Article Dans Une Revue IEEE Transactions on Mobile Computing Année : 2025

Resource-Efficient Sensor Fusion at the Edge via System-Wide Dynamic Gated Neural Networks

Résumé

Next-generation mobile systems will support multiple AI-based applications, each leveraging heterogeneous sensors and data sources through deep neural network (DNN) architectures collaboratively executed within the network. In this context, to minimize the cost of the AI inference task subject to requirements on latency, quality, and -cruciallyreliability of the inference process, it is vital to optimize (i) the set of sensors/data sources and (ii) the DNN architecture, (iii) the network nodes executing sections of the DNN, and (iv) the resources to use. To achieve these goals, we leverage dynamic gated neural networks with branches, and propose a novel algorithmic strategy called Quantile-constrained Inference (QIC), based upon quantile-Constrained policy optimization. QIC makes joint, highquality, swift decisions on all the above aspects of the system, with the aim to minimize inference energy cost. We remark that this is the first contribution connecting gated dynamic DNNs with infrastructure-level decision making. We evaluate QIC using a dynamic gated DNN with stems and branches for optimal sensor fusion and inference, trained on the RADIATE dataset offering Radar, LiDAR, and Camera data, and real-world wireless measurements. Our results confirm that QIC closely matches the optimum and outperforms existing approaches in reducing energy consumption (compute, communication, and total) and application requirements failure by over 70%.

Fichier principal
Vignette du fichier
Optimizing_Resource_Allocation_in_Multi_Modal_Systems (44).pdf (2.08 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence

Dates et versions

hal-05448895 , version 1 (08-01-2026)

Licence

Identifiants

Citer

Chetna Singhal, Yashuo Wu, Francesco Malandrino, Sharon G L Contreras, Marco Levorato, et al.. Resource-Efficient Sensor Fusion at the Edge via System-Wide Dynamic Gated Neural Networks. IEEE Transactions on Mobile Computing, 2025, 24 (12), pp.13243-13257. ⟨10.1109/TMC.2025.3586882⟩. ⟨hal-05448895⟩
56 Consultations
127 Téléchargements

Altmetric

Partager

  • More