This paper presents Neural Visibility Field (NVF), a novel uncertainty
quantification method for Neural Radiance Fields (NeRF) applied to active
mapping. Our key insight is that regions not visible in the training views lead
to inherently unreliable color predictions by NeRF at this region, resulting in
increased uncertainty in the synthesized views. To address this, we propose to
use Bayesian Networks to composite position-based field uncertainty into
ray-based uncertainty in camera observations. Consequently, NVF naturally
assigns higher uncertainty to unobserved regions, aiding robots to select the
most informative next viewpoints. Extensive evaluations show that NVF excels
not only in uncertainty quantification but also in scene reconstruction for
active mapping, outperforming existing methods.

本文提出神经显性场（NVF），这是一种用于应用于主动映射的神经辐射场（NeRF）的新型不确定性量化方法。通过使用贝叶斯网络将基于位置的场不确定性组合到基于光线的相机观测不确定性中，NVF 自然地将更高的不确定性分配给未观察到的区域，帮助机器人选择最具信息量的下一个视点。大量的评估结果表明，NVF 在不确定性量化和场景重建方面表现出色，优于现有方法。

基于不确定性驱动的主动建图的神经可见度场

Neural Visibility Field for Uncertainty-Driven Active Mapping

We address the problem of active mapping with a continually-learned neural
scene representation, namely Active Neural Mapping. The key lies in actively
finding the target space to be explored with efficient agent movement, thus
minimizing the map uncertainty on-the-fly within a previously unseen
environment. In this paper, we examine the weight space of the
continually-learned neural field, and show empirically that the neural
variability, the prediction robustness against random weight perturbation, can
be directly utilized to measure the instant uncertainty of the neural map.
Together with the continuous geometric information inherited in the neural map,
the agent can be guided to find a traversable path to gradually gain knowledge
of the environment. We present for the first time an active mapping system with
a coordinate-based implicit neural representation for online scene
reconstruction. Experiments in the visually-realistic Gibson and Matterport3D
environment demonstrate the efficacy of the proposed method.

我们提出了一种具有不断学习的神经场景表示的主动映射问题，即主动神经映射。关键在于通过高效的代理移动主动地找到要探索的目标空间，从而在以前未见过的环境中实时地最小化地图的不确定性。本文研究了不断学习的神经场中的权重空间，并通过实验证明了神经变异性，即针对随机权重扰动的预测稳健性，可以直接用于测量神经映射的即时不确定性。结合神经映射中继承的连续几何信息，代理可以被引导找到可穿越的路径，逐渐了解环境。我们首次提出了一种具有基于坐标的隐式神经表示的在线场景重建的主动映射系统。在视觉逼真的 Gibson 和 Matterport3D 环境中进行的实验证明了该方法的有效性。

主动神经映射

Active Neural Mapping

In this paper, we derive and implement a probabilistic programming idiom for
the problem of acquiring new knowledge about an environment. The idiom is
implemented utilizing a modern probabilistic programming language. We
demonstrate the utility of this idiom by implementing an algorithm for the
specific problem of active mapping and robot exploration. Finally, we evaluate
the functionality of the implementation through an extensive simulation study
utilizing the HouseExpo dataset.

本研究通过一种基于概率编程实现的语言，提出并实现了一种能够获取关于环境新知识的编程模型，通过在实验中运用此模型，成功实现了一个适用于主动建图和机器人探测的算法。最终，通过对基于 HouseExpo 数据集的广泛模拟研究，进一步验证了实现的功能。