In this paper we define criteria for industry-oriented DRL, and perform a thorough comparison according to these criteria of one family of learning approaches, DRL from demonstration, against a professional industrial integrator on the recently established NIST assembly benchmark.
Similar to computer vision problems, such as object detection, Action Image builds on the idea that object features are invariant to translation in image space.
The majority of previous work has focused on developing grasp methods that generalize over novel object geometry but are specific to a certain robot hand.
Connector insertion and many other tasks commonly found in modern manufacturing settings involve complex contact dynamics and friction.
In this work, we investigate how to improve the accuracy of domain randomization based pose estimation.
In this paper, we study how we can solve difficult control problems in the real world by decomposing them into a part that is solved efficiently by conventional feedback control methods, and the residual which is solved with RL.