LISN: 基于VLM控制器的指令引导社交导航
LISN: Language-Instructed Social Navigation with VLM-based Controller Modulating
AI总结：
LISN通过VLM控制器实现指令引导的社交导航，提出首个标准化基准并提升动态避障能力。
摘要：
在人机共存的背景下，具有社会意识的导航对于移动机器人至关重要。然而，现有研究主要集中在路径效率和行人碰撞避免上，这些是必要的，但只代表社交导航的一小部分。除此之外，机器人还必须遵循用户的指令，使行动与人类表达的任务目标和社会规范一致。在本工作中，我们提出了LISN-Bench，首个基于模拟的指令引导社交导航基准。基于Rosnav-Arena 3.0，它是首个标准化的社会导航基准，集成了指令遵循和场景理解，适用于多样化的情境。为解决这一任务，我们进一步提出了Social-Nav-Modulator，一种快慢分层系统，其中VLM代理调节成本图和控制器参数。将低层动作生成与较慢的VLM循环解耦，减少了对高频VLM推理的依赖，同时提高了动态避障和感知适应性。我们的方法实现了91.3%的平均成功率，比最有力的基线高出63%，其中大多数改进体现在挑战性任务中，如在人群中共行和严格避免指令禁止区域的导航。项目网站为：https://social-nav.github.io/LISN-project/
英文摘要：
Towards human-robot coexistence, socially aware navigation is significant for mobile robots. Yet existing studies on this area focus mainly on path efficiency and pedestrian collision avoidance, which are essential but represent only a fraction of social navigation. Beyond these basics, robots must also comply with user instructions, aligning their actions to task goals and social norms expressed by humans. In this work, we present LISN-Bench, the first simulation-based benchmark for language-instructed social navigation. Built on Rosnav-Arena 3.0, it is the first standardized social navigation benchmark to incorporate instruction following and scene understanding across diverse contexts. To address this task, we further propose Social-Nav-Modulator, a fast-slow hierarchical system where a VLM agent modulates costmaps and controller parameters. Decoupling low-level action generation from the slower VLM loop reduces reliance on high-frequency VLM inference while improving dynamic avoidance and perception adaptability. Our method achieves an average success rate of 91.3%, which is greater than 63% than the most competitive baseline, with most of the improvements observed in challenging tasks such as following a person in a crowd and navigating while strictly avoiding instruction-forbidden regions. The project website is at: https://social-nav.github.io/LISN-project/
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
