This paper investigates an approach that uses the cognitive architecture Soar to improve the performance of an automated robotic system, which uses a combination of vision and force sensing to remove screws from laptop cases. Soar's long-term memory module, semantic memory, was used to remember pieces of information regarding laptop models and screw holes. The system was trained with multiple laptop models and the method in which Soar was used to facilitate the removal of screws was varied to determine the best performance of the system. In all the cases, Soar could determine the correct laptop model and in what orientation it was placed in the system. Soar was also used to remember what circle locations that were explored contained screws and what circles did not. Remembering the locations of the holes decreased a trial time by over 60%. The system performed the best when the number of training trials used to explore circle locations was limited, as this decreased the total trial time by over 10% for most of the laptop models and orientations. Note to Practitioners-Although the amount of discarded electronic waste in the world is rapidly increasing, efficient methods that can handle this in an automated non-destructive fashion have not been developed. Screws are a common fastener used on electronic products, such as laptops, and must be removed during nondestructive methods. In this paper, we focus on using the cognitive architecture Soar to facilitate the disassembly sequence of removing these screws from the back of laptops. Soar is able to differentiate between different models of laptops and store the locations of screws for these models leading to an improvement of the disassembly time when the same laptop model is used. Currently, this paper only uses one of Soar's long-term memory modules (semantic memory) and a screwdriver tool. However, this paper can be extended to use multiple tools by using different features available in Soar such as other long-term memory modules and substates.

This brief investigates the performance of an automated robotic system, which uses a combination of vision and force sensing to remove screws from the back of laptops. This robotic system uses two webcams, one that is fixed over the robot and the other mounted on the robot, as well as a sensorequipped (SE) screwdriver. Experimental studies were conducted to test the performance of the SE screwdriver and vision system. The parameters that were varied included the internal brightness settings on the webcams, the method in which the workspace was illuminated, and color of the laptop case. A localized light source and higher brightness setting as the laptop's case became darker produced the best results. In this brief, the SE screwdriver was able to successfully remove 96.5% of the screws.

Most mechanical engineering curricula include courses in system dynamics, controls, mechatronics, and vibrations, but these courses often do not have a laboratory component. Even if there is such a component, laboratory access is often limited, and thus there is a need to increase students' laboratory experience. This paper addresses the development and testing of instructional material in the form of take-home hardware kits and software that can be used to perform control system experiments at home. The students are given a compact, low-cost hardware kit and software with which they can perform an experiment at home using only their PC/laptop. The kit consists of three components. These are: a hardware interface board which interfaces with the student's PC and with the experiment hardware, a Windows-based user interface program that the students download to their computer, and the experimental setup. Five experiments have been developed. Here we report on two of these experiments that involve control systems: a DC motor/tachometer system and a heater/temperature sensor system. Administration of the kits in several mechanical engineering courses has shown that the kits were effective in improving student understanding of key concepts.

This paper evaluates the feasibility of applying the Lin-Kernighan algorithm to the problem of optimizing cutting and welding paths. A methodology was developed to solve this problem that is based on modifying the coordinate data presented to the Lin-Kernighan algorithm and to interpret the results of this optimization to ensure the problem constraints are followed. The efficiency of the method is tested on several sample problems with very promising results. In all cases, the method is able to find at least a near-optimal tour and was able to reduce the total cutting and air distance of an industrial problem by more than 12%. The solution is applicable to any problem that needs to determine the shortest path between individual shapes on a sheet.

A novel invariant pattern recognition machine is proposed based on a modified ART architecture. Invariance is achieved by adding a new layer called F/sub 3/, beyond the F/sub 2/ layer in the ART architecture. The design of the weight connections between the nodes of the F/sub 2/ layer and the cells of the F/sub 3/ layer are similar to the invariance net. Computer simulations show that the model is not only invariant to translations and rotations of 2-D binary images but also noise-tolerant to these transformed images.>

For pt.I see ibid., p.735-45 (1990). A robot and positioning table system is a kinematically redundant system with respect to planar motion. Two strategies were developed in pt.I to resolve this redundancy and to specify path shapes that make the best utilization of the workspace and speed characteristics of the two devices. In this part, a one-variable dynamic programming approach is developed to obtain a near-minimum time and/or energy trajectory of the two devices. The developed strategies were studied using this path-planning algorithm on a model of a 3 d.o.f. robot and a two-axis linear positioning table for a variety of path shapes and constraints. In addition, experiments were performed in a typical workcell to show the feasibility of the developed strategies. In moving the two devices in opposite directions, the least travel time is obtained when the original path is resolved more in favor of the faster device, whereas the quality of resultant motion is dependent on the controller performance of each device.>

Coordinating the tool (robot) and workpiece (positioning table) motion in continuous manufacturing processes such as sealing, welding, and laser cutting offers several advantages over the motion of only the tool or workpiece. Better utilization of the speed and workspace characteristics of the two devices and improvement in tracking accuracy at sharp corners in the path are some of the merits of this approach. In coordinated motion, the two devices are simultaneously moved to track a given path, and two strategies are developed for coordinating their motion, where each is dependent on the given path information. The first strategy is applicable to any type of path and resolves the motion by splitting the displacement between any two points on the path into segments moved by the robot and the table. The robot and the table move in opposite directions in this strategy. The second strategy is applicable to sharp cornered paths and resolves the given path into two smooth paths. The first path is a double clothoid curve, whereas the second path is a tangential straight line path. The table executes a local motion around the corner in this strategy, whereas the robot is moved at all times. The uniqueness of this strategy in constructing the original corner path is proved. The proposed strategies are shown to be applicable to other coordinated motion systems.>

The design and characterization of a fast linear microactuator is described. The microactuator is constructed of number of piezoelectric plates that are placed on both sides of a sliding mass. Actuation of the plates in an accordionlike fashion provides a linear displacement of +or-0.36 mm. In addition, it has force capability of over 80 g, and is provided with both position and force-sensing capabilities. Characterization of the dynamic performance of the microactuator is presented, and initial tests on it show that it has a second-order system behavior with nonlinear response. The resolution of the microactuator is affected by the performance of the capacitive-type position sensor, and varies from 3 mu m to less than 0.6 mu m.>