Vision-based robotic gras** from object localization, object pose estimation to grasp estimation for parallel grippers: a review

G Du, K Wang, S Lian, K Zhao - Artificial Intelligence Review, 2021 - Springer
This paper presents a comprehensive survey on vision-based robotic gras**. We
conclude three key tasks during vision-based robotic gras**, which are object localization …

An Overview of Deep Neural Networks for Few-Shot Learning

J Zhao, L Kong, J Lv - Big Data Mining and Analytics, 2024 - ieeexplore.ieee.org
Recent advancements in deep learning have led to significant breakthroughs across various
fields. However, these methods often require extensive labeled data for optimal …

Unseen object few-shot semantic segmentation for robotic gras**

X Liu, Y Zhang, D Shan - IEEE Robotics and Automation …, 2022 - ieeexplore.ieee.org
Semantic segmentation is a popular technology enabling robots to perceive and interact
with the environment sufficiently. However, unseen objects in the new environment make it …

Generative robotic gras** using depthwise separable convolution

Y Teng, P Gao - Computers & Electrical Engineering, 2021 - Elsevier
In this paper, we present an end-to-end approach method using deep learning for grasp
detection. Our method is a real-time processing method for discrete depth image sampling …

Annotation Cost Reduction of Stream-based Active Learning by Automated Weak Labeling using a Robot Arm

K Suzuki, T Sunagawa, T Sasaki… - 2021 IEEE/RSJ …, 2021 - ieeexplore.ieee.org
Stream-based active learning (AL) is an efficient training data collection method, and it is
used to reduce human annotation cost required in machine learning. However, it is difficult …