PS Chib, P Singh - IEEE Transactions on Intelligent Vehicles, 2023 - ieeexplore.ieee.org
End-to-End driving is a promising paradigm as it circumvents the drawbacks associated with modular systems, such as their overwhelming complexity and propensity for error …
Modern autonomous driving system is characterized as modular tasks in sequential order, ie, perception, prediction, and planning. In order to perform a wide diversity of tasks and …
How should we integrate representations from complementary sensors for autonomous driving? Geometry-based fusion has shown promise for perception (eg, object detection …
We introduce SceneDiffuser, a conditional generative model for 3D scene understanding. SceneDiffuser provides a unified model for solving scene-conditioned generation …
D Chen, P Krähenbühl - … of the IEEE/CVF Conference on …, 2022 - openaccess.thecvf.com
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 …
X Tang, K Yang, H Wang, J Wu, Y Qin… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Motion prediction is the fundamental input for decision-making in autonomous vehicles. The current motion prediction solutions are designed with a strong reliance on black box …
Autonomous driving requires a comprehensive understanding of the surrounding environment for reliable trajectory planning. Previous works rely on dense rasterized scene …
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 …
X Jia, P Wu, L Chen, J Xie, C He… - Proceedings of the …, 2023 - openaccess.thecvf.com
End-to-end autonomous driving has made impressive progress in recent years. Existing methods usually adopt the decoupled encoder-decoder paradigm, where the encoder …