2.5D Image based Robotic Grasping
This work addresses robotic grasping for automation applications, presenting an incremental improvement by fusing depth and RGB data in a neural network.
The paper tackles robotic grasping using depth and RGB images by designing an encoder-decoder neural network for real-time grasp prediction, achieving competitive performance with state-of-the-art methods in grasp success, real-time operation, and model size.
We consider the problem of robotic grasping using depth + RGB information sampling from a real sensor. we design an encoder-decoder neural network to predict grasp policy in real time. This method can fuse the advantage of depth image and RGB image at the same time and is robust for grasp and observation height.We evaluate our method in a physical robotic system and propose an open-loop algorithm to realize robotic grasp operation. We analyze the result of experiment from multi-perspective and the result shows that our method is competitive with the state-of-the-art in grasp performance, real-time and model size. The video is available in https://youtu.be/Wxw_r5a8qV0