Search papers, labs, and topics across Lattice.
This paper introduces APT-RL, a novel framework that integrates action-pretrained transformer-based reinforcement learning to enable quadrupedal robots to navigate complex terrains with high-speed, multiskill locomotion using only onboard sensors. By generating extensive 2D motion datasets through trajectory optimization, the method equips robots with diverse locomotion skills that effectively transfer to real-world scenarios, allowing for agile maneuvers in both indoor and outdoor environments. Experimental results show that the robots achieved peak speeds of 6 meters per second while successfully traversing various obstacles, highlighting the framework's versatility and effectiveness in real-world applications.
Quadrupedal robots can now achieve high-speed, agile locomotion across complex terrains using a single onboard policy, reaching speeds of 6 meters per second.
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 multiskill locomotion to achieve high-speed traversal in complex environments through autonomous skill transitions using only onboard perception and computation. Our approach generates large-scale, feature-rich two-dimensional (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 multiskill locomotion in deployed policy. Real-world experiments demonstrate the framework's capabilities: The robot performed agile maneuvers through complex indoor obstacles and outdoor wild environments, including dynamic drop-down maneuvers that reached instantaneous peak speeds of up to 6 meters per second. A single onboard policy enabled robust traversal of diverse obstacles, including stairs, hurdles, stepping stones, gaps, and fallen branches, demonstrating the versatility and effectiveness of our approach.
