上下文作为先验:一种基于贝叶斯的意图推断方法用于非说话智能体的家用猫测试平台
Context as Prior: Bayesian-Inspired Intent Inference for Non-Speaking Agents with a Household Cat Testbed
AI总结:
本文提出CatSignal框架,通过将空间上下文作为先验约束和行为观测作为证据,实现多模态意图推断,提升非说话智能体的意图识别精度。
摘要:
许多现实环境中无法通过语言可靠传达目标的智能体,如家庭宠物、未说话的婴儿和其他非说话的具身智能体,其意图必须从不完整的上下文行为观测中推断。这产生了一个核心模糊性:可观测行为常是噪声或不明确的,而上下文提供强先验信息,但若使用不当可能引发脆弱的捷径预测。我们提出CatSignal,一种基于贝叶斯的概率框架,用于多模态意图推断,将空间上下文作为先验约束,行为观测作为证据。不同于将上下文视为普通输入特征,我们的方法使用上下文门控Product-of-Experts公式,从上下文、姿态动态和声音线索计算后验似的意图分布。我们在家庭猫设置中实例化此公式,作为意图推断非说话智能体的聚焦证明概念。在Leave-One-Video-Out评估多模态家庭猫数据集上,所提出的先验引导融合实现77.72%的最高整体准确率,优于特征拼接(71.83%)和更强的后期融合基线。更重要的是,它显著减少了在模糊情况下的上下文驱动捷径失败。虽然更简单的融合策略在Macro-F1和选择性预测中仍具竞争力,但所提模型在整体准确率和抑制上下文驱动捷径崩溃方面表现最佳。
英文摘要:
Many agents in real-world environments cannot reliably communicate their goals through language, including household pets, pre-verbal infants, and other non-speaking embodied agents. In such settings, intent must be inferred from incomplete behavioral observations in context-rich environments. This creates a core ambiguity: observable behavior is often noisy or underspecified, while context provides strong prior information but can also induce brittle shortcut predictions if used naively. We present CatSignal, a Bayesian-inspired probabilistic framework for multimodal intent inference that models spatial context as a prior-like constraint and behavioral observations as evidence. Rather than treating context as an ordinary input feature, our method uses a context-gated Product-of-Experts formulation to compute posterior-like intent distributions from context, pose dynamics, and acoustic cues. We instantiate this formulation in a household cat setting as a focused proof-of-concept for intent inference in non-speaking agents. Under Leave-One-Video-Out evaluation on a multimodal domestic cat dataset, the proposed prior-guided fusion achieves the best overall accuracy of 77.72%, outperforming feature concatenation (71.83%) and stronger late-fusion baselines. More importantly, it substantially reduces context-driven shortcut failures in ambiguous cases. While simpler fusion strategies remain competitive in Macro-F1 and selective prediction, the proposed model provides the strongest overall accuracy and the best suppression of context-based shortcut collapse.
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。