MLP-SLAM: Multilayer Perceptron-Based Simultaneous Localization and Mapping

TL;DR

This paper introduces MLP-SLAM, a real-time stereo SLAM system using multilayer perceptrons to classify dynamic/static features, improving outdoor localization accuracy and speed, supported by a new large dataset.

Contribution

The paper presents a novel MLP-based SLAM system that effectively distinguishes dynamic from static features and provides a new dataset for evaluation.

Findings

Achieved superior dynamic/static feature classification performance.

Attained highest average precision on KITTI datasets.

Demonstrated faster processing speed compared to existing methods.

Abstract

The Visual Simultaneous Localization and Mapping (V-SLAM) system has seen significant development in recent years, demonstrating high precision in environments with limited dynamic objects. However, their performance significantly deteriorates when deployed in settings with a higher presence of movable objects, such as environments with pedestrians, cars, and buses, which are common in outdoor scenes. To address this issue, we propose a Multilayer Perceptron (MLP)-based real-time stereo SLAM system that leverages complete geometry information to avoid information loss. Moreover, there is currently no publicly available dataset for directly evaluating the effectiveness of dynamic and static feature classification methods, and to bridge this gap, we have created a publicly available dataset containing over 50,000 feature points. Experimental results demonstrate that our MLP-based dynamic and static feature point discriminator has achieved superior performance compared to other methods on this dataset. Furthermore, the MLP-based real-time stereo SLAM system has shown the highest average precision and fastest speed on the outdoor KITTI tracking datasets compared to other dynamic SLAM systems.The open-source code and datasets are available at https://github.com/TaozheLi/MLP-SLAM.