Dual Control for Interactive Autonomous Merging with Model Predictive Diffusion

2025-02-14

AI Summary

This work addresses the real-time interactive decision-making challenge between autonomous vehicles and human drivers in highway on-ramp merging scenarios, where conventional “predict-then-plan” paradigms fail under behavioral uncertainty and dynamic coupling. We propose a prediction-belief-distribution-driven active learning closed-loop framework that, for the first time, integrates Bayesian dual control theory with a model-predictive diffusion solver to jointly perform online behavioral inference and adaptive planning within a receding-horizon, non-convex, high-uncertainty environment. The method unifies Bayesian dual control, model predictive control (MPC), a customized diffusion-model-based solver, and a hardware-in-the-loop real-time control system. Extensive validation on real-world traffic datasets and a physical vehicle platform demonstrates significant improvements in merging success rate and interaction naturalness, completing full-stack verification from simulation to real-world deployment.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Reasoning under Uncertainty: Sequential Decision Making
• Planning, Routing, and Scheduling: Model-Based Reasoning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Interactive decision-making is essential in applications such as autonomous driving, where the agent must infer the behavior of nearby human drivers while planning in real-time. Traditional predict-then-act frameworks are often insufficient or inefficient because accurate inference of human behavior requires a continuous interaction rather than isolated prediction. To address this, we propose an active learning framework in which we rigorously derive predicted belief distributions. Additionally, we introduce a novel model-based diffusion solver tailored for online receding horizon control problems, demonstrated through a complex, non-convex highway merging scenario. Our approach extends previous high-fidelity dual control simulations to hardware experiments, which may be viewed at https://youtu.be/Q_JdZuopGL4, and verifies behavior inference in human-driven traffic scenarios, moving beyond idealized models. The results show improvements in adaptive planning under uncertainty, advancing the field of interactive decision-making for real-world applications.

Problem

• Interactive decision-making in autonomous driving
• Inference of human driver behavior
• Real-time adaptive planning under uncertainty

Innovation

• Active learning framework
• Model-based diffusion solver
• High-fidelity dual control