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

arXiv cs.RO / 4/1/2026

📰 NewsSignals & Early TrendsModels & Research

共有:

Key Points

The paper introduces Gleanmer, a fabricated 6 mW edge SoC designed for real-time 3D Gaussian occupancy mapping using the GMMap approach.
By performing algorithm–hardware co-optimizations that enable direct computation and reuse of compact Gaussian representations, the system reduces map construction energy by up to 63% and query energy by up to 81%.
The design uses approximate computation on Gaussians to shrink accelerator area by 38% while maintaining real-time performance.
Implemented in 16nm CMOS, Gleanmer can process 640×480 images above 88 fps for map construction and supports queries at over 540K coordinates per second.
The authors claim Gleanmer is the first fabricated SoC to deliver real-time 3D occupancy mapping under a 6 mW power budget for AR/VR and autonomous edge use cases.

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.