连续空间中机器人的情绪交互模型

Robot emotional interaction model in continuous space

根据交互过程中的场力理论,在有源场情绪状态空间中建立起服务机器人的连续可控的情感调节过程。首先,在费希纳-韦伯定律的基础上,定量分析Gross策略中情绪的自发性认知重评与指导性认知重评过程;其次,根据情感强度第三定律提出一种与情绪效价相关联的情绪强度衰减模型;再次,依据动力心理学理论,建立起基于有源场的情绪能量空间,用于模拟外界刺激情绪与机器人自身情绪的相互作用过程;并建立起基于情绪唤醒度的机器人行为表达抑制模型。在此研究基础上,提出基于HMM的情绪状态刺激转移算法;并将以上模型算法用于13自由度的服务机器人平台中,实现非典型表情交互环境中机器人不确定性情绪过程的动态、可控调节。通过在连续情绪状态空间中的不确定性计算将离散的情绪状态拓展到连续空间中,并产生多种中间状态以及发挥机器人情绪调节的拟人特征。研究结果表明:具有认知能力及情绪控制力的机器人可以在交互过程中使参与者的满意程度得到一定提升。

A service robot＇s continuous and controlled emotional regulation in active field state space was proposed based on field force theory in human-robot interaction. First, on the basis of Fechner-Weber law, emotional spontaneous and guidable cognitive reappraisal in Gross strategies were analyzed quantitatively. Second, emotional attenuation model associated with valence was set up by the emotion intensity third law, and energy space in active field was proposed for simulating the interaction between external stimulus and robot＇s emotion. Finally, the stimulating emotional transfer algorithm based on Hidden Markov Model （HMM） was come up with to realize real-time dynamic control on 13 DOF service robot for uncertainty emotional regulation in interaction with atypical facial expressions. The anthropomorphic emotional regulation which operates in a continuous 3D emotional space enables a wide range of intermediary emotional states to be obtained. The results show that the robot with cognition and emotional control ability could serve more participants＇ emotional needs in the human-robot interaction （HRI）.