Robust quadruped jumping via deep reinforcement learning

Guillaume Bellegarda, Chuong Nguyen, Quan Nguyen

Abstract: Highlights•Deep reinforcement learning gives quadruped robots robust jumping skills.•Trajectory optimization can be improved with deep reinforcement learning.•Modeling motor dynamics and power constraints allows successful sim-to-real control.•Robust jumping with large uncertainties in friction, mass, and uneven terrain.

External IDs:doi:10.1016/j.robot.2024.104799