Abstract: The present technology pertains to measuring the quality of an uncertainty prediction provided by a traj ectory prediction algorithm. An AI/ML platform can receive data including predicted trajectories of objects received from the trajectory prediction algorithm and observed paths for the objects received from the plurality of sensors. The predicted trajectories indicate predicted locations of the objects at a plurality of time intervals, and uncertainty predictions reflecting an uncertainty about the location of the objects at each of the predicted time intervals. The AI/ML platform can further determine respective standard deviations of the observed paths of the objects relative to the respective uncertainty predictions and plots the respective standard deviations against an ideal distribution of path distributions relative to the predicted locations of the objects at the plurality of time intervals.

Abstract: System, methods, and computer-readable media for training an object path prediction model to reduce an uncertainty of a predicted path when the predicted path of an object adjacent to another object. The training penalizes an uncertainty area prediction associated with a predicted future location of a nearby object to an autonomous vehicle (AV) when the uncertainty area prediction overlaps with another object to which the first detected object would be adjacent at the predicted future location. The training also penalizes a set of predicted future locations that implies improbable vehicle kinematics, whereby the object path prediction model becomes trained to avoid predicting similar sets of predicted future locations with improbable vehicle kinematics.

Abstract: Disclosed herein are systems and method including a method for managing an autonomous vehicle. The method includes providing input associated with an autonomous vehicle to a machine learning model, wherein the machine learning model is trained to predict what a planning stack of the autonomous vehicle will choose with respect to selecting a low cost branch of a tree structure in which a plurality of branches of the tree structure are evaluated to determine the low cost branch associated with a future route for the autonomous vehicle. The method further includes generating an output of the machine learning model to predict an output of the planning stack and inputting the output of the machine learning model into the planning stack. The planning stack can traverse a tree structure of possible routes more efficiently with a predicted outcome based on the output of the machine learning model.

Abstract: The subject disclosure relates to techniques for increasing a quality of predicted trajectories output from a trained prediction algorithm. A process of the disclosed technology can include receiving by a trained prediction algorithm, information about objects in an environment as perceived by sensors of an autonomous vehicle, receiving by the trained prediction algorithm, information about a location of the autonomous vehicle in the environment, generating by the trained prediction algorithm, a predicted trajectory for an object among the objects in the environment, wherein the predicted trajectory being anchored by a path through a tree of paths including at least two modes, wherein each mode creates a node in the tree, wherein a mode is a semantic classification of a portion of the predicted trajectory, and outputting by the trained prediction algorithm, the predicted trajectory for the object.

Abstract: A distributed inductance integrated field effect transistor (FET) structure, comprising a plurality of FETs. Each FET comprises a plurality of source regions, a gate region having a plurality of gate fingers extending from a gate bus bar, a drain region having a plurality of drain finger extending from a drain bus bar between the plurality of gate fingers, wherein the gate region controls current flow in a conductive channel between the drain region and source region. A first distributed inductor connects the gate regions of adjacent ones of the plurality of FETs; and a second distributed inductor connects the drain regions of adjacent ones of the plurality of FETs.

Abstract: A distributed inductance integrated field effect transistor (FET) structure, comprising a plurality of FETs. Each FET comprises a plurality of source regions, a gate region having a plurality of gate fingers extending from a gate bus bar, a drain region having a plurality of drain finger extending from a drain bus bar between the plurality of gate fingers, wherein the gate region controls current flow in a conductive channel between the drain region and source region. A first distributed inductor connects the gate regions of adjacent ones of the plurality of FETs; and a second distributed inductor connects the drain regions of adjacent ones of the plurality of FETs.

Abstract: A method includes identifying one or more second digital subscriber lines from one or more first digital subscriber lines based on historical performance data. The one or more second digital subscriber lines are identified based on degraded performance that is determined using first performance information for the one or more first digital subscriber lines. The method includes applying a line profile to the one or more second digital subscriber lines. The method includes storing second performance information associated with the one or more second digital subscriber lines. The method includes sending information to a remote computing device.

