Scholarlink

<p>Navigating obstacles and understanding complex environments remain critical challenges in the deployment of automated guided vehicles (AGVs), a key area in mobile robotics. Existing AGVs often struggle with inadequate recognition of specific objects, such as plastic bags and feces, which may cause issues such as roller entanglements or contamination. Furthermore, vision-language navigation discrepancies can lead to positioning errors. In this paper, we propose a deep learning-based solution (called “<i>RoboNavGuard</i>”) specifically designed to address these issues and improve the practical deployment of AGVs. The proposed <i>RoboNavGuard</i> method builds on the PyraBiNet++ architecture for precise obstacle segmentation. The <i>RoboNavGuard</i> is composed of the following three key innovations: (a) a novel architecture that fuses local and global features for obstacle segmentation, (b) a practical and comprehensive dataset, termed “<i>FragCloud3DRef++</i>”, which establishes a new benchmark for 3D visual grounding and supports training lightweight grounding models for AGV deployment, and (c) a method that tightly integrates textual commands into AGVs’ visual perception, thereby enabling more natural and efficient human-robot interaction. The dataset “<i>FragCloud3DRef++</i>” is also used to train a lightweight 3D visual grounding model, “<i>Re_3DVG-Small</i>”, designed to enhance fragmented point cloud understanding and improve language–vision navigation. Our system is being deployed in live AGV operations to validate its real-world applicability. The code source and dataset are open at <a href="https://github.com/zehantan6970/RoboNavGuard">https://github.com/zehantan6970/RoboNavGuard</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Robonavguard: lightweight deformable obstacle segmentation and 3D visual grounding for indoor robot navigation

  • 期刊论文

  • 发表日期：

    2026年5月15日

查看全文
  • Zehan Tan,
  • Yaoyang Wu,
  • Henghua Shen

摘要

Navigating obstacles and understanding complex environments remain critical challenges in the deployment of automated guided vehicles (AGVs), a key area in mobile robotics. Existing AGVs often struggle with inadequate recognition of specific objects, such as plastic bags and feces, which may cause issues such as roller entanglements or contamination. Furthermore, vision-language navigation discrepancies can lead to positioning errors. In this paper, we propose a deep learning-based solution (called “RoboNavGuard”) specifically designed to address these issues and improve the practical deployment of AGVs. The proposed RoboNavGuard method builds on the PyraBiNet++ architecture for precise obstacle segmentation. The RoboNavGuard is composed of the following three key innovations: (a) a novel architecture that fuses local and global features for obstacle segmentation, (b) a practical and comprehensive dataset, termed “FragCloud3DRef++”, which establishes a new benchmark for 3D visual grounding and supports training lightweight grounding models for AGV deployment, and (c) a method that tightly integrates textual commands into AGVs’ visual perception, thereby enabling more natural and efficient human-robot interaction. The dataset “FragCloud3DRef++” is also used to train a lightweight 3D visual grounding model, “Re_3DVG-Small”, designed to enhance fragmented point cloud understanding and improve language–vision navigation. Our system is being deployed in live AGV operations to validate its real-world applicability. The code source and dataset are open at https://github.com/zehantan6970/RoboNavGuard.