Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for converting audio to spikes for input to a spiking neural network configured to recognize speech based on the spikes are described. In some aspects, a method includes obtaining audio data and generating frequency domain audio signals that represent the audio data by converting the audio data into a frequency domain. The frequency domain audio signals are mapped into a set of Mel-frequency bands to obtain Mel-scale frequency audio signals. A log transformation is performed on the Mel-scale frequency audio signals to obtain log-Mel signals. Spike input is generated for input to a spiking neural network (SNN) model by converting the log-Mel signals to the series of spikes. The spike input is provided as an input to the SNN model.

Abstract: A vehicle hitching assistance system includes a controller acquiring image data from the vehicle and identifying a plurality of trailers within in a specified area of the image data. The specified area is less than a total field of the image data and corresponds at least with left and right steering angle limits of the vehicle. The controller further receives a selection of a subject trailer of the plurality of trailers identified within the specified area, identifies a coupler of the subject trailer, and outputs a steering signal to the vehicle to cause the vehicle to steer to align a hitch ball of the vehicle with the coupler of the subject trailer.

Abstract: A vibration damper for damping vibrations of a cable includes an attachment portion configured to be attached to the cable while the cable is energized. The vibration damper also includes a flexible leg portion attached to the attachment portion. The vibration damper further includes a weighted portion attached to the flexible leg portion. The weighted portion is spaced a separation distance from the attachment portion and the weighted portion is movable relative to the attachment portion via the flexible leg portion to dampen the vibrations.

Abstract: Techniques for determining that a first vehicle is associated with a reverse state, and controlling a second vehicle based on the reverse state, are described herein. In some examples, the first vehicle may provide an indication that the first vehicle will be executing a reverse maneuver, such as with reverse lights on the vehicle or by positioning at an angle relative to a road or parking space to allow for the reverse maneuver into a desired location. A planning system of the second vehicle (such as an autonomous vehicle) may receive sensor data and determine a variety of these indications to determine a probability that the vehicle is going to execute a reverse maneuver. The second vehicle can further determine a likely trajectory of the reverse maneuver and can provide appropriate accommodations (e.g., time and/or space) to allow the second vehicle to execute the maneuver safely and efficiently.

Abstract: The disclosure generally pertains to systems and methods for providing a delivery assistance service having an augmented-reality digital companion (ARDC). In an example method, a first set of instructions can be received via the ARDC. The first set of instructions can direct a delivery driver to an assigned delivery vehicle within a parking lot. A second set of instructions including a driving destination can be received via the ARDC. When the delivery driver has reached the driving destination, a third set of instructions can be received via the ARDC. The third set of instructions can include a route from the driving destination to a delivery location. When the delivery driver is traveling along the route, first pop-up information can be provided via the ARDC. The delivery request can be completed, and second pop-up information can be provided via the ARDC to assist the delivery driver in reaching an intended destination.

Abstract: Techniques to predict object behavior in an environment are discussed herein. For example, such techniques may include determining a trajectory of the object, determining an intent of the trajectory, and sending the trajectory and the intent to a vehicle computing system to control an autonomous vehicle. The vehicle computing system may implement a machine learned model to process data such as sensor data and map data. The machine learned model can associate different intentions of an object in an environment with different trajectories. A vehicle, such as an autonomous vehicle, can be controlled to traverse an environment based on object's intentions and trajectories.

Abstract: A method for producing clean water from a contaminated water source, the method comprising the steps of: a) locating a clean water generating device in fluid communication with the contaminated water source, the clean water generating device including a reaction chamber containing an ionic solution; b) transferring contaminated water from the contaminated water source into the reaction chamber through an inlet in the clean water generating device; c) generating an electrolysis reaction within the reaction chamber; d) removing gas generated by the electrolysis reaction from the reaction chamber through an outlet of the reaction chamber; e) combusting the gas generated by the electrolysis reaction; and f) collecting clean water generated by the combustion of the gas.

Abstract: A discrimination system that forms a fluid column and interrogates objects within the fluid column with an excitation source. An optical arrangement collects output electromagnetic radiation emanating from the excited objects disposed within the fluid column and directs the output electromagnetic radiation to a detector. An analyzer reduces the positional dependency of the detected intensity by normalizing the value based on the position of each object.

Abstract: Techniques for determining that a first vehicle is associated with a reverse state, and controlling a second vehicle based on the reverse state, are described herein. In some examples, the first vehicle may provide an indication that the first vehicle will be executing a reverse maneuver, such as with reverse lights on the vehicle or by positioning at an angle relative to a road or parking space to allow for the reverse maneuver into a desired location. A planning system of the second vehicle (such as an autonomous vehicle) may receive sensor data and determine a variety of these indications to determine a probability that the vehicle is going to execute a reverse maneuver. The second vehicle can further determine a likely trajectory of the reverse maneuver and can provide appropriate accommodations (e.g., time and/or space) to allow the second vehicle to execute the maneuver safely and efficiently.

Abstract: The present invention relates to a solid or liquisolid formulation comprising corallopyronin A, wherein the formulation comprises an amorphous solid dispersion of corallopyronin A embedded in a water-soluble polymer or corallopyronin A loaded onto porous silica.

