VIScore: Diagnosing Planning-Relevant Quality in Latent World Models

📄 arXiv: 2608.11174v1 📥 PDF

作者: Haiyu Wu, Randall Balestriero, Morgan Levine

分类: cs.RO

发布日期: 2026-08-11


💡 一句话要点

提出VIScore以解决潜在世界模型规划成功率评估问题

🎯 匹配领域: 支柱二:RL算法与架构 (RL & Architecture)

关键词: 潜在世界模型 规划成功率 正则化损失 VIScore 自监督学习 性能评估 机器人规划

📋 核心要点

  1. 现有方法在潜在空间特性与规划成功之间缺乏有效联系,导致规划性能不佳。
  2. 本文提出VIScore度量,旨在量化编码特征下的预测能力和规划者的有效性,从而提升规划成功率。
  3. 实验结果表明,VIScore在多个模型和数据集上与成功率的Spearman相关性超过0.75,且校准误差最低。

📝 摘要(中文)

调节潜在空间至各向同性高斯分布为世界模型规划提供了稳定的信息最大化环境。然而,潜在空间特性与成功规划之间的关系仍不明确。本文比较了SIGReg和VISReg两种正则化损失函数,发现VISReg在控制中心、尺度和形状正则化权重方面更具灵活性,并且在OOD数据集上提升了规划成功率。为此,提出了VIScore度量,量化了编码特征下预测器的可达性和能力,以及基于搜索的规划者的幻觉。与其他度量相比,VIScore在成功率解释上表现更佳,且在所有测试场景中校准误差最低,展示了其在世界模型设计与诊断中的重要性。

🔬 方法详解

问题定义:本文旨在解决潜在世界模型中,潜在空间特性与规划成功率之间的脱节问题。现有的SIGReg方法虽然在自监督学习中表现良好,但对规划成功并无帮助。

核心思路:提出VISReg作为一种更灵活的正则化方法,能够更好地控制潜在空间的中心、尺度和形状,从而提升规划的成功率。通过引入VIScore度量,深入分析影响规划成功的因素。

技术框架:整体架构包括编码器、预测器和规划者三个主要模块。编码器负责特征提取,预测器评估特征的可达性,而规划者则基于这些特征进行决策。

关键创新:VIScore是一个新提出的度量标准,能够更全面地评估编码特征的有效性及其对规划成功的影响,超越了传统的度量方法。

关键设计:在VISReg中,正则化损失函数的设计允许对不同参数进行灵活调整,且采用较大的批量大小以获得更精确的分布近似。

🖼️ 关键图片

fig_0
img_1
img_2

📊 实验亮点

实验结果显示,VIScore在多个已知和未知模型及数据集上,与成功率的Spearman相关性超过0.75,且在所有测试场景中校准误差低于常数拟合,显著优于其他度量方法。

🎯 应用场景

该研究的潜在应用领域包括机器人规划、自动驾驶和智能决策系统等。通过提升潜在世界模型的规划成功率,VIScore可以为这些领域提供更可靠的性能评估和优化方案,推动智能系统的进一步发展。

📄 摘要(原文)

Regulating the latent space to an isotropic Gaussian distribution provides a stable and information-maximized landscape for world model planning. However, the latent space property and successful planning remain disconnected. We first study this by comparing SIGReg and VISReg, two regularization loss functions with the same distribution target but different properties. Compared with SIGReg, VISReg has more flexibility in controlling the weights of center, scale, and shape regularization, and a larger batch size brings a finer distribution approximation. We find that the former, despite being beneficial in self-supervised learning (SSL), does not help the planning, whereas the latter improves the planning success on out-of-domain (OOD) datasets. This motivates a deep understanding of the factors that correlate with the success rate. Unlike the previous metrics focusing on the encoded latent only, we propose the Veracity-Influence-Sobriety score (VIScore), a metric that quantifies the reachability and capacity of a predictor given the encoded feature, and the hallucination of the searching-based planner. Compared with straightness, physical-state probing, and empowerment, we show that, with the measurement covering encoder, predictor, and planner, VIScore explains the success rate better than the others, as reflected by a strong Spearman correlation. Specifically, VIScore consistently achieves a Spearman correlation over 0.75 on both seen and unseen models and datasets on the cross-task success rate pool. Moreover, VIScore is the only metric that has a calibration error below the constant fit across all testing scenarios, showcasing the importance of these three aspects in planning success. We hope this metric can help future studies on world model design and diagnosis.