SuperNav：面向任意场景任意任务的智能体导航系统

AI 摘要

浙江大学团队提出 SuperNav，一种面向通用服务机器人的智能体导航系统，让预训练多模态大模型无需导航专项微调即可处理任意场景中的任意任务。该系统通过导航技能、面向智能体的物理交互工具以及任务进度与上下文管理，将运动执行委托给导航工具，并用统一视觉点接口连接决策与运动。实验显示其在实例级、多目标和需求驱动任务上优于四个基线，并在 HM3D 类别级评估和真实四足机器人上完成部署验证。

正文节选

SuperNav: An Agentic Navigation System for Any Task in Any Scene Abstract General-purpose service robots need navigation systems that can handle diverse human requests in unfamiliar environments, combining task generality with scene generality. Some existing methods fine-tune multimodal large language models (MLLMs) to predict navigation actions, making their behavior dependent on the coverage of navigation training data and potentially limiting generalization to new requests and environments. O

发布时间：—

抓取时间：2026-10-09 11:00

来源机构：Hugging Face