基于微重启和部分客观马尔可夫决策模型的智能.docVIP

基于微重启和部分客观马尔可夫决策模型的智能 　　摘要：针对智能水下机器人（AUV）软件故障修复过程中存在的修复代价过高和系统环境只有部分可观察的问题，提出了一种基于微重启技术和部分客观马尔可夫决策（POMDP）模型的AUV软件故障修复方法。该方法结合AUV软件系统分层结构特点，构建了基于微重启的三层重启结构，便于细粒度的自修复微重启策略的实施；并依据部分可观马尔可夫决策过程理论，给出AUV软件自修复POMDP模型，同时采用基于点的值迭代（PBVI）算法求解生成修复策略，以最小化累积修复代价为目标，使系统在部分可观环境下能够以较低的修复代价执行修复动作。仿真实验结果表明，基于微重启技术和POMDP模型的AUV软件故障修复方法能够解决由软件老化及系统调用引起的AUV软件故障，同与两层微重启策略和三层微重启固定策略相比，该方法在累积故障修复时间和运行稳定性上明显更优。 　　关键词：智能水下机器人；微重启；自修复；部分客观马尔可夫决策；基于点的值迭代算法 　　中图分类号： TP311.52 　　文献标志码：A 　　Selfrepair method for autonomous underwater vehicle software based on microreboot and partially observable Markov decision process model 　　ZHANG Rubo1，2， MENG Lei1， SHI Changting1* 　　1.College of Computer Science and Technology， Harbin Engineering University， Harbin Heilongjiang 150001， China 　　； 　　2.College of Mechanical and Electronic Engineering， Dalian Nationalities University， Dalian Liaoning 116600， China 　　Abstract： 　　Aiming at the disadvantages of high fixing cost and partial observability of system environment in the process of repairing Autonomous Underwater Vehicle （AUV） software faults， a method was proposed based on microreboot mechanism and Partially Observable Markov Decision Process （POMDP） model for failure repair of AUV. To facilitate the implementation of the finegrained selfrepair microreboot strategy， a hierarchical structure was built based on microreboot combined with the characteristics of AUV software. Meanwhile， a selfrepair model was put forward according to the theory of POMDP. With the goal of minimizing the fixing cost， the repair strategy was solved by Point Based Value Iteration （PBVI） algorithm to allow the repair action to execute in the partially observable environment at a lower cost. 　　The simulation results show that the proposed repairing method can solve the AUV software failures caused by the softwareaging and system calls. Compared with twotier microrepair strategy and threetier microrepair fixing strategy， this method is obviously superior to the contrast meth