PSG-Nav: 通过多元宇宙决策的概率场景图导航
PSG-Nav: Probabilistic Scene Graph Navigation via Multiverse Decision Making
AI总结：
提出PSG-Nav方法，通过构建3D概率场景图并利用多元宇宙决策从联合分布中采样最可能的世界设置，以处理开放词汇导航中的感知不确定性，并引入证据经验校准器实现在线终身适应，在多个基准上取得最新最优结果。
摘要：
开放词汇导航要求具身智能体管理由语义歧义和模型错误引起的显著感知不确定性。然而，大多数现有工作满足于局部最优的确定性方法，剥夺了在多个复合可能性上的复杂导航决策，而这些对于全局更优解至关重要。在本文中，我们提出概率场景图导航（PSG-Nav），它构建了一个3D概率场景图，使用完整的语义类别分布来考虑感知不确定性。为了有效利用局部分布来组合和推理最优导航地标，我们提出多元宇宙决策，从联合分布中采样多个最可能的世界设置，并基于地标与多元宇宙之间的兼容性评估导航地标。为了减轻开放词汇导航中因认知不确定性导致的误报，我们引入证据经验校准器，通过将检测与过去成功和失败的记忆进行交叉验证，实现在线终身适应。在广泛使用的基准MP3D、HM3D和HSSD上的大量实验表明，PSG-Nav建立了新的最先进结果，分别实现了66.1%、44.8%和67.9%的成功率。代码可在https://psg-nav.github.io/获取。
英文摘要：
Open-vocabulary navigation requires embodied agents to manage significant perception uncertainty stemming from semantic ambiguity and model errors. However, most existing works settle for local optimal deterministic approaches, depriving complex navigation decision-making over multiple composite possibilities that are critical for globally better solutions. In this paper, we propose Probabilistic Scene Graph Navigation (PSG-Nav), which constructs a 3D Probabilistic Scene Graph that uses full semantic categorical distributions to account for perception uncertainty. To efficiently use the local distributions to compose and reason about the optimal navigation landmarks, we propose Multiverse Decision to sample multiple most likely world settings from the joint distribution, and evaluate navigation landmarks based on the compatibility between landmarks and multiverses. To mitigate false positives due to epistemic uncertainty in open-vocabulary navigation, we introduce the Evidential Experience Calibrator, which enables online lifelong adaptation by cross-validating detections against memories of past successes and failures. Extensive experiments on widely-used benchmarks MP3D, HM3D, and HSSD demonstrate that PSG-Nav establishes new state-of-the-art results, achieving Success Rates of 66.1%, 44.8%, and 67.9%, respectively. Code is available at: https://psg-nav.github.io/
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。
