In this research project, we aim to investigate computer vision methods for perception and deep understanding of the scene to enable AI empowered general purpose flexible and adaptable robotic systems for dexterous manipulation of objects so that grasping robots can easily adapt to complex and unknown objects in rapidly changing, dynamic and unpredictable real-world environments. Specifically, given a scene observed by a robot, we aim to develop a general purpose “all-in-one” computer vision model for various tasks in scene understanding, e.g.,  detecting the objects of interest, segmenting their instances, estimating their pose, performing their tracking and further predicting one or more grasp locations for the latter stage robotic effective grasping.