A new #ScienceRobotics study highlights a reinforcement learning-based, zero-shot approach that uses motion capture and animation to train humanoid and four-legged robots to perform acrobatics. https://scim.ag/4x9V6mC
A new #ScienceRobotics study highlights a reinforcement learning-based, zero-shot approach that uses motion capture and animation to train humanoid and four-legged robots to perform acrobatics. https://scim.ag/4x9V6mC
0 vue
Publié le 07/09/2026 15:46
0:12
A new #ScienceRobotics study highlights a reinforcement learning-based, zero-shot approach that uses motion capture and animation to train humanoid and four-legged robots to perform acrobatics. https://scim.ag/4x9V6mC
0 commentaire
?