About this document
Paper Ask1 Arxiv by luyx0311 is a document available to read on EtoBox.
This document discusses the design and development of a custom quadruped robot, Ask1, which utilizes reinforcement learning (RL) for control without relying on Adversarial Motion Priors (AMP) or reference trajectories. The authors demonstrate the effectiveness of their novel reward function and RL algorithm through simulations and real-world experiments, showing that Ask1 can navigate various terrains similarly to the Unitree Go1 robot. The paper details the robot
- Author
- luyx0311
- Language
- EN