An 879GOPS 243mW 80fps VGA Fully Visual CNN-SLAM Processor for Wide-Range Autonomous Exploration

📋 论文概要

本文提出了一款全视觉CNN-SLAM处理器，能够在80fps VGA分辨率下实现879GOPS的峰值性能，功耗仅243mW，支持6自由度轨迹估计和3D地图构建，解决了传统SLAM方法在资源受限平台上的实时性和能效瓶颈。

💡 主要创新点

• 首次将CNN特征提取与SLAM后端处理融合到单一处理器中，实现全硬件化的视觉SLAM流水线。
• 采用稀疏化卷积和动态精度量化技术，在保持精度前提下大幅降低计算与存储开销。
• 通过专用片上存储和可配置数据流架构，支持宽范围自主探索任务的高效执行。

🏷 关键词

📄 原文摘要

University of Michigan, Ann Arbor, MI Simultaneous localization and mapping (SLAM) estimates an agent’s trajectory for all six degrees of freedom (6 DoF) and constructs a 3D map of an unknown surrounding. It is a fundamental kernel that enables head-mounted augmented/virtual reality devices and autonomous navigation of micro aerial vehicles. A noticeable recent trend in visual SLAM is to apply computation- and memory-intensive convolutional neural networks (CNNs) that outperform traditional hand-designed feature-based methods [1]. For each video frame, CNN-extracted features are matched with stored keypoints to estimate the agent’s 6-DoF pose by solving a perspective-n-points (PnP) non-linear optimization problem (Fig. 7.3.1, left). The agent’s long-term trajectory over multiple frames is refined by a bundle adjustment process (BA, Fig. 7.3.1 right), which involves a large-scale (~120 variables) non-linear optimization. Visual SLAM requires massive computation

👥 作者与机构

Ziyun Li, Yu Chen, Luyao Gong, Lu Liu, Dennis Sylvester, David Blaauw, Hun-Seok Kim