Robotic Grasping and Manipulation Competition @IROS2016: Team Tsinghua

This chapter describes the preparation and implementation of the Robotic Grasping and Manipulation Competition @IROS 2016. Our Tsinghua Team participated in both the hand-in-hand and fully-autonomous tracks. The structure of a novel designed gripper and an algorithm for object detection and grasp pose estimation are described. The competition results demonstrates the effectiveness of the strategies used in the competition.

[1]  Kate Saenko,et al.  High precision grasp pose detection in dense clutter , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[2]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[3]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[4]  Tully Foote,et al.  tf: The transform library , 2013, 2013 IEEE Conference on Technologies for Practical Robot Applications (TePRA).

[5]  Hong Liu,et al.  DLR-Hand II: next generation of a dextrous robot hand , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[6]  Gregory P. Starr,et al.  Modeling and control of the stanford/JPL hand , 1987, Proceedings. 1987 IEEE International Conference on Robotics and Automation.

[7]  Pietro Perona,et al.  Microsoft COCO: Common Objects in Context , 2014, ECCV.

[8]  Fuchun Sun,et al.  HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).