GGCNN

• Learning an object agnostic function to grasp objects
• Grasping using uni-modal data (depth image).
• Generate pixel-wise grasp configuration for the given input.
• The Gripper approaches the target object in top-down manner. Uses a shallow network, and an eye-in-hand camera configuration.
• 
• Morrison, Douglas, Peter Corke, and Jürgen Leitner. “Closing the loop for robotic grasping: A real-time, generative grasp synthesis approach.” RSS (2018).