Paper ThAT4.6
Willecke, Alexander (Technische Universität Braunschweig), Yazici, Cengiz (Technische Universität Braunschweig), Wolf, Lars (Technische Universität Braunschweig)
Impact of Perspectives on Collective Perception
Scheduled for presentation during the Regular Session "Collective perception and localization" (ThAT4), Thursday, September 26, 2024,
12:10−12:30, Salon 7
2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada
This information is tentative and subject to change. Compiled on December 26, 2024
|
|
Keywords Cooperative Techniques and Systems, Sensing, Vision, and Perception, Simulation and Modeling
Abstract
Collective Perception (CP) is the key technology for integrating non-connected road users into the Cooperative-Intelligent Transportation System. Thereby, ITS-Stations share locally perceived object data with others via broadcast communication. Previous studies on CP focused on the trade-off between resource usage and Environmental Awareness Ratio, assuming that atomic objects are either known or unknown. However, Perceived Objects consist of multiple attributes describing their state, such as position, speed, and dimensions. Stations perceive the traffic situation and objects from different perspectives, influencing which attributes can be observed. This study shows the performance of CP in three different traffic scenarios and analyzes the completeness of objects and availability of object attributes. It shows that completeness and availability depend on the traffic situation and are influenced by average speed, traffic, building density, and road layouts. Furthermore, results indicate that important object attributes, such as dimensions, are often missing, and the object’s center point is often unknown.
|
|