Abstract: Enclosed are embodiments for navigation with drivable area detection. In an embodiment, a method comprises: receiving a point cloud from a depth sensor, receiving image data from a camera; predicting at least one label indicating a drivable area by applying machine learning to the image data; labeling the point cloud using the at least one label; obtaining odometry information; generating a drivable area by registering the labeled point cloud and odometry information to a reference coordinate system; and controlling the vehicle to drive within the drivable area.

Abstract: The present disclosure is a method and apparatus for protecting building-related elements from collision damages. The apparatus can be designed to withstand high-impact collisions such as those caused by errant operation of heavy equipment. The method and apparatus are intended to be applicable to buildings already constructed and do not have to be implemented or considered before or during building design. In one exemplary embodiment, the apparatus can protect downspouts of warehouse sprinkler systems from collision damage that could result in pipe eruption.

Abstract: Systems and methods for obtaining hand images are provided. A method, performed by at least one processor that implements at least one network, includes obtaining a single source image, a three-dimensional (3D) hand pose of a first hand in the single source image, and a 3D target hand pose; and generating an image of a second hand, that has an appearance of the first hand and a pose of the 3D target hand pose, based on the single source image, the 3D hand pose, and the 3D target hand pose.

Abstract: Electric vehicle battery pack frames constructed with extruded aluminum side and cross members. Such frames are significantly stronger than conventional cast aluminum frames, while also being much lighter than steel frames. Cross members may be affixed to side members with extruded aluminum brackets. Side members of differing lengths may be employed, to make battery pack frames of differing sizes in modular manner. Battery pack lids and bottom panels may be removably affixed to the frame such as with bolts, for improved serviceability.

Abstract: Systems and techniques are described for identifying, monitoring, and sharing vehicle information amongst sensors. In some implementations, a system includes a central server and a plurality of sensors. The plurality of sensors are positioned in a fixed location relative to a roadway. Each sensor in the plurality of sensors is configured to: detect vehicles in a first field of view on the roadway. For each detected vehicle, each sensor is configured to identify features of the detected vehicle and perform operations for each feature. The operations include generating feature data representing the feature, generating a unique identification of the detected vehicle from the detected vehicles by concatenating the feature data representing the identified features of the detected vehicle, and adding the unique identification to a list.

Abstract: A coaxial tap in a hybrid fiber coaxial cable distribution system serves subscribers with an RF signal.

Abstract: A system provides a design interface for designing and implementing graphical user interfaces that users can access through web browsers. Depending on the configuration of the graphical user interfaces, the users may be able to monitor and control industrial processes by interacting with components that correspond to the industrial processes as displayed in user interfaces at client devices. The design interface includes functionality for selecting preprogrammed components, or for generating new components for display. The design interface further allows designers to associate data values received from a variety of sources with properties of the components in the user interfaces. In particular, properties associated with a component of an interface are stored in property tree structures, making dynamic changes to the components possible. Data bindings between subtrees representing components and sets of data from industrial and other sources allows for designs that scale with the availability of the data.

Abstract: Methods and systems are provided for generating a normative medical image from an anomalous medical image. In an example, the method includes receiving an anomalous medical image, wherein the anomalous medical image includes anomalous data, mapping the anomalous medical image to a normative medical image using a trained generative network of a generative adversarial network (GAN), wherein the anomalous data of the anomalous medical image is mapped to normative data in the normative medical image. In some examples, the method may further include displaying the normative medical image via a display device, and/or utilizing the normative medical image for further image analysis tasks to generate robust outcomes from the anomalous medical image.

Abstract: A microporous membrane wipe and a method of using such microporous membrane wipe are disclosed. The microporous membrane wipe may be uniaxially or biaxially oriented microporous membrane. The uniaxially or biaxially oriented microporous membrane may be made from one or more block and/or impact copolymers of polyethylene and/or polypropylene. A method of using such a microporous membrane wipe for skin oil blotting is also disclosed. Further disclosed is a method of using such a microporous membrane wipe for cleaning a surface for the removal of fingerprints, smudges and the like, where such surfaces may include, for example, eyeglasses, electronics, cell phones, displays, optical devices, camera lenses, microscope lenses and other precision optics, and/or the like.

Abstract: A system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform: modeling a webpage as a random field, wherein the random field comprises an undirected graph comprising nodes and edges; identifying a cyclic dependency in the undirected graph, wherein the cyclic dependency involves at least three of the nodes; breaking one or more of the edges of the undirected graph that connects the at least three of the nodes in the cyclic dependency; determining a probability of the webpage having exceeded a predetermined threshold based on compatibility functions of the edges, as updated; and sending instructions to display the webpage based at least in part on the probability of the webpage having exceeded the predetermined threshold. Other embodiments are described.

