6 terms
An embodied agent is an AI system with a physical or simulated body that perceives, decides and acts through sensors and actuators in a real environment.
Imitation learning trains a robot policy from expert demonstrations, letting embodied AI systems acquire skills without hand-written rewards or code.
Physical AI is artificial intelligence that perceives, reasons about and acts in the physical world through robots, vehicles and other machines.
Sim-to-real is the practice of training robot policies in simulation and transferring them to physical robots while closing the gap between both worlds.
A vision-language-action model is a robot policy that maps camera images and a natural-language instruction directly to motor actions in embodied AI.
A world model in embodied AI is a learned internal model that predicts how a robot's environment will change in response to its actions.