A Hierarchical Approach to Active Pose Estimation

TL;DR

This paper introduces a hierarchical method for active pose estimation that combines quick image-based rough localization with detailed point cloud analysis, improving efficiency in robotic object search tasks.

Contribution

The paper presents a novel hierarchical approach that integrates RGB image analysis with point cloud data for more efficient active pose estimation in robotics.

Findings

Image feature processing accelerates search and pose estimation.

Hierarchical approach improves computational efficiency.

Method effectively handles occlusions in object localization.

Abstract

Creating mobile robots which are able to find and manipulate objects in large environments is an active topic of research. These robots not only need to be capable of searching for specific objects but also to estimate their poses often relying on environment observations, which is even more difficult in the presence of occlusions. Therefore, to tackle this problem we propose a simple hierarchical approach to estimate the pose of a desired object. An Active Visual Search module operating with RGB images first obtains a rough estimation of the object 2D pose, followed by a more computationally expensive Active Pose Estimation module using point cloud data. We empirically show that processing image features to obtain a richer observation speeds up the search and pose estimation computations, in comparison to a binary decision that indicates whether the object is or not in the current image.