Object Structure from Manipulation via Particle Filter and Robot-based Active Learning
This addresses the challenge of automating object modeling for robotic manipulation, which is incremental as it builds on existing interactive segmentation methods.
The paper tackles the problem of learning object models for robotic manipulation by developing an interactive object segmentation method based on particle filter and active learning, which allows a robot to manipulate and learn object structures automatically. The result shows that this approach enables more accurate object modeling and reveals richer object structural information compared to established methods.
To learn object models for robotic manipulation, unsupervised methods cannot provide accurate object structural information and supervised methods require a large amount of manually labeled training samples, thus interactive object segmentation is developed to automate object modeling. In this article, we formulate a novel dynamic process for interactive object segmentation, and develop a solution based on particle filter and active learning so that a robot can manipulate and learn object structures incrementally and automatically. We demonstrate our method with a humanoidrobot on different types of objects, and compare its segmentation performancewith established methods on selected objects. The result shows that our approach allows more accurate object modeling and reveals richer object structural information.