论文标题
在城市环境中的异质代理的风险敏感会合算法
Risk Sensitive Rendezvous Algorithm for Heterogeneous Agents in Urban Environments
论文作者
论文摘要
近年来，对城市环境中快速且廉价的包裹交付的需求已大大增加。设想通过利用乘车共享车辆网络来实施在城市环境中有效的最后一英里交付的框架，在那里，无人驾驶航空系统（UASS）上所述车辆上的丢弃套件，然后涵盖了大部分距离，最终将另一台UAS捡起。这种方法提出了许多工程挑战，包括两种代理的安全会合：UAS和人类操作的地面车辆。在本文中，我们引入了一个框架，以最大程度地减少故障风险，同时允许最佳使用受控代理。我们制定了一个紧凑的快速计划者，以不精确的行为将UAS驱动到被动地面车辆，同时提供直观而有意义的程序，以最少的最佳牺牲来确保安全。结果算法显示，通过数值测试可以实时实时实现。
Demand for fast and inexpensive parcel deliveries in urban environments has risen considerably in recent years. A framework is envisioned to enforce efficient last mile delivery in urban environments by leveraging a network of ride-sharing vehicles, where Unmanned Aerial Systems (UASs) drop packages on said vehicles which then cover the majority of the distance to finally be picked up by another UAS for delivery. This approach presents many engineering challenges, including the safe rendezvous of both agents: the UAS and the human-operated ground vehicle. In this paper, we introduce a framework to minimize the risk of failure, while allowing for optimal usage of the controlled agent. We formulate a compact fast planner to drive a UAS to a passive ground vehicle with inexact behavior, while providing intuitive and meaningful procedures to guarantee safety with minimal sacrifice of optimality. The resulting algorithm is shown to be fast and implementable in real-time via numerical tests.
