Ask1: Development and Reinforcement Learning-Based Control of a Custom Quadruped Robot
This work addresses the challenge of applying reinforcement learning to custom quadruped robots for real-world locomotion, but it is incremental as it builds on existing methods with modifications for a specific robot.
The researchers tackled the problem of controlling a custom quadruped robot by developing a reinforcement learning-based method with a novel reward function, eliminating the need for Adversarial Motion Priors and reference trajectories, and demonstrated its effectiveness in simulation and real-world experiments, showing the robot could navigate rugged terrains.
In this work, we present the design, development, and experimental validation of a custom-built quadruped robot, Ask1. The Ask1 robot shares similar morphology with the Unitree Go1, but features custom hardware components and a different control architecture. We transfer and extend previous reinforcement learning (RL)-based control methods to the Ask1 robot, demonstrating the applicability of our approach in real-world scenarios. By eliminating the need for Adversarial Motion Priors (AMP) and reference trajectories, we introduce a novel reward function to guide the robot's motion style. We demonstrate the generalization capability of the proposed RL algorithm by training it on both the Go1 and Ask1 robots. Simulation and real-world experiments validate the effectiveness of this method, showing that Ask1, like the Go1, is capable of navigating various rugged terrains.