الملخص
تمت ترجمة أجزاء من هذه الصفحة آلياً وقد تحتوي على أخطاء.
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/].
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Chen, Y., Che, L., Huang, Z., Fu, W., Wang, C., Cao, X., Liu, D., Yang, Y., Su, J., & Guo, L. Z. (2026). HarnessVLN: توحيد الملاحة المجسّدة بلا تدريب عبر حزام وكيل. https://omanscience.com/ar/articles/harnessvln-unifying-training-free-embodied-navigation-through-an-agent-harness
MLA 9
Chen, Yang, et al. "HarnessVLN: توحيد الملاحة المجسّدة بلا تدريب عبر حزام وكيل." https://omanscience.com/ar/articles/harnessvln-unifying-training-free-embodied-navigation-through-an-agent-harness.
شيكاغو (المؤلف–التاريخ)
Chen, Yang, Lirong Che, Zhenyu Huang, Wenbo Fu, Chuang Wang, Xu Cao, Daqi Liu, Yuzhe Yang, Jian Su, and Lan-Zhe Guo. 2026. "HarnessVLN: توحيد الملاحة المجسّدة بلا تدريب عبر حزام وكيل." https://omanscience.com/ar/articles/harnessvln-unifying-training-free-embodied-navigation-through-an-agent-harness.
هارفارد
Chen, Y., Che, L., Huang, Z., Fu, W., Wang, C., Cao, X., Liu, D., Yang, Y., Su, J. and Guo, L. Z. (2026) 'HarnessVLN: توحيد الملاحة المجسّدة بلا تدريب عبر حزام وكيل', Available at: https://omanscience.com/ar/articles/harnessvln-unifying-training-free-embodied-navigation-through-an-agent-harness.
فانكوفر
Chen Y, Che L, Huang Z, Fu W, Wang C, Cao X, et al. HarnessVLN: توحيد الملاحة المجسّدة بلا تدريب عبر حزام وكيل. https://omanscience.com/ar/articles/harnessvln-unifying-training-free-embodied-navigation-through-an-agent-harness
IEEE
Y. Chen, L. Che, Z. Huang, W. Fu, C. Wang, X. Cao, D. Liu, Y. Yang, J. Su, and L. Z. Guo, "HarnessVLN: توحيد الملاحة المجسّدة بلا تدريب عبر حزام وكيل," https://omanscience.com/ar/articles/harnessvln-unifying-training-free-embodied-navigation-through-an-agent-harness.