Many existing autonomous driving paradigms involve a multi-stage discrete pipeline of
tasks. To better predict the control signals and enhance user safety, an end-to-end approach …

Directly producing planning results from raw sensors has been a long-desired solution for
autonomous driving and has attracted increasing attention recently. Most existing end-to …

Vision-centric joint perception and prediction (PnP) has become an emerging trend in
autonomous driving research. It predicts the future states of the traffic participants in the …

Vision-centric autonomous driving has recently raised wide attention due to its lower cost.
Pre-training is essential for extracting a universal representation. However current vision …

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 …

Autonomous driving requires a comprehensive understanding of the surrounding
environment for reliable trajectory planning. Previous works rely on dense rasterized scene …

In the spectrum of vision-based autonomous driving, vanilla end-to-end models are not
interpretable and suboptimal in performance, while mediated perception models require …

While learning visuomotor skills in an end-to-end manner is appealing, deep neural
networks are often uninterpretable and fail in surprising ways. For robotics tasks, such as …

Recent vision-only perception models for autonomous driving achieved promising results by
encoding multi-view image features into Bird's-Eye-View (BEV) space. A critical step and the …

Current end-to-end autonomous driving methods either run a controller based on a planned
trajectory or perform control prediction directly, which have spanned two separately studied …