Implicit Shape Model Trees: Recognition of 3-D Indoor Scenes and Prediction of Object Poses for Mobile Robots

TL;DR

This paper introduces Implicit Shape Model (ISM) trees, a hierarchical approach enabling mobile robots to recognize 3-D indoor scenes and predict object poses efficiently by combining scene recognition and object search.

Contribution

The paper presents ISM trees for joint scene recognition and object pose prediction, along with algorithms for their generation and efficient search, advancing robotic scene understanding.

Findings

ISM trees improve scene recognition accuracy

New algorithms enable efficient object search and pose prediction

Physical experiments demonstrate practical effectiveness

Abstract

We present an approach for mobile robots to recognize scenes in object arrangements distributed across cluttered environments. Recognition is enabled by intertwining the robot's search for objects and the assignment of found objects to scenes. Our scene model called "Implicit Shape Model (ISM) trees" allows these two tasks to be solved jointly. This article presents novel algorithms for ISM trees to recognize scenes and predict poses of searched objects. We define scenes as object sets in which some objects are connected via 3-D spatial relations. In previous work, we recognized scenes with single ISMs. However, single ISMs are prone to false positives. As a remedy, we have developed ISM trees, a hierarchical model consisting of multiple ISMs. This article contributes a recognition algorithm that now enables the use of ISM trees for scene recognition. ISM trees should be ideally generated from human demonstrations of object arrangements. As a suitable algorithm was not available, we introduce such a generation algorithm. In line with the active vision paradigm, we combined scene recognition and object search in previous work. However, an efficient algorithm was lacking to make this combination effective. Physical experiments show that this is now overcome with a new algorithm achieving efficient combination through predicted object poses.