Distributed Client-Server Optimization for SLAM with Limited On-Device Resources

TL;DR

This paper introduces a client-server SLAM framework enabling resource-constrained devices to perform accurate real-time localization by offloading most computations to a server and selectively updating on-device state with summarized map information.

Contribution

The paper presents a novel client-server architecture for SLAM that reduces on-device resource requirements while maintaining high accuracy, including techniques for early loop closures and map summarization.

Findings

Achieves real-time, accurate SLAM on devices with limited resources.

Effective map summarization improves on-device localization accuracy.

Experimental validation on synthetic and real datasets confirms the framework's efficiency.

Abstract

Simultaneous localization and mapping (SLAM) is a crucial functionality for exploration robots and virtual/augmented reality (VR/AR) devices. However, some of such devices with limited resources cannot afford the computational or memory cost to run full SLAM algorithms. We propose a general client-server SLAM optimization framework that achieves accurate real-time state estimation on the device with low requirements of on-board resources. The resource-limited device (the client) only works on a small part of the map, and the rest of the map is processed by the server. By sending the summarized information of the rest of map to the client, the on-device state estimation is more accurate. Further improvement of accuracy is achieved in the presence of on-device early loop closures, which enables reloading useful variables from the server to the client. Experimental results from both synthetic and real-world datasets demonstrate that the proposed optimization framework achieves accurate estimation in real-time with limited computation and memory budget of the device.