GeniNav：生成模型驱动的图像目标导航——通过想象引导的一致性流匹配
GeniNav: Generative Model Driven Image-Goal Navigation via Imagination-Guided Consistency Flow Matching
将 VLM 驱动的潜变量子目标想象与多段一致性流匹配结合，用于无地图图像目标导航；其一致性流匹配策略与混合轨迹评估（语义对齐+几何可行性）可迁移到其他视觉导航与具身控制策略的时序平滑生成。
原文依据 Multi-Segment Consistency Flow Matching (MS-CFM) for temporally smooth and dynamically coherent motion generation
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论由生成模型驱动的图像目标导航近来展现出强劲潜力，这得益于其在连续控制空间中执行多模态推理与稳定学习的能力。尽管前景可观，现有方法仍面临若干根本性局限。许多方法依赖预构建的先验，且缺乏显式的轨迹评估机制，从而限制了无地图导航中的泛化能力与目标对齐。此外，当前的生成式策略往往存在效率低下或时序不一致的问题，导致运动在时间上不稳定。交互式闭环基准的缺失进一步限制了公平且可复现的对比。为解决这些问题，我们提出 GeniNav，一个生成式图像目标导航框架，它将 VLM 驱动的潜变量子目标想象模块（用于高层语义引导）与多段一致性流匹配（MS-CFM，用于生成时序平滑且动态连贯的运动）相耦合。一个混合轨迹评估模块进一步融合语义对齐与几何可行性，以评估目标一致性。我们还引入了一个闭环仿真基准，以及一个涵盖 176 个场景、491.6 公里的大规模数据集，用于标准化训练与评测。仿真与真实机器人上的大量实验验证了本方法的有效性。项目主页见：https://cyq638.github.io/geninav/。
英文原文摘要 1417 字符
Image-goal navigation driven by generative models has recently shown strong potential owing to their ability to perform multi-modal reasoning and stable learning in continuous control spaces. Despite their promise, current methods still face several fundamental limitations. Many rely on pre-built priors and lack explicit mechanisms for trajectory evaluation, restricting generalization and goal alignment in map-free navigation. Moreover, current generative policies often face inefficiency or temporal inconsistency, resulting in temporally unstable motion. The absence of interactive, closed-loop benchmarks further limits fair and reproducible comparison. To address these issues, we propose GeniNav, a generative image-goal navigation framework that couples a VLM-driven latent subgoal imagination module for high-level semantic guidance with Multi-Segment Consistency Flow Matching (MS-CFM) for temporally smooth and dynamically coherent motion generation. A hybrid trajectory evaluation module further integrates semantic alignment and geometric feasibility to assess goal consistency. We also introduce a closed-loop simulation benchmark with a large-scale dataset spanning 176 scenes and 491.6 km for standardized training and evaluation. Extensive experiments in simulation and on real robots demonstrate the effectiveness of our method. Our project page is available at: https://cyq638.github.io/geninav/.