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

TL;DR

This paper introduces CaAD, a causality-aware framework for end-to-end autonomous driving that models causal dependencies between the ego vehicle and surrounding agents to improve trajectory prediction and planning.

Contribution

It proposes a novel ego-centric joint-causal modeling module and causality-aware policy alignment to better capture interactions in autonomous driving.

Findings

Achieves a Driving Score of 87.53 on Bench2Drive

Attains a Success Rate of 71.81 on Bench2Drive

Achieves a PDMS of 91.1 on NAVSIM

Abstract

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/.