation between emotional quality and performance. The results achieved showed that the strategies based on temperamental decision mechanism strongly influence the system performance and there are evident dependency between emotional state of the agents and their temperamental type, as well as the dependency between the team performance and the temperamental configuration of the team members, and this enable us to conclude that the modular approach to emotional programming based on temperamental theory is the good choice to develop computational mind models for emotional behavioral Multi-Agent systems.

研究动机与目标

• 开发一种灵活、模块化的计算框架，用于建模自主智能体的情绪与气质。
• 研究情绪状态与气质类型如何影响多智能体系统中个体与集体智能体的表现。
• 评估团队构成——特别是气质多样性——对整体系统性能的影响。
• 通过生物启发模型，为人工智能与机器人系统中的情感智能行为奠定基础。

提出的方法

• 该模型采用基于气质的框架，将智能体分类为不同的情绪倾向，借鉴经典气质理论。
• 情绪状态根据环境刺激与内部阈值动态更新，实现对情绪状态的实时评估。
• 采用模块化架构，将情绪组件与核心认知及决策模块分离，支持运行时的可配置性。
• 系统采用性能评估机制，将情绪质量与行为结果相联系。
• 智能体在模拟环境中交互，其决策同时受认知推理与情绪状态的影响。
• 该模型支持可扩展性与模块化，允许在不同智能体上配置不同的气质配置。

实验结果

研究问题

• RQ1 不同气质类型在多智能体系统中如何影响个体智能体的决策？
• RQ2 智能体的情绪状态在多大程度上影响其表现与适应能力？
• RQ3 团队的气质构成在多大程度上影响集体表现与策略形成？
• RQ4 模块化、基于气质的情绪模型能否提升多智能体系统的鲁棒性与适应性？
• RQ5 情绪质量与自主智能体团队的系统级表现之间存在何种关系？

主要发现

• 基于气质的决策机制显著影响个体智能体的表现，不同气质类型导致不同的行为结果。
• 智能体的情绪状态与其气质类型之间存在明确依赖关系，表明气质决定了情绪反应性。
• 团队表现受到其成员气质配置的强烈影响，最优表现出现在气质平衡或互补的配置中。
• 情绪编程的模块化方法实现了对情绪质量及其对表现影响的有效运行时评估。
• 研究结果支持将气质理论作为设计情感智能多智能体系统的基础。
• 研究证实，情感现象与认知-行动回路密不可分，尤其在社交与自适应交互中。