METAVerse: Meta-Learning Traversability Cost Map for Off-Road Navigation

TL;DR

METAVerse introduces a meta-learning framework that enables off-road autonomous vehicles to accurately predict terrain traversability across diverse environments, improving navigation safety and stability through rapid online adaptation.

Contribution

The paper presents a novel meta-learning approach for global traversability prediction that adapts quickly to new environments, enhancing off-road navigation reliability.

Findings

Global model reduces estimation uncertainty

Online adaptation improves local accuracy

Integration with control yields safe navigation

Abstract

Autonomous navigation in off-road conditions requires an accurate estimation of terrain traversability. However, traversability estimation in unstructured environments is subject to high uncertainty due to the variability of numerous factors that influence vehicle-terrain interaction. Consequently, it is challenging to obtain a generalizable model that can accurately predict traversability in a variety of environments. This paper presents METAVerse, a meta-learning framework for learning a global model that accurately and reliably predicts terrain traversability across diverse environments. We train the traversability prediction network to generate a dense and continuous-valued cost map from a sparse LiDAR point cloud, leveraging vehicle-terrain interaction feedback in a self-supervised manner. Meta-learning is utilized to train a global model with driving data collected from multiple environments, effectively minimizing estimation uncertainty. During deployment, online adaptation is performed to rapidly adapt the network to the local environment by exploiting recent interaction experiences. To conduct a comprehensive evaluation, we collect driving data from various terrains and demonstrate that our method can obtain a global model that minimizes uncertainty. Moreover, by integrating our model with a model predictive controller, we demonstrate that the reduced uncertainty results in safe and stable navigation in unstructured and unknown terrains.