← Back to Benchmarks
simmediummanipulation-datametric · varies
OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learning
Description
Large and diverse datasets are needed for training generalist robot policies that have potential to control a variety of robot embodiments -- robot arm and gripper combinations -- across diverse tasks and environments. As re-collecting demonstrations and retraining for each new hardware platform are prohibitively costly, we show that existing robot data can be augmented for transfer and generalization. The Open X-Embodiment (OXE) dataset, which aggregates demonstrations from over 60 robot datase