Learning Getting-Up Policies for Real-World Humanoid Robots

UP provides a simple and general two-stage training method for humanoid getting-up tasks, which can be directly deployed on Unitree G1 humanoid robots [70]. Our policies showcase robust and smooth behavior that can get up from diverse lying postures (both supine and prone) on varied terrains such as grass slopes and stone tile. Abstract--Automatic fall recovery is a crucial prerequisite robust to variations in initial configuration and terrains. We find before humanoid robots can be reliably deployed. Hand-designing these innovations enable a real-world G1 humanoid robot to get controllers for getting up is difficult because of the varied up from two main situations that we considered: a) lying face up configurations a humanoid can end up in after a fall and the and b) lying face down, both tested on flat, deformable, slippery challenging terrains humanoid robots are expected to operate surfaces and slopes (e.g., sloppy grass and snowfield). This paper develops a learning framework to produce of our knowledge, this is the first successful demonstration of controllers that enable humanoid robots to get up from varying learned getting-up policies for human-sized humanoid robots in configurations on varying terrains. Stage II is optimized to track the robots), a humanoid robot may end up in an unpredictable state trajectory discovered in the first stage to tackle easier configuration upon a fall, or may be on an unknown terrain.