Literature Survey about Volumetric Grasping Network: Real-time 6 DOF Grasp Detection in Clutter

摘要

在通用机器人研究领域中，grasp detection 任务要求能够在一堆凌乱的物体中识别从未遇到过的物体以及处理物体之间的堆叠问题。作者针对此项任务提出了Volumetric Grasping Network(VGN)，以3D场景的Truncated Signed Distance Function(TSDF)表示作为输入，并能够对3D场景中的每一个体积元直接输出机器人抓取质量预测值，以及钩爪方向和张开宽度。这种方法能够在10ms内规划下一次抓取任务并且可以在现实世界凌乱物体中清除92%的物体。

本栏目推荐文章
• Center-based 3D Object Detection and Tracking
• Early lameness detection in dairy cattle based on wearable gait analysis using semi-supervised LSTM-Autoencoder
• Learning Dynamic Query Combinations for Transformer-based Object** Detection and Segmentation论文阅读笔记
• TensorFlow Object Detection API —— 开箱即用的目标检测API
• Sw-YoloX An anchor-free detector based transformer for sea surface object detection
• Relation Networks for Object Detection
• Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network
• PIDNet: A Real-time Semantic Segmentation Network Inspired by PID Controllers
• UIU-Net: U-Net in U-Net for Infrared Small Object Detection：Unet中的Unet
• Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images

Literature Volumetric Detection Real-time Graspingliterature volumetric detection real-time detection real-time holmes论文 grasping volumetric literature manipulation literature dexterous learning cloudscapes体积volumetric实时 multivocal literature review论文 积云volumetric cesiumjs高度 literature template reading survey