Abstract: A computerized method/system is provided for planning motion of a robot within a free space confined by obstacles, from an initial position to a goal position. In executing the method/system, a plan is generated so that the robot can hold and maneuver a workpiece throughout a sequence of bending operations to be performed by a bending apparatus. A plurality of proposed movements to be made by the robot are proposed for an mth movement within a sequence of movements, and at least a portion of the robot and the obstacles that confine the free space are modeled. A determination is made as to whether a collision will occur between the robot and an obstacle for each proposed movement, and a plan is generated including the sequence of movements by choosing for each movement in the sequence of movements, a proposed movement that will not result in a collision and that will bring the robot closer to the goal position.

Abstract: A method of controlling a robot to perform a weaving action and a tracking action using a non-contact sensor. When a weaving start command with a condition of a cycle Tw is issued, a laser sensor starts scanning in a cycle Tw/2n in synchronism with the start of weaving action, and outputs sensor data for every scanning time to be stored in a memory. After starting the weaving action, the robot performs a weaving action with a welding line as a reference path, until the tool reaches the weaving extreme (Sm, Sn+m, S2n+m, . . . ) or the termination of the weaving according to the weaving condition. Since a timed relationship between the weaving action and the scanning action of the laser sensor is known, the robot position corresponding to detection data can be calculated, based on which it is possible to successively determine a target position of the robot movement by adding a weaving amount for each detection point.

Abstract: A power management system for a personal computer comprises a power management processor, a switchable power supply and a keep alive power supply. The processor is powered by the keep alive power supply that continuously provides power. The computer is powered by a power supply that is switchable in response to a control signal. The processor preferably controls the switchable power supply. The processor is coupled to receive external device interrupts from a plurality of external devices that instruct the processor when to turn the switchable power supply on and off. The processor is also coupled to the computer through an interface. The power management system also includes a method for turning the computer on and off. A preferred method uses the processor to control the power provided to the computer.

Abstract: A device for discriminating an attribute of an image in a block area contained in a document image includes a device for performing a Fourier transformation based on image data in the block area and for determining a spatial frequency spectrum relating to the image in the block area; and a neural network for outputting a discrimination result as to whether or not the attribute of the image in the block area is a halftone dot image based on the spatial frequency spectrum output from the Fourier transform device.

Abstract: A robotic system that moves a surgical instrument in response to the actuation of a control panel that can be operated by the surgeon. The robotic system has an end effector that is adapted to hold a surgical instrument such as an endoscope. The end effector is coupled to a robotic arm assembly which can move the endoscope relative to the patient. The system includes a computer which controls the movement of the robotic arm in response to input signals received from the control panel. The robotic system is mounted to a cart which can be wheeled to and from an operating table. The cart has a clamping mechanism which attaches the cart to the table. The system also contains a spring loaded mount plate that allows the robotic arm to be rotated and adjusted relative to the cart and the patient. Both the robotic arm and the control panel are encapsulated by protective bags that prevent the system from being contaminated.

Abstract: A nonrecurrent version of the Neural Network Binary Code Recognizer is disclosed. This Nonrecurrent Binary Code Recognizer, which decodes an input vector of n analog components into a decoded binary word of n bits, comprises an analog-to-digital converter, an inverter circuit, a digital summing circuit and a comparator circuit.

Abstract: A power management system for a personal computer comprises a power management processor, a switchable power supply and a keep alive power supply. The processor is powered by the keep alive power supply that continuously provides power. The computer is powered by a power supply that is switchable in response to a control signal. The processor preferably controls the switchable power supply. The processor is coupled to receive external device interrupts from a plurality of external devices that instruct the processor when to turn the switchable power supply on and off. The processor is also coupled to the computer through an interface. The power management system also includes a method for turning the computer on and off. A preferred method uses the processor to control the power provided to the computer.

Abstract: A neural network includes a plurality of input nodes for receiving the respective elements of the input vector. A copy of all of the elements of the input vector is sent to the next level of nodes in the neural network denoted as intermediate nodes. The intermediate nodes each encode a separate template pattern. They compare the actual input pattern with the template and generate a signal indicative of the difference between the input pattern and the template pattern. Each of the templates encoded in the intermediate nodes has a class associated with it. The difference calculated by the intermediate nodes is passed to an output node for each of the intermediate nodes at a given class. The output node then selects the minimum difference amongst the values sent from the intermediate nodes. This lowest difference for the class represented by the output node is then forwarded to a selector.

Abstract: An optoelectronic cellular neural network, which can be programmed optically, in amorphous or polycrystalline silicon, which makes up a monolithic image processing system with optical input and output which can be programmed by optical signals. Its layered structure for both the upper and lower surfaces are occupied, without discontinuity, by photosensitive and photoemissive devices. The network basically consists of an input photosensitive layer, a processing layer, a photosensitive control layer and also an optical control mask.

Abstract: Target based machine vision useful for alignment of sensors and other objects affixed to structures, robots and the like. While addressed particularly to alignment of machine vision systems relative to structures, the techniques disclosed are useful with a multitude of different sensors and objects.

