Improving robot manipulation through fingertip perception

Better sensing is crucial to improve robotic grasping and manipulation. Most robots currently have very limited perception in their manipulators, typically only fingertip position and velocity. Additional sensors make richer interactions with the objects possible. In this paper, we present a versatile, robust and low cost sensor for robot fingertips, that can improve robotic grasping and manipulation in several ways: 3D reconstruction of the shape of objects, material surface classification, and object slip detection. We extended TUM-Rosie, our robot for mobile manipulation, with fingertip sensors on its humanoid robotic hand, and show the advantages of the fingertip sensor integrated in our robot system.

Authors

• Alexis Maldonado
• Humberto Alvarez
• Michael Beetz

Keywords

• Robot sensing systems
• Shape
• Grasping
• Sensor systems
• Optical sensors
• 3D Reconstruction
• Object Shape
• Robotic Hand
• Mobile Manipulator
• Intensity Values
• Points In Space
• Point Cloud
• Convex Hull
• Surface Texture
• Depth Camera
• 3D Shape
• Tactile Sensor
• Support Vector Machine Algorithm
• Object Surface
• Gray Level Co-occurrence Matrix
• Point Cloud Data
• Computer Mouse
• Classification Experiments
• Shape Estimation
• RGB-D Sensor
• Point Cloud Segmentation
• Robotic Gripper
• 3D Gaussian
• Shutter Speed
• Texture Of Objects
• Sensor Locations
• Learning Algorithms
• Object Motion
• Object Parts