Abstract: A computer system is disclosed for processing industrial Boolean satisfiability (SAT) problems. A computer implemented SAT image encoder is configured to encode a runtime industrial SAT problem into a pixelated problem image comprising a plurality of rows, wherein the runtime industrial SAT problem comprises a plurality of clauses and each row of the pixelated problem image represents a corresponding one of the clauses. A computer implemented clause embedding module is configured to encode each row of the pixelated problem image into a corresponding vector, and a computer implemented vector encoder is configured to encode the vectors into an output indicating whether the runtime industrial SAT problem is satisfiable or unsatisfiable.

Abstract: Described is an attack system for generating perturbations of input signals in a recurrent neural network (RNN) based target system using a deep reinforcement learning agent to generate the perturbations. The attack system trains a reinforcement learning agent to determine a magnitude of a perturbation with which to attack the RNN based target system. A perturbed input sensor signal having the determined magnitude is generated and presented to the RNN based target system such that the RNN based target system produces an altered output in response to the perturbed input sensor signal. The system identifies a failure mode of the RNN based target system using the altered output.

Abstract: Described is a system for training a neural network for estimating surface normals for use in operating an autonomous platform. The system uses a parallelizable k-nearest neighbor sorting algorithm to provide a patch of points, sampled from the point cloud data, as input to the neural network model. The points are transformed from Euclidean coordinates in a Euclidean space to spherical coordinates. A polar angle of a surface normal of the point cloud data is estimated in the spherical coordinates. The trained neural network model is utilized on the autonomous platform, and the estimate of the polar angle of the surface normal is used to guide operation of the autonomous platform within the environment.

Abstract: Described is a system for controlling a mobile platform. A neural network that runs on the mobile platform is trained based on a current state of the mobile platform. A Satisfiability Modulo Theories (SMT) solver capable of reasoning over non-linear activation functions is periodically queried to obtain examples of states satisfying specified constraints of the mobile platform. The neural network is then trained on the examples of states. Following training on the examples of states, the neural network selects an action to be performed by the mobile platform in its environment. Finally, the system causes the mobile platform to perform the selected action in its environment.

Abstract: Described is a system and method for generating safety conditions for a cyber-physical system with state space S, action space A and trajectory data labelled as either safe or unsafe. In operation, the system receives inputs and ten minimizes loss functions to cause a neural network to become a barrier function. Based on the barrier function, the system can then determine if the cyber-physical system is entering an usafe state, such that if the cyber-physical system is entering the usafe state, then the cyber-physical system is caused to initiate a maneuver to position the cyber-physical system into a safe state.

Abstract: Described is a system and method for generating safety conditions for a cyber-physical system with state space S, action space A and trajectory data labelled as either safe or unsafe. In operation, the system receives inputs and ten minimizes loss functions to cause a neural network to become a barrier function. Based on the barrier function, the system can then determine if the cyber-physical system is entering an usafe state, such that if the cyber-physical system is entering the usafe state, then the cyber-physical system is caused to initiate a maneuver to position the cyber-physical system into a safe state.

Abstract: Apparatus and methods for training a machine learning algorithm (MLA) to control a first aircraft in an environment that comprises the first aircraft and a second aircraft are described. Training of the MLA can include: the MLA determining a first-aircraft action for the first aircraft to take within the environment; sending the first-aircraft action from the MLA; after sending the first-aircraft action, receiving an observation of the environment and a reward signal at the MLA, the observation including information about the environment after the first aircraft has taken the first-aircraft action and the second aircraft has taken a second-aircraft action, the reward signal indicating a score of performance of the first-aircraft action based on dynamic and kinematic properties of the second aircraft; and updating the MLA based on the observation of the environment and the reward signal.

Abstract: Described is a system for generating environmental features using deep reinforcement learning. The system receives a policy network architecture, initialization parameters, and a simulation environment that models a trajectory of a target system through a physical environment. Landmark features sampled from the policy network are initialized, and a trained policy network is generated by training the policy network using a reinforcement learning algorithm. A set of environmental features are generated using the trained policy network and displayed on a display device.

Abstract: Described is a system for proving correctness properties of a neural network for providing estimates for point cloud data. The system receives as input a description of a neural network for generating estimates from a set of point cloud data. The description of the neural network is parsed to obtain a symbolic representation. Based on a combination of the symbolic representation and a set of analysis parameters, the system generates an analysis output indicating whether the neural network satisfies a correctness property in generating the estimates from the set of point cloud data. The analysis output is a mathematical proof artifact proving that the set of analysis parameters is satisfied, a list of one or more point clouds for which the set of analysis parameters is violated, or a report that progress could not be made by the analysis.

Abstract: Described is a system for training a neural network for estimating surface normals for use in operating an autonomous platform. The system uses a parallelizable k-nearest neighbor sorting algorithm to provide a patch of points, sampled from the point cloud data, as input to the neural network model. The points are transformed from Euclidean coordinates in a Euclidean space to spherical coordinates. A polar angle of a surface normal of the point cloud data is estimated in the spherical coordinates. The trained neural network model is utilized on the autonomous platform, and the estimate of the polar angle of the surface normal is used to guide operation of the autonomous platform within the environment.

