Details

Autor(en) / Beteiligte

• Tang, Qirong
• Zhong, Lou
• Zhou, Zheng
• Zhu, Wenfeng
• Chu, Zhugang
• Shi, Yuhui
• Tan, Ying

Titel

Primitive Shape Recognition Based on Local Point Cloud for Object Grasp

Ist Teil von

• Advances in Swarm Intelligence, p.85-91

Ort / Verlag

Cham: Springer International Publishing

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• Object recognition and grasping are important means of interaction between robot and environment, and also two of the main tasks of robot. Due to the rich information provided by depth sensors, it has paved the way for the object recognition. The geometric information is more conducive to the primitive recognition of the object, and the primitive shape information is used as the input information for the robot to grasp. This study proposes a primitive shape recognition method using local point cloud. First, 900 sets of point cloud data including three primitive shapes was created. Then the PointNet network using the point cloud data to recognize the primitive shape of the objects was trained. Experiments in simulation and physical world shows our recognition method can effectively recognize the primitive shape of the object.