The author presents a design methodology for high-level control of flexible manufacturing systems (FMSs). The design procedures are addressed for the control model specification, the process execution software and the...
详细信息
The author presents a design methodology for high-level control of flexible manufacturing systems (FMSs). The design procedures are addressed for the control model specification, the process execution software and the monitoring functions. A functional classification hierarchy of the system resources is introduced which is used for the representation of object class types in generic predicate/transition subnets (Pr/T). The subnets can be parameterized to the instances of the object class types. They can be related through internal and external topology relations. The relations describe the interaction and the synchronization between the resources. The complete Pr/T-net is called the functional model of the FMS. It describes the concurrency and synchronization of the FMS. It is used for the discrete event driven control of the process. The indeterminacy problem in the Pr/T-net was solved with the help of a task scheduler and a task-to-primitive-operation structure. The Pr/T-net was implemented in Prolog.< >
In this paper the development of a programming and simulation environment is described, which was especially tailored for programming of multifinger hands. The research has concerned with the programming of the Karlsr...
详细信息
This paper presents ROSI-Layout, a computer aided planning system for the generation of suitable workcell layouts for robot assembly applications. The idea is to derive first the spatial transformations for the produc...
详细信息
This paper presents ROSI-Layout, a computer aided planning system for the generation of suitable workcell layouts for robot assembly applications. The idea is to derive first the spatial transformations for the product parts, which lead to the assembly of the final product. A global database provides the product data and the precedence graph. This information comes from product design and assembly planning. The design of spatial transformations is derived from constraints given by the geometric shape of the product parts and from rules that define how assembly with robots should be accomplished. This is followed by the generation of a suitable layout. A layout can be developed that is specially designed for the product to be assembled. During the entire planning session, the database manages all planning data and ensures consisteny. ROSI-Layout is an extension of the RObot Simulation system ROSI.
A planning concept is proposed which meets the requirements of flexibility and simplicity of the resulting plan structures and efficiency of replanning. The concept is based on a heuristic search process (branch-and-b...
详细信息
A planning concept is proposed which meets the requirements of flexibility and simplicity of the resulting plan structures and efficiency of replanning. The concept is based on a heuristic search process (branch-and-bound) by which a plan generation tree containing (as nodes) the most promising solution graphs is partly developed. This is achieved by a heuristic evaluation function which estimates the quality of the intermediate plans during the plan synthesis phase. The concept is shown for the area of automatic assembly using a small assembly task as an example. A short description of a robot planning system which is based on the concept is included.< >
HEROS (hierarchically extendible real-time operating system), which was developed and implemented for the control and supervision of robots, is described. It allows the dynamic creation of processes and their manageme...
详细信息
HEROS (hierarchically extendible real-time operating system), which was developed and implemented for the control and supervision of robots, is described. It allows the dynamic creation of processes and their management. The processes in HEROS have no knowledge of their mutual existence and possess no global kernel routines or variables. The interprocess communication and synchronization is accomplished through a channel mechanism, using simple and effective functional calls. The uncoupling of processes attained through the channel concept enables the tasks to be defined and implemented independently and to be operated in parallel. HEROS is composed of several clusters connected through a local area network (LAN). Each cluster consists of several conventional single-board computers, a global memory, and a network controller.< >
An approach for applying a structural texture analysis method to automatic visual inspection of fabric samples in the textile industry is presented. The main steps (image preprocessing, image segmentation, model descr...
详细信息
A concept for the intelligent control of subsystems of a flexible assembly cell is presented. Unknown or uncertain data about the real world may lead towards failure during an assembly task. Therefore, a fault toleran...
详细信息
This paper describes a hierarchical robot action planning system for automatic assembly. Input to the system is a geometrical model of the parts to be assembled. The system provides a graphical editor to model the geo...
详细信息
Machine learning has been studied for more than 20 years. Most of the recent research contributions are basic and come from the areas of Cognitive Science and Artificial Intelligence. The classical domain of machine l...
Machine learning has been studied for more than 20 years. Most of the recent research contributions are basic and come from the areas of Cognitive Science and Artificial Intelligence. The classical domain of machine learning is related to vision and image analysis and image description. Since about five years there has been encreased activity to apply and to extend these general learning methods to really complex systems such as autonomous robots. The purpose of applied machine learning methods is to facilitate and to aid automatic construction and generation of knowledge based systems and to increase the system performance with time. Autonomous robot systems will operate in an unknown real environment and are based on the interaction of the basic system components such as action planner, plan executive and action monitor which need knowledge about the real world and knowledge about how to behave to reach a given goal. A robot system can learn if it is able to make changes and extensions in its behavioural control structure that enables it to better perform a given task. This includes acquisition of declarative procedural knowledge, the developement of manipulative and cognitive skills through instruction and practice as well as the organisation of knowledge into efficient representations. The purpose of automatic self-configurating or self-modifying representations is to make experience based knowledge available for possible future use in the context of increasing robot system performance. This paper reviews some general methods of machine learning application and some first results achieved to date.
This paper describes a method to simulate vision for use in robot applications. Our approach shows the physical modeling of the camera, the light sources and the objects within the scene based on a geometric model. Ma...
详细信息
This paper describes a method to simulate vision for use in robot applications. Our approach shows the physical modeling of the camera, the light sources and the objects within the scene based on a geometric model. Many parameters of the physical model may be adjusted to obtain simulation results close to reality. For processing of the picture data the SPIDER program is added to the simulation of the camera. Though a complete vision system is created. An example shows the simulation of a CCD-camera and a scene with workpieces taken from the ‘European Benchmark’ [COL85].
暂无评论