The main innovation of this model is the ability to adapt movements for various types of body, from humanoid robots to four -legged ones. This allows you to produce movements for many robots, regardless of its shapes and properties.
According to Sudarshan Map, one of the researchers, they see the movement as a language that can be “translated from English to Chinese, for example, as in the texts. This opens new opportunities for many applications from interaction with robots to use in virtual reality.
The study is already presented on the Arxiv server and will be shown at the International Robotics and Automation Conference this month. The model has been examined in two data sets containing detailed additional explanations of people and robots.
Motionglot not only reproduces movements according to text instructions, but can also adapt them to various numbers. For example, the “Show for Cardio Treking” team will cause a model that produces the image of a person working. This offers extensive opportunities for the development of applications in the field of robotics, video games and animations.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
