发表机构
University of Luxembourg（卢森堡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本综述系统梳理基于因子图和场景图的机器人世界模型，重点分析动态环境建模方法、混合模型架构及下游任务应用，并指出不确定性传播、可观测性、终身维护和评估基准等开放挑战。
AI 中文摘要
基于图的模型已成为机器人学中内部世界表示的有力基础，其中因子图和场景图是相关文献及成功机器人解决方案中最突出的模型类型。最初，许多此类模型将静态环境作为简化假设。在此背景下，因子图主要提供考虑不确定性的几何估计，而场景图则实现结构化的语义抽象。然而，现实世界的机器人环境往往是动态的，这对纯静态世界表示构成了严峻挑战。因此，本综述全面探讨了如何在基于图的世界模型中处理现实世界环境的动态方面。我们围绕三个主要方面组织评估：（I）合适的表示方法，（II）构建和更新表示的流程，以及（III）它们在下游任务中的利用。我们回顾了基于因子图或场景图的方法，但特别强调结合两种类型形成混合模型的新方法。我们主要分析在此类模型中如何建模不同类型的动态，并归类常见架构模式。最后，我们指出了新兴趋势和开放挑战，包括从学习感知通过表示层传播的不确定性、在最小传感下动态实体运动和尺度的可观测性、可扩展的终身维护，以及缺乏将世界模型质量基于动态下下游任务性能进行验证的数据集和评估协议。
英文摘要
Models based on graphs have emerged in robotics as a powerful foundation for internal world representations, where factor and scene graphs are among the most prominent model types found in the related literature and in successful robotic solutions. Initially, many of these models were assuming static environments as a simplification. Herein, factor graphs mainly provide uncertainty-aware geometric estimations while scene graphs enable a structured semantic abstraction. However, real-world robotic environments are often dynamic, posing severe challenges for purely static world representations. Therefore, this review presents a comprehensive view on how dynamic aspects of real-world environments can be addressed in such graph-based world models. We organize our assessments around three main aspects: (I) suitable representations, (II) pipelines to construct and update the representations, and (III) their exploitation for downstream tasks. We review approaches that are either based on factor or scene graphs, but put special emphasis on novel approaches that combine both types to form hybrid models. We mainly analyze how different types of dynamics can be modeled herein, and categorize common architectural patterns. Finally, emerging trends and open challenges are identified, including uncertainty propagation from learned perception through the representation layers, the observability of dynamic-entity motion and scale under minimal sensing, scalable lifelong maintenance, and the lack of datasets and evaluation protocols that ground world-model quality in downstream task performance under dynamics.
Comments34 pages, 7 tables, 8 figures
