Poster: Real-time simulator of collaborative autonomous vehicles

Abstract

Collaborative autonomous vehicles will appear in the near future and will transform deeply road transportation sys- tems, addressing in part many issues such as safety, traffic efficien- cy, etc. Validation and testing of complex scenarios involving sets of autonomous collaborative vehicles are becoming an important challenge. Each vehicle in the set is autonomous and acts asyn- chronously, receiving and processing huge amount of data in real time, coming from the environment and other vehicles. Simulation of such scenarios in real time require huge computing resources. This poster presents a simulation platform combining the real-time OPAL-RT Technologies for processing and parallel computing, and the Pro-SiVIC vehicular simulator from Civitec for realistic simula- tion of vehicles dynamic, road/environment, and sensors behaviors. The two platforms are complementary and their combining allow us to propose a real time simulator of collaborative autonomous sys- tems. The development of embedded sensors and communication technologies, during the last few decades, has affected signifi- cantly the automotive sector, helping to overcome traffic prob- lems and to achieve greater safety on roads and highways. Nowadays, on board active safety systems are essentially designed to avoid collisions rather than only reducing their impact on passengers as with passive systems. Furthermore, augmented night vision, automated park assistance and navi- gation systems are functionalities that are already imple- mented on high-end vehicles (1). Although current ADAS (Advanced Driver Assistance Systems) are built as isolated subsystems that are typically not sharing information within or between vehicles, future generations of ADAS will feature a much higher level of integration as well as extended commu- nication capabilities allowing to exchange information be- tween vehicles. This will lead to fully automated vehicles capable of sharing information and interacting with dynamic environment. Some research efforts are focusing on the coop- erative and optimized behavior of nodes, and Multi-Hop Net- works (2), some specific aspects are introduced in (3) as friends/enemies, dominance, etc. optimize the behavior of multi-hop network. On the other side, some basic scenarios on collaborative autonomous vehicles have been experimented with three collaborative autonomous vehicles at the Griffith University's Intelligent Control Systems Laboratory (ICSL) (4). In these experiments, simple scenarios were considered, such as overtaking, transversal intersection and lane platoon- ing. This poster presents a real-time simulator of collaborative autonomous vehicles on parallel computing tools. We propose a strategy to build a real time simulator architecture of colla- borative autonomous vehicles. This platform allows us to simulate the embedded information processing systems and the brain behind each individual autonomous vehicle, as well as the VANET exchange of information between each vehicle in collaborative scenarios. We provide a brief presen- tation of the Pro-SiVIC simulator and explain our choice due to its high capability to simulate the other essential compo- nents of multi-vehicular collaborative scenarios such as the various sensors, the road environment and the dynamic of each vehicle in real-time. In this work, we propose to interconnect RT-LAB and Pro-SiVIC platforms to complete the required architecture to simulate in real-time scenarios of collaborative autonomous vehicles. We give an example and present some results using a real time ACC (Adaptive Cruise Control) sce- nario with inter-vehicular communication capabilities. As the main embedded processing/control algorithms, we consider a PI controller.