Active tactile object exploration with Gaussian processes

Accurate object shape knowledge provides important information for performing stable grasping and dexterous manipulation. When modeling an object using tactile sensors, touching the object surface at a fixed grid of points can be sample inefficient. In this paper, we present an active touch strategy to efficiently reduce the surface geometry uncertainty by leveraging a probabilistic representation of object surface. In particular, we model the object surface using a Gaussian process and use the associated uncertainty information to efficiently determine the next point to explore. We validate the resulting method for tactile object surface modeling using a real robot to reconstruct multiple, complex object surfaces.

Authors

• Zhengkun Yi
• Roberto Calandra
• Filipe Veiga
• Herke van Hoof
• Tucker Hermans
• Yilei Zhang
• Jan Peters 0001

Keywords

• Surface reconstruction
• Surface treatment
• Robot sensing systems
• Surface impedance
• Shape
• Gaussian processes
• Gaussian Process
• Tactile Object
• Active Tactile Exploration
• Grid Points
• Active Strategies
• Surface Model
• Tactile Sensor
• Object Surface
• Surface Representation
• Surface Geometry
• Real Robot
• Active Touch
• Point Cloud
• Random Points
• Robotic Arm
• Exploration Process
• End-effector
• Covariance Function
• Acquisition Function
• Gaussian Process Model
• Toy Example
• Point Cloud Registration
• Bayesian Optimization
• Steel Container
• True Function
• Robotic Hand
• Robot Navigation
• Maximum A Posteriori