Abstract: Methods and apparatus for complex assembly via autonomous robots using reinforcement learning action primitives are disclosed. An example apparatus includes a construction manager and a movement manager. The construction manager is to determine sequences of reinforcement learning (RL) action primitives based on object location goals and associated assembly goals determined for respective ones of objects depicted in an imaged assembly of objects. The movement manager is to command a robot to construct a physical assembly of objects based on the sequences of RL action primitives. The physical assembly of objects is to correspond to the imaged assembly of objects.

Abstract: A device may include a processor configured to determine a layout for a plurality of automated machine clusters to be deployed in an environment based on a plurality of operation policies and an input task, wherein each operation policy provides a policy to operate one or more automated machines of one of the plurality of automated machine clusters for a trained task based on one or more policy parameters. The processor may further be configured to adjust the one or more policy parameters of at least one of the plurality of operation policies based on the determined layout in the environment and the input task.

Abstract: Techniques are disclosed to perform task allocation for autonomous systems by implementing machine-learning to perform task allocation to Autonomous Mobile Robots (AMRs) in an environment. The disclosed techniques also provide for enhanced path planning and the identification of AMR health and failure prediction to further improve upon task allocation and system efficiency.

Abstract: The present disclosure provides describes to train a multi policy ML model to control robots in a multi-robot system in collaborating to perform a task. For example, trajectories associated with manipulating an object to perform the collaborative task can be determined and an ML model trained to output control actions for the robots in the multi-robot system to collaborate to complete the task.

Abstract: Techniques disclosed for accurately predicting the occurrence of anomalous sensor readings within a sensor network and advantageously using these predictions to limit the amount of power used by relay nodes within the sensor network. Some examples analyze spatial and temporal characteristics of anomalous sensor readings to predict future occurrences. In these examples, the relay nodes operate in a reduced power mode for periods of time in which anomalous sensor readings are not predicted to occur. Also, in these examples, only relay nodes in a path between a sensor predicting an anomalous reading and a gateway of the sensor network operate in full power mode. This feature allows other relay nodes to remain in the reduced power mode even when an anomalous sensor reading is predicted elsewhere in the sensor network.

Abstract: Methods and apparatus for complex assembly via autonomous robots using reinforcement learning action primitives are disclosed. An example apparatus includes a construction manager and a movement manager. The construction manager is to determine sequences of reinforcement learning (RL) action primitives based on object location goals and associated assembly goals determined for respective ones of objects depicted in an imaged assembly of objects. The movement manager is to command a robot to construct a physical assembly of objects based on the sequences of RL action primitives. The physical assembly of objects is to correspond to the imaged assembly of objects.

Abstract: Embodiments of the present invention include an apparatus, method, and system for acoustic modeling. In an embodiment, a speech recognition system is provided. The system includes a processing unit configured to divide a received audio signal into consecutive frames having respective frame vectors, an acoustic processing unit (APU), a data bus that couples the processing unit and the APU. The APU includes a local, non-volatile memory that stores a plurality of senones, a memory buffer coupled to the memory, the acoustic processing unit being configured to load at least one Gaussian probability distribution vector stored in the memory into the memory buffer, and a scoring unit configured to simultaneously compare a plurality of dimensions of a Gaussian probability distribution vector loaded into the memory buffer with respective dimensions of a frame vector received from the processing unit and to output a corresponding score to the processing unit.

Abstract: Embodiments of the present invention include an apparatus, method, and system for acoustic modeling. In an embodiment, a speech recognition system is provided. The system includes a processing unit configured to divide a received audio signal into consecutive frames having respective frame vectors, an acoustic processing unit (APU), a data bus that couples the processing unit and the APU. The APU includes a local, non-volatile memory that stores a plurality of senones, a memory buffer coupled to the memory, the acoustic processing unit being configured to load at least one Gaussian probability distribution vector stored in the memory into the memory buffer, and a scoring unit configured to simultaneously compare a plurality of dimensions of a Gaussian probability distribution vector loaded into the memory buffer with respective dimensions of a frame vector received from the processing unit and to output a corresponding score to the processing unit.

Abstract: A switching matrix and testing platform may enable controlled testing of various configurations of radio access networks (RANs) at various signal strengths. The switching matrix and testing platform may enable testing of the radio frequency (RF) signals from RANs or telecommunications devices for new and/or predetermined scenarios, such as using different configurations of the RANs at various signal strengths. During a scenario, various operations may be performed on the telecommunications device in communication with the tested RF signals, such as making voice calls, transmitting and receiving data (messages, videos, music, etc.). A performance of the telecommunications device and/or various telecommunication network elements may be analyzed in comparison to other telecommunications device and/or various telecommunication network elements.

Abstract: An approach is described to overcome the rapid consumption of available flash space when frequently modifying files stored on the flash space. This “differential” sector approach determines the correlation between the new content and the old content, and saves only the “delta” part of the old and the new content to the sectorized memory device. A predetermined threshold can be used to determine whether to use the “differential” sector approach or the fixed sector approach, based on the amount of data change in a given memory access request.

Abstract: Embodiments of the present invention include an apparatus, method, and system for acoustic modeling. In an embodiment, a speech recognition system is provided. The system includes a processing unit configured to divide a received audio signal into consecutive frames having respective frame vectors, an acoustic processing unit (APU), a data bus that couples the processing unit and the APU. The APU includes a local, non-volatile memory that stores a plurality of senones, a memory buffer coupled to the memory, the acoustic processing unit being configured to load at least one Gaussian probability distribution vector stored in the memory into the memory buffer, and a scoring unit configured to simultaneously compare a plurality of dimensions of a Gaussian probability distribution vector loaded into the memory buffer with respective dimensions of a frame vector received from the processing unit and to output a corresponding score to the processing unit.

Abstract: A switching matrix and testing platform may enable controlled testing of various configurations of radio access networks (RANs) at various signal strengths. The switching matrix and testing platform may enable testing of the radio frequency (RF) signals from RANs or telecommunications devices for new and/or predetermined scenarios, such as using different configurations of the RANs at various signal strengths. During a scenario, various operations may be performed on the telecommunications device in communication with the tested RF signals, such as making voice calls, transmitting and receiving data (messages, videos, music, etc.). A performance of the telecommunications device and/or various telecommunication network elements may be analyzed in comparison to other telecommunications device and/or various telecommunication network elements.

Abstract: According to an aspect of the present invention, a quotient of a dividend divided by a divisor may be determined after reducing the dividend, divisor, and the remainder by using operations such as add, subtract, multiply, shift, AND which may result in reduced processor cycles (time).

Abstract: According to an aspect of the present invention, a quotient of a dividend divided by a divisor may be determined after reducing the dividend, divisor, and the remainder by using operations such as add, subtract, multiply, shift, AND which may result in reduced processor cycles (time).

Abstract: Systems and methods are disclosed for performing selective caching in network processing and other contexts. In one embodiment, upon receipt of a processor's request for a data item, a determination is made as to whether the data item is stored in the processor's cache. If the data item is not stored in the cache, then the data item is retrieved from an external memory unit. If the retrieved data item meets certain predefined criteria, the data item is stored in the cache, where it replaces a least recently used cache entry. In one embodiment, the criteria that is used to determine whether data will be cached is whether the data is associated with a data connection having at least a predefined capacity. In one such embodiment, the predefined capacity is selected such that a cache hit multiplier is optimized.