Abstract: The present disclosure relates to systems, methods, and computer-readable media for facilitating efficient retrieval of diagnostic information from a computing endpoint that experiences a failure condition. For example, systems described herein may detect or otherwise identify a failure condition associating with the computing endpoint operating in an erroneous or unpredictable matter. Systems described herein may involve carving out a portion of memory on the computing endpoint that is accessible to a host system (e.g., a CPU). Systems described herein may further provide a discoverable resource that enables a host system to identify and collect the diagnostic data in response to identifying a failure condition in an efficient manner and without requiring that the computing endpoint be capable of responding to data requests.

Abstract: Systems and methods are disclosed for generating interactive user interfaces for evaluating transactions of an organization. For example, a system can be configured to receive transactions for an organization and determine a first subset of the transactions during a trip at a first location that is different from a home location of a consumer. A respective transaction associated with a second location that occurred during the trip is identified. The respective transaction is assigned to the first subset of the of transactions for the trip. A second subset of the transactions of a spending type is determined. A parameter value associated with the spending type is identified. A parameter adjustment is determined. The system is configured to cause a display of a spending type user interface on a client device and receive a selection of a parameter component.

Abstract: A method of delivering a non-invasive neurostimulation using a Monotonic Amplitude Pulse Train is more charge-efficient than using conventional, uniform waveforms. Monotonic Amplitude Pulse Trains optimize the amplitudes of individual pulses in a train to reduce the total energy required to provide neural stimulation by as much as 50%.

Abstract: An autonomous cleaning robot (e.g., an autonomous vacuum) may clean an environment using a cleaning head that is self-actuated. The cleaning head includes an actuator assembly comprising an actuator configured to control rotation and vertical movement of a cleaning roller, a controller, and a cleaning roller having an elongated cylindrical length connected to the actuator assembly. The cleaning head also includes a computer processor connected to the actuator assembly and a non-transitory computer-readable storage medium that causes the computer processor to map the environment based on sensor data captured by the autonomous vacuum. The computer processor may determine an optimal height for the cleaning head based on the map and instruct the actuator assembly to adjust the height of the cleaning head.

Abstract: A lidar method and system for training and using a machine learning model are disclosed. An example method includes: obtaining a map of a background scene, the map including three-dimensional (3D) point cloud data; obtaining at least one point cloud representation of at least one foreground object, the at least one point cloud representation including 3D point cloud data, wherein one or more lidar sensors were used to generate the 3D point cloud data for the map and the at least one point cloud representation; generating a lidar scene by placing the at least one point cloud representation within the map; and training the machine learning model using the generated lidar scene. The model can be used to identify objects and control a vehicle.

Abstract: A storage device includes: a storage controller to receive one or more notifications corresponding to host data transferred from a host device to the storage device over a storage interface; and a response circuit connected to the storage controller, the response circuit to trigger a response to the host device, and including: a first counter to track the one or more notifications, the one or more notifications corresponding to an entirety of the host data such that each of the notifications corresponds to a portion of the host data; a second counter to track one or more acknowledgements received from the storage controller, the one or more acknowledgments corresponding to the one or more notifications such that each of the acknowledgments corresponds to a notification; and a response trigger to select one of the first counter and the second counter to trigger the response to the host device.

Abstract: Techniques for generating and presenting search filter recommendations are disclosed. A system determines a composition of search filter tiles, including a relative number of machine learning-generated search filter tiles and non-machine learning-generated search filter tiles, based on recommendation criteria. The recommendation criteria include an amount of user search history data that exists. The system applies search filter recommendation policies to generate a set of search filter recommendations, including hard-coded search filters, search filter recommendations generated by a user-specific machine learning model, search filter recommendations generated by a machine learning model trained on data from multiple different users, and algorithm-based recommendations. The system generates different sets of search filter recommendations made up of different ratios of recommendations from different sources based on determining if search filter criteria are met.

Abstract: Disclosed herein is a method for delivery stimulation to targeted deep brain structures by supplementing existing method using external electrodes with transnasal electrodes, disposed, for example, in the olfactory cleft and within the hyenoid sinus, or, more broadly, in the nasal cavity and/or in the sinuses, including, but not limited to, the frontal, ethmoidal, sphenoid sinus, etc. The method allows stimulation and/or sensing in deep brain regions which can be inaccessible from the scalp or for which existing methods are ineffective in targeting. The method can also be used for power delivery to implants that might be placed inside the brain or on its surface.

Abstract: An autonomous cleaning robot (e.g., an autonomous vacuum) may clean an environment using a cleaning head that is self-actuated. The cleaning head includes an actuator assembly comprising an actuator configured to control rotation and vertical movement of a cleaning roller, a controller, and a cleaning roller having an elongated cylindrical length connected to the actuator assembly. The cleaning head also includes a computer processor connected to the actuator assembly and a non-transitory computer-readable storage medium that causes the computer processor to map the environment based on sensor data captured by the autonomous vacuum. The computer processor may determine an optimal height for the cleaning head based on the map and instruct the actuator assembly to adjust the height of the cleaning head.

Abstract: A traceability system for a bulk commodity supply chain is provided. The system includes a tracking device, a location determination subsystem, and at least one computing device having at least one processor. The location determination subsystem is configured to determine positional information of the tracking device while placed in a bulk commodity traveling along the bulk commodity supply chain. The processor receives the positional information from the location subsystem, extracts positional values from the positional information, and processes the positional values to identify motion primitives. A modeling tool is applied to the identified motion primitives to produce a positional path of the tracking device, which is output, for example, via a user interface. The positional path represents travel of the bulk commodity along the supply chain.

