zur Hauptnavigation springen zum Inhaltsbereich springen

BayWISS-Kolleg Mobilität & Verkehr www.baywiss.de

Projekte im Kolleg Mobilität und Verkehr

© chuttersnap / unsplash.com

Application of Federated Learning Methods in Cooperative Intelligent Traffic Systems

Safer, more economical and efficient way of traveling is persistently pursed for the development of future traffic systems. Ongoing R&D projects aim at a transition to digital intelligent traffic systems or Smart Cities, in which comprehensive and rich sensor data are applied for improving the safety, traffic efficiency and convenience of traveling, and enable advanced AI-based traffic services for the next generation of traffic systems.

 

Federated Learning (FL) is a recently proposed distributed learning method, which is well suited for intelligent traffic systems and addresses the machine learning problems: (i) unbalanced local training data in non-IID among devices, (ii) massively distributed devices, (iii) expensive communication. All these features are fulfilled in the domain of intelligent road traffic. 

 

As FL only uploads the locally updated model parameters instead of raw data, the required communication load among traffic agents is usually lower than normal centralized learning methods. Moreover, compared to other distributed learning methods, FL can train learning models from broad users without accessing their private data, e.g., traveling data, raw images, etc. Hence, we believe that FL will bring great benefits in AI-powered traffic systems.

MITGLIED IM KOLLEG

seit

Betreuer Technische Hochschule Ingolstadt:

Prof. Dr. Andreas Festag

Prof. Dr. Andreas Festag lehrt und forscht auf dem Gebiet der Fahrzeugsicherheit und Car2X-Kommunikation.

 

Forschungsschwerpunkte:

  • Kommunikationsnetze und -protokolle
  • Vernetztes und automatisiertes Fahren
  • Verkehrsmanagement

Mehr erfahren Sie auf der Unterseite Prof. Festags auf der Website der TH Ingolstadt.

Betreute Projekte:

Betreuer Technische Universität München:

Prof. Dr.-Ing. Alois Christian Knoll

Forschungsschwerpunkte:

  • Autonomous systems
  • Robotics and artificial intelligence
  • Cognitive and neurorobotics
  • Medical and sensor-based robotics
  • Multi-agent systems
  • Data fusion
  • Adaptive systems
  • Multimedia information retrieval and model-driven development of embedded systems

Betreute Projekte:

Rui Song

Rui Song

Technische Hochschule Ingolstadt

Publikationen und Poster

 

R. Song, L. Zhou, V. Lakshminarasimhan, A. Festag, A. Knoll, 07/2022, Federated Learning Framework Coping with Hierarchical Heterogeneity in Cooperative ITS, Macao, China, DOI:10.1109/ITSC55140.2022.9922064

R.Song, A.Hegde, N.Senel, A.Festag, 06/2022, Edge-Aided Sensor Data Sharing in Vehicular Communication Networks, Finland, DOI:10.1109/VTC2022-Spring54318.2022.9860849

A Hegde, R Song, A Festag, 2023, Radio Resource Allocation in 5G-NR V2X: A Multi-Agent Actor-Critic Based Approach, In IEEE Access, DOI: 10.1109/ACCESS.2023.3305267, Journal Impact Fator=3.9.

L Zhou, R Song, G Chen, A Festag, A Knoll, 2023, Residual encoding framework to compress DNN parameters for fast transfer, In Knowledge-Based Systems, DOI: 10.1016/j.knosys.2023.110815, Journal Impact Fator=8.8.

R Song, D Liu, DZ Chen, A Festag, C Trinitis, M Schulz, A Knoll, 2023, Federated learning via decentralized dataset distillation in resource-constrained edge environments, Gold Coast, Australia, In International Joint Conference on Neural Networks (IJCNN), DOI: 10.1109/IJCNN54540.2023.10191879

R Song, L Lyu, W Jiang, A Festag, A Knoll, 2023, V2X-Boosted Federated Learning for Cooperative Intelligent Transportation Systems with Contextual Client Selection, International Conference on Robotics and Automation (ICRA) Workshop

R Song, L Zhou, L Lyu, A Festag, A Knoll, 2023, ResFed: Communication Efficient Federated Learning With Deep Compressed Residuals, In IEEE Internet of Things Journal, DOI: 10.1109/JIOT.2023.3324079, Journal Impact Fator=10.6.

R Song, R Xu, A Festag, J Ma, A Knoll, 2023, FedBEVT: Federated Learning Bird's Eye View Perception Transformer in Road Traffic Systems, In IEEE Transactions on Intelligent Vehicles, DOI: 10.1109/TIV.2023.3310674, Journal Impact Fator=8.2.

Koordination des Verbundkollegs Mobilität und Verkehr

Treten Sie mit uns in Kontakt. Wir freuen uns auf Ihre Fragen und Anregungen zum Verbundkolleg Mobilität und Verkehr.

Dr. Monika Kolpatzik

Dr. Monika Kolpatzik

Koordinatorin BayWISS-Verbundkolleg Mobilität & Verkehr

Technische Hochschule Ingolstadt
Doctoral School
Esplanade 10
85049 Ingolstadt

Telefon: +49 841 93481560
mobilitaet-verkehr.vk@baywiss.de

Marina Schleicher

Marina Schleicher

Koordinatorin BayWISS-Verbundkolleg Mobilität & Verkehr

Technische Hochschule Ingolstadt
Doctoral School
Esplanade 10
85049 Ingolstadt

Telefon: +49 841 93483539
mobilitaet-verkehr.vk@baywiss.de