Sim-Grasp: Learning 6-DOF Grasp Policies for Cluttered Environments Using a Synthetic Benchmark

被引：0
|
作者：
Li, Juncheng [1 ,2 ]
Cappelleri, David J. [1 ,2 ]
机构：
[1] Purdue Univ, Sch Mech Engn, Multiscale Robot & Automat Lab, W Lafayette, IN 47906 USA
[2] Purdue Univ, Weldon Sch Biomed Engn By Courtesy, W Lafayette, IN 47906 USA
来源：
IEEE ROBOTICS AND AUTOMATION LETTERS | 2024年 / 9卷 / 09期
关键词：
Point cloud compression; Grasping; Benchmark testing; 6-DOF; Robot learning; Object recognition; Clutter; mobile manipulation; deep learning in grasping and manipulation; data sets for robot learning;
D O I：
10.1109/LRA.2024.3430712
中图分类号：
TP24 [机器人技术];
学科分类号：
080202 ; 1405 ;
摘要：
In this letter, we present Sim-Grasp, a robust 6-DOF two-finger grasping system that integrates advanced language models for enhanced object manipulation in cluttered environments. We introduce the Sim-Grasp-Dataset, which includes 1,550 objects across 500 scenarios with 7.9 million annotated labels, and develop Sim-GraspNet to generate grasp poses from point clouds. The Sim-Grasp-Polices achieve grasping success rates of 97.14% for single objects and 87.43% and 83.33% for mixed clutter scenarios of Levels 1-2 and Levels 3-4 objects, respectively. By incorporating language models for target identification through text and box prompts, Sim-Grasp enables both object-agnostic and target picking, pushing the boundaries of intelligent robotic systems.
引用
收藏
页码：7645 / 7652
页数：8
相关论文
共 50 条
  • [41] Deep Learning Based 6-DoF Antipodal Grasp Planning From Point Cloud in Random Bin-Picking Task Using Single-View
    Bui, Tat Hieu
    Son, Yeong Gwang
    Moon, Seung Jae
    Nguyen, Quang Huy
    Rhee, Issac
    Hong, Ju Yong
    Choi, Hyouk Ryeol
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2023, 8 (08) : 5196 - 5203
  • [42] A model-free 6-DOF grasp detection method based on point clouds of local sphere area
    Sun, Jingkang
    Zhang, Keqin
    Yang, Genke
    Chu, Jian
    ADVANCED ROBOTICS, 2023, 37 (11) : 679 - 690
  • [43] FastGNet: an efficient 6-DOF grasp detection method with multi-attention mechanisms and point transformer network
    Ding, Zichao
    Wang, Aimin
    Gao, Maosen
    Li, Jiazhe
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2024, 35 (04)
  • [44] GraspFast: Multi-stage lightweight 6-DoF grasp pose fast detection with RGB-D image
    Gui, Haiyuan
    Pang, Shanchen
    He, Xiao
    Wang, Luqi
    Zhai, Xue
    Yu, Shihang
    Zhang, Kuijie
    PATTERN RECOGNITION, 2025, 161
  • [45] Keypoint-GraspNet: Keypoint-based 6-DoF Grasp Generation from the Monocular RGB-D input
    Chen, Yiye
    Lin, Yunzhi
    Xu, Ruinian
    Vela, Patricio A.
    2023 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2023), 2023, : 7988 - 7995
  • [46] Object 6-DoF pose estimation using auxiliary learning
    Chen M.
    Gai S.
    Da F.
    Yu J.
    Guangxue Jingmi Gongcheng/Optics and Precision Engineering, 2024, 32 (06): : 901 - 914
  • [47] KGNv2: Separating Scale and Pose Prediction for Keypoint-based 6-DoF Grasp Synthesis on RGB-D input
    Chen, Yiye
    Xu, Ruinian
    Lin, Yunzhi
    Chen, Hongyi
    Vela, Patricio A.
    2023 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, IROS, 2023, : 2971 - 2978
  • [48] A Fast Avatar Calibration Method for Virtual Environments Using Six 6-DOF Trackers
    Kilimann, J.
    Friesen, J.
    Pott, C.
    Lensing, P.
    2018 IEEE 1ST WORKSHOP ON ANIMATION IN VIRTUAL AND AUGMENTED ENVIRONMENTS (ANIVAE), 2018,
  • [49] Deep Learning-Based 6-DoF Object Pose Estimation Considering Synthetic Dataset
    Zheng, Tianyu
    Zhang, Chunyan
    Zhang, Shengwen
    Wang, Yanyan
    SENSORS, 2023, 23 (24)
  • [50] 6-DoF Pose Estimation for Axisymmetric Objects Using Deep Learning with Uncertainty
    Hashimoto, Shintaro
    Hirano, Daichi
    Ishihama, Naoki
    2020 IEEE AEROSPACE CONFERENCE (AEROCONF 2020), 2020,
12345