Beyond Conservative Automated Driving in Multi-Agent Scenarios via Coupled Model Predictive Control and Deep Reinforcement Learning

2026-04-15

AI Summary

This work addresses the challenge of complex multi-agent interactions at unsignalized intersections, where conventional approaches struggle to balance safety and efficiency. The authors propose a novel framework that integrates model predictive control (MPC) with deep reinforcement learning (RL), uniquely combining MPC’s explicit handling of safety constraints with RL’s adaptive policy learning. This integration reduces overly conservative behaviors while preserving safety, supports end-to-end training, and incorporates structured constraints. Evaluated in multi-vehicle scenarios, the method achieves a 21% reduction in collision rates and a 6.5% increase in task success compared to pure MPC. Furthermore, it demonstrates zero-shot transfer to unseen highway merging scenarios and exhibits faster training convergence.

Technology Category

• Multiagent Systems: Multiagent Learning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Automated driving at unsignalized intersections is challenging due to complex multi-vehicle interactions and the need to balance safety and efficiency. Model Predictive Control (MPC) offers structured constraint handling through optimization but relies on hand-crafted rules that often produce overly conservative behavior. Deep Reinforcement Learning (RL) learns adaptive behaviors from experience but often struggles with safety assurance and generalization to unseen environments. In this study, we present an integrated MPC-RL framework to improve navigation performance in multi-agent scenarios. Experiments show that MPC-RL outperforms standalone MPC and end-to-end RL across three traffic-density levels. Collectively, MPC-RL reduces the collision rate by 21% and improves the success rate by 6.5% compared to pure MPC. We further evaluate zero-shot transfer to a highway merging scenario without retraining. Both MPC-based methods transfer substantially better than end-to-end PPO, which highlights the role of the MPC backbone in cross-scenario robustness. The framework also shows faster loss stabilization than end-to-end RL during training, which indicates a reduced learning burden. These results suggest that the integrated approach can improve the balance between safety performance and efficiency in multi-agent intersection scenarios, while the MPC component provides a strong foundation for generalization across driving environments. The implementation code is available open-source.

Problem

• automated driving
• multi-agent scenarios
• safety-efficiency trade-off
• unsignalized intersections
• generalization

Innovation

• Model Predictive Control
• Deep Reinforcement Learning
• Multi-Agent Driving
• Zero-Shot Transfer
• Autonomous Navigation