Kinematics modeling and trajectory planning for NAO robot object grasping based on image analysis

Chang, Faliang; Jiang, Yuhan; Liang, Fuxin

doi:10.1109/cac.2017.8243179

Cited by 1 publication

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the robot needs to solve the following problems in grasping objects: object recognition, pose calculation, grab gesture generation, and motion planning. Jiang et al 10 have proposed a grasping method based on image analysis, but using this method can only recognize simple objects through the color features of the object, and cannot recognize multiple objects in robot vision. At present, the literature contains many examples of acquiring the spatial position of the object to be grasped, [3][4][5] multicategory object grasping, 6,7 and visual servo grasping system.…”

Section: Introductionmentioning

confidence: 99%

“…Judith Müller et al 9 have proposed a method of grasping a mug based on stereo vision and object shape features, but the method relies on external stereo vision, and the robot can only recognize one object. Jiang et al 10 have proposed a grasping method based on image analysis, but using this method can only recognize simple objects through the color features of the object, and cannot recognize multiple objects in robot vision. Eppe et al 11 have proposed an end-to-end robotic grabbing method that integrates visuomotor neural network and faster region-based convolutional neural network (R-CNN).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi‐target detection and grasping control for humanoid robot NAO

Zhang

Yang

et al. 2019

Adaptive Control & Signal

View full text Add to dashboard Cite

Graspirng objects is an important capability for humanoid robots. Due to complexity of environmental and diversity of objects, it is difficult for the robot to accurately recognize and grasp multiple objects. In response to this problem, we propose a robotic grasping method that uses the deep learning method You Only Look Once v3 for multi-target detection and the auxiliary signs to obtain target location. The method can control the movement of the robot and plan the grasping trajectory based on visual feedback information. It is verified by experiments that this method can make the humanoid robot NAO grasp the object effectively, and the success rate of grasping can reach 80% in the experimental environment.

show abstract