Multi-task UNet architecture for end-to-end autonomous driving
This work addresses autonomous driving safety and interpretability, but it appears incremental as it builds on existing UNet and multi-task learning approaches.
The authors tackled autonomous driving by proposing a multi-task UNet architecture for end-to-end driving, showing that their supervised learning model performs comparably to a reinforcement learning model on curvy roads.
We propose an end-to-end driving model that integrates a multi-task UNet (MTUNet) architecture and control algorithms in a pipeline of data flow from a front camera through this model to driving decisions. It provides quantitative measures to evaluate the holistic, dynamic, and real-time performance of end-to-end driving systems and thus the safety and interpretability of MTUNet. The architecture consists of one segmentation, one regression, and two classification tasks for lane segmentation, path prediction, and vehicle controls. We present three variants of the architecture having different complexities, compare them on different tasks in four static measures for both single and multiple tasks, and then identify the best one by two additional dynamic measures in real-time simulation. Our results show that the performance of the proposed supervised learning model is comparable to that of a reinforcement learning model on curvy roads for the same task, which is not end-to-end but multi-module.