Abstract: A multi-layered type neural network for a fuzzy reasoning in which an if-part of a fuzzy rule is expressed by a membership function and a then-part of the fuzzy rule is expressed by a linear expression, the network comprising an if-part neural network for receiving if-part variables of all the fuzzy rules and calculating if-part membership values of all the fuzzy rules, an intermediate neural network for calculating, as a truth value of the premise of each fuzzy rule, a product of the if-part membership values for all the if-part variables, and a then-part neural network for calculating a first sum of the truth values of the premise of all the fuzzy rules, a second sum of a product of the truth values of the premise of all the fuzzy rules and then-part outputs of all the fuzzy rules, and dividing the second sum by the first sum to obtain a quotient as an inferential result.

Abstract: A visual information processing device having a neural network function and capable of visual information processing comprises a semiconductor integrated circuit device section equipped with a plurality of neuronic circuit regions realizing a neuron function included in the neural network function, and first and second molecular film sections provided on the integrated circuit device section. The first molecular film section comprises a light-receiving molecular film section including Tij input elements having a photoelectric function and to which coupling strength levels (Tij) between the plurality of neuronic circuit regions are optically written to realize electric connection between the neuronic circuit regions and image input elements for sensing visual images, each neuronic circuit region corresponding to one pixel.

Abstract: A best first search for problem-solving in an artificial intelligence system employing a novel search priority index is disclosed. The search priority index is calculated based on a difference between scores of a node and the next node in breadth. Searching steps required to attain a solution can be reduced by employing the search priority index.

Abstract: The described and improved multi-arm invention of this application presents three strategies for adaptive control of cooperative multi-arm robots which coordinate control over a common load. In the position-position control strategy, the adaptive controllers ensure that the end-effector positions of both arms track desired trajectories in Cartesian space despite unknown time-varying interaction forces exerted through a load. In the position-hybrid control strategy, the adaptive controller of one arm controls end-effector motions in the free directions and applied forces in the constraint directions; while the adaptive controller of the other arm ensures that the end-effector tracks desired position trajectories. In the hybrid-hybrid control strategy, the adaptive controllers ensure that both end-effectors track reference position trajectories while simultaneously applying desired forces on the load.

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 robotic surgical system (10) includes a multiple degree of freedom manipulator arm (14) having a surgical tool (22). The arm is coupled to a controller (24) for controllably positioning the surgical tool within a three dimensional coordinate system. The system further includes a safety monitoring processor (38) for determining the position of the surgical tool in the three dimensional coordinate system relative to a volumetric model. The volumetric model may be represented as a constructive solid geometry (CSG) tree data structure. The system further includes an optical tracking camera system (28,32) disposed for imaging a region of space that includes at least a portion of the manipulator arm. An output of the camera system is coupled to the processor (38) that processes the volumetric model for determining if the surgical tool is positioned outside of the volumetric model.

Abstract: A data processing system preserves the contents of a volatile memory in the event of a power-loss and restores the contents upon a power-up. The system includes an AC line monitor which signals when a power loss is imminent; volatile memory modules; and a central processor which executes programs in conjunction therewith. At any specific time during program execution, the volatile memory stores data indicative of the system's state. A backup disk drive is connected to each volatile memory module and is associated with a backup battery. The backup battery is of limited capacity and only enables sufficient operation of the disk drive and volatile memory to enable a memory dump onto the disk drive from the volatile memory. A logic circuit is responsive to a signal from the line monitor to activate the backup battery and to control the volatile memory module and the backup disk drive to effect a transfer of all stored data in the volatile memory.

Abstract: A computer system is provided with both an auto power off mode and a resume mode. In the computer system, the motor off command for an HDD is kept effective from the time when the system is turned on to the time when the HDD is accessed. During the interval, therefore, no power is supplied to the HDD. When the HDD has just been accessed, the motor off command is made ineffective, to thereby supply power to the HDD. When the power supply to the HDD is started, with the system in the resume mode, the CPU permits data processing to be performed from the state immediately before the power supply is stopped.

Abstract: Control of a process in accordance with both optimal process values (t.sub.d), which may be fixed or slowly varying, and actual process output values (t.sub.r-1) generated during a previous interval (r-1) is accomplished by a differential process controller (10). The controller (10) employs two artificial neural networks (36 and 38), each generating a separate intermediate control vector for controlling the process in accordance with a separate one of the vectors t.sub.d and t.sub.r-1. A first summing amplifier (42) computes the difference between the intermediate control vectors and generates a differential control vector which varies accordingly. A second summing amplifier (44) sums the differential control vector, together with the output signal of the summing amplifier generated during the immediately previous interval (r-1), to generate a control signal c.sub.r for controlling the process.

Abstract: An information processing device having neural network functions for performing information processing comprises: a semiconductor integrated circuit section including a plurality of neuronic circuit regions having a neuronic function which is one of said neural network functions, and first and second molecular film provided on the integrated circuit section. The first molecular film has a photoelectric function and the second molecular film has a light-emitting function. Coupling between the plurality of neurons is realized through a combination or the light-emitting and light receiving functions of the first and second molecular films.