Abstract: A method includes selecting a first set of digital subscriber lines (DSLs) supported by a digital subscriber line access multiplexor (DSLAM). The DSLs of the first set exhibit reduced performance based on historical performance data. The method includes sending a request to the DSLAM for a first performance parameter for each of the DSLs of the first set. The method includes receiving the first performance parameters. The method includes removing DSLs from the first set that have suitable performance based on the first performance parameters to create a second set of DSLs. The method includes selecting a line profile to apply to the second set of DSLs. The method also includes sending a second request to the DSLAM to apply the line profile to the DSLs of the second set and then to determine a second performance parameter for each of the DSLs of the second set.

Abstract: A method includes selecting a first set of digital subscriber lines (DSLs) supported by a digital subscriber line access multiplexor (DSLAM). The DSLs of the first set exhibit reduced performance based on historical performance data. The method includes sending a request to the DSLAM for a first performance parameter for each of the DSLs of the first set. The method includes receiving the first performance parameters. The method includes removing DSLs from the first set that have suitable performance based on the first performance parameters to create a second set of DSLs. The method includes selecting a line profile to apply to the second set of DSLs. The method also includes sending a second request to the DSLAM to apply the line profile to the DSLs of the second set and then to determine a second performance parameter for each of the DSLs of the second set.

Abstract: The present application discloses an automated digital subscriber line performance control system comprising a computer system including a logic module to evaluate performance of a plurality of DSL lines and to automatically select a set of DSL lines from the plurality of DSL lines, a line profile database responsive to the computer system, the line profile database providing a plurality of line profiles in response to a request from the computer system, and a digital subscriber line access multiplexer coupled to the computer system.

Abstract: A system and method of determining broadband transport performance data are provided. The system includes an input to receive a request including a telephone number corresponding to a broadband data transport element. The system also includes logic to map the telephone number to a port address of network equipment associated with the broadband data transport element. The system further includes a performance analysis tool to determine performance information associated with the broadband data transport element.

Abstract: A system and method of accessing digital subscriber line data is provided. The system includes a first server having an input to receive a telephone number from a web browser interface and having an output to provide performance analysis data associated with at least one of a plurality of network elements that form a distributed and geographically diverse data communication system. The system also includes a second server including logic to convert telephone numbers to port addresses for network elements of the communication system. The system also includes a plurality of regional servers, each of the plurality of regional servers responsive to the second server and a plurality of network element management systems respectively coupled to each of the plurality of regional servers. The second server includes logic to convert telephone numbers to port addresses for network elements of the communication system.

Abstract: The present application discloses an automated digital subscriber line performance control system comprising a computer system including a logic module to evaluate performance of a plurality of DSL lines and to automatically select a set of DSL lines from the plurality of DSL lines, a line profile database responsive to the computer system, the line profile database providing a plurality of line profiles in response to a request from the computer system, and a digital subscriber line access multiplexer coupled to the computer system. The digital subscriber line access multiplexer is configured to measure a performance parameter of a plurality of physical DSL lines and to change a profile for at least one of the plurality of DSL lines. The set of DSL lines has degraded performance characteristics based on historical performance data.

Abstract: The present application discloses an automated digital subscriber line performance control system comprising a computer system including a logic module to evaluate performance of a plurality of DSL lines and to automatically select a set of DSL lines from the plurality of DSL lines, a line profile database responsive to the computer system, the line profile database providing a plurality of line profiles in response to a request from the computer system, and a digital subscriber line access multiplexer coupled to the computer system. The digital subscriber line access multiplexer is configured to measure a performance parameter of a plurality of physical DSL lines and to change a profile for at least one of the plurality of DSL lines. The set of DSL lines has degraded performance characteristics based on historical performance data.

Abstract: Methods to prepare intermediates for the conjugation of active ingredients to hydrophilic carriers are described. The polyhydroxylated carriers are first derivatized to convert the hydroxyls to leaving groups and then reacted with an alkylene diamine in the presence of a reducing agent. The resulting derivatized carrier can then be coupled to substituents containing carboxyl groups in the presence of dehydrating agents.