arXiv 2603.084752026-03-09cs.ROcs.AI

R2F：利用射线前沿进行无需大语言模型的对象导航

R2F: Repurposing Ray Frontiers for LLM-free Object Navigation

Department of Computer, Automation and Management Engineering, Sapienza University of Rome（罗马萨皮恩扎大学计算机、自动化与管理工程系）；Department of Electronics and Automation, Mohamed Khider University of Biskra（比斯克拉Mohamed Khider大学电子与自动化系）；International University of Rome UNINT, Rome（罗马国际大学UNINT）

Francesco Argenziano, John Mark Alexis Marcelo, Michele Brienza, Abdel Hakim Drid, Emanuele Musumeci, Daniele Nardi, Domenico D. Bloisi, Vincenzo Suriani

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

R2F通过重新利用射线前沿技术，开发无需大语言模型的室内开放词汇对象导航框架，实现实时高效导航性能。

摘要：

零样本开放词汇对象导航随着大型视觉-语言模型（VLM）和大型语言模型（LLM）的出现而迅速发展，现在广泛用作高层决策者而不是端到端策略。尽管有效，此类系统往往在推理时依赖迭代的大模型查询，引入延迟和计算开销，限制了实时部署。为了解决这个问题，我们重新利用最近提出的基于前沿的探索范式“射线前沿”（R2F），开发一个无需大语言模型的室内开放词汇对象导航框架。虽然射线前沿最初用于利用射线携带的语义线索来偏斜探索，但我们重新解释前沿区域为显式的、方向条件的语义假设，作为导航目标。沿超出范围射线积累的语言对齐特征被稀疏存储在前沿中，其中每个区域维护多个方向嵌入，编码可能的未见内容。这样，导航就减少为在经典映射和规划管道中基于嵌入的前沿评分和目标跟踪，消除了迭代的大模型推理。我们进一步引入R2F-VLN，一种轻量级扩展，用于自由形式语言指令，使用语法解析和关系验证，无需额外的VLM或LLM组件。在Habitat-sim和真实机器人平台上的实验表明，该方法在零样本性能上具有竞争力，具有实时执行能力，达到VLM基替代方案的6倍快的运行时间。

英文摘要：

Zero-shot open-vocabulary object navigation has progressed rapidly with the emergence of large Vision-Language Models (VLMs) and Large Language Models (LLMs), now widely used as high-level decision-makers instead of end-to-end policies. Although effective, such systems often rely on iterative large-model queries at inference time, introducing latency and computational overhead that limit real-time deployment. To address this problem, we repurpose ray frontiers (R2F), a recently proposed frontier-based exploration paradigm, to develop an LLM-free framework for indoor open-vocabulary object navigation. While ray frontiers were originally used to bias exploration using semantic cues carried along rays, we reinterpret frontier regions as explicit, direction-conditioned semantic hypotheses that serve as navigation goals. Language-aligned features accumulated along out-of-range rays are stored sparsely at frontiers, where each region maintains multiple directional embeddings encoding plausible unseen content. In this way, navigation then reduces to embedding-based frontier scoring and goal tracking within a classical mapping and planning pipeline, eliminating iterative large-model reasoning. We further introduce R2F-VLN, a lightweight extension for free-form language instructions using syntactic parsing and relational verification without additional VLM or LLM components. Experiments in Habitat-sim and on a real robotic platform demonstrate competitive state-of-the-art zero-shot performance with real-time execution, achieving up to 6 times faster runtime than VLM-based alternatives.

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。