Many enterprises experience difficulty in training people to work with expensive equipment, which is needed for carrying out profitable work tasks (e.g., production line robots). Similar problems are found when work is of a complex and safety-critical nature (e.g., nuclear environments, explosive placement, surgery). A common problem faced by educational institutions concerns the limited availability of expensive robotics equipment, with which students in the didactic program can work, in order to acquire valuable "hands on" experience. This paper describes a method of education and training involving off-line usage of virtual reality environments for task planning. When tasks are developed to the satisfaction of the trainee, they are exported to remote physical hardware, via the Internet, for real-world execution. Development of the system and the training experiments is discussed, along with some of the issues raised for telerobotics and solutions to the problem of detecting collisions in the virtual world. The approach has been shown to be viable, and increases the education and training possibilities for key workers while maintaining a low cost of ownership. The downtime of mission critical equipment is minimized while the gaining of valuable experience is maximized.

The active surface device is a new type of automation concept to handle multiple objects with high precision. The concept consists of using a massively parallel microactuator array to generate a pressure field on a planar surface. The objects can be translated, rotated, and flipped by controlling this pressure field surrounding the objects. The architecture of the active surface device is designed in a modular manner, which allows the array to be expanded by simply adding modules to the system. A general-purpose test bed has been built to experiment with this new design. An object recognition algorithm and several control techniques have been successfully implemented to perform basic sensing and handling operations. The architecture and mechanisms of this prototype test bed and the implementation of algorithms are presented.

Research related to sub-millimeter or even micro-sized objects, such as micromechatronics, has the potential to make huge impacts on our society. Current manufacturing techniques, however, are incapable of massive parallel handling of objects at these scales. The lack of manufacturing techniques for massive parallel manipulation of so small objects presents a technology barrier to the eventual commercial success in fields like MEMS. The programmable and position closed-loop controllable pneumatic active surface device presented in this paper is a fundamentally new approach to automated massive small-sized parts manipulation. The appropriate choice of force generated by blowing or sucking air-flow through tubes of the pneumatic active surface device, is shown to cause objects placed on the array to be moved in manners that are useful It offers greater ability and speed and it can be employed to position, orient, identify, sort, feed, and assemble parts or objects on the active surface device. It can control several objects simultaneously. This paper first describes an experimental device and potential applications, and then it focuses on closed-loop positioning control techniques (translating) for rigid (VLSI chips, MEMS) objects and flexible (PVC polyvinyl foil, paper). The implemented control strategies have been successfully tested on the experimental device as described in the paper.

In this paper a neural network controller for trajectory tracking for a two DOF SCARA robot mechanism is presented. Two types of neural network controllers have been built: a joint space neural network controller and a task space neural network controller. The two controllers have been compared with the computed torque method controller, also in the joint and task space. The four controllers were tested on a real robot mechanism. Lyapunov theory, for deriving the adaptation law, or the learning algorithm of neural networks, was used to prove the robot system stability with a neural network controller.>