Scholarlink

Robotic systems may navigate unexpected locations without prior knowledge. Robots that need position data need SLAM. This work introduces 2.5D mapping, which combines 2D mapping with more information, to overcome 3D mapping’s information restrictions. 2.5D mapping requires Intel RealSense D435 RGBD frames. Hitmaps are made from frame items of interest. Hitmap is updated using robot self-position and individuals’ mainly error-free center positions. Our robot estimates its position using visual odometry and an inertial measurement unit. Hitmaps are 3D dot maps of self-placements and interest. A 3D map turns 2.5D in two steps. Make a 2D map. A feature vector array with rich information is then created for each map point. Rasterize the 2D map to make a 3D model. 2.5D mapping uses feature vectors and two-dimensional maps. A 2.5D map guides robot mergers. Through the map, people may observe their surroundings. Reducing 3D pictures to 2.5D reduces visual information. Humans get the integrated map. Human operators create 3D maps from 2.5D maps. We created valuable components and significant results for design viability.

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

Robot-to-Robot Collaborative Knowledge Sharing with Human Operators Under Constraint Resources Through Connotative 2.5D Mapping

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Nafiul Alam,
  • M. I. R. Shuvo,
  • Jong-Hoon Kim

摘要

Robotic systems may navigate unexpected locations without prior knowledge. Robots that need position data need SLAM. This work introduces 2.5D mapping, which combines 2D mapping with more information, to overcome 3D mapping’s information restrictions. 2.5D mapping requires Intel RealSense D435 RGBD frames. Hitmaps are made from frame items of interest. Hitmap is updated using robot self-position and individuals’ mainly error-free center positions. Our robot estimates its position using visual odometry and an inertial measurement unit. Hitmaps are 3D dot maps of self-placements and interest. A 3D map turns 2.5D in two steps. Make a 2D map. A feature vector array with rich information is then created for each map point. Rasterize the 2D map to make a 3D model. 2.5D mapping uses feature vectors and two-dimensional maps. A 2.5D map guides robot mergers. Through the map, people may observe their surroundings. Reducing 3D pictures to 2.5D reduces visual information. Humans get the integrated map. Human operators create 3D maps from 2.5D maps. We created valuable components and significant results for design viability.