Contact State Segmentation Using Particle Filters for Programming by Human Demonstration in Compliant Motion Tasks

Abstract

This paper presents a contribution to programming by human demonstration, in the context of compliant motion task specification for sensor-controlled robot systems that physically interact with the environment. One wants to learn about the geometric parameters of the task and segment the total motion executed by the human into subtasks for the robot that can each be executed with simple compliant motion task specifications. The motion of the human demonstration tool is sensed with a 3D camera, and the interaction with the environment is sensed with a force sensor in the human demonstration tool. Both measurements are uncertain, and do not give direct information about the geometric parameters of the contacting surfaces, or about the contact formations encountered during the human demonstration. The paper uses a Bayesian Sequential Monte Carlo method (also known as a particle filter) to do the simultaneous estimation of the contact formation (discrete information) and the geometric parameters (continuous information). The simultaneous contact formation segmentation and the geometric parameter estimation are helped by the availability of a contact state graph of all possible contact formations. The presented approach applies to all compliant motion tasks involving polyhedral objects with a known geometry, where the uncertain geometric parameters are the poses of the objects. The approach has been verified in real world experiments, in which it is able to discriminate in realtime between 245 different contact formations of the contact state graph.