Robotics: Science and Systems XXI

Robot Learning with Super-Linear Scaling

Marcel Torne Villasevil, Arhan Jain, Jiayi Yuan, Vidyaaranya Macha, Lars Lien Ankile, Anthony Simeonov, Pulkit Agrawal, Abhishek Gupta

Abstract:

Scaling robot learning requires data collection pipelines that scale favorably with human effort. In this work, we propose *Crowdsourcing and Amortizing Human Effort for Real-to-Sim-to-Real* (**CASHER**), a pipeline for scaling up data collection and learning in simulation where the performance scales superlinearly with human effort. The key idea is to crowdsource digital twins of real-world scenes using 3D reconstruction and collect large-scale data in simulation, rather than the real-world. Data collection in simulation is initially driven by RL, bootstrapped with human demonstrations. As the training of a generalist policy progresses across environments, its generalization capabilities can be used to replace human effort with model-generated demonstrations. This results in a pipeline where behavioral data is collected in simulation with continually reducing human effort. We show that **CASHER** demonstrates zero-shot and few-shot scaling laws on three real-world tasks across diverse scenarios. We show that **CASHER** enables fine-tuning of pre-trained policies to a target scenario using a video scan without any additional human effort.

Download:

Bibtex:

  
@INPROCEEDINGS{VillasevilM-RSS-25, 
    AUTHOR    = {Marcel Torne Villasevil AND Arhan Jain AND Jiayi Yuan AND Vidyaaranya Macha AND Lars Lien Ankile AND Anthony Simeonov AND Pulkit Agrawal AND Abhishek Gupta}, 
    TITLE     = {{Robot Learning with Super-Linear Scaling}}, 
    BOOKTITLE = {Proceedings of Robotics: Science and Systems}, 
    YEAR      = {2025}, 
    ADDRESS   = {LosAngeles, CA, USA}, 
    MONTH     = {June}, 
    DOI       = {10.15607/RSS.2025.XXI.025} 
}