LOCOMOTIONCURRENT2026-05-25

ParkourFormer: Integrating Predictive Supervision and Sequence Modeling into Parkour Locomotion

Yanheng Mai, Wenhao Xu, Zirui Huang, Yifei Fu, Shengwei Dong, Xinjue Wang, Kailun Huang, Yanzhe Xie, Renjing Xu

This shows how to build a humanoid Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. that autonomously navigates complex terrain (stairs, gaps, obstacles) by predicting its own future body Core ConceptsStateThe robot’s current condition, such as joint positions, velocity, object positions, or internal variables.—achieving 94% success on parkour tasks with a single unified Core ConceptsPolicyThe rule or model that maps observations or states to actions.. Instead of Control & PlanningReactive controlControl that responds immediately to sensor input or disturbances., the Core ConceptsPolicyThe rule or model that maps observations or states to actions. explicitly anticipates upcoming Movement, Mechanics & Robot BodyContactPhysical interaction between the robot and an object or surface. and Movement, Mechanics & Robot BodyDynamicsThe study of motion including forces, torques, mass, and inertia., which is critical for agile movements where Control & PlanningPlanningFiguring out what the robot should do before or during movement. ahead matters more than reflexive responses.

THE PROBLEM

This paper focuses on Navigation & LocomotionLocomotionMovement of the robot body through space, like walking, rolling, or running.. This shows how to build a humanoid Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. that autonomously navigates complex terrain (stairs, gaps, obstacles) by predicting its own future body Core ConceptsStateThe robot’s current condition, such as joint positions, velocity, object positions, or internal variables.—achieving 94% success on parkour tasks with a single unified Core ConceptsPolicyThe rule or model that maps observations or states to actions.. Instead of Control & PlanningReactive controlControl that responds immediately to sensor input or disturbances., the Core ConceptsPolicyThe rule or model that maps observations or states to actions. explicitly anticipates upcoming Movement, Mechanics & Robot BodyContactPhysical interaction between the robot and an object or surface. and Movement, Mechanics & Robot BodyDynamicsThe study of motion including forces, torques, mass, and inertia., which is critical for agile movements where Control & PlanningPlanningFiguring out what the robot should do before or during movement. ahead matters more than reflexive responses. 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 Navigation & LocomotionLocomotionMovement of the robot body through space, like walking, rolling, or running.. Start here because it defines what success means and which assumptions the rest of the method inherits.

2

Core method

This shows how to build a humanoid Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. that autonomously navigates complex terrain (stairs, gaps, obstacles) by predicting its own future body Core ConceptsStateThe robot’s current condition, such as joint positions, velocity, object positions, or internal variables.—achieving 94% success on parkour tasks with a single unified Core ConceptsPolicyThe rule or model that maps observations or states to actions.. Instead of Control & PlanningReactive controlControl that responds immediately to sensor input or disturbances., the Core ConceptsPolicyThe rule or model that maps observations or states to actions. explicitly anticipates upcoming Movement, Mechanics & Robot BodyContactPhysical interaction between the robot and an object or surface. and Movement, Mechanics & Robot BodyDynamicsThe study of motion including forces, torques, mass, and inertia., which is critical for agile movements where Control & PlanningPlanningFiguring out what the robot should do before or during movement. ahead matters more than reflexive responses. 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 shows how to build a humanoid Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. that autonomously navigates complex terrain (stairs, gaps, obstacles) by predicting its own future body Core ConceptsStateThe robot’s current condition, such as joint positions, velocity, object positions, or internal variables.—achieving 94% success on parkour tasks with a single unified Core ConceptsPolicyThe rule or model that maps observations or states to actions.. Instead of Control & PlanningReactive controlControl that responds immediately to sensor input or disturbances., the Core ConceptsPolicyThe rule or model that maps observations or states to actions. explicitly anticipates upcoming Movement, Mechanics & Robot BodyContactPhysical interaction between the robot and an object or surface. and Movement, Mechanics & Robot BodyDynamicsThe study of motion including forces, torques, mass, and inertia., which is critical for agile movements where Control & PlanningPlanningFiguring out what the robot should do before or during movement. ahead matters more than reflexive responses.

WHY DEVELOPERS SHOULD CARE

This shows how to build a humanoid Core ConceptsRobotA physical system with sensors and actuators that can observe the world and take actions. that autonomously navigates complex terrain (stairs, gaps, obstacles) by predicting its own future body Core ConceptsStateThe robot’s current condition, such as joint positions, velocity, object positions, or internal variables.—achieving 94% success on parkour tasks with a single unified Core ConceptsPolicyThe rule or model that maps observations or states to actions.. Instead of Control & PlanningReactive controlControl that responds immediately to sensor input or disturbances., the Core ConceptsPolicyThe rule or model that maps observations or states to actions. explicitly anticipates upcoming Movement, Mechanics & Robot BodyContactPhysical interaction between the robot and an object or surface. and Movement, Mechanics & Robot BodyDynamicsThe study of motion including forces, torques, mass, and inertia., which is critical for agile movements where Control & PlanningPlanningFiguring out what the robot should do before or during movement. ahead matters more than reflexive responses.

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 Navigation & LocomotionLocomotionMovement of the robot body through space, like walking, rolling, or running. 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