Efficient understanding of the environment is a crucial prerequisite for autonomous driving,
but explicitly modeling the environment is hard to come true. In contrast, imitation learning, in …

Efficient reasoning about the semantic, spatial, and temporal structure of a scene is a crucial
prerequisite for autonomous driving. We present NEural ATtention fields (NEAT), a novel …

This study aims to improve the performance and generalization capability of end-to-end
autonomous driving with scene understanding leveraging deep learning and multimodal …

Vision-based end-to-end driving models trained by imitation learning can lead to affordable
solutions for autonomous driving. However, training these well-performing models usually …

Imitation learning for end-to-end autonomous driving has drawn attention from academic
communities. Current methods either only use images as the input which is ambiguous …

In this paper, a road lane is detected as a reference point in a road driving image, and the
objects that are likely to affect the driving situation are detected depending on a reference …

End-to-end autonomous driving provides a simple and efficient framework for autonomous
driving systems, which can directly obtain control commands from raw perception data …

We present an unsupervised adaptation approach for visual scene understanding in
unstructured traffic environments. Our method is designed for unstructured real-world …

Conditional imitation learning (CIL) trains deep neural networks, in an end-to-end manner,
to mimic human driving. This approach has demonstrated suitable vehicle control when …

Imitation learning is becoming more and more successful for autonomous driving. End-to-
end (raw signal to command) performs well on relatively simple tasks (lane keeping and …