Integrated Whole-Body Loco-Manipulation Policy for Sliding Heavy Objects with a Single-Arm Quadruped Robot
This paper presents an end-to-end deep reinforcement learning (DRL) framework for integrated whole-body loco-manipulation control of a single-arm quadrupedal robot in contact-rich tasks. A single policy simultaneously controls all 18 joints of a Unitree Go2 robot equipped with a 6-DoF PiPER arm, trained in NVIDIA Isaac...