FeCCM for scene understanding: Helping the robot to learn multiple tasks

Abstract

Helping a robot to understand a scene can include many sub-tasks, such as scene categorization, object detection, geometric labeling, etc. Each sub-task is notoriously hard, and state-of-art classifiers exist for many sub-tasks. It is desirable to have an algorithm that can capture such correlation without requiring to make any changes to the inner workings of any classifier, and therefore make the perception for a robot better. We have recently proposed a generic model (Feedback Enabled Cascaded Classification Model) that enables us to easily take state-of-art classifiers as black-boxes and improve performance. In this video, we show that we can use our FeCCM model to quickly combine existing classifiers for various sub-tasks, and build a shoe finder robot in a day. The video shows our robot using FeCCM to find a shoe on request.