Gleanmer: A 6 mW SoC for Real-Time 3D Gaussian Occupancy Mapping

2026-03-30

AI Summary

This work addresses the challenge of real-time, high-fidelity 3D occupancy mapping on power-constrained edge devices. The authors propose Gleanmer, a system-on-chip that, for the first time, enables real-time 3D occupancy map processing under 6 mW in 16nm CMOS technology. Through algorithm-hardware co-optimization, Gleanmer introduces a Gaussian-based map representation (GMMap) with direct computation, efficient data reuse, and approximate computing mechanisms, substantially reducing hardware overhead while enhancing energy efficiency. Compared to the baseline, the proposed design reduces energy consumption by 63% during map construction and by 81% during query operations, while shrinking accelerator area by 38%. It supports processing of 640×480 images at over 88 frames per second and enables more than 540,000 coordinate queries per second.

Abstract

High-fidelity 3D occupancy mapping is essential for many edge-based applications (such as AR/VR and autonomous navigation) but is limited by power constraints. We present Gleanmer, a system on chip (SoC) with an accelerator for GMMap, a 3D occupancy map using Gaussians. Through algorithm-hardware co-optimizations for direct computation and efficient reuse of these compact Gaussians, Gleanmer reduces construction and query energy by up to 63% and 81%, respectively. Approximate computation on Gaussians reduces accelerator area by 38%. Using 16nm CMOS, Gleanmer processes 640x480 images in real time beyond 88 fps during map construction and processes over 540K coordinates per second during map query. To our knowledge, Gleanmer is the first fabricated SoC to achieve real-time 3D occupancy mapping under 6 mW for edge-based applications.

Problem

• 3D occupancy mapping
• edge computing
• power constraints
• real-time processing
• Gaussian representation

Innovation

• 3D Gaussian occupancy mapping
• algorithm-hardware co-optimization
• ultra-low-power SoC
• real-time mapping
• approximate computing