Perception and motion planning for pick-and-place of dynamic objects

Mobile manipulators have brought a new level of flexibility to traditional automation tasks such as tabletop manipulation, but are not yet capable of the same speed and reliability as industrial automation. We present approaches to 3D perception and manipulator motion planning that enable a general purpose robotic platform to recognize and manipulate a variety of objects at a rate of one pick-and-place operation every 6.7 s, and work with a conveyor belt carrying objects at a speed of 33^cm/s.

I. INTRODUCTION

Robotics researchers regularly endow robot platforms with new capabilities that increase the breadth of potential applications and push the boundaries of autonomy. In contrast, industrial automation is driven by a pragmatism dictated by the need to optimize throughput and reliability. The hope of both is that, as multi-purpose robotic platforms become more capable, they will be able to take over an increasing fraction of the tasks currently handled by application specific, fixed installation automation, thereby granting all applications greater levels of modularity and adaptability.