End-to-End Deep Learning of Lane Detection and Path Prediction for Real-Time Autonomous Driving
This work provides a more efficient and effective solution for real-time lane detection and path prediction, which is crucial for the performance of autonomous driving systems.
This paper proposes a lightweight UNet architecture, DSUNet, for end-to-end lane detection and path prediction in autonomous driving. DSUNet is 5.16x lighter and 1.61x faster than UNet, and it outperforms UNet-PP in mean average errors for predicted curvature and lateral offset in dynamic simulation, as well as a modified UNet in lateral error in real-world tests.
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.