Completed activities

• Designed the DRFSM DEDS framework for recursive inspection.

• Implemented image processing modules for recognizing features and probe position on the parts.

• Designed and implemented visual structure recovery techniques for machine parts (using stereo, contour and illumination map data,) and implemented calibration routines.

• Designed and implemented a sensing CAD interface for generating _1code for bodies from depth, contour (and data reduction,) illumination map, and the recursive feature relationships.

• Implemented the DRFSM DEDS automata for recursive inspection (using robot-held camera, probe and actual parts.)

• Designed sensor and strategy-based uncertainty modelling techniques for the robot-held camera, for recovering the DEDS transitional ``events'' with uncertainty.

• Designed and implemented a modification to an existing reactive behavior design tool (GIJoe) to accommodate ``dumping'' the code of DRFSM DEDS from a graphical interface (used to draw the inspection control automaton.)

The application environment we eventually intend to develop consists of three major working elements: the sensing, design, and manufacturing modules. The ultimate goal is to establish a computational framework that is capable of deriving designs for machine parts or objects, inspect and refine them, while creating a flexible and consistent engineering environment that is extensible. The control flow is from the sensing module to the design module and then to the manufacturing component. Feedback can be re-supplied to the sensing agent to inspect manufactured parts, compare them to the originals and continue the flow in the loop until a certain tolerance is met. The system is intended to be ultimately as autonomous as possible. We study what parts of the system can be implemented in hardware. Some parts seem to be inherently suited to hardware, while some other parts of the system may be possible to put in hardware, but experimentation will provide the basis for making that decision. Providing language interfaces between the different components in the inspection and reverse engineering control loop is an integral part of the project.

The software and hardware requirements of the environment are the backbone for this project. We selected parts of the system for possible hardware implementation. The DEDS model, as an automaton controller, is very suitable for Path Programmable Logic (PPL) implementation. A number of the visual sensing algorithms could be successfully implemented in PPL, saving considerable computing time. There is a lot of interfacing involved in constructing the inspection and reverse engineering environments under consideration. Using multi-language object-based communication and control methodology between the three major components (Sensing, CAD and CAM) is essential.

We intend to develop the CAD interface to be more accurate and to accept more complicated models. The goal is to enhance the automatic programming interface between the data obtained in the sensing module to the _1programming environment. The parametric and 3-D point descriptions are to be integrated to provide consistent and efficient surface descriptions for the CAD tool. For pure inspection purposes the computer aided geometric description of parts could be used as a driver for guiding both the robotic manipulator and the coordinate measuring machine for exploring the object and recognizing discrepancies between the real part and the model.

The computer aided design parameters are then to be used for manufacturing the prototypes. Considerable effort has been made for automatically moving from a computer aided geometric model to a process plan for making the parts on the appropriate NC machines and then to automatically generate the appropriate machine instructions [9]. We intend to use the Monarch VMC-45 milling machine as the manufacturing host. The _1system will produce the NC code for manufacturing the parts.