MTF-Grasp: A Multi-tier Federated Learning Approach for Robotic Grasping

TL;DR

This paper introduces MTF-Grasp, a multi-tier federated learning method designed to improve robotic grasping by addressing non-IID data challenges across robots, leading to significant performance gains on standard datasets.

Contribution

The paper proposes a novel multi-tier federated learning framework that leverages data quality and quantity to enhance robotic grasping performance under non-IID data conditions.

Findings

Outperforms conventional FL by up to 8% on grasping datasets.

Effectively handles non-IID data distribution across robots.

Improves model robustness in low-data robots.

Abstract

Federated Learning (FL) is a promising machine learning paradigm that enables participating devices to train privacy-preserved and collaborative models. FL has proven its benefits for robotic manipulation tasks. However, grasping tasks lack exploration in such settings where robots train a global model without moving data and ensuring data privacy. The main challenge is that each robot learns from data that is nonindependent and identically distributed (non-IID) and of low quantity. This exhibits performance degradation, particularly in robotic grasping. Thus, in this work, we propose MTF-Grasp, a multi-tier FL approach for robotic grasping, acknowledging the unique challenges posed by the non-IID data distribution across robots, including quantitative skewness. MTF-Grasp harnesses data quality and quantity across robots to select a set of "top-level" robots with better data distribution and higher sample count. It then utilizes top-level robots to train initial seed models and distribute them to the remaining "low-level" robots, reducing the risk of model performance degradation in low-level robots. Our approach outperforms the conventional FL setup by up to 8% on the quantity-skewed Cornell and Jacquard grasping datasets.