Robot Localization in Floor Plans Using a Room Layout Edge Extraction Network
This addresses the problem of reducing expert labor and sensor dependency for service robot deployment, though it is incremental as it builds on existing localization techniques with a new method for edge extraction.
The paper tackles robot indoor localization by proposing a monocular camera-based system that estimates robot pose from architectural floor plans, using a convolutional neural network to extract room layout edges and a particle filter for matching, and demonstrates robustness and accuracy in real-world experiments.
Indoor localization is one of the crucial enablers for deployment of service robots. Although several successful techniques for indoor localization have been proposed, the majority of them relies on maps generated from data gathered with the same sensor modality used for localization. Typically, tedious labor by experts is needed to acquire this data, thus limiting the readiness of the system as well as its ease of installation for inexperienced operators. In this paper, we propose a memory and computationally efficient monocular camera-based localization system that allows a robot to estimate its pose given an architectural floor plan. Our method employs a convolutional neural network to predict room layout edges from a single camera image and estimates the robot pose using a particle filter that matches the extracted edges to the given floor plan. We evaluate our localization system using multiple real-world experiments and demonstrate that it has the robustness and accuracy required for reliable indoor navigation.