Abstract: Described is a system for automatically generating images that satisfy specific image properties. Using a code parser component, a tensor expression intermediate representation (IR) of a deep neural network code is produced. A specification describing a set of image properties is parsed in a fixed formal syntax. The tensor expression IR and the specification is input into a rewriting and analysis engine. The rewriting and analysis engine queries an external solver to obtain pixel values satisfying the specification. When pixel values satisfying the specification can be found in a fixed time period, the rewriting and analysis engine combines the pixel values into an image that satisfies the specification and outputs the image.

Abstract: Described is an attack system for generating perturbations of input signals in a recurrent neural network (RNN) based target system using a deep reinforcement learning agent to generate the perturbations. The attack system trains a reinforcement learning agent to determine a magnitude of a perturbation with which to attack the RNN based target system. A perturbed input sensor signal having the determined magnitude is generated and presented to the RNN based target system such that the RNN based target system produces an altered output in response to the perturbed input sensor signal. The system identifies a failure mode of the RNN based target system using the altered output.

Abstract: Described is a control command system for generating control commands for a vehicle. The system receives a networked control system corresponding to a network of subsystems of sensors and actuators of the vehicle and data collected from sensors on the vehicle. Multiple subsystems are formed from the networked control system. A dynamic mode decomposition with control (DMDc) process is applied to each subsystem, yielding a linear approximation for each subsystem. The linear approximations are combined into a single linear approximation for the networked control system, and a linear control system approximating the networked control system is output. Control commands are generated for the vehicle based on the linear control system, which cause the vehicle to perform a vehicle operation.

Abstract: Apparatus and methods for training a machine learning algorithm (MLA) to control a first aircraft in an environment that comprises the first aircraft and a second aircraft are described. Training of the MLA can include: the MLA determining a first-aircraft action for the first aircraft to take within the environment; sending the first-aircraft action from the MLA; after sending the first-aircraft action, receiving an observation of the environment and a reward signal at the MLA, the observation including information about the environment after the first aircraft has taken the first-aircraft action and the second aircraft has taken a second-aircraft action, the reward signal indicating a score of performance of the first-aircraft action based on dynamic and kinematic properties of the second aircraft; and updating the MLA based on the observation of the environment and the reward signal.

Abstract: Described is a system for controlling a mobile platform. A neural network that runs on the mobile platform is trained based on a current state of the mobile platform. A Satisfiability Modulo Theories (SMT) solver capable of reasoning over non-linear activation functions is periodically queried to obtain examples of states satisfying specified constraints of the mobile platform. The neural network is then trained on the examples of states. Following training on the examples of states, the neural network selects an action to be performed by the mobile platform in its environment. Finally, the system causes the mobile platform to perform the selected action in its environment.

Abstract: Described is a high-assurance network gateway generator that generates and encodes network gateway code on a computer readable medium. In operation, the network gateway generator receives input artifacts, which are translated into corresponding formats as translated data. The translated data is distributed to an OS code generator, a glue code generator, and a communications code generator. The OS code generator then generates OS code based on the translated data. The communications code generator proceeds to generate deserialization and filtering code based on the translated data. Further, a glue code generator generates glue code based on the OS code and translated data. An executable network gateway code is then generated by combining the glue code, deserialization code, and filtering code. Finally, the executable network gateway code is then encoded on a computer readable medium.

Abstract: Described is a system for automatically generating images that satisfy specific image properties. Using a code parser component, a tensor expression intermediate representation (IR) of a deep neural network code is produced. A specification describing a set of image properties is parsed in a fixed formal syntax. The tensor expression IR and the specification is input into a rewriting and analysis engine. The rewriting and analysis engine queries an external solver to obtain pixel values satisfying the specification. When pixel values satisfying the specification can be found in a fixed time period, the rewriting and analysis engine combines the pixel values into an image that satisfies the specification and outputs the image.

Abstract: Described is a high-assurance network gateway generator that generates and encodes network gateway code on a computer readable medium. In operation, the network gateway generator receives input artifacts, which are translated into corresponding formats as translated data. The translated data is distributed to an OS code generator, a glue code generator, and a communications code generator. The OS code generator then generates OS code based on the translated data. The communications code generator proceeds to generate deserialization and filtering code based on the translated data. Further, a glue code generator generates glue code based on the OS code and translated data. An executable network gateway code is then generated by combining the glue code, deserialization code, and filtering code. Finally, the executable network gateway code is then encoded on a computer readable medium.

Abstract: A cigarette packaging machine is provided with a mechanism for rejecting defective cigarette packs of a two pack stack of cigarette packs. A defective top pack of the stack is rejected at a first rejection station by a blast of pressurized air or a pusher bar and a defective bottom pack of the stack is rejected at a second rejection station downstream of the first rejection station by a movable arm which pivots away from a position supporting the stack and then pivots toward the stack to strike the bottom pack and eject it from the stack. A magazine filled with acceptable packs is located downstream of the second rejection station for replacing defective packs ejected from the stack.

Abstract: The invention provides package inspection systems which are capable of high speed sensing and evaluation of package integrity as packages are continuously conveyed in the manufacturing process. The systems are capable of measuring predetermined parameters of packages, e.g. cigarette packages, comparing the measured parameters with predetermined values, evaluating from the measured parameters the integrity of the packages and determining whether such packages are acceptable or, alternatively, should be rejected. The system can additionally obtain and store data on sensed package parameters for evaluating long-term and short-term manufacturing trends. In various embodiments of the invention, the system can inspect a single or plural package side(s), employing a single or plural line scan or area array camera(s) and may employ special optics to enable plural package side images to be obtained using a single camera.