Abstract: Described is a system for controlling autonomous platform. Based on an input image, the system generates a motor control command decision for the autonomous platform. A probability of the input image belonging to a set of training images is determined, and a reliability measure for the motor control command decision is generated using the determined probability. An exploratory action is performed when the reliability measure is above a predetermined threshold. Otherwise, an exploitation action corresponding with the motor control command decision is performed when the reliability measure is below a predetermined threshold.

Abstract: Described is a system for inducing a desired behavioral effect using an electrical current stimulation. A brain monitoring subsystem includes monitoring electrodes for sensing brain activity, and a brain stimulation subsystem includes stimulating electrodes for applying an electrical current stimulation. Multi-scale distributed data is registered into a graphical representation. The system identifies a sub-graph in the graphical representation and maps the sub-graph onto concept features, generating a concept lattice which relates the concept features to a behavioral effect. Finally, an electrical current stimulation to be applied to produce the behavioral effect is determined.

Abstract: Described is a system for object identification using sparse associative memory. In operation, the system converts signature data regarding an object into a set of binary signals representing activations in a layer of input neurons. The input neurons are connected to hidden neurons based on the activations in the layer of input neurons, which allows for recurrent connections to be formed from hidden neurons back onto the input neurons. An activation pattern of the input neurons is then identified upon stabilization of the input neurons in the layer of input neurons. The activation pattern is a restored pattern, which allows the system to identify the object by comparing the restored pattern against stored patterns in a relational database. Based upon the object identification, a device, such as a robotic arm, etc., can then be controlled.

Abstract: Described is a system for classifying novel objects in imagery. In operation, the system extracts salient patches from a plurality of unannotated images using a multi-layer network. Activations of the multi-layer network are clustered into key attribute, with the key attributes being displayed to a user on a display, thereby prompting the user to annotate the key attributes with class label. An attribute database is then generated based on user prompted annotations of the key attributes. A test image can then be passed through the system, allowing the system to classify at least one object in the test image by identifying an object class in the attribute database. Finally, a device can be caused to operate or maneuver based on the classification of the at least one object in the test image.

Abstract: Described is a system for object detection and recognition from a moving platform under adverse visual conditions. The system generates a predicted change regarding how a moving platform's surrounding change in an image captured from the moving platform. Based on an agreement of the predicted change and an actual input image obtained via an image sensor positioned on the moving platform and corrupted by a visual disturbance, a transformation-consistency map is generated. The transformation-consistency map and the actual input image are used to improve detection and recognition performance of a machine learning method in detecting at least one object in the moving platform's surroundings.

Abstract: A method, system and computer program product are provided for identifying wire contact insertion holes of a connector to facilitate the automated insertion of the wire ends of a wire bundle assembly into the wire contact insertion holes of a connector. In the context of a method, each of a plurality of pixels of an image of the connector is analyzed to identify one or more candidate contact insertion holes for the connector. The method also determines whether the one or more candidate contact insertion holes are to be consolidated and, if so, consolidates the one or more candidate contact insertion holes. The method further includes assigning contact identification numbers of the connector to the one or more candidate contact insertion holes.

Abstract: Depicted and described herein is a diaphragm pump (1) for conveying a gaseous and/or liquid medium, having at least one deformable membrane (2) for changing the size of a work chamber (3) of the diaphragm pump (1), and having at least one actuating unit (4) for deforming the membrane (2) by means of applying contact-free force to the membrane (2) using a magnetic field, wherein the membrane (2) comprises and/or consists of a material which is magnetic and/or magnetizable, and the actuating unit (4) features at least one magnetic and/or magnetizable actuating means (7). According to the invention, the actuating unit (4) is rotatably mounted and the membrane (2) is arranged circumferentially with respect to the actuating unit (4), wherein, in a dead point position of the membrane (2), the polarization direction of the magnetic field generated between the material of the membrane (2) and the actuating means (7) is oriented in a direction radial to the axis of rotation of the actuating unit (4).

Abstract: Described is a system for detecting attacks on mobile networks. The system includes the relevant hardware and components to perform a variety of operations including continuously measuring time-varying signals at each node in a network. The system determines network flux on the time-varying signals of all nodes in the network and detects a network attack if the network flux exceeds a predetermined threshold. Further, a reactive protocol is initiated if the network flux exceeds the predetermined threshold.

Abstract: Described is a system for automatically tuning the sensor feedback of a prosthetic device. The system comprises an electrode or plurality of electrodes in contact with a peripheral nerve of a user wearing a prosthetic device for administering the sensory feedback and an additional stimulus that evokes a muscle response in the user. A sensor is used to measure the muscle response. One or more processors generate a current stimulation pattern that encodes a posture of the prosthetic device. The current stimulation pattern is used in a spinal cord simulation to produce predicted muscle activations. Using the muscle response and the predicted muscle activations, an adjusted stimulation pattern is determined.

Abstract: Described is a system for reducing the probability of large-scale failures in a transmission network. Tripped or damaged transmission lines in a transmission network are identified following a cascading failure. After each cascading failure, a subset of transmission lines is updated according to a specified rule to alter long-term dynamics of the transmission network such that the transmission network does not converge into a critical state.

