Context and Learning to Programming of Intelligent Equipment

.. of Automation of Production in Machine Building, … and Computational Intelligence in development of programming languages for industrial applications such as industrial robots … Context and Learning based Approach to Programming of Intelligent Equipment Andrey V. Gavrilov Department of Automation of Production in Machine Building, Novosibirsk State Technical University Karl Marx Av., 20, Novosibirsk 92, 630092 Russia Andr_gavrilov@yahoo.com Abstract In this paper novel approach for programming of intelligent equipment …

One of most actual problems in development of intelligent systems for manufacturing is human- machine interface. Two kinds of such interfaces are known, oriented on programming and learning respectively. Programming is used usually for industrial robots and other technological equipment. Learning is more oriented for service and toy robotics. There are many different programming languages for different kinds of intelligent equipment, for industrial robots-manipulators, mobile robots, technological equipment [1, 2]. The re-programming of industrial robotic systems is still a difficult, costly, and time consuming operation. In order to increase flexibility, a common approach is to consider the work- cell programming at a high level of abstraction, which enables a description of the sequence of actions at a task-level. A task-level programming environment provides mechanisms to automatically convert high- level task specification into low level code. Task-level programming languages may be procedure oriented [3] and declarative oriented [4, 5, 6, 7] and now we have a tendency to focus on second kind of languages. But in current time practically all programming languages for manufacturing are deterministic and not oriented on usage of learning and fuzzy concepts like in service or military robotics. But it is possible to expect in recent future reduce of difference between industrial and service applications. For example, known plans of Toyota Inc. to employ humanoid robots in automobile manufacturing. So it seems interesting and perspective to apply achievements of AI and Computational Intelligence in development of programming languages for industrial applications such as industrial robots or technological equipment. In this paper we suggest novel approach to programming of robots and technological equipment based on usage of context and learning and so oriented on usage of natural language for learning. In this approach we do not distinguish learning and programming combining in one system declarative (description of context) and procedural knowledge (routines for processing of context). Also here new Context Based Language for Robot (CBLR) is proposed and elements of one are described. This suggested approach is based on research of author during development of system software for transportation industrial robots based on learning [8, 9] and development of software for searching of documents by natural language query [10]. 2. Previous example of usage of similar approach for programming of transportation industrial robots… The language BLRP consisted of following groups of commands: 1) For assignment of context, 2) For control of moving, 3) For control of execution of routines, 4) For definition of conditions, 5) For determination of points in environment (service area) of robot, 6) For description of state of robot and technological equipment, 7) Serving commands. Architecture of software developed for robot consists of subsystems for programming, checking and execution of routines (figure 1). Context included main following parameters: 1) X, Y, Z - coordinates of point, 2) Description of condition operator, 3) State of equipment, 4) State of robot, 5) Number of link of robot, 6) Number of cell of equipment, 7) Number of object. Number in these parameters means identifier. Fig. 1. Architecture of software for transport robot. Programming in this system was replaced by learning. Result of one was knowledge base with associations between words of natural language and sequences of commands for description of context and….