Distributed Upload and Active Labeling for Resource-Constrained Fleet Learning

Oguzhan Akcin, Harsh Goel, Ruihan Zhao, Sandeep P. Chinchali
Proceedings of The 9th Conference on Robot Learning, PMLR 305:3463-3482, 2025.

Abstract

In multi-robot systems, fleets are often deployed to collect data that improves the performance of machine learning models for downstream perception and planning. However, real-world robotic deployments generate vast amounts of data across diverse conditions, while only a small portion can be transmitted or labeled due to limited bandwidth, constrained onboard storage, and high annotation costs. To address these challenges, we propose Distributed Upload and Active Labeling (DUAL), a decentralized, two-stage data collection framework for resource-constrained robotic fleets. In the first stage, each robot independently selects a subset of its local observations to upload under storage and communication constraints. In the second stage, the cloud selects a subset of uploaded data to label, subject to a global annotation budget. We evaluate DUAL on classification tasks spanning multiple sensing modalities, as well as on RoadNet—a real-world dataset we collected from vehicle-mounted cameras for time and weather classification. We further validate our approach in a physical experiment using a Franka Emika Panda robot arm, where it learns to move a red cube to a green bowl. Finally, we test DUAL on trajectory prediction using the nuScenes autonomous driving dataset to assess generalization to complex prediction tasks. Across all settings, DUAL consistently outperforms state-of-the-art baselines, achieving up to 31.1% gain in classification accuracy and a 13% improvement in real-world robotics task completion rates.

Cite this Paper

BibTeX
@InProceedings{pmlr-v305-akcin25a, title = {Distributed Upload and Active Labeling for Resource-Constrained Fleet Learning}, author = {Akcin, Oguzhan and Goel, Harsh and Zhao, Ruihan and Chinchali, Sandeep P.}, booktitle = {Proceedings of The 9th Conference on Robot Learning}, pages = {3463--3482}, year = {2025}, editor = {Lim, Joseph and Song, Shuran and Park, Hae-Won}, volume = {305}, series = {Proceedings of Machine Learning Research}, month = {27--30 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v305/main/assets/akcin25a/akcin25a.pdf}, url = {https://proceedings.mlr.press/v305/akcin25a.html}, abstract = {In multi-robot systems, fleets are often deployed to collect data that improves the performance of machine learning models for downstream perception and planning. However, real-world robotic deployments generate vast amounts of data across diverse conditions, while only a small portion can be transmitted or labeled due to limited bandwidth, constrained onboard storage, and high annotation costs. To address these challenges, we propose Distributed Upload and Active Labeling (DUAL), a decentralized, two-stage data collection framework for resource-constrained robotic fleets. In the first stage, each robot independently selects a subset of its local observations to upload under storage and communication constraints. In the second stage, the cloud selects a subset of uploaded data to label, subject to a global annotation budget. We evaluate DUAL on classification tasks spanning multiple sensing modalities, as well as on RoadNet—a real-world dataset we collected from vehicle-mounted cameras for time and weather classification. We further validate our approach in a physical experiment using a Franka Emika Panda robot arm, where it learns to move a red cube to a green bowl. Finally, we test DUAL on trajectory prediction using the nuScenes autonomous driving dataset to assess generalization to complex prediction tasks. Across all settings, DUAL consistently outperforms state-of-the-art baselines, achieving up to 31.1% gain in classification accuracy and a 13% improvement in real-world robotics task completion rates.} }
Endnote
%0 Conference Paper %T Distributed Upload and Active Labeling for Resource-Constrained Fleet Learning %A Oguzhan Akcin %A Harsh Goel %A Ruihan Zhao %A Sandeep P. Chinchali %B Proceedings of The 9th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2025 %E Joseph Lim %E Shuran Song %E Hae-Won Park %F pmlr-v305-akcin25a %I PMLR %P 3463--3482 %U https://proceedings.mlr.press/v305/akcin25a.html %V 305 %X In multi-robot systems, fleets are often deployed to collect data that improves the performance of machine learning models for downstream perception and planning. However, real-world robotic deployments generate vast amounts of data across diverse conditions, while only a small portion can be transmitted or labeled due to limited bandwidth, constrained onboard storage, and high annotation costs. To address these challenges, we propose Distributed Upload and Active Labeling (DUAL), a decentralized, two-stage data collection framework for resource-constrained robotic fleets. In the first stage, each robot independently selects a subset of its local observations to upload under storage and communication constraints. In the second stage, the cloud selects a subset of uploaded data to label, subject to a global annotation budget. We evaluate DUAL on classification tasks spanning multiple sensing modalities, as well as on RoadNet—a real-world dataset we collected from vehicle-mounted cameras for time and weather classification. We further validate our approach in a physical experiment using a Franka Emika Panda robot arm, where it learns to move a red cube to a green bowl. Finally, we test DUAL on trajectory prediction using the nuScenes autonomous driving dataset to assess generalization to complex prediction tasks. Across all settings, DUAL consistently outperforms state-of-the-art baselines, achieving up to 31.1% gain in classification accuracy and a 13% improvement in real-world robotics task completion rates.
APA
Akcin, O., Goel, H., Zhao, R. & Chinchali, S.P.. (2025). Distributed Upload and Active Labeling for Resource-Constrained Fleet Learning. Proceedings of The 9th Conference on Robot Learning, in Proceedings of Machine Learning Research 305:3463-3482 Available from https://proceedings.mlr.press/v305/akcin25a.html.

Related Material