arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.02137cs.ROcs.AIcs.NE
收藏

领导还是追随?基于主动推理框架的二进机器人模拟交互

Leading or Following? Dyadic Robot Imitative Interaction Using the Active Inference Framework

Okinawa Institute of Science and Technology Graduate University(冲绳科学技术大学院大学)

Nadine Wirkuttis, Jun Tani

摘要:

本研究探讨了机器人智能体之间的社会互动如何根据个体对行动意图的信念而动态变化。在一组仿真研究中,我们研究二进模仿机器人的相互作用,使用变分递归神经网络模型。该模型基于自由能原理,使得一对相互作用的机器人发现自己处于循环中,试图使用主动推理来预测和推断彼此的动作。我们研究了如何调节复杂性项,以最大限度地减少自由能确定网络和相互作用的动态特性。当一个训练较严格的规则和另一个训练较宽松的规则相互作用,后者倾向于通过施加更强的动作意图来引导交互,而前者倾向于通过适应其观察来跟随。研究证实,二进模仿互动成为成功的实现高同步率时,领导者和追随者是由发展的行动意图与强信念和弱信念,分别。

英文摘要:

This study investigated how social interaction among robotic agents changes dynamically depending on the individual belief of action intention. In a set of simulation studies, we examine dyadic imitative interactions of robots using a variational recurrent neural network model. The model is based on the free energy principle such that a pair of interacting robots find themselves in a loop, attempting to predict and infer each other's actions using active inference. We examined how regulating the complexity term to minimize free energy determines the dynamic characteristics of networks and interactions. When one robot trained with tighter regulation and another trained with looser regulation interact, the latter tends to lead the interaction by exerting stronger action intention, while the former tends to follow by adapting to its observations. The study confirms that the dyadic imitative interaction becomes successful by achieving a high synchronization rate when a leader and a follower are determined by developing action intentions with strong belief and weak belief, respectively.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