Deployable, Data-Driven Unmanned Vehicle Navigation System in GPS-Denied, Feature-Deficient Environments

TL;DR

This paper introduces a data-driven navigation system for unmanned vehicles operating in GPS-denied, feature-scarce environments, optimizing landmark deployment to ensure accurate localization with minimal resources.

Contribution

It develops a systematic method combining estimation, machine learning, and optimization to minimize landmarks while maintaining localization accuracy in challenging environments.

Findings

Effective localization with fewer landmarks demonstrated in simulations

Systematic approach reduces resource use in GPS-denied environments

Method maintains desired position uncertainty levels

Abstract

This paper presents a novel data-driven navigation system to navigate an Unmanned Vehicle (UV) in GPS-denied, feature-deficient environments such as tunnels, or mines. The method utilizes landmarks that vehicle can deploy and measure range from to enable localization as the vehicle traverses its pre-defined path through the tunnel. A key question that arises in such scenario is to estimate and reduce the number of landmarks that needs to be deployed for localization before the start of the mission, given some information about the environment. The main focus is to keep the maximum position uncertainty at a desired value. In this article, we develop a novel vehicle navigation system in GPS-denied, feature-deficient environment by combining techniques from estimation, machine learning, and mixed-integer convex optimization. This article develops a novel, systematic method to perform localization and navigate the UV through the environment with minimum number of landmarks while maintaining desired localization accuracy. We also present extensive simulation experiments on different scenarios that corroborate the effectiveness of the proposed navigation system.