From Universal Humanoid Control to Automatic Physically Valid Character Creation
This work addresses the need for automated character creation in games, movies, and robotics, offering a method to customize humanoid designs for specific motions, though it appears incremental as it builds on existing design-and-control frameworks.
The paper tackles the problem of automatically generating physically valid humanoid bodies customized for specific motions like karate kicks and parkour jumps, by proposing a framework that uses a pre-trained humanoid controller and physics simulation to optimize body designs, resulting in the discovery of new humanoid designs tailored to perform these motions.
Automatically designing virtual humans and humanoids holds great potential in aiding the character creation process in games, movies, and robots. In some cases, a character creator may wish to design a humanoid body customized for certain motions such as karate kicks and parkour jumps. In this work, we propose a humanoid design framework to automatically generate physically valid humanoid bodies conditioned on sequence(s) of pre-specified human motions. First, we learn a generalized humanoid controller trained on a large-scale human motion dataset that features diverse human motion and body shapes. Second, we use a design-and-control framework to optimize a humanoid's physical attributes to find body designs that can better imitate the pre-specified human motion sequence(s). Leveraging the pre-trained humanoid controller and physics simulation as guidance, our method is able to discover new humanoid designs that are customized to perform pre-specified human motions.