Object mapping, recognition, and localization from tactile geometry

We present a method for performing object recognition using multiple images acquired from a tactile sensor. The method relies on using the tactile sensor as an imaging device, and builds an object representation based on mosaics of tactile measurements. We then describe an algorithm that is able to recognize an object using a small number of tactile sensor readings. Our approach makes extensive use of sequential state estimation techniques from the mobile robotics literature, whereby we view the object recognition problem as one of estimating a consistent location within a set of object maps. We examine and test approaches based on both traditional particle filtering and histogram filtering. We demonstrate both the mapping and recognition / localization techniques on a set of raised letter shapes using real tactile sensor data.

Authors

• Zachary A. Pezzementi
• Caitlin Reyda
• Gregory D. Hager

Keywords

• Histograms
• Robot sensing systems
• Atmospheric measurements
• Particle measurements
• Robot kinematics
• Object Recognition
• Object Location
• Map Objects
• Particle Filter
• Tactile Sensor
• Sensor Readings
• Sequential Estimation
• Time Step
• Measurement Model
• State Space
• Sensory Systems
• Continuous State
• Radians
• Sensor Response
• Point Spread Function
• Elastography
• Grid Resolution
• Mode Of Distribution
• Rotational Symmetry
• Object Identification
• Object Pose
• Force Resolution
• Occupancy Grid
• Measurement Update
• Histogram Bins
• Unknown Objects
• Object In Frame
• Localization Performance
• Spatial Resolution