Clearing a pile of unknown objects using interactive perception

We address the problem of clearing a pile of unknown objects using an autonomous interactive perception approach. Our robot hypothesizes the boundaries of objects in a pile of unknown objects (object segmentation) and verifies its hypotheses (object detection) using deliberate interactions. To guarantee the safety of the robot and the environment, we use compliant motion primitives for poking and grasping. Every verified segmentation hypothesis can be used to parameterize a compliant controller for manipulation or grasping. The robot alternates between poking actions to verify its segmentation and grasping actions to remove objects from the pile. We demonstrate our method with a robotic manipulator. We evaluate our approach with real-world experiments of clearing cluttered scenes composed of unknown objects.

Authors

• Dov Katz
• Moslem Kazemi
• J. Andrew Bagnell
• Anthony Stentz

Keywords

• Grasping
• Motion segmentation
• Image color analysis
• Image segmentation
• Object detection
• Reliability
• Interactive
• Unknown Objects
• Pile Of Objects
• Object Segmentation
• Robot Manipulator
• Compliance Control
• Center Of Mass
• Multiple Aspects
• Point Cloud
• Segmentation Algorithm
• Path Planning
• Change Of Perspective
• Self-supervised Learning
• 3D Motion
• Contiguous Regions
• Unstructured Environments
• Rigid Body Transformation
• Surface Normals
• Scene Segmentation
• Average Color
• RGB-D Sensor
• SIFT Features
• Reliable Interaction
• Color Histogram
• Arbitrary Configuration
• Partial Obstruction
• Object Recognition