FLAME：面向機器人操作的聯邦學習基準

FLAME: A Federated Learning Benchmark for Robotic Manipulation

March 3, 2025

作者: Santiago Bou Betran, Alberta Longhini, Miguel Vasco, Yuchong Zhang, Danica Kragic

cs.AI

摘要

近期機器人操作技術的進步，得益於在多元環境中收集的大規模數據集。傳統上，這些數據集用於集中式訓練機器人操作策略，但這種方式在可擴展性、適應性和數據隱私方面引發了擔憂。雖然聯邦學習能夠實現去中心化且保護隱私的訓練，但其在機器人操作領域的應用仍鮮有探索。我們提出了FLAME（跨操作環境的聯邦學習），這是首個專為機器人操作中的聯邦學習設計的基準測試。FLAME包含：(i) 一組超過160,000次專家示範的大規模數據集，涵蓋多種模擬環境下的操作任務；(ii) 一個在聯邦設置下進行機器人策略學習的訓練與評估框架。我們在FLAME中評估了標準的聯邦學習算法，展示了它們在分佈式策略學習中的潛力，並突出了關鍵挑戰。我們的基準測試為可擴展、適應性強且注重隱私的機器人學習奠定了基礎。

English

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.