Skip to main content

and
  1. No Access

    Article

    A Graph-Based Deep Reinforcement Learning Approach to Gras** Fully Occluded Objects

    Gras** in cluttered scenes is an important issue in robotic manipulation. The cooperation of gras** and pushing actions based on reinforcement learning is an effective means to obtain the target object whe...

    Guoyu Zuo, Jiayuan Tong, Zihao Wang, Daoxiong Gong in Cognitive Computation (2023)

  2. No Access

    Article

    SOAR Improved Artificial Neural Network for Multistep Decision-making Tasks

    Recently, artificial neural networks (ANNs) have been applied to various robot-related research areas due to their powerful spatial feature abstraction and temporal information prediction abilities. Decision-m...

    Guoyu Zuo, Tingting Pan, Tielin Zhang, Yang Yang in Cognitive Computation (2021)