Add to Favourites
To login click here
A team of researchers has proposed a solution inspired by the generalization achieved by pretraining large vision or language models on diverse data, known as X-embodiment training, to overcome the obstacles in robotics and move towards a massive data regime akin to what has worked in other fields. The team has shared their Open X-Embodiment (OXE) Repository, which includes a dataset featuring 22 different robotic embodiments from 21 institutions, along with open-source tools to facilitate further research on X-embodiment models.