This paper describes a new unified formal modeling framework based on generic place/transition nets (PTNs) for concurrent integrated design and planning of electromechanical assemblies. First, a generic PTN model is defined as an abstract (meta)class of all types of PTNs. Then, an integrated object modeling framework is proposed for capturing and representing information and knowledge in the assembly design and planning processes based on the defined generic PTN modeling language and formalisms. The proposed integrated assembly model with the generic PTNs can uniformly represent the causal relations at the assembly level, the operation level, and the feature-based single-part level through the data abstraction of components and connectors on various levels of integrated assembly design and planning. An assembly model compatible with the STandard for the Exchange of Product model data (STEP, officially ISO 10303) is also built with the generic PTNs. To validate the proposed modeling framework, a prototype system has been developed, and a case study on gearbox assembly design and planning is provided.

This paper presents a unified approach to coordination planning and control of trajectories for robot manipulators. The generalized robot pose is defined as the robot configuration consisting of both its position and orientation. The unified treatment for the position and orientation of the end-effector is based on the robot pose ruled surface that is formed as a 3-D motion locus of its configuration vector. The coordination planning and control of pose trajectories is accomplished by generating and optimizing the pose ruled surface under the constraints of kinematics and dynamics performances, and controlling the motion laws of two end points of the orientation vector and calculating the coordinates of instantaneous corresponding points. The simulation of Puma 560 robot is given to verify the feasibility of the proposed approach and demonstrate the capabilities of generation and control models.

Presents a preliminary research effort, on a Web-based collaborative design platform for robotic systems. The issues involved in the development process of (micro) robotic systems are first discussed. Then, a knowledge-server based Web distributed object modeling and evaluation framework (WebDOME) is proposed to enable designers to build concurrent integrated models using both local and distributed resources, and to collaborate by exchanging services based upon the CORBA standard communication protocol. To facilitate the rapid construction of integrated models for robotic system CAD, a prototype Web-based collaborative environment, WebRobot, is implemented under the WebDOME framework with concurrent integration of multiple cooperative knowledge sources and software. The system can provide platform-independent and distributed users access to WebDOME module servers throughout the network over the Internet/intranet and WWW. A case study is provided to demonstrate the functionality of the system and to illustrate how designers in different teams and organizations may participate and collaborate in the design process of robotic systems.

This paper presents an approach to the design of robotic systems from the perspectives of product family design and knowledge support, i.e., a platform based robot family design using a knowledge intensive support paradigm. The high-level information and knowledge modeling issues regarding the design of families of robotic systems are addressed. A module-based integrated robot family design scheme is proposed with knowledge support for task or customer requirement modeling, robot architecture modeling, robot platform establishment, robot family generation, and robot assessment. The issues and requirements, related to the development of knowledge intensive support framework and system for module-based robot family design, are also addressed. The developed web-based prototype system can provide support for robot/family customization design over the Internet. Finally, the design cases are provided.

This paper provides an integrated intelligent approach to rapid robotic assembly prototyping, planning and control. The developed RAPID assembly system can process various types of knowledge in assembly design, process and task planning, and assembly operation control. It provides the possibility for integrating a development team to work over a network and allows concurrent and cooperative specification, design, planning and analysis of complex mechanical systems and assemblies. The generation and experimental implementation and verification of a CAD-driven hybrid neuro-fuzzy control strategies for robotic assembly are presented. In particular, the use of neuro-fuzzy expert Petri net for assembly and task planning and Prolog as computer language for the specification of the discrete event system in operations control is proposed. Details are given for the vision-guided robotic assembly implementation, together with experimental validation of the concepts, hardware and software system using a sample optic lens assembly.

This paper identifies and describes how knowledge based systems (KBSs), fuzzy logic and artificial neural networks (ANNs) can be integrated, and provides a novel (fuzzy) expert Petri net (EPN (FEPN)) based approach for the integration of KBSs and ANNs. A generic expert Petri net model of single neuron is presented, and a two-layer generic Petri net model for (fuzzy) neural networks and neural (fuzzy) expert Petri nets (NEPN, NFEPN)) that use this neuron model as a building block is described. The NEPN and NFEPN models can be used for representing a (fuzzy) knowledge base and (fuzzy) reasoning. Also, they can be utilized to develop ANN-like multilayered Petri net architectures of distributed hybrid intelligence having learning ability. Some application examples are illustrated for validation of the proposed models.