Abstract: A method of sorting cells including magnetically coupling a nozzle assembly to a flow cytometer in a predetermined orientation to form a fluid stream having a sheath fluid and a sample fluid. Particles within the sample fluid are oriented and then interrogated at an inspection zone to produces signals representative of emitted or reflected electromagnetic radiation. The electromagnetic radiation is analyzed to classify the cells and the cells are sorted according to their classification.

Abstract: Systems and methods are disclosed configured to train an autoencoder using images that include faces, wherein the autoencoder comprises an input layer, an encoder configured to output a latent image from a corresponding input image, and a decoder configured to attempt to reconstruct the input image from the latent image. An image sequence of a face exhibiting a plurality of facial expressions and transitions between facial expressions is generated and accessed. Images of the plurality of facial expressions and transitions between facial expressions are captured from a plurality of different angles and using different lighting. An autoencoder is trained using source images that include the face with different facial expressions captured at different angles with different lighting, and using destination images that include a destination face.

Abstract: In flow cytometry, particles (2) can be distinguished between populations (8) by combining n-dimensional parameter data, which may be derived from signal data from a particle, to mathematically achieve numerical results representative of an alteration (48). An alteration may include a rotational alteration, a scaled alteration, or perhaps even a translational alteration. Alterations may enhance separation of data points which may provide real-time classification (49) of signal data corresponding to individual particles into one of at least two populations.

Abstract: A method for generating and capturing biothermal energy comprising: forming a heap comprising an amended organic material; subjecting the amended organic material to a continuous fermentation process to produce a convection current, and to stimulate capture of non-visible radiation, and using a heat exchanger in contact with the heap, capture and/or store biothermal energy generated by the continuous fermentation process within the heap.

Abstract: An antenna housing is provided that is configured to be mounted to a pole. The antenna housing has spaced upper and lower ends. A sidewall extends between and around the spaced ends to define an interior of the housing. This interior may house and/or partially conceal one or more antennas. Inlet and outlet ducting extend through the sidewall of the housing to individually cool each antenna within the interior of the housing. The inlet and outlet duct may connect to a cooling duct that is in fluid communication with a heat rejection surface of the antenna. Accordingly, each antenna may be cooled using ambient air and the heated air may be exhausted outside of the housing.

Abstract: Systems for obtaining an image of a target are provided including at least one multi-wavelength illumination module configured to illuminate a target using two or more different wavelengths, each penetrating the target at different depths; a multi-wavelength camera configured to detect the two or more different wavelengths illuminating the target on corresponding different channels and acquire corresponding images of the target based on the detected two or more different wavelengths illuminating the target; a control module configured synchronize illumination of the target by the at least one multi-wavelength illumination module and detection of the two or more different wavelengths by the camera; an analysis module configured to receive the acquired images of the target and analyze the acquired images to provide analysis results; and an image visualization module modify the acquired images based on the analysis results to provide a final improved image in real-time.

Abstract: The invention encompasses methods for reducing the proportion of sperm cells with abnormal morphology, and unviable sperm cells, in a sperm cell population.

Abstract: A method for biological hydrosynthesis, energy generation and storage and/or topsoil restoration comprising the steps of: undertaking a primary amendment of a site with a first catalyst and a second catalyst, wherein the first catalyst and the second catalyst are applied to at least a portion of the site such that a matrix of biological energy generation points are constructed on about 5% of the site by area; undertaking a secondary amendment of the site with the first catalyst and the second catalyst, wherein the first catalyst and the second catalyst are applied to at least a portion of the site such that a matrix of biological energy generation points are constructed on about 20% of the site by area, and undertaking a tertiary amendment of the site with the first catalyst and the second catalyst, wherein the first catalyst and the second catalyst are applied to at least a portion of the site such that a matrix of biological energy generation points are constructed on about 75% of the site by area, wherein

Abstract: Systems and methods for virtual vehicle parking assistance are disclosed herein. An example method includes determining a current vehicle position and vehicle dimensions of a vehicle, determining parking space dimensions of a parking space, receiving a desired parking position for the vehicle through an augmented reality interface, the augmented reality interface including a three-dimensional vehicle model based on the vehicle dimensions, the augmented reality interface being configured to allow a user to virtually place the three-dimensional vehicle model in the parking space to determine the desired parking position, determining a virtual parking procedure for the vehicle based on the desired parking position selected by the user and the parking space dimensions of a parking space and causing the vehicle to autonomously park based on the virtual parking procedure.

Abstract: Method for converting organic material into catalyst for biological hydrosynthesis, comprising providing organic material comprising at least one source of readily available carbon, at least one complex carbon-containing compound and at least one source of protein and contacting the organic material with preparatory catalyst is provided. The organic material is subjected to a size reduction process to produce size-reduced organic material and a solid to liquid ratio of the size-reduced organic material is adjusted to form organic material slurry. The organic material slurry is subjected to a fermentation process to produce amended organic material, by applying a process catalyst to at least a portion of the organic material slurry. A liquid is recovered from the amended organic material and transferred to a fermentation chamber, where it is subjected to a fermentation process to produce amended liquid by applying balancing catalyst to the liquid. The amended liquid is the catalyst.