SPAQ-DL-SLAM: Towards Optimizing Deep Learning-based SLAM for Resource-Constrained Embedded Platforms

TL;DR

This paper introduces SPAQ-DL-SLAM, a framework that applies structured pruning and quantization to optimize deep learning-based SLAM algorithms for resource-limited embedded platforms, achieving significant efficiency gains and improved accuracy.

Contribution

The paper presents a novel framework, SPAQ-DL-SLAM, that enhances DL-SLAM models with structured pruning and quantization, improving efficiency and accuracy for embedded systems.

Findings

Achieved 18.9% reduction in FLOPs and 79.8% model size reduction.

Surpassed original DROID-SLAM by 10.5% on ATE metric.

Demonstrated improved generalization on ETH3D benchmark.

Abstract

Optimizing Deep Learning-based Simultaneous Localization and Mapping (DL-SLAM) algorithms is essential for efficient implementation on resource-constrained embedded platforms, enabling real-time on-board computation in autonomous mobile robots. This paper presents SPAQ-DL-SLAM, a framework that strategically applies Structured Pruning and Quantization (SPAQ) to the architecture of one of the state-ofthe-art DL-SLAM algorithms, DROID-SLAM, for resource and energy-efficiency. Specifically, we perform structured pruning with fine-tuning based on layer-wise sensitivity analysis followed by 8-bit post-training static quantization (PTQ) on the deep learning modules within DROID-SLAM. Our SPAQ-DROIDSLAM model, optimized version of DROID-SLAM model using our SPAQ-DL-SLAM framework with 20% structured pruning and 8-bit PTQ, achieves an 18.9% reduction in FLOPs and a 79.8% reduction in overall model size compared to the DROID-SLAM model. Our evaluations on the TUM-RGBD benchmark shows that SPAQ-DROID-SLAM model surpasses the DROID-SLAM model by an average of 10.5% on absolute trajectory error (ATE) metric. Additionally, our results on the ETH3D SLAM training benchmark demonstrate enhanced generalization capabilities of the SPAQ-DROID-SLAM model, seen by a higher Area Under the Curve (AUC) score and success in 2 additional data sequences compared to the DROIDSLAM model. Despite these improvements, the model exhibits performance variance on the distinct Vicon Room sequences from the EuRoC dataset, which are captured at high angular velocities. This varying performance at some distinct scenarios suggests that designing DL-SLAM algorithms taking operating environments and tasks in consideration can achieve optimal performance and resource efficiency for deployment in resource-constrained embedded platforms.