CauTraj: A Causal-Knowledge-Guided Framework for Lane-Changing Trajectory Planning of Autonomous Vehicles

TL;DR

This paper introduces CauTraj, a framework that integrates causal knowledge into trajectory planning for lane-changing autonomous vehicles, improving alignment with human driving behaviors and enhancing safety and realism.

Contribution

It proposes a novel causal-knowledge-guided trajectory planning framework that models vehicle interactions and embeds causal effects into model predictive control for autonomous driving.

Findings

Causal inference provides interpretable vehicle interaction quantification.

The approach reveals driver heterogeneity through causal effects.

It significantly reduces trajectory deviation and improves stability compared to baseline methods.

Abstract

Enhancing the performance of trajectory planners for lane - changing vehicles is one of the key challenges in autonomous driving within human - machine mixed traffic. Most existing studies have not incorporated human drivers' prior knowledge when designing trajectory planning models. To address this issue, this study proposes a novel trajectory planning framework that integrates causal prior knowledge into the control process. Both longitudinal and lateral microscopic behaviors of vehicles are modeled to quantify interaction risk, and a staged causal graph is constructed to capture causal dependencies in lane-changing scenarios. Causal effects between the lane-changing vehicle and surrounding vehicles are then estimated using causal inference, including average causal effects (ATE) and conditional average treatment effects (CATE). These causal priors are embedded into a model predictive control (MPC) framework to enhance trajectory planning. The proposed approach is validated on naturalistic vehicle trajectory datasets. Experimental results show that: (1) causal inference provides interpretable and stable quantification of vehicle interactions; (2) individual causal effects reveal driver heterogeneity; and (3) compared with the baseline MPC, the proposed method achieves a closer alignment with human driving behaviors, reducing maximum trajectory deviation from 1.2 m to 0.2 m, lateral velocity fluctuation by 60%, and yaw angle variability by 50%. These findings provide methodological support for human-like trajectory planning and practical value for improving safety, stability, and realism in autonomous vehicle testing and traffic simulation platforms.