TY - CHAP A1 - Segler, Christoph A1 - Kugele, Stefan A1 - Obergfell, Philipp A1 - Osman, Mohd Hafeez A1 - Shafaei, Sina A1 - Sax, Eric A1 - Knoll, Alois T1 - Evaluation of feature selection for anomaly detection in automotive E/E architectures T2 - Proceedings: 2019 IEEE/ACM 41st International Conference on Software Engineering: Companion Proceedings: ICSE-Companion 2019 UR - https://doi.org/10.1109/ICSE-Companion.2019.00104 KW - feature selection KW - anomaly detection KW - automotive KW - E/E architecture Y1 - 2019 UR - https://doi.org/10.1109/ICSE-Companion.2019.00104 SN - 978-1-7281-1764-5 SN - 2574-1934 SP - 260 EP - 261 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Song, Rui A1 - Hegde, Anupama A1 - Senel, Numan A1 - Knoll, Alois A1 - Festag, Andreas T1 - Edge-Aided Sensor Data Sharing in Vehicular Communication Networks T2 - 2022 IEEE 95th Vehicular Technology Conference: (VTC2022-Spring) Proceedings UR - https://doi.org/10.1109/VTC2022-Spring54318.2022.9860849 KW - sensor data sharing and fusion KW - cooperative perception KW - vehicular communication KW - distributed estimation KW - measurement noise Y1 - 2022 UR - https://doi.org/10.1109/VTC2022-Spring54318.2022.9860849 SN - 978-1-6654-8243-1 SN - 2577-2465 PB - IEEE CY - Piscataway (NJ) ER - TY - CHAP A1 - Dirndorfer, Tobias A1 - Botsch, Michael A1 - Knoll, Alois T1 - Model-based analysis of sensor-noise in predictive passive safety algorithms T2 - The 22nd ESV Conference Proceedings Y1 - 2011 UR - https://www-esv.nhtsa.dot.gov/Proceedings/22/isv7/main.htm PB - NHTSA CY - Washington, D.C. ER - TY - CHAP A1 - Shafaei, Sina A1 - Kugele, Stefan A1 - Osman, Mohd Hafeez A1 - Knoll, Alois ED - Gallina, Barbara ED - Skavhaug, Amund ED - Schoitsch, Erwin ED - Bitsch, Friedemann T1 - Uncertainty in Machine Learning: A Safety Perspective on Autonomous Driving T2 - Computer Safety, Reliability, and Security UR - https://doi.org/10.1007/978-3-319-99229-7_39 KW - artificial intelligence KW - uncertainty KW - safety Y1 - 2018 UR - https://doi.org/10.1007/978-3-319-99229-7_39 SN - 978-3-319-99228-0 SN - 978-3-319-99229-7 SN - 0302-9743 SN - 1611-3349 SP - 458 EP - 464 PB - Springer CY - Cham ER - TY - CHAP A1 - Shafaei, Sina A1 - Müller, Fabian A1 - Salzmann, Tim A1 - Hashemi Farzaneh, Morteza A1 - Kugele, Stefan A1 - Knoll, Alois T1 - Context Prediction Architectures in Next Generation of Intelligent Cars T2 - 2018 IEEE Intelligent Transportation Systems Conference UR - https://doi.org/10.1109/ITSC.2018.8569617 KW - Automobiles KW - Software KW - Automotive engineering KW - Computer architecture KW - Informatics KW - Context-aware services Y1 - 2018 UR - https://doi.org/10.1109/ITSC.2018.8569617 SN - 978-1-7281-0323-5 SP - 2923 EP - 2930 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Song, Rui A1 - Zhou, Liguo A1 - Lakshminarasimhan, Venkatnarayanan A1 - Festag, Andreas A1 - Knoll, Alois T1 - Federated Learning Framework Coping with Hierarchical Heterogeneity in Cooperative ITS T2 - 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC) KW - Training KW - Deep learning KW - Data privacy KW - Federated learning KW - Roads KW - Computational modeling KW - Data models Y1 - 2022 SN - 978-1-6654-6880-0 SP - 3502 EP - 3508 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Hashemi Farzaneh, Morteza A1 - Kugele, Stefan A1 - Knoll, Alois T1 - A graphical modeling tool supporting automated schedule synthesis for time-sensitive networking T2 - 2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation UR - https://doi.org/10.1109/ETFA.2017.8247599 Y1 - 2017 UR - https://doi.org/10.1109/ETFA.2017.8247599 SN - 978-1-5090-6505-9 SN - 1946-0759 PB - IEEE CY - Piscataway ER - TY - CHAP A1 - Kugele, Stefan A1 - Cebotari, Vadim A1 - Gleirscher, Mario A1 - Hashemi