HS-SLAM: A Fast and Hybrid Strategy-Based SLAM Approach for Low-Speed Autonomous Driving

TL;DR

HS-SLAM is a hybrid SLAM method that combines direct and feature-based techniques to achieve fast, accurate localization for low-speed autonomous vehicles, reducing computation while maintaining high performance.

Contribution

The paper introduces HS-SLAM, a novel hybrid framework that enhances SLAM speed and accuracy by integrating IMU-based tracking with multi-layer direct refinement and selective descriptor bypassing.

Findings

HS-SLAM outperforms ORB-SLAM3 in localization accuracy.

HS-SLAM increases tracking efficiency by 15%.

The approach effectively balances speed and precision in low-speed scenarios.

Abstract

Visual-inertial simultaneous localization and mapping (SLAM) is a key module of robotics and low-speed autonomous vehicles, which is usually limited by the high computation burden for practical applications. To this end, an innovative strategy-based hybrid framework HS-SLAM is proposed to integrate the advantages of direct and feature-based methods for fast computation without decreasing the performance. It first estimates the relative positions of consecutive frames using IMU pose estimation within the tracking thread. Then, it refines these estimates through a multi-layer direct method, which progressively corrects the relative pose from coarse to fine, ultimately achieving accurate corner-based feature matching. This approach serves as an alternative to the conventional constant-velocity tracking model. By selectively bypassing descriptor extraction for non-critical frames, HS-SLAM significantly improves the tracking speed. Experimental evaluations on the EuRoC MAV dataset demonstrate that HS-SLAM achieves higher localization accuracies than ORB-SLAM3 while improving the average tracking efficiency by 15%.