工程设计比语言智能更关键，简单几何策略可媲美大模型导航
When Engineering Outruns Intelligence: Rethinking Instruction-Guided Navigation
- 用几何前沿探测替代复杂语言模型，不调用API
- 在HM3D和MP3D上达到与指令跟随者相当的准确率
- 适合关注高效导航系统设计的研究者
近期的物体导航系统将零样本性能提升归功于大语言模型（LLMs），但其语言与几何贡献仍不明确。本文重新评估指令引导的InstructNav流程，在检测器控制环境下引入两种无需训练的变体：仅依赖几何的前沿接近探测器（FPE）和轻量语义启发式前沿（SHF），后者通过简单前沿投票询问LLM。在HM3D和MP3D数据集上，FPE无需任何API调用且运行更快，性能持平或超越检测器控制下的指令跟随者；SHF以更小、局部化的语言先验实现相近准确率。结果表明，精心设计的前沿几何已解释了大部分性能提升，而语言更适合作为轻量启发式而非端到端规划器。代码见：https://github.com/matinaghaei/instructnav-scrutinized
原文摘要 · Abstract (English)
Recent ObjectNav systems credit large language models (LLMs) for sizable zero-shot gains, yet it remains unclear how much comes from language versus geometry. We revisit this question by re-evaluating an instruction-guided pipeline, InstructNav, under a detector-controlled setting and introducing two training-free variants that only alter the action value map: a geometry-only Frontier Proximity Explorer (FPE) and a lightweight Semantic-Heuristic Frontier (SHF) that polls the LLM with simple frontier votes. Across HM3D and MP3D, FPE matches or exceeds the detector-controlled instruction follower while using no API calls and running faster; SHF attains comparable accuracy with a smaller, localized language prior. These results suggest that carefully engineered frontier geometry accounts for much of the reported progress, and that language is most reliable as a light heuristic rather than an end-to-end planner. Code available at: https://github.com/matinaghaei/instructnav-scrutinized
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。