人間らしいエージェントのための生成的具現化複数行動制御システム
Generative Embodied Multiple Behavior Control Systems for Human-like Agents
習慣的行動と目標指向的行動を統合的にモデル化し、個人差や内部状態に応じて両者を動的に調整する人間らしいエージェントの行動制御フレームワークを提案した。
著者: Chongyu Bao, Haokai Yang, Yuhan Wang, Zhaochong An, Kunpeng Liu, Xiaolan Liu
分類: cs.AI
原文アブストラクト
An enduring and richly elaborated dichotomy in cognitive neuroscience is that of human behavior control mechanisms, divided into habitual versus goal-directed. While existing human-like agent frameworks primarily focus on modeling goal- directed behavior, habitual behavior has been largely overlooked, though it plays a crucial role in human daily life. In this paper, we address this gap by studying multiple behavior control systems that jointly model goal-directed and habitual behaviors. We propose a human behavior control mechanism-inspired framework which the Habitual Controller retrieves cue-triggered behaviors from personal- ized habit memory, while the Goal-directed Controller employs a context-aware world model to predict action consequences and estimate their values. The Arbiter dynamically balances the influence of both systems according to individual differ- ences and momentary internal states. To reconstruct diverse human-level behavior instructions in 3D environments, we further develop a keyframe-guided 3D mo- tion generation module. Through extensive evaluation methods, human studies, and ablations studies, experimental results demonstrate that human-likeness per- formance is significantly improved by our approach. The efficacy of our approach indicates the benefits of leveraging habitual behavior and multiple behavior con- trol system coordination for believable embodied human-like agents.