Abstract: Described is a system for detecting moving objects. During operation, the system obtains ego-motion velocity data of a moving platform and generates a predicted image of a scene proximate the moving platform by projecting three-dimensional (3D) data into an image plane based on pixel values of the scene. A contrast image is generated based on a difference between the predicted image and an actual image taken at a next step in time. Next, an actionable prediction map is then generated based on the contrast mage. Finally, one or more moving objects may be detected based on the actionable prediction map.

Abstract: Described is a system for discriminant localization of objects. During operation, the system causes one or more processors to perform an operation of identifying an object in an image using a multi-layer network. Features of the object are derived from the activations of two or more layers of the multi-layer network. The image is then classified to contain one or more object classes, and the desired object class is localized. A device can then be controlled based on localization of the object in the image. For example, a robotic arm can be controlled to reach for the object.

Abstract: Described is a system for understanding machine-learning decisions. In an unsupervised learning phase, the system extracts, from input data, concepts represented by a machine-learning (ML) model in an unsupervised manner by clustering patterns of activity of latent variables of the concepts, where the latent variables are hidden variables of the ML model. The extracted concepts are organized into a concept network by learning functional semantics among the extracted concepts. In an operational phase, a subnetwork of the concept network is generated. Nodes of the subnetwork are displayed as a set of visual images that are annotated by weights and labels, and the ML model per the weights and labels.

Abstract: Described is a system for searching a continuous data stream for exact matches with a priori stored data sequences. The system includes a neural network with an input and an output layer. The input layer has one neuron for each possible character or number in the data stream, and the output layer has one neuron for each stored pattern. Importantly, the delays of the connections from input to output layer are engineered to match the temporal occurrence of an input character within a stored sequence. Thus, if an input sequence has the proper time gaps between characters, matching a stored pattern, then the delayed neural signals result in a simultaneous activation at the receiving neuron, which indicates a detected pattern. For storing a pattern, only one connection for each pair of input character and output neuron has to be specified resulting in sparse coding and quick storage.

Abstract: Described is a system for classifying objects and scenes in images. The system identifies salient regions of an image based on activation patterns of a convolutional neural network (CNN). Multi-scale features for the salient regions are generated by probing the activation patterns of the CNN at different layers. Using an unsupervised clustering technique, the multi-scale features are clustered to identify key attributes captured by the CNN. The system maps from a histogram of the key attributes onto probabilities for a set of object categories. Using the probabilities, an object or scene in the image is classified as belonging to an object category, and a vehicle component is controlled based on the object category causing the vehicle component to perform an automated action.

Abstract: A method for performing an operation on an object includes capturing a plurality of images of the object. Each image is a different view of the object. The method also includes generating a sparse 3D point cloud from the plurality of images. The sparse 3D point cloud defines a 3D model of the object. The sparse 3D point cloud includes a multiplicity of missing points that each correspond to a hole in the 3D model that renders the 3D model unusable for performing the operation on the object. The method additionally includes performing curvature-based upsampling to generate a denser 3D point cloud. The denser 3D point cloud includes a plurality of filled missing points. The missing points are filled from performance of the curvature-based upsampling. The denser 3D point cloud defines a dense 3D model that is useable for performing the operation on the object.

Abstract: Described is a system for inducing a desired behavioral effect using an electrical current stimulation. A brain monitoring subsystem includes monitoring electrodes for sensing brain activity, and a brain stimulation subsystem includes stimulating electrodes for applying an electrical current stimulation. Multi-scale distributed data is registered into a graphical representation. The system identifies a sub-graph in the graphical representation and maps the sub-graph onto concept features, generating a concept lattice which relates the concept features to a behavioral effect. Finally, an electrical current stimulation to be applied to produce the behavioral effect is determined.

Abstract: Described is a system for system for gait intervention and fall prevention. The system is incorporated into a body suit having a plurality of distributed sensors and a vestibulo-muscular biostim array. The sensors are operable for providing biosensor data to the analytics module, while the vestibulo-muscular biostim array includes a plurality of distributed effectors. The analytics module is connected with the body suit and sensors and is operable for receiving biosensor data and analyzing a particular user's gait and predicting falls. Finally, a closed-loop biostim control module is included for activating the vestibulo-muscular biostim array to compensate for a risk of a predicted fall.

Abstract: Described is a system for generating an adaptable predictive model of the dynamics of a complex system, such as a vehicle. A set of current sensory data describing the vehicle's current state is collected from the vehicle. A set of predictive models is evaluated to identify a predictive model that best matches the vehicle's current state. If a predictive model is identified as a match, then the predictive model is adapted to better fit the vehicle's current state, resulting in an adapted predictive model. If a match is not identified, then a new predictive model is generated through automatic model learning using the current set of sensory data. The adapted predictive model or the new predictive model is then used to generate control outputs for the vehicle.

Abstract: A method, system and computer program product are provided for identifying wire contact insertion holes of a connector to facilitate the automated insertion of the wire ends of a wire bundle assembly into the wire contact insertion holes of a connector. In the context of a method, each of a plurality of pixels of an image of the connector is analyzed to identify one or more candidate contact insertion holes for the connector. The method also determines whether the one or more candidate contact insertion holes are to be consolidated and, if so, consolidates the one or more candidate contact insertion holes. The method further includes assigning contact identification numbers of the connector to the one or more candidate contact insertion holes.