基于操作者推断的具身感知控制：一项仿真研究
Embodiment-aware control by inference over the operator: a simulation study
- Pace University（佩斯大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出通用具身引擎（UEE），通过推断操作者具身状态和线索权重来优化遥操作控制，仿真显示其优于固定设置，收益源于贝叶斯推断而非主动推断的信息寻求。
AI中文摘要：
遥操作系统通常针对信道保真度进行调优，而操作者是否将设备体验为身体的一部分，即具身感（Sense of Embodiment, SoE），仅在事后通过问卷测量。预测处理理论认为，控制设备以减少操作者预测与返回反馈之间的不匹配是可行的，但这些预测是不可观测的，且仅惩罚不匹配的目标函数会因移除反馈而达到最小化。我们提出了一种具身感知控制器——通用具身引擎（Universal Embodiment Engine, UEE），它从隐式注视和瞳孔信号及任务结果中推断操作者的具身状态和视觉-本体感觉线索权重，并在显式偏好下选择有界设备设置，建模为离散的主动推断（Active Inference）智能体。在包含300个异构合成操作者的仿真中，UEE在大多数操作者中于半分钟内找到合适设置，早于识别出其确切类型，并在会话后半段接近Oracle性能（在0-2量表上，具身得分为1.68，而最佳固定设置为0.73）。不读取操作者而进行自适应并不优于固定控制，无模型赌博机算法表现更差，而具有相同推断的期望效用控制器表现完全一致：收益来自对操作者进行贝叶斯推断并结合显式偏好，而非主动推断的信息寻求项。一个朴素的预测误差最小化器会如其所隐含的目标那样撤回反馈，并导致任务成功率下降（0.74对0.90）。对于控制器模型族之外的操作者，收益缩小但持续存在；随群体多样性增加而增长；当控制器信任无信息信号或线索权重在会话中途改变且未被建模时，收益消失。这些失败表明，在人体研究中必须首先确立：校准信号和变化模型。
英文摘要：
Teleoperation systems are tuned for channel fidelity, while whether the operator experiences the device as part of the body, the Sense of Embodiment (SoE), is measured only afterwards, by questionnaire. Predictive-processing accounts suggest controlling devices to reduce the mismatch between the operator's predictions and the returned feedback, but those predictions are unobservable, and an objective that only penalizes mismatch is minimized by removing feedback. We formulate an embodiment-aware controller, the Universal Embodiment Engine (UEE), that infers the operator's embodiment and visuo-proprioceptive cue weighting from implicit gaze and pupil signals and task outcome, and chooses bounded device settings under explicit preferences, cast as a discrete Active Inference agent. In simulations with 300 heterogeneous synthetic operators, the UEE found the suitable setting within half a minute for most operators, before identifying their exact type, and came close to an oracle in the second half of the session (embodiment 1.68 against 0.73 for the best fixed setting, on a 0-2 scale). Adapting without reading the operator did no better than fixed control, and model-free bandits did worse, whereas an expected-utility controller with the same inference did exactly as well: the benefit comes from Bayesian inference over the operator with explicit preferences, not from the information-seeking term of Active Inference. A naive prediction-error minimizer withheld feedback, as its objective implies, and lost task success (0.74 vs 0.90). The benefit shrank but persisted for operators outside the controller's model family, grew with the variety of the population, and vanished when the controller trusted an uninformative signal or when cue weighting changed mid-session without being modeled. These failures show what studies with people must establish first: calibrated signals and a model of change.
