Coordination and Cooperation in Self-Driving Vehicles

尽管自动驾驶汽车正在成为有形的现实，但它们目前面临着几个挑战：它们在速度性能、防撞、传感、合作和协调能力方面受到限制。他们的决策，因此他们的行动，仅仅依赖于他们在船上的感官和内部控制模型。为了避免撞车和防止交通拥堵，自动驾驶车辆必须预测其他车辆在其环境中的行为(自动驾驶和人工操作车辆)，与这些车辆共享其内部状态，并协同操作，选择安全高效的联合控制政策。自动驾驶合作行为的一个原始例子可以在排队中看到，一小群卡车聚集在一个线性结构中，使用无线连接来保持彼此之间的规定距离。在这种情况下，这项研究计划的目标是开发一个框架，以协调自动驾驶车辆车队之间的互动和合作，在复杂的驾驶条件下在有人操作的车辆存在的情况下操作。合作感知和情况评估能力以及行动合作和协调构成拟议框架的基石。受生物启发的计算将被视为实现集体感知和促进协作协调驾驶的一种战略。集体感知、协作和协调的问题将被分解为一组简单的行为，从这些行为中可以构造出一组更复杂的行为，作为情况复杂性和驾驶条件的函数。博弈论将被用作一个工具来建立一个总体框架，以引入激励合作和惩罚自私的行为动力学。将进行各种群体/集体行为用例研究，以验证本研究工作的结果，包括理论和使用模拟。感兴趣的用例包括速度协调、紧急响应、交叉口协商、碰撞避免、排和车队。拟议的研究计划将有助于高素质人才的培训(博士水平3人，硕士水平4人，高级本科生水平10人)。这些学生将有机会获得先进的汽车和计算机技术方面的知识和技能。该计划将通过减少拥堵和撞车事件对道路安全产生积极影响。它将有助于创造科学工具来设计先进的安全驾驶能力。它将有助于在软件制造业创造就业机会，并将通过自动化驾驶和最大限度地减少拥堵来提高生产率。此外，这项研究计划将产生能够加强加拿大汽车行业的技术。

Although they are becoming tangible reality, Self-driving vehicles currently face several challenges: They are limited in their speed performance, crash prevention, sensing, cooperation, and coordination capabilities. Their decision making, and hence their actions, rely merely on their on-board sensory and internal control models. To avoid crashes and prevent traffic congestion, self-driving vehicles must anticipate the behaviour of other vehicles in their environment (self-driving and human-operated vehicles), share their internal state with these vehicles, and cooperatively operate to choose joint safe and efficient control policies. A primitive example of self-driving cooperative behaviour can be seen in platooning, where a small group of trucks assemble in a linear structure, using wireless connectivity to maintain a prescribed distance between each other. In this context, the goal of this research program is the development of a framework for coordinating interaction and cooperation among a convoy of self-driving vehicles, operating in complex driving conditions in the presence of human-operated vehicles. Cooperative sensing and situational assessment capabilities, as well as action cooperation and coordination constitute the building blocks of the proposed framework. Biologically inspired computing will be considered as a strategy for enabling collective sensing, and for facilitating cooperative coordinated driving. The issues of collective sensing, cooperation and coordination will be decomposed into a simple set of behaviors, from which a more complex set of behaviors can be constructed as a function of situation complexity and driving conditions. Game theory will be used as a tool to build an overarching framework for introducing behavior dynamics that motivate cooperation and penalizes selfishness. Various group/collective behavior use-case studies will be conducted to validate the outcome of this research work, both theoretically and using simulations. Examples of use cases of interest include speed harmonization, emergency response, intersection negotiation, crash avoidance, platoons and Convoys. The proposed research program will contribute to the training of Highly Qualified Personnel (3 at the PhD level, 4 at the MSc level, and 10 at the senior undergraduate level.). These students will be provided opportunities to gain knowledge and develop skills in advanced automotive and computing technologies. The program will positively impact road safety by reducing congestions and crashes. It will contribute to creating scientific tools for designing advanced safe-driving capabilities. It will contribute to creating jobs in software manufacturing and will enhance productivity by automating driving and minimizing congestion. Furthermore, this research program will produce technologies that can strengthen the automotive sector in Canada.