# FLAME: A Federated Learning Benchmark for Robotic Manipulation

arXiv: https://arxiv.org/abs/2503.01729 · HTML: https://mlsanity.com/paper/2503.01729/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2025.

## Built on by (most cited first, 4 of 4)

- [ForgeVLA: Federated Vision-Language-Action Learning without Language Annotations](https://mlsanity.com/paper/2605.07474/) (2026)
- [An Empirical Study and Open Testbed for Federated Fine-Tuning of Vision-Language-Action Models](https://mlsanity.com/paper/2609.22973/) (2026)
- [Federated Subspace Guided Vision-Language-Action Policy Distillation for Non-IID Multi-Robot Manipulation](https://mlsanity.com/paper/2609.32239/) (2026)
- [RoboFL: Federated Expert Assembly for World Action Models](https://mlsanity.com/paper/2609.34968/) (2026)

## Abstract (arXiv)

Recent progress in robotic manipulation has been fueled by large-scale datasets collected across diverse environments. Training robotic manipulation policies on these datasets is traditionally performed in a centralized manner, raising concerns regarding scalability, adaptability, and data privacy. While federated learning enables decentralized, privacy-preserving training, its application to robotic manipulation remains largely unexplored. We introduce FLAME (Federated Learning Across Manipulation Environments), the first benchmark designed for federated learning in robotic manipulation. FLAME consists of: (i) a set of large-scale datasets of over 160,000 expert demonstrations of multiple manipulation tasks, collected across a wide range of simulated environments; (ii) a training and evaluation framework for robotic policy learning in a federated setting. We evaluate standard federated learning algorithms in FLAME, showing their potential for distributed policy learning and highlighting key challenges. Our benchmark establishes a foundation for scalable, adaptive, and privacy-aware robotic learning.