Search papers, labs, and topics across Lattice.
This paper introduces APT-RL, a novel framework that leverages Action Pretrained Transformers for reinforcement learning to enable quadrupedal robots to autonomously transition between multiple locomotion skills in complex environments. By generating large-scale 2D motion datasets through trajectory optimization, the approach trains versatile locomotion skills that effectively transfer to real-world scenarios, allowing robots to navigate rugged terrains and urban landscapes at high speeds. Experimental results show that the robots can perform agile maneuvers and reach speeds of up to 6 meters per second while overcoming various obstacles, highlighting the framework's practical applicability and robustness.
Quadrupedal robots can now achieve high-speed, agile locomotion across diverse terrains using a single onboard policy that seamlessly integrates multiple motor skills.
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.
