Pushing the Limits of Learning-based Traversability Analysis for Autonomous Driving on CPU
This work addresses the need for safe navigation in self-driving vehicles and autonomous ground robots, but it is incremental as it builds on existing machine learning methods with a focus on implementation details.
The paper tackled the problem of reliable and accurate traversability analysis for autonomous driving by proposing a hybrid SVM classifier that combines geometric and appearance-based features, achieving 89.2% accuracy on a public dataset and running efficiently on CPU with faster operation and lower hardware requirements.
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.