End-to-End Deep Learning of Lane Detection and Path Prediction for Real-Time Autonomous Driving

TL;DR

This paper introduces DSUNet, a lightweight deep learning model for real-time lane detection and path prediction in autonomous driving, demonstrating improved efficiency and accuracy over traditional UNet-based approaches.

Contribution

We propose DSUNet, a compact and faster UNet variant using depthwise separable convolutions, and integrate it with a path prediction algorithm for enhanced autonomous driving performance.

Findings

DSUNet is 5.16 times smaller and 1.61 times faster than UNet.

DSUNet-PP achieves lower mean average errors in path prediction metrics.

Real-world tests show DSUNet-PP outperforms modified UNet in lateral error.

Abstract

Inspired by the UNet architecture of semantic image segmentation, we propose a lightweight UNet using depthwise separable convolutions (DSUNet) for end-to-end learning of lane detection and path prediction (PP) in autonomous driving. We also design and integrate a PP algorithm with convolutional neural network (CNN) to form a simulation model (CNN-PP) that can be used to assess CNN's performance qualitatively, quantitatively, and dynamically in a host agent car driving along with other agents all in a real-time autonomous manner. DSUNet is 5.16x lighter in model size and 1.61x faster in inference than UNet. DSUNet-PP outperforms UNet-PP in mean average errors of predicted curvature and lateral offset for path planning in dynamic simulation. DSUNet-PP outperforms a modified UNet in lateral error, which is tested in a real car on real road. These results show that DSUNet is efficient and effective for lane detection and path prediction in autonomous driving.