Open access
Jul 2026
Agile perceptive multiskill locomotion for quadrupedal robots in the wild
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, is presented.
Jun-Gill Kang, Jaehyun Park, Tae-Gyu Song et al.
· Sci. Robotics · 1 citation