Pushing the Limits of Learning-based Traversability Analysis for Autonomous Driving on CPU

TL;DR

This paper presents a real-time, CPU-based machine learning method for environment traversability analysis in autonomous driving, combining geometric and visual features to achieve high accuracy and efficiency.

Contribution

It introduces a hybrid SVM-based approach that improves performance and reliability while operating fully on CPU, outperforming some deep learning methods in resource usage.

Findings

Achieves 89.2% accuracy on outdoor driving datasets.

Operates faster and with fewer hardware resources than deep learning methods.

Demonstrates robustness across varying environmental complexities.

Abstract

Self-driving vehicles and autonomous ground robots require a reliable and accurate method to analyze the traversability of the surrounding environment for safe navigation. This paper proposes and evaluates a real-time machine learning-based Traversability Analysis method that combines geometric features with appearance-based features in a hybrid approach based on a SVM classifier. In particular, we show that integrating a new set of geometric and visual features and focusing on important implementation details enables a noticeable boost in performance and reliability. The proposed approach has been compared with state-of-the-art Deep Learning approaches on a public dataset of outdoor driving scenarios. It reaches an accuracy of 89.2% in scenarios of varying complexity, demonstrating its effectiveness and robustness. The method runs fully on CPU and reaches comparable results with respect to the other methods, operates faster, and requires fewer hardware resources.