HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining
For embodied AI researchers, this work demonstrates that scalable and low-cost egocentric video can outperform expensive real-robot data for pretraining, offering a new paradigm for data collection.
The paper investigates whether egocentric human video can replace teleoperated real-robot data for pretraining embodied foundation models. Surprisingly, models pretrained on egocentric data achieve 24% lower validation loss on real-robot action prediction and 52.5% higher in-distribution and 90% higher out-of-distribution success rates compared to those pretrained on real-robot data.
Embodied foundation models are expected to benefit from data scaling like large language models, but face a much tighter data bottleneck. Teleoperated real-robot trajectories remain the dominant pretraining source due to their precise action supervision and embodiment alignment, yet their scalability is limited by high collection cost, acquisition difficulty, and low behavioral and environmental diversity. These limitations have sparked interest in egocentric human video as a scalable, substantially lower-cost, and more diverse alternative for embodied model pretraining. However, its effectiveness compared to teleoperated real-robot data remains underexplored. To address this question, we conduct a systematic study comparing egocentric human video and teleoperated real-robot trajectories as pretraining data sources for embodied foundation models, under fixed post-training and validation protocols. Surprisingly, we find that egocentric data, when processed through a carefully designed filtering and labeling pipeline, is not merely a viable substitute for model pretraining but can lead to superior performance. With the same amount of pretraining data, models pretrained on egocentric data achieve a 24% lower validation loss on real-robot action prediction, as well as 52.5% and 90% higher success rates on in-distribution and out-of-distribution real-robot task execution, respectively. This finding verifies a scalable paradigm for embodied foundation models: pretrain on egocentric human video to learn diverse world representations, then adapt with a small amount of labeled real-robot data for action-space alignment. We hope this study encourages broader exploration of egocentric data and offers guidance for data quality assessment before costly robot data collection.