TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkour

arXiv:2602.02331 · cs.RO, cs.AI · Submitted 2026-02-02 · Read on arXiv

cs.RO, cs.AI

Submitted: 2026-02-02

Updated: 2026-10-13

Code: https://github.com/1xtechnologies/wb

Project page: https://tttparkour.github.io

Terminology

• Fidelity — 2× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Sim-to-Real Transfer — 1× in this paper · explained in 2 episodes

Sources

• The Surprising Effectiveness of Test-Time Training for Few-Shot Learning
• Test-time Offline Reinforcement Learning on Goal-related Experience
• Titans: Learning to Memorize at Test Time
• Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3D Constrained Terrains
• NeRF2Real: Sim2real Transfer of Vision-guided Bipedal Motion Skills using Neural Radiance Fields
• Mirage: Cross-Embodiment Zero-Shot Policy Transfer with Cross-Painting
• SAM 3D: 3Dfy Anything in Images
• GaussGym: An open-source real-to-sim framework for learning locomotion from pixels
• Advancing Humanoid Locomotion: Mastering Challenging Terrains with Denoising World Model Learning
• Re$^3$Sim: Generating High-Fidelity Simulation Data via 3D-Photorealistic Real-to-Sim for Robotic Manipulation
• Emergence of Locomotion Behaviours in Rich Environments
• Flexible Locomotion Learning with Diffusion Model Predictive Control
• MoE-Loco: Mixture of Experts for Multitask Locomotion
• Planning with Diffusion for Flexible Behavior Synthesis
• MapAnything: Universal Feed-Forward Metric 3D Reconstruction
• RMA: Rapid Motor Adaptation for Legged Robots
• RoboGSim: A Real2Sim2Real Robotic Gaussian Splatting Simulator
• SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining
• Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding
• BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies