Active Perception for Ambiguous Objects Classification
This addresses the challenge of object classification in real-world robotics where objects have ambiguous features, though it appears incremental as it builds on existing pose estimation methods.
The paper tackles the problem of classifying ambiguous objects that cannot be reliably identified from a single view by proposing a framework that selects optimal next viewpoints to resolve ambiguities, validated with a robot and household objects.
Recent visual pose estimation and tracking solutions provide notable results on popular datasets such as T-LESS and YCB. However, in the real world, we can find ambiguous objects that do not allow exact classification and detection from a single view. In this work, we propose a framework that, given a single view of an object, provides the coordinates of a next viewpoint to discriminate the object against similar ones, if any, and eliminates ambiguities. We also describe a complete pipeline from a real object's scans to the viewpoint selection and classification. We validate our approach with a Franka Emika Panda robot and common household objects featured with ambiguities. We released the source code to reproduce our experiments.