VINet: Visual and Inertial-based Terrain Classification and Adaptive Navigation over Unknown Terrain

TL;DR

VINet is a novel visual-inertial system that classifies terrains and adapts navigation strategies, significantly improving accuracy and control performance on both known and unknown terrains for robotic applications.

Contribution

The paper introduces VINet, a new perception and control framework that enhances terrain classification and adaptive navigation over unknown surfaces using a novel labeling scheme.

Findings

Achieves 98.37% accuracy on known terrains

Improves unknown terrain classification accuracy by 8.51%

Enhances navigation control, reducing RMSE by 10.3% on diverse terrains

Abstract

We present a visual and inertial-based terrain classification network (VINet) for robotic navigation over different traversable surfaces. We use a novel navigation-based labeling scheme for terrain classification and generalization on unknown surfaces. Our proposed perception method and adaptive scheduling control framework can make predictions according to terrain navigation properties and lead to better performance on both terrain classification and navigation control on known and unknown surfaces. Our VINet can achieve 98.37% in terms of accuracy under supervised setting on known terrains and improve the accuracy by 8.51% on unknown terrains compared to previous methods. We deploy VINet on a mobile tracked robot for trajectory following and navigation on different terrains, and we demonstrate an improvement of 10.3% compared to a baseline controller in terms of RMSE.