Towards Generalization and Data Efficient Learning of Deep Robotic Grasping
This addresses data efficiency and generalization issues in robotic grasping for practical applications, representing an incremental improvement over existing methods.
The paper tackles the problem of data inefficiency in deep reinforcement learning for robotic grasping by separating visual perception and control policy training, resulting in a system that demonstrates impressive robustness and generalization across various grasping tasks without requiring further training when transferred to real robots.
Deep reinforcement learning (DRL) has been proven to be a powerful paradigm for learning complex control policy autonomously. Numerous recent applications of DRL in robotic grasping have successfully trained DRL robotic agents end-to-end, mapping visual inputs into control instructions directly, but the amount of training data required may hinder these applications in practice. In this paper, we propose a DRL based robotic visual grasping framework, in which visual perception and control policy are trained separately rather than end-to-end. The visual perception produces physical descriptions of grasped objects and the policy takes use of them to decide optimal actions based on DRL. Benefiting from the explicit representation of objects, the policy is expected to be endowed with more generalization power over new objects and environments. In addition, the policy can be trained in simulation and transferred in real robotic system without any further training. We evaluate our framework in a real world robotic system on a number of robotic grasping tasks, such as semantic grasping, clustered object grasping, moving object grasping. The results show impressive robustness and generalization of our system.