信息与控制2025，Vol.54Issue(3)：372-389,18.DOI:10.13976/j.cnki.xk.2024.1731
基于视觉的机器人端到端策略抓取估计综述
Review of Vision-based Robot End-to-end Strategic Grasping Estimation
苏康 1李嘉良 1李俊国 2张馨文 3刘闯1
作者信息
- 1. 石家庄铁道大学机械工程学院,河北石家庄 050043
- 2. 华北理工大学,河北唐山 063210
- 3. 汇通建设集团股份有限公司,河北保定 074000
- 折叠
摘要
Abstract
The rapid development and continuing breakthroughs in artificial intelligence technology have greatly improved the grasping capabilities of intelligent robots.Grasp estimation is critical for robots to perform grasping tasks,which directly affects subsequent grasping planning and control systems.Unlike traditional approaches requiring step-by-step target localization and pose estimation,end-to-end grasping strategies directly learn and output grasping information from input data.We review vision-based end-to-end strategic grasping estimation methods,covering planar-level and spatial-level grasping methods.Planar-level grasping methods are categorized into estima-ting grasping contact points and estimating oriented rectangles.Spatial-level grasping methods are also divided into two categories:object-oriented and scene-oriented approaches.In addition,we introduce relevant datasets and grasping evaluation metrics and highlights the challenges and future directions in vision-based end-to-end grasping estimation for robots.关键词
抓取估计/端到端/平面级抓取/空间级抓取Key words
grasp estimation/end-to-end/planar-level grasping/spatial-level grasping分类
信息技术与安全科学引用本文复制引用
苏康,李嘉良,李俊国,张馨文,刘闯..基于视觉的机器人端到端策略抓取估计综述[J].信息与控制,2025,54(3):372-389,18.
