Enhancing Door-Status Detection for Autonomous Mobile Robots during Environment-Specific Operational Use

TL;DR

This paper presents a deep learning-based door-status detection system tailored for autonomous mobile robots, improving accuracy by leveraging environment-specific data and fine-tuning, with validated results in simulation and real-world settings.

Contribution

It introduces a novel dataset creation method and a fine-tuning approach to enhance door-status detection tailored for long-term robot operation in specific environments.

Findings

Effective door-status detection in simulation and real-world

Fine-tuning improves model performance in specific environments

Trade-offs between fine-tuning costs and benefits

Abstract

Door-status detection, namely recognizing the presence of a door and its status (open or closed), can induce a remarkable impact on a mobile robot's navigation performance, especially for dynamic settings where doors can enable or disable passages, changing the topology of the map. In this work, we address the problem of building a door-status detector module for a mobile robot operating in the same environment for a long time, thus observing the same set of doors from different points of view. First, we show how to improve the mainstream approach based on object detection by considering the constrained perception setup typical of a mobile robot. Hence, we devise a method to build a dataset of images taken from a robot's perspective and we exploit it to obtain a door-status detector based on deep learning. We then leverage the typical working conditions of a robot to qualify the model for boosting its performance in the working environment via fine-tuning with additional data. Our experimental analysis shows the effectiveness of this method with results obtained both in simulation and in the real-world, that also highlight a trade-off between costs and benefits of the fine-tuning approach.