CONTROL2026-04-15

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

Saeed Rahmani, Gözde Körpe, Zhenlin Xu, Bruno Brito, Simeon Craig Calvert, Bart van Arem

This paper combines two complementary Control & PlanningControlThe method used to make the robot move the way you want. approaches for autonomous vehicles navigating complex intersections. Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. ensures safety through mathematical optimization with explicit constraints, while Deep Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. enables the system to learn efficient, less conservative behaviors from experience. Think of it as combining a rule-based safety system with an AI learning system: Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. acts as guardrails ensuring the vehicle doesn't crash, while Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. learns when and how to be more aggressive to improve traffic flow. The key benefit for developers is that this hybrid approach achieves 21% fewer collisions than pure Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. while being 6.5% more successful, and importantly, the Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. backbone helps the learned behaviors transfer to new driving scenarios (like highway merging) without retraining—something end-to-end learning systems struggle with.

THE PROBLEM

This paper focuses on Control & PlanningControlThe method used to make the robot move the way you want.. This paper combines two complementary Control & PlanningControlThe method used to make the robot move the way you want. approaches for autonomous vehicles navigating complex intersections. Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. ensures safety through mathematical optimization with explicit constraints, while Deep Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. enables the system to learn efficient, less conservative behaviors from experience. Think of it as combining a rule-based safety system with an AI learning system: Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. acts as guardrails ensuring the vehicle doesn't crash, while Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. learns when and how to be more aggressive to improve traffic flow. The key benefit for developers is that this hybrid approach achieves 21% fewer collisions than pure Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. while being 6.5% more successful, and importantly, the Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. backbone helps the learned behaviors transfer to new driving scenarios (like highway merging) without retraining—something end-to-end learning systems struggle with. Read the paper by tracking the Core ConceptsTaskThe job the robot is supposed to complete, such as pick-and-place, navigation, or drawer opening. definition, the Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. or data assumptions, and the evidence that supports the claimed improvement.

HOW IT WORKS

1

Task framing

The paper frames the work as Control & PlanningControlThe method used to make the robot move the way you want.. Start here because it defines what success means and which assumptions the rest of the method inherits.

2

Core method

This paper combines two complementary Control & PlanningControlThe method used to make the robot move the way you want. approaches for autonomous vehicles navigating complex intersections. Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. ensures safety through mathematical optimization with explicit constraints, while Deep Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. enables the system to learn efficient, less conservative behaviors from experience. Think of it as combining a rule-based safety system with an AI learning system: Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. acts as guardrails ensuring the vehicle doesn't crash, while Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. learns when and how to be more aggressive to improve traffic flow. The key benefit for developers is that this hybrid approach achieves 21% fewer collisions than pure Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. while being 6.5% more successful, and importantly, the Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. backbone helps the learned behaviors transfer to new driving scenarios (like highway merging) without retraining—something end-to-end learning systems struggle with. When reading the method section, identify the inputs, the learned or engineered representation, and the Core ConceptsActionA command the robot sends to its motors, controller, or low-level system. or prediction produced by the system.

3

Data and supervision

For robotics work, the data story is part of the method: check whether the system depends on Imitation & Reinforcement LearningTeleoperation (teleop)A human remotely controlling the robot, often to collect demonstrations., Simulation & Sim-to-RealSimulationA virtual environment where robots can be trained or tested., internet video, human labels, or Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. rollouts.

4

Evaluation evidence

The paper should be judged through its Simulation & Sim-to-RealEvaluationMeasuring how well a robot system performs. protocol: what data is used, what Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. or simulator is tested, and which Evaluation & ResearchBaselineA reference method used for comparison. comparisons support the claim. Look for the gap between the headline result and the Simulation & Sim-to-RealDeploymentPutting the trained system on a real robot. setting you would actually care about.

FIGURES

KEY RESULTS

Main contributionConceptual contribution

This paper combines two complementary Control & PlanningControlThe method used to make the robot move the way you want. approaches for autonomous vehicles navigating complex intersections. Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. ensures safety through mathematical optimization with explicit constraints, while Deep Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. enables the system to learn efficient, less conservative behaviors from experience. Think of it as combining a rule-based safety system with an AI learning system: Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. acts as guardrails ensuring the vehicle doesn't crash, while Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. learns when and how to be more aggressive to improve traffic flow. The key benefit for developers is that this hybrid approach achieves 21% fewer collisions than pure Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. while being 6.5% more successful, and importantly, the Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. backbone helps the learned behaviors transfer to new driving scenarios (like highway merging) without retraining—something end-to-end learning systems struggle with.

WHY DEVELOPERS SHOULD CARE

This paper combines two complementary Control & PlanningControlThe method used to make the robot move the way you want. approaches for autonomous vehicles navigating complex intersections. Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. ensures safety through mathematical optimization with explicit constraints, while Deep Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. enables the system to learn efficient, less conservative behaviors from experience. Think of it as combining a rule-based safety system with an AI learning system: Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. acts as guardrails ensuring the vehicle doesn't crash, while Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. learns when and how to be more aggressive to improve traffic flow. The key benefit for developers is that this hybrid approach achieves 21% fewer collisions than pure Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. while being 6.5% more successful, and importantly, the Control & PlanningModel Predictive Control (MPC)A control method that repeatedly plans a short future path, acts a little, then replans. backbone helps the learned behaviors transfer to new driving scenarios (like highway merging) without retraining—something end-to-end learning systems struggle with.

LIMITATIONS

The main limitation to check is whether the claimed behavior holds outside the paper's reported setup. That means testing across different Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. embodiments, scenes, objects, and data distributions.

WHAT COMES NEXT

The practical next step is independent reproduction with clear baselines, ablations, and stress tests. For a developer, the useful follow-up is to map the paper's Control & PlanningControlThe method used to make the robot move the way you want. assumptions onto a concrete Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. stack, then test the smallest version of the method that could run end to end.

RELATED PAPERS