VLACURRENT2026-06-17

Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement

Kinam Kim, Namiko Saito, Heecheol Kim, Katsushi Ikeuchi, Jaegul Choo, Yasuyuki Matsushita

This paper shows you can boost a frozen Modern Robot LearningVision-Language-Action model (VLA)A model that takes images and language as input and outputs robot actions. model's real-world performance from 42% to 76% success by Robot LearningTrainingThe process of fitting a model using data or experience. a corrective Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. Core ConceptsPolicyThe rule or model that maps observations or states to actions. in Simulation & Sim-to-RealSimulationA virtual environment where robots can be trained or tested. using object poses as the Core ConceptsObservationThe information the robot receives from sensors, such as images, depth, touch, or joint readings. space, then deploying Modern Robot LearningZero-shotDoing a new task without task-specific training. to a real Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. without any real-world Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards.. The key trick is using pose-based observations instead of images to avoid the visual domain gap, making Simulation & Sim-to-RealSim-to-real (sim2real)Transferring a policy trained in simulation to a real robot. transfer reliable.

THE PROBLEM

This paper focuses on Modern Robot LearningVision-Language-Action model (VLA)A model that takes images and language as input and outputs robot actions.. This paper shows you can boost a frozen Modern Robot LearningVision-Language-Action model (VLA)A model that takes images and language as input and outputs robot actions. model's real-world performance from 42% to 76% success by Robot LearningTrainingThe process of fitting a model using data or experience. a corrective Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. Core ConceptsPolicyThe rule or model that maps observations or states to actions. in Simulation & Sim-to-RealSimulationA virtual environment where robots can be trained or tested. using object poses as the Core ConceptsObservationThe information the robot receives from sensors, such as images, depth, touch, or joint readings. space, then deploying Modern Robot LearningZero-shotDoing a new task without task-specific training. to a real Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. without any real-world Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards.. The key trick is using pose-based observations instead of images to avoid the visual domain gap, making Simulation & Sim-to-RealSim-to-real (sim2real)Transferring a policy trained in simulation to a real robot. transfer reliable. 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 Modern Robot LearningVision-Language-Action model (VLA)A model that takes images and language as input and outputs robot actions.. Start here because it defines what success means and which assumptions the rest of the method inherits.

2

Core method

This paper shows you can boost a frozen Modern Robot LearningVision-Language-Action model (VLA)A model that takes images and language as input and outputs robot actions. model's real-world performance from 42% to 76% success by Robot LearningTrainingThe process of fitting a model using data or experience. a corrective Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. Core ConceptsPolicyThe rule or model that maps observations or states to actions. in Simulation & Sim-to-RealSimulationA virtual environment where robots can be trained or tested. using object poses as the Core ConceptsObservationThe information the robot receives from sensors, such as images, depth, touch, or joint readings. space, then deploying Modern Robot LearningZero-shotDoing a new task without task-specific training. to a real Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. without any real-world Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards.. The key trick is using pose-based observations instead of images to avoid the visual domain gap, making Simulation & Sim-to-RealSim-to-real (sim2real)Transferring a policy trained in simulation to a real robot. transfer reliable. 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 shows you can boost a frozen Modern Robot LearningVision-Language-Action model (VLA)A model that takes images and language as input and outputs robot actions. model's real-world performance from 42% to 76% success by Robot LearningTrainingThe process of fitting a model using data or experience. a corrective Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. Core ConceptsPolicyThe rule or model that maps observations or states to actions. in Simulation & Sim-to-RealSimulationA virtual environment where robots can be trained or tested. using object poses as the Core ConceptsObservationThe information the robot receives from sensors, such as images, depth, touch, or joint readings. space, then deploying Modern Robot LearningZero-shotDoing a new task without task-specific training. to a real Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. without any real-world Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards.. The key trick is using pose-based observations instead of images to avoid the visual domain gap, making Simulation & Sim-to-RealSim-to-real (sim2real)Transferring a policy trained in simulation to a real robot. transfer reliable.

WHY DEVELOPERS SHOULD CARE

This paper shows you can boost a frozen Modern Robot LearningVision-Language-Action model (VLA)A model that takes images and language as input and outputs robot actions. model's real-world performance from 42% to 76% success by Robot LearningTrainingThe process of fitting a model using data or experience. a corrective Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards. Core ConceptsPolicyThe rule or model that maps observations or states to actions. in Simulation & Sim-to-RealSimulationA virtual environment where robots can be trained or tested. using object poses as the Core ConceptsObservationThe information the robot receives from sensors, such as images, depth, touch, or joint readings. space, then deploying Modern Robot LearningZero-shotDoing a new task without task-specific training. to a real Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. without any real-world Imitation & Reinforcement LearningReinforcement Learning (RL)Teaching a robot through trial and error using rewards.. The key trick is using pose-based observations instead of images to avoid the visual domain gap, making Simulation & Sim-to-RealSim-to-real (sim2real)Transferring a policy trained in simulation to a real robot. transfer reliable.

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 Modern Robot LearningVision-Language-Action model (VLA)A model that takes images and language as input and outputs robot actions. 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