Using Manipulation Primitives for Object Sorting in Cluttered Environments

This paper explores the idea of manipulation-aided perception and grasping in the context of sorting small objects on a cluttered tabletop. We present a robust pipeline that combines perception and manipulation to accurately sort objects by some property (e.g., color, size, shape, etc.). The pipeline uses two motion primitives to manipulate the scene in ways that help the robot to improve its perception and grasps. This results in the ability to sort cluttered object piles accurately. We also present an implementation on the PR2 robot that applies our algorithm to sort Duplo bricks by color and size, and compare our method to brick sorting without the aid of manipulation. The experimental results demonstrate the benefits of our approach, particularly in environments with a high degree of clutter. Note to Practitioners-Autonomous robots perceive the world using sensors and then typically use the perceived data to manipulate or physically interact with the world, thus changing its state. One of the challenges of making robots useful in households and everyday life is to make them capable of understanding their surroundings well. However, home and office environments are usually unstructured and cluttered. This introduces errors in perception and can lead to manipulation failures. This paper explores the idea that manipulation of the world to enable efficient perception can in turn improve performance on the overall manipulation task. This suggests a paradigm shift in the way robots interact with their environments. Traditionally, most of the objects in the environment are considered obstacles and any contact with them is considered a collision. We present an algorithm that uses simple actions to manipulate a cluttered scene to improve the robot's perceptual, (and hence) grasping and sorting abilities. Our encouraging results demonstrate substantial improvement on sorting tasks by inserting manipulation aids into the task operation. We believe that deliberate manipulation of unstructured environments by robots would be crucial to their introduction into our homes.