GAN-SLAM: Real-Time GAN Aided Floor Plan Creation Through SLAM

2025-04-28

AI Summary

In dynamic indoor environments, conventional 2D SLAM produces noisy and structurally incomplete occupancy grid maps (OGMs), leading to failure in automated floorplan generation. To address this, we propose the first real-time joint mapping framework integrating generative adversarial networks (GANs) with 2D SLAM. Our method innovatively transfers high-precision pose estimation from 3D LiDAR odometry into the 2D SLAM pipeline and introduces a lightweight online GAN module that performs end-to-end noise suppression and geometric structure completion on occupancy grids. The framework operates in real time and is validated across multiple complex indoor scenes. Experimental results demonstrate significant improvements in map fidelity and structural completeness; floorplan generation error is reduced by over 60%. This work establishes a novel paradigm for high-quality, fully automated floorplan construction.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

SLAM is a fundamental component of modern autonomous systems, providing robots and their operators with a deeper understanding of their environment. SLAM systems often encounter challenges due to the dynamic nature of robotic motion, leading to inaccuracies in mapping quality, particularly in 2D representations such as Occupancy Grid Maps. These errors can significantly degrade map quality, hindering the effectiveness of specific downstream tasks such as floor plan creation. To address this challenge, we introduce our novel 'GAN-SLAM', a new SLAM approach that leverages Generative Adversarial Networks to clean and complete occupancy grids during the SLAM process, reducing the impact of noise and inaccuracies introduced on the output map. We adapt and integrate accurate pose estimation techniques typically used for 3D SLAM into a 2D form. This enables the quality improvement 3D LiDAR-odometry has seen in recent years to be effective for 2D representations. Our results demonstrate substantial improvements in map fidelity and quality, with minimal noise and errors, affirming the effectiveness of GAN-SLAM for real-world mapping applications within large-scale complex environments. We validate our approach on real-world data operating in real-time, and on famous examples of 2D maps. The improved quality of the output map enables new downstream tasks, such as floor plan drafting, further enhancing the capabilities of autonomous systems. Our novel approach to SLAM offers a significant step forward in the field, improving the usability for SLAM in mapping-based tasks, and offers insight into the usage of GANs for OGM error correction.

Problem

• Improving 2D SLAM mapping accuracy using GANs
• Reducing noise and errors in occupancy grid maps
• Enhancing floor plan creation for autonomous systems

Innovation

• Uses GANs to clean occupancy grids
• Adapts 3D pose estimation for 2D
• Improves map fidelity with minimal noise