In emergency situations such as traffic accidents and disasters, every second counts. A quickly and correctly formed emergency lane can have a life-saving effect. Rescue service associations estimate that if emergency services arrive four minutes earlier, the chances of survival are increased by up to 40%. However, a correctly and timely formed emergency lane is rare and difficult to implement without the foresight and prudent actions of all road users. Many drivers lack an overview of the situation of all the traffic around them, which is why they often fail to react correctly. As a result, emergency vehicles get stuck in traffic jams and lose valuable time. The underlying project suggests control and communication solutions which purposefully manipulate the collective behavior in the micro- as well as macroscale of the traffic in order to facilitate safe and fast interventions.
 

The AORTA platform is implemented in the form of a hierarchical architecture (macro and micro management) and interacts with a variety of sensors and road users. These include smart traffic lights, IoT sensors, and vehicles with varying degrees of connectivity and automation. The AORTA platform uses traffic data collected along with the emergency vehicle's route to the scene, connects to the traffic and emergency management systems, and manages the individual connection with each connected vehicle. This ensures that a maximum number of vehicles receive early notification of emergency vehicle deployment and route, and minimizes the risk of accidents, especially with crossing traffic.

This is achieved by means of a tight integration of infrastructure, sensor technology, communication, human-machine interface and vehicle technology, which enables coordinated decision-making levels of different degrees of abstraction, from the operations control center to the automated driving maneuver on a small scale. In the course of the project, a decentralized platform based on artificial intelligence and vehicle communication that performs cooperative driving tasks to form an emergency lane by means of centralized or/and distributed decision making will be developed. For this purpose, the platform aggregates all necessary static and dynamic information from connected vehicles, digital road infrastructure, and sensors along or at specific points of the route of emergency vehicles. The collected information is processed locally using AI and control algorithms to calculate situation- and vehicle-specific maneuvers.
 

• Micromanagement system with the objective of influencing the traffic in the immediate vicinity of the emergency vehicle in real time in such a way, that an emergency lane is formed autonomously by means of AI-based cooperative automated functions.
• Macromanagement system, whereby traffic interventions along the deployment route are planned and implemented via special communication interfaces to the road users located in the vicinity of the deployment site.
• Design and implementation of a holistic Digital Twin for road transport infrastructure and traffic.
• Autonomous driving utilizing hierarchical AI techniques and model-predictive control (MPC).

Project website
 

• Autonomous Connected Cars
• Emergence Lanes
• V2X Communication
• Digital Twin
• Cloud Services
• Mixed Traffic

Projektträger: DLR
 

Projektsteckbrief
 

Jan 2021 - Dec 2023

2 LE: Capgemini, AKKA
5 SME: 3D Mapping Solutions, DC Vision Systems, Dresden Elektronic, Embeteco, SysGen
1 Research Partner: Bundesanstalt für Straßenwesen (BASt)
1 Relief Organisation: Arbeiter-Samariter-Bund (ASB)
1 Municipality: Stadt Kaiserslautern

Prof. Dr.-Ing. Naim Bajcinca
Gottlieb-Daimler-Str. 42
67663, Kaiserslautern
+49 (0)631/205-3230
naim.bajcinca(at)mv.uni-kl.de