Abstract: Methods, apparatus and systems for wireless sensing based on deep learning are described.

Abstract: The disclosure describes an autotuning framework for tuning an image signal processing (ISP) module of an autonomous driving vehicle (ADV). The autotuning framework can generate different sets of parameter values using a variety of optimization algorithms to configure the ISP module. Each processed image generated by the ISP module configured with the different sets of parameter values is compared by an ISP module testing device with a reference image stored therein to generate an objective core measuring one or more differences between each of the processed images and the reference image. The objective scores and the corresponding sets of parameter values are stored in a database. Different sets of optimal parameter values for different environments can be selected from the database, and uploaded to a cloud database for use by an ADV, which can select a different set of ISP parameter values based on an environment that the ADV is travelling in.

Abstract: In one embodiment, a system configures an image signal processor (ISP) of an autonomous driving vehicle (ADV) with a first set of ISP configuration parameters, where the ISP is used to process raw image data of an image sensor of the ADV based on the first set of ISP configuration parameters. The system determines whether one or more criteria is satisfied, where the one or more criteria corresponds to an expected change in a characteristic of ambient light being perceived by the image sensor of the ADV. In response to determining that the one or more criteria is satisfied, the system configures the ISP of the ADV with a second set of ISP configuration parameters, where the ISP is used to apply an image processing algorithm to raw image data based on the second set of ISP configuration parameters to generate an image.

Abstract: According to some embodiments, systems, methods, and media for operating an autonomous driving vehicle (ADV) encountered with small objects are described. According to a method, the ADV, when detecting an object in a lane in which the ADV is travelling, can determine whether the ADV can safely drive over the object based on attributes of the object and attributes of the ADV, and if so, can generate one or more planned trajectories that each enable the ADV to drive over the object. From the one or more planned trajectories, the ADV can select a planned trajectory that enables the ADV to drive over the object along the centerline of the ADV without causing the ADV to drive out of the lane. If no such planned trajectory exists, the ADV can bypass the object, or stop within a predetermined distance of the object.

Abstract: In one embodiment, a system generates an image using either a first or a second image signal processing (ISP) algorithm, where the first or second ISP algorithm is applied to raw image data of a camera of an autonomous driving vehicle (ADV) to generate the image. The system applies a machine learning model to the image to identify a representation of an obstacle, where the machine learning model is generated by a few shots learning algorithm that contrasts labeled data of a positive training sample from images corresponding to the first and second ISP algorithms to labeled data of a negative training sample from images corresponding to the first and second ISP algorithm. The system determines a classification and a location of the obstacle based on the representation of the obstacle. The system plans a motion control of the ADV based on the classification and location of the detected object.

Abstract: A receptacle connector includes a receptacle housing, pin contacts, and a retainer. The receptacle housing has a convex wall portion, a concave wall portion, a first side wall portion that extends between the convex wall portion and the concave wall portion, and a second side wall portion that extends between the convex wall portion and the concave wall portion. The convex wall portion, the concave wall portion, the first side wall portion, and the second side wall portion at least partially define a cavity having an open end. The pin contacts are located in the cavity of the receptacle housing. The retainer has a first side latch and a second side latch that are configured to extend into the cavity in an engaged position and to move outward from the cavity to a disengaged position.

Abstract: Methods, apparatus and systems for wireless human-nonhuman motion detection are described.

Abstract: Methods, apparatus and systems for wireless motion recognition are described. In one example, a described system comprises: a transmitter configured for transmitting a first wireless signal through a wireless multipath channel of a venue; a receiver configured for receiving a second wireless signal through the wireless multipath channel; and a processor. The second wireless signal differs from the first wireless signal due to the wireless multipath channel that is impacted by a motion of an object in the venue. The processor is configured for: obtaining a time series of channel information (TSCI) of the wireless multipath channel based on the second wireless signal, tracking the motion of the object based on the TSCI to generate a gesture trajectory of the object, and determining a gesture shape based on the gesture trajectory and a plurality of pre-determined gesture shapes.

Abstract: A network of matrix processing units (MPUs) is provided on a device, where each MPU is connected to at least one other MPU in the network, and each MPU is to perform matrix multiplication operations. Computer memory stores tensor data and a master control central processing unit (MCC) is provided on the device to receive an instruction from a host device, where the instruction includes one or more tensor operands based on the tensor data. The MCC invokes a set of operations on one or more of the MPUs based on the instruction, where the set of operations includes operations on the tensor operands. A result is generated from the set of operations, the result embodied as a tensor value.

Abstract: Methods, apparatus and systems for wireless gait recognition and rhythmic motion monitoring are described. In one example, a described system comprises: a transmitter, a receiver, and a processor. The transmitter is configured for transmitting a first wireless signal towards an object in a venue through a wireless multipath channel of the venue. The receiver is configured for: receiving a second wireless signal through the wireless multipath channel between the transmitter and the receiver. The second wireless signal differs from the first wireless signal due to the wireless multipath channel which is impacted by a rhythmic motion of the object. The processor is configured for: obtaining a time series of channel information (CI) of the wireless multipath channel based on the second wireless signal, monitoring the rhythmic motion of the object based on the time series of CI (TSCI), and triggering a response action based on a result of the monitoring.