Abstract: A control apparatus for controlling a control amount of a control target by changing an operating amount which is supplied to the control target, comprises an adjusting section for calculating an adjustment signal in accordance with the control amount measured by the control target and a target control amount, an operating section for transmitting an operating amount to the control target in accordance with the adjustment signal calculated by the adjusting section, an observation data storing section for storing observation data having control amounts and operating amounts observed previously, and a learning section for learning internal parameters for the adjusting section in accordance with response time taken for the control target from input of the operating amount from the operating section to the control target to appearance of an influence of the operating amount on the control amount and observation data stored in the observation data storing section.

Abstract: Constructing and simulating artificial neural networks and components thereof within a spreadsheet environment results in user friendly neural networks which do not require algorithmic based software in order to train or operate. Such neural networks can be easily cascaded to form complex neural networks and neural network systems, including neural networks capable of self-organizing so as to self-train within a spreadsheet, neural networks which train simultaneously within a spreadsheet, and neural networks capable of autonomously moving, monitoring, analyzing, and altering data within a spreadsheet. Neural networks can also be cascaded together in self training neural network form to achieve a device prototyping system.

Abstract: Constructing and simulating artificial neural networks and components thereof within a spreadsheet environment results in user friendly neural networks which do not require algorithmic based software in order to train or operate. Such neural networks can be easily cascaded to form complex neural networks and neural network systems, including neural networks capable of self-organizing so as to self-train within a spreadsheet, neural networks which train simultaneously within a spreadsheet, and neural networks capable of autonomously moving, monitoring, analyzing, and altering data within a spreadsheet. Neural networks can also be cascaded together in self training neural network form to achieve a device prototyping system.

Abstract: A method for causing a neural circuit model to learn typical past control results of a process and using the neural circuit model for supporting an operation of the process. The neural circuit model is caused to learn by using, as input signals, a typical pattern of values of input variables at different points in time and, as a teacher signal, its corresponding values of the control variable. An unlearned pattern of input variables is inputted to the thus-learned neuron circuit model, whereby a corresponding value of the control variable is determined. Preferably, plural patterns at given time intervals can be simultaneously used as patterns to be learned.

Abstract: A method for rapid and sensitive protein family identification is disclosed. The new designs include an n-gram term weighting algorithm for extracting local motif patterns, an enhanced n-gram method for extracting residues of long-range correlation, and integrated neural networks for combining global and motif sequence information.

Abstract: A fuzzy control system, particularly for dose rate control in an X-ray diagnostics apparatus, such a control system converting input signals into output signals. A first and a second individual module are provided, whereby respectively at least two input signals can be supplied to the first and to the second individual module for generating an output signal. Compared to a fuzzy control system that does not comprise these individual modules, the rule base becomes smaller, only input conditions that have influence on the individual module need be provided with rules, so that a simple check of the rules for completeness is assured.

Abstract: A robotic system that moves a surgical instrument in response to the actuation of a foot pedal that can be operated by the foot of a surgeon. The robotic system has an end effector that is adapted to hold a surgical instrument such as an endoscope. The end effector is coupled to an articulate arm which can move the endoscope relative to the patient. The articulate arm can be located within a first coordinate system, the end effector may be located in a second coordinate system and the surgical instrument may be located within a third coordinate system. The system includes a computer which controls the movement of the robotic arm in response to input commands received from an input device such as the foot pedal. The controller may perform a software routine that computes the movement of the articulate arm and end effector in response to the input commands. The software routine may utilize transformation functions to transfer movement of the instrument from one coordinate system to another coordinate system.

Abstract: In a fuzzy inference system using a plurality of output label membership functions mBi(y), each of which is represented by a singleton having a position yi and a consequent grade gi, a defuzzifying method comprising the steps of: selecting and identifying n singletons in magnitude order of the consequent grade as g1, g2, . . . , gn (g1 is the highest); and obtaining the center of gravity y0 as the final result of defuzzification, by calculating the following approximate equation (n=2, 3, . . . )y0.apprxeq.y1+g2 (y2-y1)+g3 (y3-y1)+. . .+gn(yn-y1).

Abstract: A robot and associated control system, as well as a method of control, for servicing a heat exchanger having a substantially planar tube sheet which defines a multiplicity of laterally spaced tube openings of known shape, each of which is centered at a coordinate on a tube sheet coordinate system. A sensory system associated with the robot end effector and the associated digital processing system, includes a vision subsystem for generating an image of a portion of the tube sheet and generating a first signal commensurate with the spatial relationship of the tool to a selected tube opening. An optical subsystem is also provided, for projecting a structured light beam toward the tube sheet and receiving a reflected structured light pattern, indicative of how closely the tool is aligned with the target opening.

Abstract: An image forming apparatus for forming an image on a recording material comprising: a plurality of processing devices for forming the image; a detecter for detecting at least a quantity of state relating to a control of the processing devices; an inference computer for inferring, in accordance with the quantity of state, a quantity of control for use to control the processing devices.