Research Of Services Task Planning Based On Parameter-driven Mechanism In Intelligent Space

Under the dynamic environment, it is difficult for service robot to provide active and intelligent service according to the change of environmental information. With the development of computer and communication technology, the research to service robot based on intelligent space technology is becoming an inevitable trend. With the ubiquitous characteristic of intelligent space, robot can improve its ability of environment perception and processing. In complex and dynamic environment, the robot task planning based on interaction and coordination mechanism between robot and intelligent space technology is an important way for reducing the cost of robot, improving its task execution ability and service quality, expanding its application. Based on the intelligent space experimental environment of service robot laboratory in Shandong University, this thesis studied the interaction between intelligent space technology and service robot, predicted the context data in intelligent spatial and provided the intelligent service for users. The main works of this thesis are shown as followed:Firstly, in order to solve the complexity and uncertainty characteristics of context information in smart space, this thesis uses first-order predicate logic to describe the context information and uses Markov logic network to achieve the unification of the first-order logic and probabilistic graphical models. And then we builds Markov logic network model based on some particular scenes which were predicted by Neural network and at last uses this model to realize the prediction of device information which is valuable to the task planning by relevant complex context information.Secondly, a framework of automatic service composition for service robot based on parameter-driven is built. A fast service composition (FSC) algorithm is designed to realize the robot’s task planning. The service robot is given the ability to dynamically compose and deliver service under this framework, so service intelligence and service quality were improved correspondingly.Thirdly, due to the uncertainty of equipment operation, network communications and data storage, the thesis proposes a service recovery strategy based on the framework of automatic service composition. For the causes of service failure, such as: the missing of driving parameters, services, devices and so on, and appropriate repair strategies are established respectively to enable service processes executed smoothly and efficiently and to improve fault tolerance of the system.Fourthly, these modules mentioned in above chapter are integrated and a server framework is built to construct an intelligent software system in the intelligent space. The real operation of each module according to the daily service needs and emergencies are verified.