Curating Long-term Vector Maps

TL;DR

This paper presents a recursive algorithm for building and updating long-term vector maps for mobile robots, improving localization robustness in changing environments by filtering dynamic features and reasoning over multiple deployments.

Contribution

It introduces a novel recursive method to construct and update Long-Term Vector Maps using visibility constraints and SDF filtering, enhancing long-term localization accuracy.

Findings

Accurate and robust LTVMs built from multiple deployments.

Effective filtering of dynamic features improves localization.

LTVMs are compact and suitable for long-term use.

Abstract

Autonomous service mobile robots need to consistently, accurately, and robustly localize in human environments despite changes to such environments over time. Episodic non-Markov Localization addresses the challenge of localization in such changing environments by classifying observations as arising from Long-Term, Short-Term, or Dynamic Features. However, in order to do so, EnML relies on an estimate of the Long-Term Vector Map (LTVM) that does not change over time. In this paper, we introduce a recursive algorithm to build and update the LTVM over time by reasoning about visibility constraints of objects observed over multiple robot deployments. We use a signed distance function (SDF) to filter out observations of short-term and dynamic features from multiple deployments of the robot. The remaining long-term observations are used to build a vector map by robust local linear regression. The uncertainty in the resulting LTVM is computed via Monte Carlo resampling the observations arising from long-term features. By combining occupancy-grid based SDF filtering of observations with continuous space regression of the filtered observations, our proposed approach builds, updates, and amends LTVMs over time, reasoning about all observations from all robot deployments in an environment. We present experimental results demonstrating the accuracy, robustness, and compact nature of the extracted LTVMs from several long-term robot datasets.