TASK-PLANNINGCURRENT2026-05-29

On-Device Robotic Planning: Eliminating Inference Redundancy for Efficient Decision-Making

Joonhee Lee, Hyunseung Shin, Hyunmi Kim, Pei Zhang, Jeonggil Ko

REIS cuts Robot LearningInferenceUsing a trained model to make predictions or choose actions. Simulation & Sim-to-RealLatencyDelay between input, computation, and action. for LLM/VLM-based robotic policies by ~50% or more by skipping redundant reasoning steps when consecutive frames would produce the same Core ConceptsActionA command the robot sends to its motors, controller, or low-level system.. This makes real-time Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. Control & PlanningControlThe method used to make the robot move the way you want. feasible on edge devices without sacrificing semantic Control & PlanningPlanningFiguring out what the robot should do before or during movement. capability—you get fast, smart decision-making instead of choosing between speed and reasoning.

THE PROBLEM

This paper focuses on Core ConceptsTaskThe job the robot is supposed to complete, such as pick-and-place, navigation, or drawer opening. Control & PlanningPlanningFiguring out what the robot should do before or during movement.. REIS cuts Robot LearningInferenceUsing a trained model to make predictions or choose actions. Simulation & Sim-to-RealLatencyDelay between input, computation, and action. for LLM/VLM-based robotic policies by ~50% or more by skipping redundant reasoning steps when consecutive frames would produce the same Core ConceptsActionA command the robot sends to its motors, controller, or low-level system.. This makes real-time Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. Control & PlanningControlThe method used to make the robot move the way you want. feasible on edge devices without sacrificing semantic Control & PlanningPlanningFiguring out what the robot should do before or during movement. capability—you get fast, smart decision-making instead of choosing between speed and reasoning. 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 Core ConceptsTaskThe job the robot is supposed to complete, such as pick-and-place, navigation, or drawer opening. Control & PlanningPlanningFiguring out what the robot should do before or during movement.. Start here because it defines what success means and which assumptions the rest of the method inherits.

2

Core method

REIS cuts Robot LearningInferenceUsing a trained model to make predictions or choose actions. Simulation & Sim-to-RealLatencyDelay between input, computation, and action. for LLM/VLM-based robotic policies by ~50% or more by skipping redundant reasoning steps when consecutive frames would produce the same Core ConceptsActionA command the robot sends to its motors, controller, or low-level system.. This makes real-time Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. Control & PlanningControlThe method used to make the robot move the way you want. feasible on edge devices without sacrificing semantic Control & PlanningPlanningFiguring out what the robot should do before or during movement. capability—you get fast, smart decision-making instead of choosing between speed and reasoning. 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

REIS cuts Robot LearningInferenceUsing a trained model to make predictions or choose actions. Simulation & Sim-to-RealLatencyDelay between input, computation, and action. for LLM/VLM-based robotic policies by ~50% or more by skipping redundant reasoning steps when consecutive frames would produce the same Core ConceptsActionA command the robot sends to its motors, controller, or low-level system.. This makes real-time Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. Control & PlanningControlThe method used to make the robot move the way you want. feasible on edge devices without sacrificing semantic Control & PlanningPlanningFiguring out what the robot should do before or during movement. capability—you get fast, smart decision-making instead of choosing between speed and reasoning.

WHY DEVELOPERS SHOULD CARE

REIS cuts Robot LearningInferenceUsing a trained model to make predictions or choose actions. Simulation & Sim-to-RealLatencyDelay between input, computation, and action. for LLM/VLM-based robotic policies by ~50% or more by skipping redundant reasoning steps when consecutive frames would produce the same Core ConceptsActionA command the robot sends to its motors, controller, or low-level system.. This makes real-time Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. Control & PlanningControlThe method used to make the robot move the way you want. feasible on edge devices without sacrificing semantic Control & PlanningPlanningFiguring out what the robot should do before or during movement. capability—you get fast, smart decision-making instead of choosing between speed and reasoning.

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 Core ConceptsTaskThe job the robot is supposed to complete, such as pick-and-place, navigation, or drawer opening. Control & PlanningPlanningFiguring out what the robot should do before or during movement. 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