通过结构化剪枝与量化，让SLAM模型在嵌入式设备上更省资源、更高效。
SPAQ-DL-SLAM: Towards Optimizing Deep Learning-based SLAM for Resource-Constrained Embedded Platforms
- 对DROID-SLAM模型分层分析敏感度后进行结构化剪枝与8位量化
- 模型体积缩小79.8%，计算量减少18.9%，轨迹误差降低10.5%
- 适合部署在资源受限的机器人平台，尤其关注能效与实时性
优化基于深度学习的同步定位与地图构建（DL-SLAM）算法对于在资源受限的嵌入式平台高效实现至关重要，可支持自主移动机器人实时机载计算。本文提出SPAQ-DL-SLAM框架，针对最先进的DL-SLAM算法DROID-SLAM，采用结构化剪枝与量化（SPAQ）策略以提升资源与能效效率。具体地，基于逐层敏感度分析进行结构化剪枝并微调，随后对DROID-SLAM中的深度学习模块执行8位静态后训练量化（PTQ）。使用该框架优化后的SPAQ-DROID-SLAM模型（20%结构化剪枝 + 8位PTQ），相比原DROID-SLAM模型，浮点运算量（FLOPs）减少18.9%，整体模型尺寸减少79.8%。在TUM-RGBD基准测试中，其平均绝对轨迹误差（ATE）性能优于原模型10.5%。在ETH3D SLAM训练基准上，该模型展现出更强泛化能力，表现为更高的曲线下面积（AUC）得分，并成功处理额外2个数据序列。然而，在EuRoC数据集的Vicon Room序列（高角速度拍摄）上表现波动，表明需结合运行环境与任务特性设计DL-SLAM算法，才能在资源受限平台上实现最优性能与能效。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。