Researchers from NVIDIA and Carnegie Mellon University are teaching humanoid robots to move like top athletes using artificial intelligence.
The team just introduced a new humanoid robot training framework called ASAP, short for Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills. ASAP was tested in three environments: NVIDIA’s Isaac Gym, Isaac Sym, and a real Unitree G1 humanoid robot.
In their paper, the researchers said the reinforcement learning method made the robot’s movements more natural and reduced errors by more than 50 percent. They said it’s a promising way to make humanoid robots move like real people in the future.
“ASAP enables highly agile motions that were previously difficult to achieve, demonstrating the potential of delta action learning in bridging simulation and real-world dynamics,” the researchers wrote.
The research team used videos of real people doing moves like Cristiano Ronaldo’s celebration jump, Lebron James’s “silencer” pose, and Kobe Bryan’s fadeaway shot. They also taught it dance moves inspired “APT,” the viral hit from K-Pop megastar Rosé. A tool called TRAM converted the videos into 3D motion data to teach the robots.
Jim Fan, who leads NVIDIA’s GR00T project to accelerate humanoid robotics development, said on the X social media platform that ASAP is a “real2sim2real” model that “masters extremely smooth and dynamic motions” for whole-body control.
“We pretrain the robot in simulation first, but there is a notorious ‘real2sim2real’ gap: it’s very difficult for hand-engineered physics equations to match real-world dynamics,” he wrote. “Our fix is simple: just deploy a pretrained policy on real hardware, collect data, and replay the motion in sim.”
The robots trained in simulation first but struggled in the real world because of differences in physics. The motion data included body position, movement, and shape details. They finetuned the data before using it to train G1 AI robots to copy the actions.
“The replay will obviously have many errors, but that gives a rich signal to compensate for the physics discrepancy,” Fan wrote on X. “Use another neural net to learn the delta. Bas
The replay will obviously have many errors, but that gives a rich signal to compensate for the physics discrepancy. Use another neural net to learn the delta. Basically, we “patch up” a traditional physics engine, so that the robot can experience almost the real world at scale in GPUs.
The researchers concluded that humanoid robots can get much better at moving like humans, but there are still big physical limitations. The researchers had to stop testing because of overheating and mechanical failures.
Two robots were damaged during testing because the high-energy movements overheated their motors and stressed hardware.
“Future directions could focus on developing damage-aware policy architectures to mitigate hardware risks,” they wrote.