Transformation&Translation Occupancy Grid Mapping: 2-Dimensional Deep Learning Refined SLAM

2025-04-28

AI Summary

To address the significant noise, structural distortion, and low-quality floorplan generation in occupancy grid maps (OGMs) caused by odometry drift and pose estimation errors in 2D LiDAR SLAM within large, complex environments, this paper proposes a novel OGM paradigm integrating geometric transformation modeling with translation-invariance constraints. It pioneers the adaptation of robust 3D SLAM pose estimation principles to the 2D domain and introduces a deep reinforcement learning–based synthetic data generation strategy to support end-to-end GAN training for joint correction of SLAM errors. The method achieves real-time, high-accuracy mapping in real-world campus environments, markedly improving map clarity and geometric fidelity. Extensive evaluation across diverse large-scale, complex scenes demonstrates superior generalizability: the proposed approach consistently outperforms state-of-the-art 2D SLAM methods in map quality, localization accuracy, and system robustness.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Search and Optimization: Learning to Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

SLAM (Simultaneous Localisation and Mapping) is a crucial component for robotic systems, providing a map of an environment, the current location and previous trajectory of a robot. While 3D LiDAR SLAM has received notable improvements in recent years, 2D SLAM lags behind. Gradual drifts in odometry and pose estimation inaccuracies hinder modern 2D LiDAR-odometry algorithms in large complex environments. Dynamic robotic motion coupled with inherent estimation based SLAM processes introduce noise and errors, degrading map quality. Occupancy Grid Mapping (OGM) produces results that are often noisy and unclear. This is due to the fact that evidence based mapping represents maps according to uncertain observations. This is why OGMs are so popular in exploration or navigation tasks. However, this also limits OGMs' effectiveness for specific mapping based tasks such as floor plan creation in complex scenes. To address this, we propose our novel Transformation and Translation Occupancy Grid Mapping (TT-OGM). We adapt and enable accurate and robust pose estimation techniques from 3D SLAM to the world of 2D and mitigate errors to improve map quality using Generative Adversarial Networks (GANs). We introduce a novel data generation method via deep reinforcement learning (DRL) to build datasets large enough for training a GAN for SLAM error correction. We demonstrate our SLAM in real-time on data collected at Loughborough University. We also prove its generalisability on a variety of large complex environments on a collection of large scale well-known 2D occupancy maps. Our novel approach enables the creation of high quality OGMs in complex scenes, far surpassing the capabilities of current SLAM algorithms in terms of quality, accuracy and reliability.

Problem

• Improving 2D SLAM accuracy in large complex environments
• Reducing noise and errors in Occupancy Grid Mapping
• Enhancing map quality for complex scene tasks

Innovation

• Adapt 3D SLAM pose estimation to 2D
• Use GANs for SLAM error correction
• Generate datasets via deep reinforcement learning