CPS: Synergy: Collaborative Research: Formal Design of Semi-Autonomous Cyberphysical Transportation Systems

这项研究的目标是为分析和设计具有人工操作员的安全关键型网络-物理运输系统开发基础理论、高效算法和现实实验。这项研究的重点是防止汽车在道路交叉口相撞，因为这类事故约占车辆碰撞总数的40%。具体地说，这项工作的主要目标是设计可证明安全的驾驶员辅助系统，该系统能够理解驾驶员的意图并提供警告/超驰以防止碰撞。为了实现这一目标，从人的因素实验出发，建立了驾驶员-车辆-交叉口系统的混合自动机模型，将驾驶员的行为和性能作为一个有机的组成部分。根据模型参数的置信度，构造了这些混合自动机模型的偏序。然后将驾驶员辅助设计问题描述为一组部分有序的不完全信息混合微分对策，并根据参数置信度对对策进行排序。所产生的设计在驾驶模拟器和大规模计算机模拟中得到了实验验证。这项研究利用嵌入式控制和通信技术的潜力来预防交通路口的撞车，使智能车辆网络相互协作，与周围的基础设施和司机合作，使交通更安全、更愉快、更高效。这项工作是基于形式方法、自主控制和人为因素方面的研究人员之间的合作，他们正在研究现实的、可被证明正确的警告/覆盖算法，这些算法可以很容易地过渡到productionvehicles.http://ares.lids.mit.edu/intersections

The goal of this research is to develop fundamental theory, efficient algorithms, and realisticexperiments for the analysis and design of safety-critical cyber-physical transportation systemswith human operators. The research focuses on preventing crashes between automobiles at roadintersections, since these account for about 40% of overall vehicle crashes. Specifically, the mainobjective of this work is to design provably safe driver-assist systems that understand driver?sintentions and provide warnings/overrides to prevent collisions. In order to pursue this goal,hybrid automata models for the driver-vehicles-intersection system, incorporating driverbehavior and performance as an integral part, are derived from human-factors experiments. Apartial order of these hybrid automata models is constructed, according to confidence levels onthe model parameters. The driver-assist design problem is then formulated as a set of partiallyordered hybrid differential games with imperfect information, in which games are orderedaccording to parameter confidence levels. The resulting designs are validated experimentally ina driving simulator and in large-scale computer simulations.This research leverages the potential of embedded control and communication technologies toprevent crashes at traffic intersections, by enabling networks of smart vehicles to cooperate witheach other, with the surrounding infrastructure, and with their drivers to make transportationsafer, more enjoyable, and more efficient. The work is based on a collaboration amongresearchers in formal methods, autonomous control, and human factors who are studying realistic andprovably correct warning/override algorithms that can be readily transitioned to productionvehicles.http://ares.lids.mit.edu/intersections