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 …

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 …

Current deep learning based autonomous driving approaches yield impressive results also
leading to in-production deployment in certain controlled scenarios. One of the most popular …

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 …

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 …

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 …

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 …

End-to-end autonomous driving aims to build a fully differentiable system that takes raw
sensor data as inputs and directly outputs the planned trajectory or control signals of the ego …

Autonomous driving systems need to handle complex scenarios such as lane following,
avoiding collisions, taking turns, and responding to traffic signals. In recent years …