CATEGORIZATION OF OBJECTS TO BE GRASPED BASED ON THE RECS CONCEPT AND GRASPING TASK USING 3D MODEL MATCHING

Read full text Summarise with VIRAT
Authors: Naoya Mukai, Yasuki Tanaka, Tomokazu TAKAHASHI, Masato Suzuki, Kazuyo TSUZUKI, Yasushi Mae, Seiji Aoyagi
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This paper presents a practical grasping method for domestic robots based on the RECS (Robot Environment Compromise System) concept. The method classifies and registers the shapes and dimensions of household objects. A depth camera captures RGB images and point cloud data, while a YOLO-based deep learning model detects objects and estimates their positions. Subsequently, 3D model matching identifies each object's posture, enabling grasping at optimal registered points. The system is implemented on a mobile robot equipped with a dual-arm manipulator. Experimental results demonstrate the robot's ability to effectively grasp various household items, highlights its potential for real-world home and office robotic applications.

Fields of Study & Subjects

Robot Manipulation and Learning 3D Shape Modeling and Analysis Advanced Neural Network Applications

Publication details

Journal / source
Institutional Repositories DataBase (IRDB)
Volume
68
Pages
13–25
Publication date
16 March 2026
Language
EN