DRIVE: Data-driven Robot Input Vector Exploration

TL;DR

DRIVE introduces a data-driven protocol for efficiently characterizing uncrewed ground vehicle input limits, significantly reducing data collection time while improving model accuracy, especially under extreme slip conditions.

Contribution

The paper presents DRIVE, a novel protocol for empirical data collection and model training for UGVs, outperforming traditional human-driven data gathering methods.

Findings

Increased predictive performance over human-driven protocols

Converges with 46 seconds of training data, four times less than traditional methods

Effective in extreme slip conditions on icy terrain

Abstract

An accurate motion model is a fundamental component of most autonomous navigation systems. While much work has been done on improving model formulation, no standard protocol exists for gathering empirical data required to train models. In this work, we address this issue by proposing Data-driven Robot Input Vector Exploration (DRIVE), a protocol that enables characterizing uncrewed ground vehicles (UGVs) input limits and gathering empirical model training data. We also propose a novel learned slip approach outperforming similar acceleration learning approaches. Our contributions are validated through an extensive experimental evaluation, cumulating over 7 km and 1.8 h of driving data over three distinct UGVs and four terrain types. We show that our protocol offers increased predictive performance over common human-driven data-gathering protocols. Furthermore, our protocol converges with 46 s of training data, almost four times less than the shortest human dataset gathering protocol. We show that the operational limit for our model is reached in extreme slip conditions encountered on surfaced ice. DRIVE is an efficient way of characterizing UGV motion in its operational conditions. Our code and dataset are both available online at this link: https://github.com/norlab-ulaval/DRIVE.