aiqbench analysis
This research demonstrates a practical application of AI for data compression and retrieval in autonomous underwater vehicles, enabling real-time transmission of critical imagery over severely constrained satellite links. By intelligently selecting representative images from massive datasets, the method reduces data volume by nearly 400,000-fold while maintaining operational awareness during long-duration missions. The field tests confirm that machine learning techniques can effectively bridge the gap between high-volume sensor capture and low-bandwidth communication realities in remote environments.
Remote Awareness of Seafloor Images Collected by AUVs over Low-Bandwidth Communication Links
arXiv:2607.18013v1 Announce Type: cross Abstract: This paper introduces a method for real-time processing and transmission of autonomous underwater vehicle (AUV) imagery over low-bandwidth communication links. It leverages artificial intelligence (AI) techniques to identify a set of images that best represent an entire dataset, or automatically finds the most similar images to a given query image for transmission to operators. Combined with metadata of a larger set of images, compressed versions of the selected images can be transmitted over satellite communication links or underwater modems, and provide operators on shore with information about the type of imagery the AUV is collecting while it is still deployed. Data from three deployments off the coast of the UK and in Gran Canaria using different AUVs and imaging systems demonstrate the method in the field. It achieved an almost 400,000-fold reduction in data volume compared to the raw data size, enabling transmission of data summaries of a 2-hour 47-minute-long mapping mission in just over 34 minutes over low-bandwidth satellite communication.
Authors:Adrian Bodenmann, Cailei Liang, Miquel Massot-Campos, Samuel Simmons, Alexander B. Phillips, Alberto Consensi, Matthew Kingsland, Rashiid Sherif, Stan Brown, Adam Riese, Blair Thornton
Abstract:This paper introduces a method for real-time processing and transmission of autonomous underwater vehicle (AUV) imagery over low-bandwidth communication links. It leverages artificial intelligence (AI) techniques to identify a set of images that best represent an entire dataset, or automatically finds the most similar images to a given query image for transmission to operators. Combined with metadata of a larger set of images, compressed versions of the selected images can be transmitted over satellite communication links or underwater modems, and provide operators on shore with information about the type of imagery the AUV is collecting while it is still deployed. Data from three deployments off the coast of the UK and in Gran Canaria using different AUVs and imaging systems demonstrate the method in the field. It achieved an almost 400,000-fold reduction in data volume compared to the raw data size, enabling transmission of data summaries of a 2-hour 47-minute-long mapping mission in just over 34 minutes over low-bandwidth satellite communication.
Information Retrieval (cs.IR); Machine Learning (cs.LG); Robotics (cs.RO); Image and Video Processing (eess.IV)
arXiv:2607.18013 [cs.IR]
(or arXiv:2607.18013v1 [cs.IR] for this version)
https://doi.org/10.48550/arXiv.2607.18013 arXiv-issued DOI via DataCite (pending registration)
Full text under the publisher's open licence · 212 words
Related coverage
Building Blocks for Foundation Model Training and Inference on AWS
Hugging Face · May 11, 2026
NVIDIA Video Codec SDK 13.1: Zero-Copy Transcode, AV1 B-Frames, and Frame-Accurate Seek
NVIDIA · Jul 31, 2026
Scaling MoE reinforcement learning on Amazon EKS with EFA and DeepEP with 40% more throughput
AWS · Sep 25, 2026
An Educational GEMM Ladder for Helios GPUs
AMD · Sep 14, 2026