Visual Room-Awareness for Humanoid Robot Self-Localization

TL;DR

This paper introduces a visual room-awareness module for humanoid robots that enhances self-localization accuracy by matching visual backgrounds with color histograms, especially in symmetric environments, using a particle-filter based approach.

Contribution

The proposed module improves self-localization by integrating visual background matching with confidence-based hypothesis generation, inspired by psychological experiments.

Findings

Significant improvement in self-localization accuracy demonstrated

Effective in symmetric environments with ambiguous initial poses

Works with both simulated and real humanoid robots

Abstract

Humanoid robots without internal sensors such as a compass tend to lose their orientation after a fall. Furthermore, re-initialisation is often ambiguous due to symmetric man-made environments. The room-awareness module proposed here is inspired by the results of psychological experiments and improves existing self-localization strategies by mapping and matching the visual background with colour histograms. The matching algorithm uses a particle-filter to generate hypotheses of the viewing directions independent of the self-localization algorithm and generates confidence values for various possible poses. The robot's behaviour controller uses those confidence values to control self-localization algorithm to converge to the most likely pose and prevents the algorithm from getting stuck in local minima. Experiments with a symmetric Standard Platform League RoboCup playing field with a simulated and a real humanoid NAO robot show the significant improvement of the system.