Abstract: A process is disclosed to identify the minimal set of sequential and combinational signals needed to fully reconstruct the combinational layout after emulation is complete. A minimal subset of sequential and combinational elements is output from the emulator to maximize the emulator speed and limit the utilization of emulator resources, e.g., FPGA resources. An efficient reconstruction of combinational waveforms or SAIF data is performed using a parallel computing grid.

Abstract: A lidar method and system for training and using a machine learning model are disclosed. An example method includes: obtaining a map of a background scene, the map including three-dimensional (3D) point cloud data; obtaining at least one point cloud representation of at least one foreground object, the at least one point cloud representation including 3D point cloud data, wherein one or more lidar sensors were used to generate the 3D point cloud data for the map and the at least one point cloud representation; generating a lidar scene by placing the at least one point cloud representation within the map; and training the machine learning model using the generated lidar scene. The model can be used to identify objects and control a vehicle.

Abstract: Methods and systems related to intelligent space management are described. An example method of monitoring an environment includes receiving a first image of an environment captured by a camera, receiving a point cloud of the environment generated by a lidar device, registering at least a portion of the point cloud with at least a portion of the first image, receiving, from a user device, a user selection of a zone in the environment based on a user interaction with a second image presented on the user device, the second image including at least one of a portion of the first image or a portion of the point cloud, and monitoring point cloud data collected by the lidar device for the selected zone.

Abstract: A storage device includes: a storage controller to receive one or more notifications corresponding to host data transferred from a host device to the storage device over a storage interface; and a response circuit connected to the storage controller, the response circuit to trigger a response to the host device, and including: a first counter to track the one or more notifications, the one or more notifications corresponding to an entirety of the host data such that each of the notifications corresponds to a portion of the host data; a second counter to track one or more acknowledgements received from the storage controller, the one or more acknowledgments corresponding to the one or more notifications such that each of the acknowledgments corresponds to a notification; and a response trigger to select one of the first counter and the second counter to trigger the response to the host device.

Abstract: Disclosed is an autonomous vacuum system that detects and responds to obstructions in a cleaning channel of the vacuum. Pressure sensors repeatedly measure pressure at different points in the cleaning channel, and the autonomous vacuum system analyzes the pressure measurements to determine whether an obstruction is likely present. Such a determination may be made based on, e.g., computed pressure differentials across the pressure sensors, and/or pressures of individual pressures sensors. The autonomous vacuum system can respond to the detection of an obstruction by, for example, performing a change in vacuum speed, such as ramping up to or near a maximum speed, and then decreasing again to a more normal speed.

Abstract: A cleaning system may have a brush roller that moves dust and debris towards a duct opening for collection. The cleaning system may be an autonomous vacuum robot or include an autonomous vacuum robot. The cleaning system may include guards that reduce the likelihood that fibrous debris wraps around rotating portions of the brush roller (e.g., around a drive pinion). Buffer zones in the brush roller may receive fibrous debris that would otherwise wrap around the brush roller and increase undesirable friction during operation. The brush roller is configured to be unlocked from a position contacting the inner surface of a cleaning head of the cleaning system. The fibrous debris stored in the buffer zones may be suctioned into a debris collection compartment of the cleaning system after the brush roller is unlocked. The cleaning system includes a wedge to seal a cavity for ingesting debris within the cleaning head from the environment.

Abstract: An autonomous vacuum includes mopping and sweeping functionalities. A magnetic locking system secures a cleaning head of the autonomous vacuum into a mopping position when in a mopping state, allowing the vacuum to move a mop roller back and forth to scrub stubborn stains on a floor surface without the cleaning head shifting into an alternate sweeping position. The autonomous vacuum also includes snorkel ducts to direct fluid waste and water from the mop roller to a waste bag without mixing the fluid waste with dry waste collected by a sweeping system. The snorkel ducts are configured to kink shut when the cleaning head is in a sweeping state, to avoid unnecessary suction through the snorkel system. Additionally, the mopping system includes cleaning logic routines that can sense and control mop roller saturation and drying, and that can perform automatic mop cleaning.

Abstract: A storage device includes: a storage controller to receive one or more notifications corresponding to host data transferred from a host device to the storage device over a storage interface; and a response circuit connected to the storage controller, the response circuit to trigger a response to the host device, and including: a first counter to track the one or more notifications, the one or more notifications corresponding to an entirety of the host data such that each of the notifications corresponds to a portion of the host data; a second counter to track one or more acknowledgements received from the storage controller, the one or more acknowledgments corresponding to the one or more notifications such that each of the acknowledgments corresponds to a notification; and a response trigger to select one of the first counter and the second counter to trigger the response to the host device.

Abstract: A process is disclosed to identify the minimal set of sequential and combinational signals needed to fully reconstruct the combinational layout after emulation is complete. A minimal subset of sequential and combinational elements is output from the emulator to maximize the emulator speed and limit the utilization of emulator resources, e.g., FPGA resources. An efficient reconstruction of combinational waveforms or SAIF data is performed using a parallel computing grid.

Abstract: The present disclosure include an exemplary method comprising receiving a transaction history comprising transaction information associated with a plurality of transactions for an entity, wherein the transaction information involves transactions completed between employees of the entity and one or more merchants; detecting, using a machine learning algorithm, one or more leakage events associated with a transaction, the one or more leakage events comprising a first leakage event, wherein the first leakage event indicates a non-compliance of a spending rule of the entity by a participant in the transaction, wherein the one or more detected leakage events are analyzed as inputs to improve performance of the machine learning algorithm using unsupervised machine learning; and performing an analysis of a compliance level of the entity based on performing the detection of the one or more leakage events for the plurality of transactions.