Saved in:
Bibliographic Details
Main Authors: Kang, Woonsang, Lee, Joohyung, Kim, Seungjun, Cho, Jungchan, Oh, Yoonseon
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.05861
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918245176442880
author Kang, Woonsang
Lee, Joohyung
Kim, Seungjun
Cho, Jungchan
Oh, Yoonseon
author_facet Kang, Woonsang
Lee, Joohyung
Kim, Seungjun
Cho, Jungchan
Oh, Yoonseon
contents Grasp pose detection (GPD) is a fundamental capability for robotic autonomy, but its reliance on large, diverse datasets creates significant data privacy and centralization challenges. Federated Learning (FL) offers a privacy-preserving solution, but its application to GPD is hindered by the substantial communication overhead of large models, a key issue for resource-constrained robots. To address this, we propose a novel module-wise FL framework that begins by analyzing the learning dynamics of the GPD model's functional components. This analysis identifies slower-converging modules, to which our framework then allocates additional communication effort. This is realized through a two-phase process: a standard full-model training phase is followed by a communication-efficient phase where only the identified subset of slower-converging modules is trained and their partial updates are aggregated. Extensive experiments on the GraspNet-1B dataset demonstrate that our method outperforms standard FedAvg and other baselines, achieving higher accuracy for a given communication budget. Furthermore, real-world experiments on a physical robot validate our approach, showing a superior grasp success rate compared to baseline methods in cluttered scenes. Our work presents a communication-efficient framework for training robust, generalized GPD models in a decentralized manner, effectively improving the trade-off between communication cost and model performance.
format Preprint
id arxiv_https___arxiv_org_abs_2507_05861
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Communication-Efficient Module-Wise Federated Learning for Grasp Pose Detection in Cluttered Environments
Kang, Woonsang
Lee, Joohyung
Kim, Seungjun
Cho, Jungchan
Oh, Yoonseon
Robotics
Machine Learning
Grasp pose detection (GPD) is a fundamental capability for robotic autonomy, but its reliance on large, diverse datasets creates significant data privacy and centralization challenges. Federated Learning (FL) offers a privacy-preserving solution, but its application to GPD is hindered by the substantial communication overhead of large models, a key issue for resource-constrained robots. To address this, we propose a novel module-wise FL framework that begins by analyzing the learning dynamics of the GPD model's functional components. This analysis identifies slower-converging modules, to which our framework then allocates additional communication effort. This is realized through a two-phase process: a standard full-model training phase is followed by a communication-efficient phase where only the identified subset of slower-converging modules is trained and their partial updates are aggregated. Extensive experiments on the GraspNet-1B dataset demonstrate that our method outperforms standard FedAvg and other baselines, achieving higher accuracy for a given communication budget. Furthermore, real-world experiments on a physical robot validate our approach, showing a superior grasp success rate compared to baseline methods in cluttered scenes. Our work presents a communication-efficient framework for training robust, generalized GPD models in a decentralized manner, effectively improving the trade-off between communication cost and model performance.
title Communication-Efficient Module-Wise Federated Learning for Grasp Pose Detection in Cluttered Environments
topic Robotics
Machine Learning
url https://arxiv.org/abs/2507.05861