让机器人在陌生环境里边走边学，自动修正错误，减少试错。
EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigation
- 从过往经验中提取可执行规则，构建会自我更新的记忆库。
- 引入置信度优先检索策略，选对规则提升导航成功率10.1%。
- 预判动作后果减少无效探索，适合需要快速适应的新场景。
零样本目标导航要求智能体在未见过的环境中探索并找到目标物体。现有方法虽借助基础模型，但多依赖静态先验知识，缺乏适应能力，导致重复出错和高成本试错。本文提出一种自演化零样本目标导航框架，支持测试时持续优化。具体地，通过提取历史轨迹中的可操作知识构建代理式规则记忆；设计基于上置信界（UCB）的检索策略，在语义相关性与历史成功率间权衡，选择有效规则；引入记忆引导的预反思模块，提前预测动作结果，降低无效探索。大量实验表明，该方法优于现有零样本基线，成功率达10.1%提升，且行动步数更少。
原文摘要 · Abstract (English)
Zero-Shot Object-Goal Navigation (ZS-OGN) requires embodied agents to explore and locate target objects without any prior training. To this end, recent methods leverage foundation models. But they typically rely on static priors and lack adaptation, which leads to repeated errors and costly trial and error. In this paper, we propose a self-evolving ZS-OGN framework that enables continuous test-time improvement. Specifically, we build an agentic rule memory by extracting actionable knowledge from past trajectories. Then, we propose a retrieval strategy based on upper confidence bound, selecting effective rules by balancing semantic relevance and historical success. In addition, we introduce a memory-guided preflection module that forecasts potential outcomes before action, reducing inefficient exploration. Extensive experiments show that our method outperforms existing zero-shot baselines, achieving a 10.1\% improvement in success rate with fewer unnecessary steps.
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。