An Integrated Simulator and Dataset that Combines Grasping and Vision for Deep Learning
This addresses the data scarcity problem for researchers in robotics and AI working on dexterous grasping, though it is incremental as it builds on existing simulation approaches.
The authors tackled the challenge of insufficient data for applying deep learning to robotic grasping by developing a simulator to collect cylindrical precision grasps for a multi-fingered dexterous hand, enabling structured data acquisition for this task.
Deep learning is an established framework for learning hierarchical data representations. While compute power is in abundance, one of the main challenges in applying this framework to robotic grasping has been obtaining the amount of data needed to learn these representations, and structuring the data to the task at hand. Among contemporary approaches in the literature, we highlight key properties that have encouraged the use of deep learning techniques, and in this paper, detail our experience in developing a simulator for collecting cylindrical precision grasps of a multi-fingered dexterous robotic hand.