... Robotic grasping 3D object detection Grasp detection Collision detection In recent years, robotic grasping technology has played an increasingly significant role in industrial production. However, reliably and accurately calculating the grasping pose remains a challenge in this field. Most...

... the accessibility of grasping poses so that various grasps are required to ensure that the collision-free motion trajectory can be planned. Traditional robotic grasping needs to solve two sub-problems: perception and planning. Perception is to estimation the pose of the target object, which requires a known target...

.../methodology/approach In this paper, a cascaded convolutional neural network (CNN) method for robotic grasping based on monocular vision and small data set of scattered parts is proposed. This method can be divided into three steps: object detection, monocular depth estimation and keypoint estimation...

...-world robotic grasping of unknown objects. Findings The ablation study of the pyramid pooling module shows that the multi-scale information fusion significantly improves the model performance. The regression approach outperforms the classification approach based on same feature embedding framework...