# Robo-DM: Data Management For Large Robot Datasets

arXiv: https://arxiv.org/abs/2505.15558 · HTML: https://mlsanity.com/paper/2505.15558/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 47 references that are in the map.
- First posted on arXiv 21 May 2025.

## Builds on (most cited first, 21 of 21)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/1806.10293/) (2018)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [The Surprising Effectiveness of Representation Learning for Visual Imitation](https://mlsanity.com/paper/2112.01511/) (2021)
- [In-Context Imitation Learning via Next-Token Prediction](https://mlsanity.com/paper/2408.15980/) (2024)
- [Multi-Stage Cable Routing through Hierarchical Imitation Learning](https://mlsanity.com/paper/2307.08927/) (2023)
- [RLDS: an Ecosystem to Generate, Share and Use Datasets in Reinforcement Learning](https://mlsanity.com/paper/2111.02767/) (2021)
- [FogROS: An Adaptive Framework for Automating Fog Robotics Deployment](https://mlsanity.com/paper/2108.11355/) (2021)
- [A Fog Robotics Approach to Deep Robot Learning: Application to Object Recognition and Grasp Planning in Surface Decluttering](https://mlsanity.com/paper/1903.09589/) (2019)
- [A Fog Robotic System for Dynamic Visual Servoing](https://mlsanity.com/paper/1809.06716/) (2018)
- [Fog Robotics for Efficient, Fluent and Robust Human-Robot Interaction](https://mlsanity.com/paper/1811.05578/) (2018)
- [FogROS2-SGC: A ROS2 Cloud Robotics Platform for Secure Global Connectivity](https://mlsanity.com/paper/2306.17157/) (2023)

## Built on by (most cited first, 2 of 2)

- [RIO: Flexible Real-Time Robot I/O for Cross-Embodiment Robot Learning](https://mlsanity.com/paper/2605.11564/) (2026)
- [SPINE: Bridging the Cyber-Physical Gap with Agentic AI](https://mlsanity.com/paper/2607.13049/) (2026)

## Abstract (arXiv)

Recent results suggest that very large datasets of teleoperated robot demonstrations can be used to train transformer-based models that have the potential to generalize to new scenes, robots, and tasks. However, curating, distributing, and loading large datasets of robot trajectories, which typically consist of video, textual, and numerical modalities - including streams from multiple cameras - remains challenging. We propose Robo-DM, an efficient open-source cloud-based data management toolkit for collecting, sharing, and learning with robot data. With Robo-DM, robot datasets are stored in a self-contained format with Extensible Binary Meta Language (EBML). Robo-DM can significantly reduce the size of robot trajectory data, transfer costs, and data load time during training. Compared to the RLDS format used in OXE datasets, Robo-DM's compression saves space by up to 70x (lossy) and 3.5x (lossless). Robo-DM also accelerates data retrieval by load-balancing video decoding with memory-mapped decoding caches. Compared to LeRobot, a framework that also uses lossy video compression, Robo-DM is up to 50x faster when decoding sequentially. We physically evaluate a model trained by Robo-DM with lossy compression, a pick-and-place task, and In-Context Robot Transformer. Robo-DM uses 75x compression of the original dataset and does not suffer reduction in downstream task accuracy.