外观
论文arXiv 2605.0252527 天前
面向 VLM 集成室内移动机器人的语义自主框架：混合确定性推理与跨机器人自适应记忆
原文链接：A Semantic Autonomy Framework for VLM-Integrated Indoor Mobile Robots: Hybrid Deterministic Reasoning and Cross-Robot Adaptive Memory（arXiv 2605.02525 · 发布日期：2026-10-01）
A Semantic Autonomy Framework for VLM-Integrated Indoor Mobile Robots: Hybrid Deterministic Reasoning and Cross-Robot Adaptive Memory
针对语义室内导航中的指令目的地关联与经验保留，SAS以确定性优先级联结合VLM，在室内物理机器人配置上验证。
核心要点
- 问题：机器人需将人类指令关联到空间目的地，执行任务并保留有用运行经验。
- 方法：SAS六层框架在ROS 2/Nav2基础上扩展语义推理、任务接口和操作记忆。
- 推理级联先用路线图、语义对象、状态和记忆确定性求解，未决情况再交给预训练VLM。
- 实验中216个决策周期有112个确定性解决；28条封闭挑战得到17个可接受结果。
验证范围与局限：验证限于一个室内环境中的两个物理机器人配置，导航感知在机载端，推理和记忆在共享工作站。
英文摘要 (Abstract)
Semantic indoor navigation requires robots to connect human instructions with spatial destinations, execute missions and retain useful operational experience. This paper presents the Semantic Autonomy Stack (SAS), a six-layer integration framework, and develops its semantic-reasoning, mission-interface and operational-memory layers over a previously validated ROS 2/Nav2 foundation. A deterministic-first cascade combines the route graph, semantic objects, robot state and stored instruction–destination associations, escalating unresolved or guarded cases to a pretrained Vision-Language Model (VLM). SAS separates destination selection, action validation, navigation execution and post-arrival confirmation. Recurrent model-mediated associations can pass a frequency-and-consistency gate and be compiled for deterministic M3 reuse; this gate measures sampled-output stability rather than semantic truth. The frozen v4.8-review implementation was evaluated on two physical robot configurations in one indoor environment, with onboard navigation and perception and shared-workstation reasoning and memory. Of 216 decision cycles outside the start gate, 112 resolved deterministically at sub-millisecond resolver-compute latency. A sealed 28-instruction challenge yielded 17 acceptable outcomes; five fast-path decisions included one incorrect selection. One promoted association was reused on the second platform through deliberate shared-digest installation. A controlled 594-observation offline comparison identified descriptive semantic and latency benefits from M3 reuse in five familiar cases. The M3-disabled cascade reduced VLM calls but matched direct-VLM decision quality in standardized context. Large latency savings were concentrated in paths avoiding VLM inference. Together, the results establish a working integration of selective hybrid reasoning and reusable operational memory, while identifying implementation and evaluation boundaries for further development within SAS.
作者：Bogdan Felician Abaza, Andrei-Alexandru Staicu, Cristian Vasile Doicin
来源
本页事实对应的公开页面，以原文为准。