logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Approaching for manipulation: Robot termination pose generation via active object detection and task-oriented logical reasoning

delete2026-03-03
delete0
PRE
AI
Y
Yuhao Wang
田国会 cover
田国会 (Guohui Tian) *
X
Xuyang Shao
DOI：10.1016/j.eswa.2026.131929delete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
• A novel framework for robots to approach objects. • The framework integrates reinforcement learning with logical reasoning. • Spatial attention and a new reward function improve model performance. • A viewpoint adjustment method for manipulation based on D-S theory. • Using large multimodal models to fine-tune viewpoint positions.
Keywords:
reinforcement learning
logical reasoning
spatial attention
viewpoint adjustment
manipulation

Journal

Expert Systems with Applications cover
Expert Systems with Applications
IF:
7.5
Papers:
2.9W
Citations:
10.2W

Organization

No organization information available