OmniNav：动态环境中的鲁棒长时程目标导航
OmniNav: Robust Long-Horizon Target Navigation in Dynamic Environments
浏览论文内容
中文总结 AI 辅助
OmniNav通过因子化任务状态后验持续推断，结合可更新3D场景记忆、证据感知贝叶斯信念修正和交互约束终点选择，实现动态环境下的鲁棒长时程目标导航，显著提升成功率。
中文摘要 AI 辅助
长时程目标导航要求机器人在不断变化的观测、决策和物理交互中持续执行任务。这需要三种耦合的能力：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。然而，每种能力所依赖的状态仅条件性有效：当物体移动或消失时，场景表示变得过时；不成功的搜索会改变对目标位置的信念；几何上便利的终点可能仍不适合操作。为应对这些挑战，我们提出了OmniNav，它将长时程导航形式化为对因子化任务状态后验的持续推断，该后验耦合了场景有效性、目标信念和交互可行性。在表示方面，OmniNav增量构建可更新的3D物体场景记忆，防止过时的场景证据传播到后续决策。在探索方面，它引入了一种基于证据的贝叶斯信念修正机制，从语义上下文推导依赖感知的区域先验，将不成功的搜索作为负面证据纳入，并更新它们以进行后验引导的前沿选择。在交互方面，OmniNav将操作可达性和碰撞约束纳入导航终点选择，并通过分层闭环恢复传播执行反馈。大量实验表明，OmniNav在语义ObjectNav和细粒度实例导航基准上取得了比较方法中最高的成功率，对目标重定位保持鲁棒，并在真实世界拾取-放置任务中，相比适应的开环基线，将成功率从53.3%提升至71.7%。OmniNav的项目页面可在https://这个URL获取。
英文摘要
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/.
发表机构
- School of Automation, Beijing Institute of Technology（北京理工大学自动化学院）
机构由 AI 辅助整理，请以论文原文为准。
