In this paper, we present a system to train driving policies from experiences collected not just
from the ego-vehicle, but all vehicles that it observes. This system uses the behaviors of …

Despite significant recent progress in the field of autonomous driving modern methods still
struggle and can incur serious accidents when encountering long-tail unforeseen events …

An accurate model of the environment and the dynamic agents acting in it offers great
potential for improving motion planning. We present MILE: a Model-based Imitation …

Many adaptations of transformers have emerged to address the single-modal vision tasks,
where self-attention modules are stacked to handle input sources like images. Intuitively …

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 …

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

Methods for 3D lane detection have been recently proposed to address the issue of
inaccurate lane layouts in many autonomous driving scenarios (uphill/downhill, bump, etc.) …

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 …

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 …

The large-scale deployment of autonomous vehicles is yet to come, and one of the major
remaining challenges lies in urban dense traffic scenarios. In such cases, it remains …