Implementation of a Perception Module for Smart Mobility Applications in Eclipse MOSAIC


  • Robert Protzmann Fraunhofer Institute for Open Communication Systems image/svg+xml
  • Karl Schrab Daimler Center for Automotive Information Technology Innovations image/svg+xml
  • Moritz Schweppenhäuser Fraunhofer Institute for Open Communication Systems image/svg+xml
  • Ilja Radusch Daimler Center for Automotive Information Technology Innovations image/svg+xml



Nowadays, smart mobility applications could benefit from environment perception, enabled by evolving sensor technology and processing capabilities available for traffic entities. On the application level, in many cases, information about detected objects is required instead of the raw sensor data. Developing and evaluating the impacts of such applications can be done in co-simulation frameworks, which combine the modeling of different domains such as application, communication, and traffic. Eclipse MOSAIC is a suitable solution for this task, combining the traffic simulation of Eclipse SUMO with other simulators, such as the integrated Application Simulator, or OMNeT++ and ns-3 for modeling communication. However, a model for perceiving surrounding traffic entities, such as vehicles, traffic signals, and traffic signs, is only available to a limited extent. In this paper, we introduce an object-level perception module to the MOSAIC Application simulator. It takes advantage of state-of-the-art spatial indexing methods to get rapid access to traffic objects, especially moving objects, within a defined field of view. We furthermore evaluate the computational performance of the indexing techniques as well as the integration with the traffic simulator SUMO using TraCI and libsumo. With the aid of this model, novel connected applications that analyze or share surrounding objects, e.g. for an improved traffic state estimation, can now be evaluated with Eclipse MOSAIC.


Download data is not yet available.


MOSAIC contributors. Eclipse MOSAIC Source Code. Eclipse Foundation on Github, [online], 2020-2022.

Alexey Dosovitskiy, German Ros, Felipe Codevilla, Antonio Lopez, and Vladlen Koltun. Carla: An open urban driving simulator. In Conference on robot learning, pages 1–16. PMLR, 2017.

Eclipse MOSAIC Core Team. Berlin SUMO Traffi c (BeST) Scenario., 2022.

Eclipse MOSAIC Core Team. Eclipse MOSAIC: A Multi-Domain and Multi-Scale Simulation Framework for Connected and Automated Mobility., 2022.

Antonin Guttman. R-trees: A dynamic index structure for spatial searching. In Proceedings of the 1984 ACM SIGMOD international conference on Management of data, pages 47–57, 1984.

Maike Hartstern, Viktor Rack, Mohsen Kaboli, and Wilhelm Stork. Simulation-based evaluation of automotive sensor setups for environmental perception in early development stages. In 2020 IEEE Intelligent Vehicles Symposium (IV), pages 858–864. IEEE, 2020.

Ravi Kanth V Kothuri, Siva Ravada, and Daniel Abugov. Quadtree and r-tree indexes in oracle spatial: a comparison using gis data. In Proceedings of the 2002 ACM SIGMOD international conference on Management of data, pages 546–557, 2002.

Clemens Linnhoff, Philipp Rosenberger, Simon Schmidt, Lukas Elster, Rainer Stark, and Hermann Winner. Towards serious perception sensor simulation for safety validation of automated driving-a collaborative method to specify sensor models. In 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), pages 2688–2695. IEEE, 2021.

Pablo Alvarez Lopez, Michael Behrisch, Laura Bieker-Walz, Jakob Erdmann, Yun-Pang Flötteröd, Robert Hilbrich, Leonhard Lücken, Johannes Rummel, Peter Wagner, and Evamarie Wießner. Microscopic traffic simulation using sumo. In The 21st IEEE International Conference on Intelligent Transportation Systems. IEEE, 2018.

Kay Massow, Fabian Maximilian Thiele, K Schrab, BS Bunk, I Tschinibaew, and Ilja Radusch. Scenario definition for prototyping cooperative advanced driver assistance systems. In 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC), pages 1–8. IEEE, 2020.

Robert Protzmann, Björn Schünemann, and Ilja Radusch. Simulation of convergent networks for intelligent transport systems with vsimrti. Networking Simulation for Intelligent Transportation Systems: High Mobile Wireless Nodes, pages 1–28, 2017.

Francisca Rosique, Pedro J Navarro, Carlos Fernández, and Antonio Padilla. A systematic review of perception system and simulators for autonomous vehicles research. Sensors, 19(3):648, 2019.

Dominik Ziemke, Ihab Kaddoura, and Kai Nagel. The matsim open berlin scenario: A multimodal agent-based transport simulation scenario based on synthetic demand modeling and open data. Procedia Computer Science, 151:870–877, 2019. The 10th International Conference on Ambient Systems, Networks and Technologies (ANT 2019) / The 2nd International Conference on Emerging Data and Industry 4.0 (EDI40 2019) / Affi liated Workshops.




How to Cite

Protzmann, R., Schrab, K., Schweppenhäuser, M., & Radusch, I. (2022). Implementation of a Perception Module for Smart Mobility Applications in Eclipse MOSAIC. SUMO Conference Proceedings, 3, 199–214.

Conference Proceedings Volume


Conference papers

Funding data