OmniNav: Robust Long-Horizon Target Navigation in Dynamic Environments

📄 arXiv: 2609.08159v1 📥 PDF

作者: Yujie Tang, Meiling Wang, Jinhao Jiang, Sibo Zuo, Yinan Deng, Xinyu Zhang, Yufeng Yue

分类: cs.RO

发布日期: 2026-09-08

备注: 20 pages, Project page: https://omni-nav.github.io/

🔗 代码/项目: PROJECT_PAGE


💡 一句话要点

提出OmniNav以解决动态环境中的长距离目标导航问题

🎯 匹配领域: 支柱一:机器人控制 (Robot Control)

关键词: 长距离导航 动态环境 机器人导航 贝叶斯推理 场景记忆 目标信念 交互可行性

📋 核心要点

  1. 现有方法在动态环境中难以保持有效的场景记忆和目标信念,导致导航失败。
  2. OmniNav通过持续推理耦合场景有效性、目标信念和交互可行性,构建可更新的3D场景记忆。
  3. 在ObjectNav和实例导航基准测试中,OmniNav的成功率最高,实际应用中的成功率从53.3%提升至71.7%。

📝 摘要(中文)

长距离目标导航要求机器人在不断变化的观察、决策和物理交互中持续执行任务。这需要三种相互关联的能力:维护有效的场景记忆、在部分可观测性下修正目标信念以及选择可交互的导航终点。为了解决这些挑战,本文提出了OmniNav,将长距离导航表述为对耦合场景有效性、目标信念和交互可行性的任务状态后验的持续推理。OmniNav通过增量构建可更新的3D物体场景记忆来防止过时的场景证据影响后续决策,并引入基于证据的贝叶斯信念修正机制来更新目标信念。实验表明,OmniNav在多个基准测试中表现优异,成功率显著提高。

🔬 方法详解

问题定义:本文旨在解决动态环境中长距离目标导航的挑战,现有方法在场景记忆、目标信念和交互可行性方面存在不足,导致导航效果不佳。

核心思路:OmniNav通过将长距离导航视为对耦合状态的持续推理,设计了一个增量更新的3D场景记忆系统,以应对动态变化带来的不确定性。

技术框架:OmniNav的整体架构包括三个主要模块:场景记忆模块、信念修正模块和导航选择模块。场景记忆模块负责实时更新3D场景,信念修正模块利用贝叶斯推理更新目标信念,导航选择模块则基于交互可行性选择导航终点。

关键创新:OmniNav的创新在于其引入了基于证据的贝叶斯信念修正机制和层次化闭环恢复策略,显著提高了动态环境中的导航成功率。

关键设计:在设计中,OmniNav采用了依赖性感知的区域先验,结合负证据更新信念,并在导航终点选择中考虑了操作可达性和碰撞约束。具体的损失函数和网络结构细节在论文中详细描述。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

在多个基准测试中,OmniNav的成功率超过了其他对比方法,特别是在语义ObjectNav和细粒度实例导航中表现突出,成功率从53.3%提升至71.7%,显示出其在实际应用中的显著优势。

🎯 应用场景

OmniNav的研究成果在机器人导航、自动化仓储、智能家居等领域具有广泛的应用潜力。通过提高机器人在动态环境中的导航能力,能够显著提升自动化系统的效率和可靠性,推动智能机器人技术的进一步发展。

📄 摘要(原文)

Long-horizon target navigation requires a robot to sustain task execution across evolving observations, decisions, and physical interactions. This requires three coupled capabilities: maintaining valid scene memory, revising target beliefs under partial observability, and selecting interaction-feasible navigation endpoints. However, the state underlying each capability is only conditionally valid: scene representations become stale when objects move or disappear, unsuccessful searches alter beliefs over target locations, and geometrically convenient endpoints may still be infeasible for manipulation. To address these challenges, we present OmniNav, which formulates long-horizon navigation as continual inference over a factorized task state posterior coupling scene validity, target belief, and interaction feasibility. For representation, OmniNav incrementally constructs an updatable 3D object scene memory, preventing stale scene evidence from propagating to subsequent decisions. For exploration, it introduces an evidence-aware Bayesian belief-revision mechanism that derives dependency-aware region priors from semantic context, incorporates unsuccessful searches as negative evidence, and updates them for posterior-guided frontier selection. For interaction, OmniNav incorporates manipulation reachability and collision constraints into navigation-endpoint selection and propagates execution feedback through hierarchical closed-loop recovery. Extensive experiments demonstrate that OmniNav achieves the highest success rates among the compared methods on semantic ObjectNav and fine-grained instance navigation benchmarks, remains robust to target relocation, and improves real-world pick-and-place success from 53.3% to 71.7% over an adapted open-loop baseline. The project page of OmniNav is available at https://omni-nav.github.io/.