MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Deshpande, Abhay, Guru, Maya, Hendrix, Rose, Jauhri, Snehal, Eftekhar, Ainaz, Tripathi, Rohun, Argus, Max, Salvador, Jordi, Fang, Haoquan, Wallingford, Matthew, Pumacay, Wilbert, Kim, Yejin, Pfeifer, Quinn, Lee, Ying-Chun, Wolters, Piper, Rayyan, Omar, Zhang, Mingtong, Duan, Jiafei, Farley, Karen, Han, Winson, Vanderbilt, Eli, Fox, Dieter, Farhadi, Ali, Chalvatzaki, Georgia, Shah, Dhruv, Krishna, Ranjay
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908915436879872
author Deshpande, Abhay
Guru, Maya
Hendrix, Rose
Jauhri, Snehal
Eftekhar, Ainaz
Tripathi, Rohun
Argus, Max
Salvador, Jordi
Fang, Haoquan
Wallingford, Matthew
Pumacay, Wilbert
Kim, Yejin
Pfeifer, Quinn
Lee, Ying-Chun
Wolters, Piper
Rayyan, Omar
Zhang, Mingtong
Duan, Jiafei
Farley, Karen
Han, Winson
Vanderbilt, Eli
Fox, Dieter
Farhadi, Ali
Chalvatzaki, Georgia
Shah, Dhruv
Krishna, Ranjay
author_facet Deshpande, Abhay
Guru, Maya
Hendrix, Rose
Jauhri, Snehal
Eftekhar, Ainaz
Tripathi, Rohun
Argus, Max
Salvador, Jordi
Fang, Haoquan
Wallingford, Matthew
Pumacay, Wilbert
Kim, Yejin
Pfeifer, Quinn
Lee, Ying-Chun
Wolters, Piper
Rayyan, Omar
Zhang, Mingtong
Duan, Jiafei
Farley, Karen
Han, Winson
Vanderbilt, Eli
Fox, Dieter
Farhadi, Ali
Chalvatzaki, Georgia
Shah, Dhruv
Krishna, Ranjay
contents A prevailing view in robot learning is that simulation alone is not enough; effective sim-to-real transfer is widely believed to require at least some real-world data collection or task-specific fine-tuning to bridge the gap between simulated and physical environments. We challenge that assumption. With sufficiently large-scale and diverse simulated synthetic training data, we show that zero-shot transfer to the real world is not only possible, but effective for both static and mobile manipulation. We introduce MolmoBot-Engine, a fully open-source pipeline for procedural data generation across robots, tasks, and diverse simulated environments in MolmoSpaces. With it, we release MolmoBot-Data, a dataset of 1.8 million expert trajectories for articulated object manipulation and pick-and-place tasks. We train three policy classes: MolmoBot, a Molmo2-based multi-frame vision-language model with a flow-matching action head; MolmoBot-Pi0, which replicates the $π_0$ architecture to enable direct comparison; and MolmoBot-SPOC, a lightweight policy suitable for edge deployment and amenable to RL fine-tuning. We evaluate on two robotic platforms: the Franka FR3 for tabletop manipulation tasks and the Rainbow Robotics RB-Y1 mobile manipulator for door opening, drawer manipulation, cabinet interaction, and mobile pick-and-place. Without any real-world fine-tuning, our policies achieve zero-shot transfer to unseen objects and environments. On tabletop pick-and-place, MolmoBot achieves a success rate of 79.2% in real world evaluations across 4 settings, outperforming $π_{0.5}$ at 39.2%. Our results demonstrate that procedural environment generation combined with diverse articulated assets can produce robust manipulation policies that generalize broadly to the real world. Technical website: https://allenai.github.io/MolmoBot
format Preprint
id arxiv_https___arxiv_org_abs_2603_16861
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation
Deshpande, Abhay
Guru, Maya
Hendrix, Rose
Jauhri, Snehal
Eftekhar, Ainaz
Tripathi, Rohun
Argus, Max
Salvador, Jordi
Fang, Haoquan
Wallingford, Matthew
Pumacay, Wilbert
Kim, Yejin
Pfeifer, Quinn
Lee, Ying-Chun
Wolters, Piper
Rayyan, Omar
Zhang, Mingtong
Duan, Jiafei
Farley, Karen
Han, Winson
Vanderbilt, Eli
Fox, Dieter
Farhadi, Ali
Chalvatzaki, Georgia
Shah, Dhruv
Krishna, Ranjay
Robotics
A prevailing view in robot learning is that simulation alone is not enough; effective sim-to-real transfer is widely believed to require at least some real-world data collection or task-specific fine-tuning to bridge the gap between simulated and physical environments. We challenge that assumption. With sufficiently large-scale and diverse simulated synthetic training data, we show that zero-shot transfer to the real world is not only possible, but effective for both static and mobile manipulation. We introduce MolmoBot-Engine, a fully open-source pipeline for procedural data generation across robots, tasks, and diverse simulated environments in MolmoSpaces. With it, we release MolmoBot-Data, a dataset of 1.8 million expert trajectories for articulated object manipulation and pick-and-place tasks. We train three policy classes: MolmoBot, a Molmo2-based multi-frame vision-language model with a flow-matching action head; MolmoBot-Pi0, which replicates the $π_0$ architecture to enable direct comparison; and MolmoBot-SPOC, a lightweight policy suitable for edge deployment and amenable to RL fine-tuning. We evaluate on two robotic platforms: the Franka FR3 for tabletop manipulation tasks and the Rainbow Robotics RB-Y1 mobile manipulator for door opening, drawer manipulation, cabinet interaction, and mobile pick-and-place. Without any real-world fine-tuning, our policies achieve zero-shot transfer to unseen objects and environments. On tabletop pick-and-place, MolmoBot achieves a success rate of 79.2% in real world evaluations across 4 settings, outperforming $π_{0.5}$ at 39.2%. Our results demonstrate that procedural environment generation combined with diverse articulated assets can produce robust manipulation policies that generalize broadly to the real world. Technical website: https://allenai.github.io/MolmoBot
title MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation
topic Robotics
url https://arxiv.org/abs/2603.16861