[RL] Quadruped Blind Trot Speed Test with Reinforcement Learning in "MiniPongBot"
Due to the limitations of the treadmill,
the maximum speed was 1.564 m/s
Zero-shot sim2real Experiment
As input to the neural network, Encoders and IMU information are used.
(External observation sensors such as cameras, lidar, and depth cameras, etc. were not used.
all computations are performed on the robot's internal CPU (without GPU)