A Novel Gaussian Process Based Ground Segmentation Algorithm with Local-Smoothness Estimation

TL;DR

This paper introduces a Gaussian process-based ground segmentation algorithm for autonomous vehicles that models local smoothness and uses a novel non-stationary covariance function, improving accuracy in rough terrains.

Contribution

The paper proposes a new GP-based ground segmentation method utilizing local-smoothness estimation and a non-stationary covariance function, with a multi-task Bayesian inference approach for whole-frame ground modeling.

Findings

Outperforms existing GP-based methods in rough, uneven terrains

Provides efficient whole-frame ground estimation rather than segment-wise

Effective in modeling local ground surface variations

Abstract

Autonomous Land Vehicles (ALV) shall efficiently recognize the ground in unknown environments. A novel $\mathcal{GP}$-based method is proposed for the ground segmentation task in rough driving scenarios. A non-stationary covariance function is utilized as the kernel for the $\mathcal{GP}$. The ground surface behavior is assumed to only demonstrate local-smoothness. Thus, point estimates of the kernel's length-scales are obtained. Thus, two Gaussian processes are introduced to separately model the observation and local characteristics of the data. While, the \textit{observation process} is used to model the ground, the \textit{latent process} is put on length-scale values to estimate point values of length-scales at each input location. Input locations for this latent process are chosen in a physically-motivated procedure to represent an intuition about ground condition. Furthermore, an intuitive guess of length-scale value is represented by assuming the existence of hypothetical surfaces in the environment that every bunch of data points may be assumed to be resulted from measurements from this surfaces. Bayesian inference is implemented using \textit{maximum a Posteriori} criterion. The log-marginal likelihood function is assumed to be a multi-task objective function, to represent a whole-frame unbiased view of the ground at each frame. Simulation results shows the effectiveness of the proposed method even in an uneven, rough scene which outperforms similar Gaussian process based ground segmentation methods. While adjacent segments do not have similar ground structure in an uneven scene, the proposed method gives an efficient ground estimation based on a whole-frame viewpoint instead of just estimating segment-wise probable ground surfaces.