外观
论文arXiv 2606.08029今天
IntentNav:基于人类演示的空间视觉导航框架实现SOTA与零样本跨形态迁移
本文由 AI 根据公开内容整理,可能有误,请以原文为准:IntentNav: Learning Spatial-Visual Object Navigation from Human Demonstrations(arXiv 2606.08029)
核心内容
针对未知环境中目标物体导航(ObjectNav)的部分可观测挑战,研究团队提出IntentNav空间视觉模仿学习框架。该方法旨在从人类演示中学习类人搜索策略,通过选择性探测视觉前沿并依赖空间记忆避免冗余重访。实验表明,IntentNav在MP3D、HM3D-v1和HM3D-v2三大主流ObjectNav基准测试中均取得State-of-the-Art性能,成功率超越现有所有学习型方法,验证了从人类低层动作推断高层搜索意图的有效性。
技术上引入“基于前沿的人类意图标注”机制,通过前瞻分析演示轨迹标记解释未来搜索方向的最佳前沿。系统构建包含BEV记忆(追踪已探区域、未探前沿及轨迹历史)与自我中心视觉语义记忆的空间-视觉候选空间。训练VLM策略时采用“意图对齐目标函数”确保探索一致性。关键工程突破在于该候选级导航接口具备强泛化能力,无需对VLM进行额外微调,即可直接零样本部署于轮式、四足及人形三种不同形态的机器人本体。
关键看点
- 意图标注机制:提出Frontier-based Human-Intent Labeling,前瞻分析人类演示以标记解释未来搜索方向的最佳前沿,将低层动作转化为高层搜索意图监督信号。
- 双重记忆架构:构建空间-视觉候选空间,利用BEV记忆跟踪探索状态与轨迹历史,结合自我中心视觉记忆提供语义线索,为VLM决策提供接地候选集。
- 零样本跨形态迁移:候选级导航接口解耦了策略与本体控制,无需微调VLM即可直接迁移至轮式、四足和人形机器人,验证了具身导航策略的通用性。
- 基准测试SOTA:在MP3D、HM3D-v1及HM3D-v2 ObjectNav基准上刷新纪录,取得所有对比方法中的最高成功率,证明类人模仿学习在长程搜索任务中的优势。
工程与产业观察
IntentNav证明了通过结构化记忆与意图对齐训练,VLM可从人类演示中提取通用导航原语。其零样本跨形态迁移能力降低了具身算法适配成本,为异构机器人复用同一套高层认知策略提供了可行范式,对解决开放世界长程探索具有显著工程参考价值。
英文摘要 (Abstract)
Object navigation requires a robot to search for an unobserved target in an unknown environment by deciding where to explore next under partial observability. Effective search resembles human-like exploration: selectively probing visually promising frontiers while relying on spatial memory to avoid redundant revisits. We propose IntentNav, a spatial-visual imitation framework that learns human-like ObjectNav policies from human demonstrations. To infer high-level search intent from low-level human actions, we introduce Frontier-based Human-Intent Labeling, which looks ahead in human demonstrations and labels the frontier that best explains the demonstrator's future search direction. We construct a spatial-visual candidate space, where BEV memory tracks explored regions, unexplored frontiers, and trajectory history, while egocentric visual memory provides semantic cues for each candidate. A VLM policy is trained to select among these grounded candidates, using Intent-Aligned Objective to encourage consistent and human-like exploration. IntentNav achieves state-of-the-art performance among learning-based methods on the MP3D, HM3D-v1, and HM3D-v2 ObjectNav benchmarks, attaining the best success rate among all compared methods. The proposed candidate-level navigation interface transfers zero-shot to wheeled, quadruped, and humanoid robots without further VLM fine-tuning. \href{https://wmn7.github.io/IntentNav/}{Project page}.
作者:Yuxin Cai, Zongtai Li, Maonan Wang, Muyi Bao, Haokun Zhu, Ruofei Bai, Ding Zhao, Zirui Li, Wenshan Wang, Wei-Yun Yau, Ji Zhang, Chen Lv
来源
本页事实对应的公开页面,以原文为准。