Abstract: A self-organizing neural network and method for classifying a pattern signature having N-features is provided. The network provides a posteriori conditional class probability that the pattern signature belongs to a selected class from a plurality of classes with which the neural network was trained. In its training mode, a plurality of training vectors is processed to generate an N-feature, N-dimensional space defined by a set of non-overlapping trained clusters. Each training vector has N-feature coordinates and a class coordinate. Each trained cluster has a center and a radius defined by a vigilance parameter. The center of each trained cluster is a reference vector that represents a recursive mean of the N-feature coordinates from training vectors bounded by a corresponding trained cluster.

Abstract: There is a provided a system of one or more uninterrupted power supply (UPS) units, each UPS unit having distributed processing system and a network interface for interfacing with a local area network, the network providing a communication between the one or more UPS devices and also to loads powered by such UPS devices. In one embodiment having a plurality of UPSs, one of the UPSs is a main upstream UPS which is in communication with each down stream UPS to which it supplies supplemental power and which in turn supply power to respective loads. In another embodiment the UPS supplies power to a plurality of prioritized loads, and is in communication with each such load over a network and also controls power distribution to each such load through a power distribution module (PDM).

Abstract: A heuristic processor incorporates a digital arithmetic unit arranged to compute the squared norm of each member of a training data set with respect to each member of a set of centers, and to transform the squared norms in accordance with a nonlinear function to produce training .phi. vectors. A systolic array arranged for QR decomposition and least mean squares processing forms combinations of the elements of each .phi. vector to provide a fit to corresponding training answers. The form of combination is then employed with like-transformed test data to provide estimates of unknown results. The processor is applicable to provide estimated results for problems which are nonlinear and for which explicit mathematical formalisms are unknown.

Abstract: A stored data protection apparatus for an electronic device has a CPU (20) and a volatile memory (21) controlled by the CPU for storing data therein. Both of the CPU and the volatile memory ace supplied power voltage from a main battery (22) in normal operation of the device. The volatile memory as supplied power voltage from a back-up battery (23) when the main battery is removed from the device. The apparatus has a switch (29) operable in first and second positions, taking the first position in the normal operation of the device, and being switched from the first position to the second position when the main battery is removed from the device, a circuit (44, 48) for inhibiting the CPU to access the volatile memory when the switch is in the second position, and a circuit (38, 34, 42, 43) for releasing the inhibition of the CPU by the inhibiting circuit when the switch is switched from the second position to the first position.

Abstract: A voltage regulator connected to a microcomputer is switched from main power to standby power by a monitoring integrated circuit in response to a switch off by the control circuit after receiving a switch off command, from an ignition switch, and only after the computer has been reset. The monitoring integrated circuit has a plurality of circuit elements including a circuit element which generates a control signal for switching the voltage regulator to a state producing a standby voltage which powers the microprocessor to save the information in the microprocessor memory. Preferably the circuit element generating the control signal is an operational amplifier whose output is fed by a time delay network which delays switching of the voltage regulator.

Abstract: The present invention, by manually operating a robot and memorizing a position of the extremity of the robot, teaches a reference point representing a representative position and orientation on a moving path and a relative position of an operating position of a robot extremity in operation from the above-mentioned reference point, and designate a path of a moving position of the robot extremity in operation by an array of the reference points, and teachings of the moving path and a gripping position can be separated each other, and an accurate and easy teaching is enabled.

Abstract: An asynchronous control system for a neuro computer, includes an inter-connected type neural network composed of a plurality of neurons for multiplying a plurality of input signals with corresponding weights, calculating a total sum-of-products of the input signals and weight, thereby providing the sum-of product signals, and converting the sum-of-product signal using a non-linear function. A weight memory is provided for storing data of the weights for said neurons, and a controller is provided for generating a control pattern which controls the neural network. A selector randomly selects one of the neurons which performs signal processing during one processing cycle.

Abstract: An adaptive process control system selectively controls vibrations in a given medium in real time. Unwanted vibrations present at a point being monitored in a given medium are sensed, and the system generates an appropriate offsetting vibration that is applied to the medium at a convenient location, which may be remote from the monitored point. The system includes a vibration sensor, such as one or more accelerometers, that sense both input and output vibrations present within the medium; at least one vibration generator, such as an electromagnetic shaker, that generates appropriate offsetting vibrations that are applied to the medium at one or more appropriate locations; and a neural network controller that controls the vibration generator(s) so as to force the sensed vibration at the monitored point(s) to a desired level. The adaptive vibration cancellation provided by the invention takes place in real time, and without the need to process time-consuming complex mathematical algorithms.

Abstract: In a fuzzy controller comprising a fuzzy inference device for subjecting one or a plurality of input signals to fuzzy inference operations using membership functions in accordance with a predetermined rule and outputting a non-fuzzy value determined on the basis of the results of the inferences, there are provided an input signal level converter for converting signal levels of the input signals on the input side of the fuzzy inference device and an output signal level converter for converting a signal level of the output signal on the output side of the fuzzy inference device.

Abstract: A navigation system for a mobile autonomous robot that includes apparatus for creating and maintaining a map of an environment the mobile autonomous robot is to traverse including provision for storing in a map at an assigned location features representative of geometric beacons located in the environment. Because of the uncertainty in its sensor's operating conditions and changes in the environment, a credibility measure is associated with each map feature stored. This credibility measure is increased or decreased whenever the map feature assigned to a location matches or does not match, respectively, a geometric beacon corresponding to such location. Whenever a geometric beacon is observed for a location that does into match a previously stored map features, an appropriate map feature is added for such location.