Agile perceptive multi-skill locomotion for quadrupedal robots in the wild

Abstract

Enabling quadrupedal robots to traverse complex terrains-from rugged outdoor environments to urban landscapes-requires seamless integration of multiple motor skills, smooth transitions between gaits, and high-speed perceptive locomotion using only onboard sensors. We present APT-RL (Action Pretrained Transformer-based Reinforcement Learning), a unified framework that enables multi-skill locomotion to achieve high-speed traversal in complex environments through autonomous skill transitions utilizing only onboard perception and computation. Our approach generates large-scale, feature-rich 2D motion datasets through trajectory optimization with simplified dynamics. These datasets enable training of diverse, reusable locomotion skills that transfer effectively to a real quadruped robot operating on complex uneven terrains. The resulting high-quality skills serve as strong priors for efficient learning of complex downstream tasks and extend naturally to 3D environments, enabling smooth, high-speed multi-skill locomotion in deployed policy. Real-world experiments demonstrate the framework's capabilities: the robot performs agile maneuvers through complex indoor obstacles and outdoor wild environments, including dynamic drop-down maneuvers that reach instantaneous peak speeds of up to 6 meters per second. A single onboard policy enables robust traversal of diverse obstacles, including stairs, hurdles, stepping stones, gaps, and fallen branches, demonstrating the versatility and effectiveness of our approach.

Project page: https://skillquadsr.github.io/ ,This is the author's version of the work. It is posted here by permission of the AAAS for personal use, not for redistribution. The definitive version was published in Science Robotics on 7.15.2026; doi: 10.1126/scirobotics.adz7397. Jun-Gill Kang and Jaehyun Park are co-first authors. Seungwoo Hong and Hae-Won Park are co-corresponding authors

References in corpus (12)

• Learning agile and dynamic motor skills for legged robots
• Learning robust perceptive locomotion for quadrupedal robots in the wild
• AMP: Adversarial Motion Priors for Stylized Physics-Based Character Control
• ASE: Large-Scale Reusable Adversarial Skill Embeddings for Physically Simulated Characters
• Multi-expert learning of adaptive legged locomotion
• Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotion
• Representation-Free Model Predictive Control for Dynamic Motions in Quadrupeds
• DTC: Deep Tracking Control
• Lifelike Agility and Play in Quadrupedal Robots using Reinforcement Learning and Generative Pre-trained Models
• RL + Model-based Control: Using On-demand Optimal Control to Learn Versatile Legged Locomotion
• Contact-Implicit Model Predictive Control: Controlling Diverse Quadruped Motions Without Pre-Planned Contact Modes or Trajectories
• DreamWaQ++: Obstacle-Aware Quadrupedal Locomotion With Resilient Multi-Modal Reinforcement Learning