Farzaneh, Morteza A1 - Segler, Christoph A1 - Shafaei, Sina A1 - Vögel, Hans-Jörg A1 - Bauer, Fridolin A1 - Knoll, Alois A1 - Marmsoler, Diego A1 - Michel, Hans-Ulrich ED - Eibl, Maximilian ED - Gaedke, Martin T1 - Research Challenges for a Future-Proof E/E Architecture: A Project Statement T2 - INFORMATIK 2017 UR - https://doi.org/10.18420/in2017_146 KW - automotive KW - safety assurance KW - service-oriented architectures KW - communication KW - timesensitive network KW - deep learning KW - machine learning KW - artificial intelligence Y1 - 2017 UR - https://doi.org/10.18420/in2017_146 SN - 978-3-88579-669-5 SP - 1463 EP - 1474 PB - Gesellschaft für Informatik CY - Bonn ER - TY - JOUR A1 - Zhou, Liguo A1 - Song, Rui A1 - Chen, Guang A1 - Festag, Andreas A1 - Knoll, Alois T1 - Residual encoding framework to compress DNN parameters for fast transfer JF - Knowledge-Based Systems UR - https://doi.org/10.1016/j.knosys.2023.110815 Y1 - 2023 UR - https://doi.org/10.1016/j.knosys.2023.110815 SN - 1872-7409 SN - 0950-7051 VL - 2023 IS - 277 PB - Elsevier CY - Amsterdam ER - TY - CHAP A1 - Rothmeier, Thomas A1 - Huber, Werner A1 - Knoll, Alois T1 - Time to Shine: Fine-Tuning Object Detection Models with Synthetic Adverse Weather Images T2 - Proceedings, 2024 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2024 UR - https://doi.org/10.1109/WACV57701.2024.00439 Y1 - 2024 UR - https://doi.org/10.1109/WACV57701.2024.00439 SN - 979-8-3503-1892-0 N1 - Zu dieser Veröffentlichung existiert eine frei zugängliche Version: https://openaccess.thecvf.com/content/WACV2024/papers/Rothmeier_Time_To_Shine_Fine-Tuning_Object_Detection_Models_With_Synthetic_Adverse_WACV_2024_paper.pdf SP - 4435 EP - 4444 PB - IEEE CY - Los Alamitos ER - TY - CHAP A1 - Song, Rui A1 - Lyu, Lingjuan A1 - Jiang, Wei A1 - Festag, Andreas A1 - Knoll, Alois T1 - V2X-Boosted Federated Learning for Cooperative Intelligent Transportation Systems with Contextual Client Selection T2 - CoPerception: Collaborative Perception and Learning, ICRA 2023 workshop Y1 - 2023 UR - https://drive.google.com/file/d/1-OQAeNryd7-lksCTuWnhhyydpFSnw5On/view?usp=share_link ER - TY - INPR A1 - Song, Rui A1 - Liang, Chenwei A1 - Cao, Hu A1 - Yan, Zhiran A1 - Zimmer, Walter A1 - Gross, Markus A1 - Festag, Andreas A1 - Knoll, Alois T1 - Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehicles N2 - Collaborative perception in automated vehicles leverages the exchange of information between agents, aiming to elevate perception results. Previous camera-based collaborative 3D perception methods typically employ 3D bounding boxes or bird's eye views as representations of the environment. However, these approaches fall short in offering a comprehensive 3D environmental prediction. To bridge this gap, we introduce the first method for collaborative 3D semantic occupancy prediction. Particularly, it improves local 3D semantic occupancy predictions by hybrid fusion of (i) semantic and occupancy task features, and (ii) compressed orthogonal attention features shared between vehicles. Additionally, due to the lack of a collaborative perception dataset designed for semantic occupancy prediction, we augment a current collaborative perception dataset to include 3D collaborative semantic occupancy labels for a more robust evaluation. The experimental findings highlight that: (i) our collaborative semantic occupancy predictions excel above the results from single vehicles by over 30%, and (ii) models anchored on semantic occupancy outpace state-of-the-art collaborative 3D detection techniques in subsequent perception applications, showcasing enhanced accuracy and enriched semantic-awareness in road environments. UR - https://doi.org/10.48550/arXiv.2402.07635 Y1 - 2024 UR - https://doi.org/10.48550/arXiv.2402.07635 