Skip to main content
QUICK REVIEW

[论文解读] An ASP-Based Architecture for Autonomous UAVs in Dynamic Environments: Progress Report

Marcello Balduccini, William C. Regli|arXiv (Cornell University)|May 6, 2014
Logic, Reasoning, and Knowledge参考文献 18被引用 8
一句话总结

本文提出了一种基于ASP的自主无人机代理架构,通过集成网络感知推理,以应对动态环境中不可靠且高成本的通信问题。通过结合集中式规划、分布式执行和基于答案集编程的实时监控,该系统相较非网络感知方法,将任务时长减少了最多30%,图像数据陈旧度降低了50–100%。

ABSTRACT

Traditional AI reasoning techniques have been used successfully in many domains, including logistics, scheduling and game playing. This paper is part of a project aimed at investigating how such techniques can be extended to coordinate teams of unmanned aerial vehicles (UAVs) in dynamic environments. Specifically challenging are real-world environments where UAVs and other network-enabled devices must communicate to coordinate---and communication actions are neither reliable nor free. Such network-centric environments are common in military, public safety and commercial applications, yet most research (even multi-agent planning) usually takes communications among distributed agents as a given. We address this challenge by developing an agent architecture and reasoning algorithms based on Answer Set Programming (ASP). ASP has been chosen for this task because it enables high flexibility of representation, both of knowledge and of reasoning tasks. Although ASP has been used successfully in a number of applications, and ASP-based architectures have been studied for about a decade, to the best of our knowledge this is the first practical application of a complete ASP-based agent architecture. It is also the first practical application of ASP involving a combination of centralized reasoning, decentralized reasoning, execution monitoring, and reasoning about network communications. This work has been empirically validated using a distributed network-centric software evaluation testbed and the results provide guidance to designers in how to understand and control intelligent systems that operate in these environments.

研究动机与目标

  • 解决多智能体无人机协同中通信建模不切实际的问题,其中通信常被假设为可靠或免费。
  • 开发一种实用的端到端基于ASP的代理架构,集成集中式规划、分布式执行和实时监控。
  • 使无人机能够动态推理网络状况,包括故障和带宽限制,以维持任务有效性。
  • 证明网络感知推理相较于忽略或过度简化的通信动态的传统方法具有优越性。
  • 提供一种任务感知网络框架,可根据实时任务和网络状态自适应调整QoS。

提出的方法

  • 使用答案集编程(ASP)灵活表示无人机协同中的知识、动作和推理任务。
  • 设计一种混合架构,结合集中式任务规划与分布式执行,并对无人机行为进行实时监控。
  • 在CORE网络仿真器中使用现实的无线模型来建模网络状况,包括通信范围有限、带宽受限和动态连接性。
  • 集成OLSR路由协议以维护最新的路由表,并确定无人机与中继节点之间实时的通信可用性。
  • 使用clasp求解器执行高效的ASP推理,在复杂场景下执行时间也低于一秒。
  • 使用CORE在MANET环境中仿真无人机任务,允许未修改的Linux应用程序在虚拟节点上运行,并具备真实的网络行为。

实验结果

研究问题

  • RQ1基于ASP的推理能否在通信不可靠且代价高昂的动态、网络受限环境中有效协调无人机团队?
  • RQ2与非网络感知规划相比,网络感知推理在任务时长和数据陈旧度方面如何提升任务性能?
  • RQ3基于ASP的架构在不预先指定行为的情况下,能在多大程度上处理通信故障并动态自适应调整计划?
  • RQ4在无人机协同中,集成网络感知推理与任务感知网络时,可实现多大的性能提升?
  • RQ5在复杂、实时的网络环境中,基于ASP的方法在可扩展性和效率方面表现如何?

主要发现

  • 与非网络感知规划相比,网络感知的基于ASP的方法将任务时长最多减少了30%。
  • 在所有测试案例中,总图像陈旧度降低了50–100%,证明了在动态网络条件下具有更优的数据新鲜度。
  • 即使网络意外发生故障,网络感知方法仍通过检测和适应故障,保持了比非网络感知方法更低的陈旧度。
  • 使用clasp求解器在现代台式机上,ASP推理的执行时间始终低于一秒,表明其具备实际可行性。
  • 将网络感知推理与任务感知网络集成,实现了自适应QoS推断,提升了系统的鲁棒性和性能。
  • 该系统优于非网络感知方法以及乐观方法(假设通信完美),证明了真实网络建模的价值。

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。