Guest
We introduce Berkeley Humanoid, a reliable and low-cost middle- sized humanoid research platform for learning-based control. Our lightweight, in-house-built robot is designed specifically for learning algorithms with low simulation complexity, anthropomorphic motion, and high reliability against falls. Thanks to the narrow sim-to-real gap, our research platform enables state-of-the-art robust outdoor experiments over various terrains with a simple reinforcement learning controller using light domain randomization. Capable of omnidirectional locomotion and withstanding large perturbations with a compact setup, our system aims for scalable, sim-to-real deployment of learning-based humanoid systems. Please check out our website for robot videos and code.
