Collaborative Navigation Strategies Based on Vehicles Features in Connected Environments

In the intelligent vehicles community, exploring and navigating through urban environments represent one of the greatest challenges to overcome. This challenge can be addressed using Vehicle-To-Everything technologies which enable connected vehicles to communicate with each other and with other actors in the scenario such as smart infrastructures and pedestrians. In this work, we propose a communication strategy among actors in urban scenarios to exchange useful data to improve their performance in achieving their respective goals. Our approach is inspired by communities of interest in human groups, where members share data on a common topic. As actors are organized as communities, the data transmitted among actors is more efficient and thus reduces the overall communication effort. To demonstrate the effectiveness of this communication strategy, we propose a case study to explore its influence on the navigation behaviours of a fleet of autonomous vehicles and the decrease of the total bandwidth, especially in dynamic areas with traffic jams. We show that, when performing navigation in simulated environments, it reduces by seven times the average number of messages exchanged among actors while maintaining the same efficiency in navigation toward vehicles' respective goals. Our method is also validated in real-world experiments, in an unstructured environment with a fleet of mobile robots. For more information, the video of the experiments is available at https://youtu.be/Dp4LxykEGAY