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

2025-12-21

AI Summary

To address the lack of human driving prior modeling in lane-change trajectory planning for human–autonomous vehicle mixed traffic, this paper pioneers the systematic integration of causal inference into autonomous lane-change decision-making. We propose a staged causal graph to explicitly model traffic interaction risks, quantify driver heterogeneity via Average Treatment Effect (ATE) and Conditional Average Treatment Effect (CATE) estimation, and design a causal-augmented Model Predictive Control (MPC) framework. Our method jointly models microscopic longitudinal and lateral driving behaviors, enabling interpretable, stable, and human-like trajectory generation. Experimental results demonstrate significant improvements over baseline MPC: maximum trajectory deviation decreases by 83% (from 1.2 m to 0.2 m), lateral velocity fluctuation reduces by 60%, and yaw angle variation drops by 50%. These gains substantially enhance safety, trajectory stability, and human consistency.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Causal Learning
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

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.

Problem

• Integrates causal prior knowledge into autonomous vehicle lane-changing trajectory planning.
• Models vehicle interactions and constructs causal graphs for lane-changing scenarios.
• Enhances trajectory planning using causal inference within a model predictive control framework.

Innovation

• Integrates causal prior knowledge into model predictive control framework.
• Uses causal inference to estimate vehicle interaction effects.
• Models longitudinal and lateral behaviors with staged causal graphs.