An approach to force controlled robot programming by human demonstration is presented. A human operator utilises a joystick to guide a robot with a force sensor to do a task including continuous contact between a manipulated object and an un-modelled environment. During the demonstration, the position, velocity and force of the object manipulated are acquired. Then the recorded data are processed, analysed, and translated into a textual robot program, which provides more robust execution in the presence of uncertainties. This approach consists of three key techniques-data processing, subtask segmentation and termination condition identification. A software package is developed to generate the programs automatically. Experiments show the industrial applicability.

An integrated system for programming by demonstration, visualizing, and executing compliant motion programs is described. A human operator utilises a joystick to guide a robot with a force sensor to do a task including continuous contact between manipulator and environment. The demonstration may be executed either on an actual robot, or in a graphically simulated environment. During the demonstration, the position, velocity and force of the object manipulated are acquired. Then the recorded data are processed, analysed, and translated into a textual robot program, which provides more robust execution in the presence of uncertainties. The system is composed of a model-based reaction force simulator, a visualization package, a rule-based translator, and an interpreter for compliant motion programs. Experiments show the industrial applicability.

Numerous generalized architectures for telerobotic systems have been proposed. Most are hard-wired instantiations of a specific approach, which rarely address the interactions between human and autonomous elements of teleautonomous systems. The work described here provides a more general, easily extensible and modifiable architecture. Specific issues addressed include methods that fuse decisions from multiple sources (such as human, reactive, or deliberative), integrate multiple command sources, and accommodate multipurpose event recognizers to change operating modes. These methods may be dynamically altered to generate a variety of control modes. A result of the research described in this paper is a modifiable, extensible framework for the unification of the many modes of control, such as shared, teleoperative, and supervisory, which are described in the telerobotics literature.

Session management of a telerobotic operation is an important aspect which has not been adequately addressed by the research community. This paper describes work performed by the Universities Space Automation/Robotics Consortium (USARC) which allows dynamic configuration and monitoring of a telerobotic system which is distributed over a wide-area network. The Telerobotic Session Manager (TSM) allows the session manager to coordinate control among multiple operators, to perform task handoffs or to control multiple robots. This provides greater modularity and reconfigurability than previous telerobot control systems. Motion control of the telerobot is provided by a generic robot motion controller which receives configuration information from TSM. Real or virtual environments are simulated by predictive simulation software which is also configured via TSM. This paper describes TSM, the motion controller, the simulation system, and a variety of tasks which have been performed by the system.>

Describes a control architecture for telerobotics research. The architecture was object-oriented and data-driven, and can be distributed over many processors on a wide-area network (WAN). The basic capabilities of this testbed have already been demonstrated in tests distributed over four cities. The data distribution techniques of this control architecture are described, as well as details of the current implementation and experimental results.>