MGpi:一个多智能体群体感知与交互的计算模型
MGpi: A Computational Model of Multiagent Group Perception and Interaction
摘要:
为了使下一代机器人能够与人类进行社会智能互动,我们提出了一个$\mathbf{computational\; model}$的多个代理和多个群体的社会环境中的互动。多智能体群体感知和交互(MGpi)网络是一种深度神经网络,其预测在群体对话中执行的适当社交动作(例如,说、听、响应、离开),考虑邻居的可观察特征(例如,人的位置、注视方向、分心等)。MGpi的一个核心组件是Kinesic-Proxemic-Message(KPM)门,它执行社交信号门控以从组对话中提取重要信息。特别是,KPM门过滤器传入的社会线索从附近的代理人通过观察他们的身体姿势(身势)和空间行为(体势)。MGpi网络及其KPM门是通过模仿学习来学习的,使用我们设计的$\mathbf{social\; interaction\; simulator}$的演示。此外,我们证明了KPM门作为社会注意力机制的功效,在不使用显式组注释、布局假设或手动选择参数的情况下,实现了$\mathbf{group\; identification}$任务的最先进性能。
英文摘要:
Toward enabling next-generation robots capable of socially intelligent interaction with humans, we present a $\mathbf{computational\; model}$ of interactions in a social environment of multiple agents and multiple groups. The Multiagent Group Perception and Interaction (MGpi) network is a deep neural network that predicts the appropriate social action to execute in a group conversation (e.g., speak, listen, respond, leave), taking into account neighbors' observable features (e.g., location of people, gaze orientation, distraction, etc.). A central component of MGpi is the Kinesic-Proxemic-Message (KPM) gate, that performs social signal gating to extract important information from a group conversation. In particular, KPM gate filters incoming social cues from nearby agents by observing their body gestures (kinesics) and spatial behavior (proxemics). The MGpi network and its KPM gate are learned via imitation learning, using demonstrations from our designed $\mathbf{social\; interaction\; simulator}$. Further, we demonstrate the efficacy of the KPM gate as a social attention mechanism, achieving state-of-the-art performance on the task of $\mathbf{group\; identification}$ without using explicit group annotations, layout assumptions, or manually chosen parameters.
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。