EvolveNav: ゼロショット物体目標ナビゲーションのための先行的内省と自己進化メモリ
EvolveNav: Proactive Preflection and Self-Evolving Memory for Zero-Shot Object Goal Navigation
ゼロショット物体目標ナビゲーションにおいて、過去の軌跡からルールを抽出し、探索前に結果を予測する自己進化フレームワークを提案し、成功率を向上させた。
著者: Qi Chai, Wenhao Shen, Nanjie Yao, Yue Xia, Kaiyong Zhao, Jie Ma, Guosheng Lin, Hao Wang
分類: cs.AI
原文アブストラクト
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.