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-46035 PB - arXiv CY - Ithaca ER - TY - JOUR A1 - Song, Rui A1 - Xu, Runsheng A1 - Festag, Andreas A1 - Ma, Jiaqi A1 - Knoll, Alois T1 - FedBEVT: Federated Learning Bird's Eye View Perception Transformer in Road Traffic Systems JF - IEEE Transactions on Intelligent Vehicles N2 - Bird's eye view (BEV) perception is becoming increasingly important in the field of autonomous driving. It uses multi-view camera data to learn a transformer model that directly projects the perception of the road environment onto the BEV perspective. However, training a transformer model often requires a large amount of data, and as camera data for road traffic are often private, they are typically not shared. Federated learning offers a solution that enables clients to collaborate and train models without exchanging data but model parameters. In this paper, we introduce FedBEVT, a federated transformer learning approach for BEV perception. In order to address two common data heterogeneity issues in FedBEVT: (i) diverse sensor poses, and (ii) varying sensor numbers in perception systems, we propose two approaches - Federated Learning with Camera-Attentive Personalization (FedCaP) and Adaptive Multi-Camera Masking (AMCM), respectively. To evaluate our method in real-world settings, we create a dataset consisting of four typical federated use cases. Our findings suggest that FedBEVT outperforms the baseline approaches in all four use cases, demonstrating the potential of our approach for improving BEV perception in autonomous driving. UR - https://doi.org/10.1109/TIV.2023.3310674 Y1 - 2023 UR - https://doi.org/10.1109/TIV.2023.3310674 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-42789 SN - 2379-8904 SN - 2379-8858 VL - 9 IS - 1 SP - 958 EP - 969 PB - IEEE CY - New York ER - TY - INPR A1 - Song, Rui A1 - Lyu, Lingjuan A1 - Jiang, Wei A1 - Festag, Andreas A1 - Knoll, Alois T1 - V2X-Boosted Federated Learning for Cooperative Intelligent Transportation Systems with Contextual Client Selection N2 - Machine learning (ML) has revolutionized transportation systems, enabling autonomous driving and smart traffic services. Federated learning (FL) overcomes privacy constraints by training ML models in distributed systems, exchanging model parameters instead of raw data. However, the dynamic states of connected vehicles affect the network connection quality and influence the FL performance. To tackle this challenge, we propose a contextual client selection pipeline that uses Vehicle-to-Everything (V2X) messages to select clients based on the predicted communication latency. The pipeline includes: (i) fusing V2X messages, (ii) predicting future traffic topology, (iii) pre-clustering clients based on local data distribution similarity, and (iv) selecting clients with minimal latency for future model aggregation. Experiments show that our pipeline outperforms baselines on various datasets, particularly in non-iid settings. UR - https://doi.org/10.48550/arXiv.2305.11654 Y1 - 2023 UR - https://doi.org/10.48550/arXiv.2305.11654 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-41441 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Nair, Saasha A1 - Shafaei, Sina A1 - Kugele, Stefan A1 - Osman, Mohd Hafeez A1 - Knoll, Alois ED - Espinoza, Huáscar ED - ÓhÉigeartaigh, Seán S. ED - Huang, Xiaowei ED - Hernández-Orallo, José ED - Castillo-Effen, Mauricio T1 - Monitoring Safety of Autonomous Vehicles with Crash Prediction Network T2 - Proceedings of the AAAI Workshop on Artificial Intelligence Safety 2019, co-located with the Thirty-Third AAAI Conference on Artificial Intelligence 2019 (AAAI 2019) Y1 - 2019 UR - https://ceur-ws.org/Vol-2301/ PB - RWTH Aachen CY - Aachen ER -