GMMap: Memory-Efficient Continuous Occupancy Map Using Gaussian Mixture Model

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Peter Zhi Xuan, Karaman, Sertac, Sze, Vivienne
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916099180724224
author Li, Peter Zhi Xuan
Karaman, Sertac
Sze, Vivienne
author_facet Li, Peter Zhi Xuan
Karaman, Sertac
Sze, Vivienne
contents Energy consumption of memory accesses dominates the compute energy in energy-constrained robots which require a compact 3D map of the environment to achieve autonomy. Recent mapping frameworks only focused on reducing the map size while incurring significant memory usage during map construction due to multi-pass processing of each depth image. In this work, we present a memory-efficient continuous occupancy map, named GMMap, that accurately models the 3D environment using a Gaussian Mixture Model (GMM). Memory-efficient GMMap construction is enabled by the single-pass compression of depth images into local GMMs which are directly fused together into a globally-consistent map. By extending Gaussian Mixture Regression to model unexplored regions, occupancy probability is directly computed from Gaussians. Using a low-power ARM Cortex A57 CPU, GMMap can be constructed in real-time at up to 60 images per second. Compared with prior works, GMMap maintains high accuracy while reducing the map size by at least 56%, memory overhead by at least 88%, DRAM access by at least 78%, and energy consumption by at least 69%. Thus, GMMap enables real-time 3D mapping on energy-constrained robots.
format Preprint
id arxiv_https___arxiv_org_abs_2306_03740
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle GMMap: Memory-Efficient Continuous Occupancy Map Using Gaussian Mixture Model
Li, Peter Zhi Xuan
Karaman, Sertac
Sze, Vivienne
Robotics
Energy consumption of memory accesses dominates the compute energy in energy-constrained robots which require a compact 3D map of the environment to achieve autonomy. Recent mapping frameworks only focused on reducing the map size while incurring significant memory usage during map construction due to multi-pass processing of each depth image. In this work, we present a memory-efficient continuous occupancy map, named GMMap, that accurately models the 3D environment using a Gaussian Mixture Model (GMM). Memory-efficient GMMap construction is enabled by the single-pass compression of depth images into local GMMs which are directly fused together into a globally-consistent map. By extending Gaussian Mixture Regression to model unexplored regions, occupancy probability is directly computed from Gaussians. Using a low-power ARM Cortex A57 CPU, GMMap can be constructed in real-time at up to 60 images per second. Compared with prior works, GMMap maintains high accuracy while reducing the map size by at least 56%, memory overhead by at least 88%, DRAM access by at least 78%, and energy consumption by at least 69%. Thus, GMMap enables real-time 3D mapping on energy-constrained robots.
title GMMap: Memory-Efficient Continuous Occupancy Map Using Gaussian Mixture Model
topic Robotics
url https://arxiv.org/abs/2306.03740