Abstract: Various dispensing devices, such as foaming soap pumps, are disclosed. The soap pump can include a fluid storage unit and a fluid handling unit. The fluid storage unit can include a reservoir that is configured to hold a quantity of product, such as liquid soap. The fluid handling unit can include a pumping assembly and dispensing assembly. The soap pump can be configured to withdraw liquid soap from the reservoir, convert the liquid soap to foamed soap, and dispense the foamed soap from the discharge assembly.

Abstract: Methods for treating cancer and/or inducing tumor regression in mammals (e.g., humans) by increasing the metabolism of the mammal, administering a BA dye to the mammal, and thereafter exposing the tumor to actinic light for activation of the BA dye.

Abstract: Devices and methods for a compact injector are provided with a compact configuration for ease of carrying or storage, and an activated configuration ready for injection. In the compact configuration, a plunger and a needle are both retracted into the injector housing, and upon actuation to the activated configuration, the plunger extends proximally and the needle extends distally, ready for injection. An extendable needle shield is also provided to block visibility of the needle during injection, and to reduce the risk of inadvertent needle stick at other times, including disposal.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for planning robotic movements to perform a given task while satisfying object pose estimation accuracy requirements. One of the methods includes generating a plurality of candidate measurement configurations for measuring an object to be manipulated by a robot; determining respective measurement accuracies for the plurality of candidate measurement configurations; determining a measurement accuracy landscape for the object including defining a high measurement accuracy region based on the respective measurement accuracies for the plurality of candidate measurement configurations; and generating a motion plan for manipulating the object in the robotic process that moves the robot, a sensor, or both, through the high measurement accuracy region when performing pose estimation for the object.

Abstract: In one embodiment, a system is disclosed for registration of point clouds for autonomous driving vehicles (ADV). The system receives a number of point clouds and corresponding poses from ADVs equipped with LIDAR sensors capturing point clouds of a navigable area to be mapped, where the point clouds correspond to a first coordinate system. The system partitions the point clouds and the corresponding poses into one or more loop partitions based on navigable loop information captured by the point clouds. For each of the loop partitions, the system applies an optimization model to point clouds corresponding to the loop partition to register the point clouds. They system merges the one or more loop partitions together using a pose graph algorithm, where the merged partitions of point clouds are utilized to perceive a driving environment surrounding the ADV.

Abstract: In exemplary embodiments, methods and systems are provided for determining vehicle events. In an exemplary embodiment, a system is provided that includes: one or more cameras onboard a vehicle that are configured to generate camera data; and a processor that is coupled to the one or more cameras and configured to at least facilitate: identifying a change in position of one or more objects of the camera data using the camera data; and determining that a vehicle event has occurred, based on the change in position of the one or more objects of the camera data.

Abstract: A system comprises a first body, comprising: a backpack suspension; a first storage region; and a first portion of a first attachment mechanism. A second body comprises: a second storage region; and a first portion of a second attachment mechanism. A third body comprises: a third storage region; a second portion of the first attachment mechanism; and a second portion of the second attachment mechanism. In a first configuration, the first portion of the first attachment mechanism is coupled to the first portion of the second attachment mechanism. In a second configuration, the first portion of the first attachment mechanism is coupled to the second portion of the first attachment mechanism, and the first portion of the second attachment mechanism is coupled to the second portion of the second attachment mechanism.

Abstract: A method of automatically programming a new load control device that replaces an old load control device takes advantage of a remote identification tag (e.g., an RFID tag) located in the vicinity of the old device. The remote identification tag stores an identifier that is representative of a location in which the old device is installed. The method includes the steps of: (1) storing a setting of an old device in a memory of a controller; (2) associating the setting with the identifier of the old device in the memory of the controller; (3) the new device retrieving the identifier from the remote identification tag after the new device is installed in the location of the old device; (4) the new device transmitting the identifier to the controller; and (5) the controller transmitting the setting of the old device to the new device in response to receiving the identifier.

Abstract: A method of populating a data set includes generating a plurality of models that model the behavior of an agent process, where the plurality of models includes a first model, a second model, and a third model. The method also includes using the plurality of models to generate one or more requests for one or more external data sources, and using the plurality of models to select a plurality of queries from a data store of predefined queries. The plurality of queries are selected by the plurality of models to request information that is missing from the data set. The method also includes populating at least a portion of the data set using information received in response to the one or more requests for the one or more external data sources and the plurality of queries.

Abstract: Vehicles and related systems and methods are provided for monitoring health of a power conversion module. A method involves operating the power conversion module to conduct a heating current until reaching a steady-state temperature, obtaining measurement data for an electrical characteristic associated with the power conversion module after reaching the steady-state temperature, determining a current thermal characterization curve for the power conversion module based on the measurement data and comparing the current thermal characterization curve to one or more reference thermal characterization curves for the power conversion module to identify a deviation associated with the current thermal characterization curve.