FAST-LIVO2 on Resource-Constrained Platforms: LiDAR-Inertial-Visual Odometry with Efficient Memory and Computation

2025-01-23

AI Summary

To address the trade-off between real-time performance and accuracy in multi-sensor fusion localization under resource-constrained edge devices, this paper proposes a lightweight LiDAR-inertial-visual odometry (LIVO) system. Methodologically: (i) a degradation-aware adaptive visual keyframe selection mechanism reduces computational redundancy; (ii) a memory-efficient mapping architecture jointly leverages a local unified visual–LiDAR map and a long-term visual-only map; (iii) an error-state iterated Kalman filter (ESIKF) is employed with serialized updates and hybrid multi-modal map management, alongside ARM/x86 cross-platform optimization. Evaluated on the Hilti dataset, the system achieves a 33% reduction in per-frame latency and a 47% decrease in memory footprint, while incurring only a marginal 3 cm increase in RMSE—outperforming FAST-LIO2 and state-of-the-art LIVO systems.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Security and Privacy: Large-scale security measurements

Abstract

This paper presents a lightweight LiDAR-inertial-visual odometry system optimized for resource-constrained platforms. It integrates a degeneration-aware adaptive visual frame selector into error-state iterated Kalman filter (ESIKF) with sequential updates, improving computation efficiency significantly while maintaining a similar level of robustness. Additionally, a memory-efficient mapping structure combining a locally unified visual-LiDAR map and a long-term visual map achieves a good trade-off between performance and memory usage. Extensive experiments on x86 and ARM platforms demonstrate the system's robustness and efficiency. On the Hilti dataset, our system achieves a 33% reduction in per-frame runtime and 47% lower memory usage compared to FAST-LIVO2, with only a 3 cm increase in RMSE. Despite this slight accuracy trade-off, our system remains competitive, outperforming state-of-the-art (SOTA) LIO methods such as FAST-LIO2 and most existing LIVO systems. These results validate the system's capability for scalable deployment on resource-constrained edge computing platforms.

Problem

• Efficient Localization
• Resource-constrained Devices
• Multi-sensor Fusion

Innovation

• Optimized Localization Technique
• Efficient Filtering
• Innovative Mapping Storage