Environment-Agent Interaction in Autonomous Networked Teams with Applications to Minimum-Time Coordinated Control of Multi-Agent Systems

该奖项的研究目标是开发用于小型/微型无人机(UAV/MAV)的运动协调和路径规划算法，使用适当的、依赖于状态的性能指标来捕捉飞行器与环境的交互作用、任务目标以及网络的系统理论属性。环境既包括环境条件(例如，风)，也包括在车辆附近操作的任何对手的实际或感知的敌对行为。在开发这些结果中将发挥主要作用的一个关键概念将是广义(Zermelo)Voronoi图，它可以比仅基于欧几里德距离的传统Voronoi图更好地捕捉网络中代理状态的动态(例如，估计到达时间、路径曲率约束)。在这些图的帮助下，将表征不同智能体之间和/或智能体与一组目标之间的接近关系，并将制定分散和分布式控制策略。如果研究成功，该研究结果将使小型自主空中、海洋或水下机器人能够在局部强风或洋流存在的情况下，在有限的船上功率和计算资源下，朝着共同的目标如环境监测、分布式监视、多目标分配、协调目标追逐等团队操作。由于这些高空平台体积较小，其运行轨迹受到盛行风向以及船上现有资源的限制的强烈影响。本研究中开发的工具还将应用于网络控制系统的其他领域，在这些领域，智能代理必须合作才能完成他们的任务，如果这项任务由团队中的单个成员承担，则是不可行的。工程学研究生和本科生以及当地高中教师将通过国家科学基金会、S、REU和RET项目以及佐治亚理工学院、S、普拉和达什本科生研究奖学金项目参与到这项研究中来。

The research objective of this award is to develop motion coordination and path-planning algorithms for small/micro unmanned aerial vehicles (UAVs/MAVs) using appropriate, state-dependent performance metrics that capture the interactions of the vehicle with the environment, the mission objectives, as well as the system-theoretic attributes of the network. The environment includes both the ambient conditions (e.g., winds) as well as the actual, or perceived, adversarial behavior of any opponents operating in the vicinity of the vehicle. A key concept that will play a major role in developing these results will be the generalized (Zermelo) Voronoi diagrams which can capture the dynamics of the state of the agents in the network (e.g., estimated-time-of-arrival, path curvature constraints) much better than traditional Voronoi diagrams that are based solely on Euclidean distance. With the help of these diagrams, the proximity relations between different agents and/or between the agents and a set of targets will be characterized, and decentralized and distributed control strategies will be developed.If successful, the results of this research will enable small-scale autonomous aerial, marine or underwater vehicles to operate in teams towards a common objective such as environmental monitoring, distributed surveillance, multiple target allocation, coordinated target pursuit, etc. in the presence of locally strong winds or currents and with limited on-board power and computational resources. Owing to their small size, the trajectories of these aerial platforms are strongly influenced by the prevailing winds, as well as the limitations imposed by the available on-board resources. The tools to be developed in this research will also find application in other areas of networked controlled systems, where intelligent agents must cooperate to perform their mission, a task that would be infeasible if it were to be undertaken by a single member of the team. Graduate and undergraduate engineering students as well as local high school teachers will benefit from their involvement in this research through NSF?s REU and RET projects and through Georgia Tech?s PURA and Dash undergraduate research fellowship programs.