Abstract: A method, system, and article provide image processing with power reduction while using universal serial bus cameras.

Abstract: A network of matrix processing units (MPUs) is provided on a device, where each MPU is connected to at least one other MPU in the network, and each MPU is to perform matrix multiplication operations. Computer memory stores tensor data and a master control central processing unit (MCC) is provided on the device to receive an instruction from a host device, where the instruction includes one or more tensor operands based on the tensor data. The MCC invokes a set of operations on one or more of the MPUs based on the instruction, where the set of operations includes operations on the tensor operands. A result is generated from the set of operations, the result embodied as a tensor value.

Abstract: A method for printing materials by: providing a receiving substrate; providing a target substrate having a photon-transparent support, a photon absorbent interlayer coated on the support, and a transfer material of a solid-phase environmental sample coated on top of the interlayer opposite to the support; and directing photon energy through the transparent support so that the photon energy strikes the interlayer is described. The environmental sample includes living organisms. A portion of the interlayer is energized by absorption of the photon energy, and the energized interlayer causes a transfer of a portion of the environmental sample including the microorganisms across a gap between the target substrate and the receiving substrate and onto the receiving substrate.

Abstract: Provided herein are methods and compositions for treating and preventing vascular malformations including lymphatic, venous, capillary, arteriovenous, and combinations thereof. Methods of treatment and prevention include the administration of proteasome inhibitors, omipalisib, disulfiram, and agents which target genes in the PI3K/AKT/mTOR or RAS/RAF/MAPK pathways, including but not limited to Pik3ca, Pik3r3, Tsc2, Rasa1, Map2k2, and Glmn.

Abstract: An article comprising hollow ceramic microspheres and multi-component fibers is disclosed. The multi-component fibers are adhered together, and the hollow ceramic microspheres are adhered to external surfaces of the multi-component fibers. A method of making the article and use of the article for insulation are also disclosed.

Abstract: Embodiments include an apparatus comprising an execution unit coupled to a memory, a microcode controller, and a hardware controller. The microcode controller is to identify a global power and performance hint in an instruction stream that includes first and second instruction phases to be executed in parallel, identify a local hint based on synchronization dependence in the first instruction phase, and use the first local hint to balance power consumption between the execution unit and the memory during parallel executions of the first and second instruction phases. The hardware controller is to use the global hint to determine an appropriate voltage level of a compute voltage and a frequency of a compute clock signal for the execution unit during the parallel executions of the first and second instruction phases. The first local hint includes a processing rate for the first instruction phase or an indication of the processing rate.

Abstract: A network of matrix processing units (MPUs) is provided on a device, where each MPU is connected to at least one other MPU in the network, and each MPU is to perform matrix multiplication operations. Computer memory stores tensor data and a master control central processing unit (MCC) is provided on the device to receive an instruction from a host device, where the instruction includes one or more tensor operands based on the tensor data. The MCC invokes a set of operations on one or more of the MPUs based on the instruction, where the set of operations includes operations on the tensor operands. A result is generated from the set of operations, the result embodied as a tensor value.

Abstract: Methods and apparatus for performing a ranging operation are provided. In one example, an apparatus comprises a transmitter circuit, a receiver circuit, a controller, and a code storage. The controller can obtain a first code from the code storage, determine, from the first code, first timing information and first amplitude information of a corresponding first group of one or more signals, and control the transmitter circuit to transmit the first group of one or more signals based on the first timing information and the first amplitude information. The controller can configure a matched filter based on the first timing information and the first amplitude information, identify return signals of the first group of one or more signals based on processing received signals using the configured matched filter, and perform a ranging operation based on the identified return signals and the first group of one or more signals.

Abstract: A method for operating a LiDAR system in an automobile that can include receiving noise data corresponding to an ambient noise level, receiving false positive data corresponding to a rate of false positive object detection occurrences; determining an object detection range spanning a distance defined by a minimum range of object detection and a maximum range of object detection for the LiDAR system; generating an object detection threshold value for detecting objects based on the noise data and the rate of false positive data; applying the object detection threshold value to each of a plurality of range values within the object detection range; and applying a gain sensitivity profile to the object detection threshold value at each of a plurality of range values.

Abstract: In one example, an apparatus is provided. The apparatus is part of a Light Detection and Ranging (LiDAR) module and comprises a transmitter circuit, a receiver circuit, and a controller. The receiver circuit comprises a photodetector configured to convert a light signal into a photocurrent signal. The controller is configured to: transmit, using the transmitter circuit, a first light signal; receive, using the photodetector of the receiver circuit, a second light signal; determine whether the second light signal includes a scatter signal coupled from the transmitter circuit, and a reflected first light signal; and based on whether the second light signal includes the scatter signal and the reflected first light signal, determine a time-of-flight of the first light signal based on one of: a width of the second light signal, or a time difference between the transmission of the first light signal and the reception of the second light signal.