Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Moon, Seokha, Lee, Minseung, Seo, Joon, Kim, Jinkyu, Lee, Jungbeom
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913146048872448
author Moon, Seokha
Lee, Minseung
Seo, Joon
Kim, Jinkyu
Lee, Jungbeom
author_facet Moon, Seokha
Lee, Minseung
Seo, Joon
Kim, Jinkyu
Lee, Jungbeom
contents End-to-end autonomous driving, which bypasses traditional modular pipelines by directly predicting future trajectories from sensor inputs, has recently achieved substantial progress. However, existing methods often overlook the causal inter-dependencies in ego-vehicle planning, ignoring the reciprocal relations between the ego vehicle and surrounding agents. This causal oversight leads to inconsistent and unreliable trajectory predictions, especially in interaction-critical scenarios where ego decisions and neighboring agent behaviors must be reasoned about jointly. To address this limitation, we propose CaAD, a Causality-aware end-to-end Autonomous Driving framework that captures these dependencies within a shared latent scene representation. First, we propose an ego-centric joint-causal modeling module that builds on the marginal prediction branch, and learns causal dependencies between the ego vehicle and interaction-relevant agents. Second, we employ a causality-aware policy alignment stage implemented with joint-mode embeddings to align the stochastic ego policy with planning-oriented closed-loop feedback computed from surrounding traffic and map context. On the Bench2Drive and NAVSIM benchmarks, CaAD demonstrates strong closed-loop planning performance, achieving a Driving Score of 87.53 and Success Rate of 71.81 on Bench2Drive, and a PDMS of 91.1 on NAVSIM. The project page is available at https://moonseokha.github.io/CaAD/.
format Preprint
id arxiv_https___arxiv_org_abs_2605_13646
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling
Moon, Seokha
Lee, Minseung
Seo, Joon
Kim, Jinkyu
Lee, Jungbeom
Robotics
Artificial Intelligence
End-to-end autonomous driving, which bypasses traditional modular pipelines by directly predicting future trajectories from sensor inputs, has recently achieved substantial progress. However, existing methods often overlook the causal inter-dependencies in ego-vehicle planning, ignoring the reciprocal relations between the ego vehicle and surrounding agents. This causal oversight leads to inconsistent and unreliable trajectory predictions, especially in interaction-critical scenarios where ego decisions and neighboring agent behaviors must be reasoned about jointly. To address this limitation, we propose CaAD, a Causality-aware end-to-end Autonomous Driving framework that captures these dependencies within a shared latent scene representation. First, we propose an ego-centric joint-causal modeling module that builds on the marginal prediction branch, and learns causal dependencies between the ego vehicle and interaction-relevant agents. Second, we employ a causality-aware policy alignment stage implemented with joint-mode embeddings to align the stochastic ego policy with planning-oriented closed-loop feedback computed from surrounding traffic and map context. On the Bench2Drive and NAVSIM benchmarks, CaAD demonstrates strong closed-loop planning performance, achieving a Driving Score of 87.53 and Success Rate of 71.81 on Bench2Drive, and a PDMS of 91.1 on NAVSIM. The project page is available at https://moonseokha.github.io/CaAD/.
title Causality-Aware End-to-End Autonomous Driving via Ego-Centric Joint Scene Modeling
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2605.13646