Developing, Analyzing, and Evaluating Vehicular Lane Keeping Algorithms Under Dynamic Lighting and Weather Conditions Using Electric Vehicles

TL;DR

This paper develops and compares two vehicular lane-keeping algorithms under dynamic weather conditions, demonstrating that a hybrid deep learning and hand-crafted approach outperforms an end-to-end deep learning model in terms of laps completed.

Contribution

It introduces a combined deep learning and hand-crafted lane-keeping algorithm and evaluates its performance against an end-to-end deep learning approach under adverse weather conditions.

Findings

Hybrid model completes more laps than end-to-end model

Hybrid approach achieves better average steering error

Both models are tested under dynamic weather conditions

Abstract

Self-driving vehicles have the potential to reduce accidents and fatalities on the road. Many production vehicles already come equipped with basic self-driving capabilities, but have trouble following lanes in adverse lighting and weather conditions. Therefore, we develop, analyze, and evaluate two vehicular lane-keeping algorithms under dynamic weather conditions using a combined deep learning- and hand-crafted approach and an end-to-end deep learning approach. We use image segmentation- and linear-regression based deep learning to drive the vehicle toward the center of the lane, measuring the amount of laps completed, average speed, and average steering error per lap. Our hybrid model completes more laps than our end-to-end deep learning model. In the future, we are interested in combining our algorithms to form one cohesive approach to lane-following.