日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

把持arXiv:2003.09644

PointNet++把持:疎な点群からのエンドツーエンド空間把持生成

PointNet++ Grasping: Learning An End-to-end Spatial Grasp Generation Algorithm from Sparse Point Clouds

シェア:XThreadsFacebookLINEはてブBluesky

疎な点群を入力に、把持の姿勢・カテゴリ・スコアをサンプリングなしで直接予測するエンドツーエンド手法を提案し、単一物体・多物体データセットで高い成功率を達成した。

著者: Peiyuan Ni, Wenguang Zhang, Xiaoxiao Zhu, Qixin Cao

分類: cs.RO

原文アブストラクト

Grasping for novel objects is important for robot manipulation in unstructured environments. Most of current works require a grasp sampling process to obtain grasp candidates, combined with local feature extractor using deep learning. This pipeline is time-costly, expecially when grasp points are sparse such as at the edge of a bowl. In this paper, we propose an end-to-end approach to directly predict the poses, categories and scores (qualities) of all the grasps. It takes the whole sparse point clouds as the input and requires no sampling or search process. Moreover, to generate training data of multi-object scene, we propose a fast multi-object grasp detection algorithm based on Ferrari Canny metrics. A single-object dataset (79 objects from YCB object set, 23.7k grasps) and a multi-object dataset (20k point clouds with annotations and masks) are generated. A PointNet++ based network combined with multi-mask loss is introduced to deal with different training points. The whole weight size of our network is only about 11.6M, which takes about 102ms for a whole prediction process using a GeForce 840M GPU. Our experiment shows our work get 71.43% success rate and 91.60% completion rate, which performs better than current state-of-art works.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  4. 4GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  5. 5Google DeepMind、ロボット向けAIを発表新製品・発表

PR・アフィリエイト広告

FRONTIER(GPU搭載BTOパソコン)

FRONTIER(GPU搭載BTOパソコン)の公式広告バナーFRONTIERでGPU搭載PCを見る ↗
PR本紙発行元 EmplifAI