Future automated vehicles will be able to negotiate cooperative maneuvers with each other via vehicle-to-everything communication, increasing safety, driving comfort, and traffic flow. Researchers have proposed several enabling cooperation protocols, but only a few have already been implemented in real-world vehicles. While simulations can be helpful for the development of a cooperation protocol, in the end, it is necessary to validate functionality in the target system. This paper implements one explicit general-purpose protocol for cooperative maneuvers in an automated vehicle, evaluating the overall cooperative, connected, and automated system in-depth. We show its feasibility, suitability for an example use case, and improvement potentials.

Connected and automated vehicles will not only autonomously plan their motions but also use vehicle-to-vehicle communication to negotiate cooperative maneuvers. Via intent-sharing and joint decision-making, those vehicles will perform coordinated actions together. Up to now, studies on cooperative maneuvers mostly assumed participants always cooperate. This scenario is fair but unrealistic. In our contribution, we investigate how vehicles can assess cooperative maneuver requests to decide whether or not to participate in them. Our decision algorithm ensures safety and fairness while being independent of the underlying cooperative maneuver protocol. We show the algorithm’s feasibility in simulations. This paper is thus another step towards realizing cooperative maneuvers.

Automated vehicles will be able to drive autonomously in various environments. An essential part of that is to predict other vehicles' intents and to coordinate maneuvers jointly. Such cooperative maneuvers have the ability to make driving safer and traffic more efficient. However, among the various communication protocols proposed for maneuver coordination, no single one satisfies all requirements. This paper assesses failure risks and mitigation strategies for cooperative maneuvers, including an analysis of popular protocols regarding this aspect. Next, we evaluate one particular cooperation protocol, the complex vehicular interactions protocol (CVIP), concerning performance of mitigation mechanisms and their influence on maneuver success rates or times to reach consensus among maneuver participants. Via simulation, we show that CVIP is suitable for cooperative maneuvers in realistic scenarios and investigate the trade-offs individual mitigation mechanisms face. These results are well-suited as guidelines and benchmark for other researchers developing cooperative maneuver protocols.

Cooperative maneuvers will enable automated vehicles to optimize traffic flow and increase safety via vehicle-to-vehicle communication. Different approaches and protocols exist, but no study has investigated how to generate intelligent suggestions for cooperative maneuvers. We use machine learning to propose safe and suitable overtake maneuvers. To this end, we train a classifier for maneuver success as well as regression models on an extensive data set of randomized initial situations. In addition, we show that changing objective functions allows optimizing for different goals like smoothness or driven distance. Our evaluation shows that machine learning is well-suited to suggest cooperative maneuvers while also facing some trade-offs. This work may thus provide a benchmark for advanced studies on cooperative maneuver proposals.

Automated vehicles need to interact: to create mutual awareness and to coordinate maneuvers. How this interaction shall be achieved is still an open issue. Several new protocols are discussed for cooperative services such as changing lanes or overtaking, e.g., within the European Telecommunications Standards Institute (ETSI) and Society of Automotive Engineers (SAE). These communication protocols are, however, usually specific to individual maneuvers or based on implicit assumptions on other vehicles' intentions. To enable reuse and support extensibility towards future maneuvers, we propose CVIP, a protocol framework for complex vehicular interactions. CVIP supports explicitly negotiating maneuvers between the involved vehicles and allows monitoring maneuver progress via status updates. We present our design in detail and demonstrate via simulations that it enables complex inter-vehicle interactions in a flexible, efficient and robust manner. We also discuss open questions to be answered before complex interactions among automated vehicles can become a reality.