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

• URL: http://arxiv.org/abs/2602.02331v1
• Date: Mon, 02 Feb 2026 16:55:10 GMT
• Title: TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkour
• Abstract summary: We propose a real-to-sim-to-real framework for humanoid robot parkour.<n>A policy is first pre-trained on procedurally generated terrains, followed by rapid fine-tuning on high-fidelity meshes reconstructed from real-world captures.<n>We demonstrate that TTT-Parkour empowers humanoid robots to master complex obstacles, including wedges, stakes, boxes, trapezoids, and narrow beams.
• Score: 29.110035197783162
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Achieving highly dynamic humanoid parkour on unseen, complex terrains remains a challenge in robotics. Although general locomotion policies demonstrate capabilities across broad terrain distributions, they often struggle with arbitrary and highly challenging environments. To overcome this limitation, we propose a real-to-sim-to-real framework that leverages rapid test-time training (TTT) on novel terrains, significantly enhancing the robot's capability to traverse extremely difficult geometries. We adopt a two-stage end-to-end learning paradigm: a policy is first pre-trained on diverse procedurally generated terrains, followed by rapid fine-tuning on high-fidelity meshes reconstructed from real-world captures. Specifically, we develop a feed-forward, efficient, and high-fidelity geometry reconstruction pipeline using RGB-D inputs, ensuring both speed and quality during test-time training. We demonstrate that TTT-Parkour empowers humanoid robots to master complex obstacles, including wedges, stakes, boxes, trapezoids, and narrow beams. The whole pipeline of capturing, reconstructing, and test-time training requires less than 10 minutes on most tested terrains. Extensive experiments show that the policy after test-time training exhibits robust zero-shot sim-to-real transfer capability.

Related papers

• Agile perceptive multi-skill locomotion for quadrupedal robots in the wild [4.14240816913171]
  APT-RL (Action Pretrained Transformer-based Reinforcement Learning) is a unified framework that enables multi-skill locomotion.<n>Our approach generates large-scale, feature-rich 2D motion datasets through trajectory optimization with simplified dynamics.<n>The resulting high-quality skills serve as strong priors for efficient learning of complex downstream tasks and extend naturally to 3D environments.
  arXiv  Detail & Related papers  (2026-07-15T08:22:52Z)
• Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching [77.28042137892943]
  We present Perceptive Humanoid Parkour (PHP), a modular framework that enables humanoid robots to autonomously perform long-horizon, vision-based parkour.<n>We train motion-tracking reinforcement learning expert policies for these composed motions, and distill them into a single depth-based, multi-skill student policy.<n>We validate our framework with extensive real-world experiments on a Unitree G1 humanoid robot.
  arXiv  Detail & Related papers  (2026-02-17T18:59:11Z)
• PUMA: Perception-driven Unified Foothold Prior for Mobility Augmented Quadruped Parkour [18.593929869124864]
  Parkour tasks for quadrupeds have emerged as a promising benchmark for agile locomotion.<n>We present PUMA, an end-to-end learning framework that integrates visual perception and foothold priors into a single-stage training process.
  arXiv  Detail & Related papers  (2026-01-22T14:16:12Z)
• Gait-Adaptive Perceptive Humanoid Locomotion with Real-Time Under-Base Terrain Reconstruction [86.53248703859718]
  We introduce a perceptive locomotion framework that merges terrain sensing, gait regulation, and whole-body control into a single reinforcement learning policy.<n>Experiments conducted on a 31-DoF, 1.65 m humanoid robot demonstrate robust locomotion in both simulation and real-world settings.
  arXiv  Detail & Related papers  (2025-12-08T11:42:41Z)
• Learning Sim-to-Real Humanoid Locomotion in 15 Minutes [51.500643119683225]
  We introduce a simple and practical recipe based on off-policy RL algorithms, i.e., FastSAC and FastTD3.<n>Our simple recipe stabilizes off-policy RL algorithms at massive scale with thousands of parallel environments.<n>We demonstrate rapid end-to-end learning of humanoid locomotion controllers on Unitree G1 and Booster T1 robots.
  arXiv  Detail & Related papers  (2025-12-01T18:55:17Z)
• BeamDojo: Learning Agile Humanoid Locomotion on Sparse Footholds [35.62230804783507]
  Existing learning-based approaches often struggle on complex terrains due to sparse foothold rewards and inefficient learning processes.<n>We introduce BeamDojo, a reinforcement learning framework designed for enabling agile humanoid locomotion on sparse footholds.<n>We show that BeamDojo achieves efficient learning in simulation and enables agile locomotion with precise foot placement on sparse footholds in the real world.
  arXiv  Detail & Related papers  (2025-02-14T18:42:42Z)
• Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control [106.32794844077534]
  This paper presents a study on using deep reinforcement learning to create dynamic locomotion controllers for bipedal robots. We develop a general control solution that can be used for a range of dynamic bipedal skills, from periodic walking and running to aperiodic jumping and standing. This work pushes the limits of agility for bipedal robots through extensive real-world experiments.
  arXiv  Detail & Related papers  (2024-01-30T10:48:43Z)
• Robot Parkour Learning [70.56172796132368]
  Parkour is a grand challenge for legged locomotion that requires robots to overcome various obstacles rapidly. We develop a reinforcement learning method inspired by direct collocation to generate parkour skills. We distill these skills into a single vision-based parkour policy and transfer it to a quadrupedal robot using its egocentric depth camera.
  arXiv  Detail & Related papers  (2023-09-11T17:59:17Z)
• Learning Robust, Agile, Natural Legged Locomotion Skills in the Wild [17.336553501547282]
  We propose a new framework for learning robust, agile and natural legged locomotion skills over challenging terrain. Empirical results on both simulation and real world of a quadruped robot demonstrate that our proposed algorithm enables robustly traversing challenging terrains.
  arXiv  Detail & Related papers  (2023-04-21T11:09:23Z)
• Learning and Adapting Agile Locomotion Skills by Transferring Experience [71.8926510772552]
  We propose a framework for training complex robotic skills by transferring experience from existing controllers to jumpstart learning new tasks. We show that our method enables learning complex agile jumping behaviors, navigating to goal locations while walking on hind legs, and adapting to new environments.
  arXiv  Detail & Related papers  (2023-04-19T17:37:54Z)
• Robust and Versatile Bipedal Jumping Control through Reinforcement Learning [141.56016556936865]
  This work aims to push the limits of agility for bipedal robots by enabling a torque-controlled bipedal robot to perform robust and versatile dynamic jumps in the real world. We present a reinforcement learning framework for training a robot to accomplish a large variety of jumping tasks, such as jumping to different locations and directions. We develop a new policy structure that encodes the robot's long-term input/output (I/O) history while also providing direct access to a short-term I/O history.
  arXiv  Detail & Related papers  (2023-02-19T01:06:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.