Interactive Learning of Physical Object Properties Through Robot Manipulation and Database of Object Measurements
This work addresses the challenge of digitizing physical object properties for robotics applications, though it is incremental as it builds on existing methods for exploratory manipulation and Bayesian inference.
The paper tackles the problem of automatically extracting physical object properties like material, mass, volume, and stiffness through robot manipulation, using a Bayesian network and exploratory actions to maximize learning, with experiments showing effective action selection and intelligent handling of trick objects.
This work presents a framework for automatically extracting physical object properties, such as material composition, mass, volume, and stiffness, through robot manipulation and a database of object measurements. The framework involves exploratory action selection to maximize learning about objects on a table. A Bayesian network models conditional dependencies between object properties, incorporating prior probability distributions and uncertainty associated with measurement actions. The algorithm selects optimal exploratory actions based on expected information gain and updates object properties through Bayesian inference. Experimental evaluation demonstrates effective action selection compared to a baseline and correct termination of the experiments if there is nothing more to be learned. The algorithm proved to behave intelligently when presented with trick objects with material properties in conflict with their appearance. The robot pipeline integrates with a logging module and an online database of objects, containing over 24,000 measurements of 63 objects with different grippers. All code and data are publicly available, facilitating automatic digitization of objects and their physical properties through exploratory manipulations.