CONTROL2026-04-14

Synthesis and Deployment of Maximal Robust Control Barrier Functions through Adversarial Reinforcement Learning

Donggeon David Oh, Duy P. Nguyen, Haimin Hu, Jaime Fernández Fisac

This paper solves a critical robotics problem: how to guarantee a Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. stays safe even when things go wrong (worst-case disturbances) without needing to manually specify system Movement, Mechanics & Robot BodyDynamicsThe study of motion including forces, torques, mass, and inertia.. Instead of requiring engineers to write down explicit mathematical models, the approach uses Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. to learn safety constraints that work on real systems with unknown or black-box Movement, Mechanics & Robot BodyDynamicsThe study of motion including forces, torques, mass, and inertia.. The key innovation is combining Control & PlanningControlThe method used to make the robot move the way you want. barrier functions (mathematical safety certificates) with Q-learning (a Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. technique) to create robust safety filters that can be deployed on complex robots like quadrupeds. This matters because real robots are unpredictable, and this method provides formal safety guarantees while being practical for systems where you don't have a perfect model.

THE PROBLEM

This paper focuses on Control & PlanningControlThe method used to make the robot move the way you want.. This paper solves a critical robotics problem: how to guarantee a Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. stays safe even when things go wrong (worst-case disturbances) without needing to manually specify system Movement, Mechanics & Robot BodyDynamicsThe study of motion including forces, torques, mass, and inertia.. Instead of requiring engineers to write down explicit mathematical models, the approach uses Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. to learn safety constraints that work on real systems with unknown or black-box Movement, Mechanics & Robot BodyDynamicsThe study of motion including forces, torques, mass, and inertia.. The key innovation is combining Control & PlanningControlThe method used to make the robot move the way you want. barrier functions (mathematical safety certificates) with Q-learning (a Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. technique) to create robust safety filters that can be deployed on complex robots like quadrupeds. This matters because real robots are unpredictable, and this method provides formal safety guarantees while being practical for systems where you don't have a perfect model. 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 solves a critical robotics problem: how to guarantee a Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. stays safe even when things go wrong (worst-case disturbances) without needing to manually specify system Movement, Mechanics & Robot BodyDynamicsThe study of motion including forces, torques, mass, and inertia.. Instead of requiring engineers to write down explicit mathematical models, the approach uses Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. to learn safety constraints that work on real systems with unknown or black-box Movement, Mechanics & Robot BodyDynamicsThe study of motion including forces, torques, mass, and inertia.. The key innovation is combining Control & PlanningControlThe method used to make the robot move the way you want. barrier functions (mathematical safety certificates) with Q-learning (a Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. technique) to create robust safety filters that can be deployed on complex robots like quadrupeds. This matters because real robots are unpredictable, and this method provides formal safety guarantees while being practical for systems where you don't have a perfect model. 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.

KEY RESULTS

Main contributionConceptual contribution

This paper solves a critical robotics problem: how to guarantee a Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. stays safe even when things go wrong (worst-case disturbances) without needing to manually specify system Movement, Mechanics & Robot BodyDynamicsThe study of motion including forces, torques, mass, and inertia.. Instead of requiring engineers to write down explicit mathematical models, the approach uses Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. to learn safety constraints that work on real systems with unknown or black-box Movement, Mechanics & Robot BodyDynamicsThe study of motion including forces, torques, mass, and inertia.. The key innovation is combining Control & PlanningControlThe method used to make the robot move the way you want. barrier functions (mathematical safety certificates) with Q-learning (a Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. technique) to create robust safety filters that can be deployed on complex robots like quadrupeds. This matters because real robots are unpredictable, and this method provides formal safety guarantees while being practical for systems where you don't have a perfect model.

WHY DEVELOPERS SHOULD CARE

This paper solves a critical robotics problem: how to guarantee a Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. stays safe even when things go wrong (worst-case disturbances) without needing to manually specify system Movement, Mechanics & Robot BodyDynamicsThe study of motion including forces, torques, mass, and inertia.. Instead of requiring engineers to write down explicit mathematical models, the approach uses Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. to learn safety constraints that work on real systems with unknown or black-box Movement, Mechanics & Robot BodyDynamicsThe study of motion including forces, torques, mass, and inertia.. The key innovation is combining Control & PlanningControlThe method used to make the robot move the way you want. barrier functions (mathematical safety certificates) with Q-learning (a Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. technique) to create robust safety filters that can be deployed on complex robots like quadrupeds. This matters because real robots are unpredictable, and this method provides formal safety guarantees while being practical for systems where you don't have a perfect model.

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