HarnessVLN：通过智能体控制器统一免训练具身导航
HarnessVLN: Unifying Training-Free Embodied Navigation through an Agent Harness
- Nanjing University（南京大学）
- AGIBOT
- Tsinghua University（清华大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出免训练框架HarnessVLN，通过智能体控制器统一协调感知、导航与恢复，在多个基准上超越先前免训练最先进结果，并支持人形机器人部署。
AI中文摘要：
具身导航要求智能体解释视觉观察、积累空间知识并执行动作以遵循指令或定位物体。基于训练的方法面临泛化挑战，而免训练方法利用多模态大语言模型（MLLM），但往往缺乏将提议的动作与空间证据、任务进度和执行失败相协调的机制。我们提出了HarnessVLN，一个零样本、免训练的框架，其智能体控制器通过统一的工具接口协调感知、检索、定位、导航、恢复和终止。控制器根据空间证据、几何可行性和子目标一致性验证规划器的提议，并将结构化工具反馈纳入后续决策。分层事件记忆跟踪任务进度和执行历史，而持久化的时空图维护可复用的空间证据和失败注释，用于验证和恢复。可替换的导航执行器将验证后的目标转换为可执行的运动，使相同的控制器协议能够支持指令跟随和物体目标导航。HarnessVLN在R2R、RxR、HM3D-v2和HM3D-OVON上分别实现了60.8%、53.9%、76.0%和59.3%的成功率，超越了先前的免训练最先进结果。人形机器人部署进一步证明了其在真实环境中对两种任务的适用性。项目页面为：this https URL。
英文摘要：
Embodied navigation requires agents to ground instructions or object goals in spatial observations and translate plans into successful execution. As multimodal large language models (MLLMs) become increasingly capable, they offer stronger support for navigation without task-specific training; however, improved semantic reasoning alone does not ensure that proposed actions remain consistent with spatial evidence, task progress, and execution outcomes. We introduce HarnessVLN, a zero-shot, training-free framework that unifies instruction-following and object-goal navigation through a shared Agent Harness. The Harness coordinates perception, memory, and execution tools through a unified interface, validating planner proposals for evidential support, geometric feasibility, and subgoal consistency before dispatch. It jointly manages hierarchical event memory and a persistent Spatiotemporal Graph to track task progress, preserve spatial evidence, and contextualize failures. Structured execution feedback updates this shared state, guiding subsequent planning, recovery, and termination. Across R2R, RxR, HM3D-v2, and HM3D-OVON, HarnessVLN achieves success rates of 59.6%, 51.4%, 76.0%, and 59.3%, respectively, outperforming prior training-free methods. Humanoid robot deployment further demonstrates its applicability to both navigation tasks in real-world environments. The project page is available at [https://agibot-harnessvln.netlify.app/].
