让机器人通过心理建模实现社交决策，提升复杂环境下的协作能力。
Latent Perspective-Taking via a Schrödinger Bridge in Influence-Augmented Local Models
- 用分解式贝叶斯网络构建可学习的心理模型
- 通过量子桥接机制实现自我与他人视角的信念转换
- 适用于需要实时社会推理的机器人任务
在与人类共存的环境中，机器人需在不确定性下做决策，不仅考虑外部动态，还需推断他人隐藏的心理模型与状态。尽管交互式部分可观测马尔可夫决策过程（Interactive POMDPs）和贝叶斯心智理论方法具有理论基础，但精确的嵌套信念推断难以计算，且手工设定模型在开放世界中易失效。为此，我们学习结构化的心理模型并构建他人状态估计器。基于影响抽象，我们构建了影响增强局部模型（Influence-Augmented Local Model），将社交感知任务分解为局部动态、社会影响和外生因素。提出（a）一个神经符号世界模型，采用因子化离散动态贝叶斯网络；（b）一种视角转换算子，以近似量子桥接方式在学习到的局部动态上，将个体中心信念转移到他人中心信念。该架构支持基于模型的强化学习中合成社交意识策略，通过决策时刻的心理状态规划（信念空间中的量子桥接），初步实验在MiniGrid社交导航任务中取得有效结果。
原文摘要 · Abstract (English)
Operating in environments alongside humans requires robots to make decisions under uncertainty. In addition to exogenous dynamics, they must reason over others' hidden mental-models and mental-states. While Interactive POMDPs and Bayesian Theory of Mind formulations are principled, exact nested-belief inference is intractable, and hand-specified models are brittle in open-world settings. We address both by learning structured mental-models and an estimator of others' mental-states. Building on the Influence-Based Abstraction, we instantiate an Influence-Augmented Local Model to decompose socially-aware robot tasks into local dynamics, social influences, and exogenous factors. We propose (a) a neuro-symbolic world model instantiating a factored, discrete Dynamic Bayesian Network, and (b) a perspective-shift operator modeled as an amortized Schrödinger Bridge over the learned local dynamics that transports factored egocentric beliefs into other-centric beliefs. We show that this architecture enables agents to synthesize socially-aware policies in model-based reinforcement learning, via decision-time mental-state planning (a Schrödinger Bridge in belief space), with preliminary results in a MiniGrid social navigation task.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。