Abstract: A method for generating a dynamic neural network includes: utilizing a neural architecture search (NAS) method to obtain a searched result, wherein the searched result comprises a plurality of sub-networks; combining the plurality of sub-networks to generate a combined neural network; and fine-tuning the combined neural network to generate the dynamic neural network.

Abstract: A system for dynamically adjusting neural network efficiency of a dynamic neural network running on a device includes a detector and a signal generator. The detector is arranged to detect a change of a status of the device, to generate a trigger signal. The signal generator is arranged to generate a control signal according to the trigger signal, to dynamically adjust the neural network efficiency of the dynamic neural network.

Abstract: Aspects of the disclosure provide an evolutionary neural architecture search (ENAS) method. For example, the ENAS method can include steps (a) performing one or more evolutionary operations on an initial population of neural architectures to generate offspring neural architectures, (b) evaluating performance of each of the offspring neural architectures to obtain at least one evaluation value of the offspring neural architecture with respect to a performance metric, (c) adjusting the evaluation values of the offspring neural architectures based on at least one constraint on the evaluation values, (d) selecting at least one of the offspring neural architectures as a new population of neural architectures, and (e) outputting the new population of neural architectures as a last population of neural architectures when a stopping criterion is achieved, or (f) iterating steps (a) to (d) with the new population of neural architectures being taken as the initial population of neural architectures.

Abstract: Aspects of the disclosure provide an evolutionary neural architecture search (ENAS) method. For example, the ENAS method can include steps (a) performing one or more evolutionary operations on an initial population of neural architectures to generate offspring neural architectures, (b) evaluating performance of each of the offspring neural architectures to obtain at least one evaluation value of the offspring neural architecture with respect to a performance metric, (c) adjusting the evaluation values of the offspring neural architectures based on at least one constraint on the evaluation values, (d) selecting at least one of the offspring neural architectures as a new population of neural architectures, and (e) outputting the new population of neural architectures as a last population of neural architectures when a stopping criterion is achieved, or (f) iterating steps (a) to (d) with the new population of neural architectures being taken as the initial population of neural architectures.

Abstract: A vehicle includes drive wheels, an energy source having an available energy, a torque-generating device powered by the energy source to provide an input torque, a transmission configured to receive the input torque and deliver an output torque to the set of drive wheels, and a controller. The controller, as part of a programmed method, predicts consumption of the available energy along a predetermined travel route using onboard data, offboard data, and a first logic block, and also corrects the predicted energy consumption using the onboard data, offboard data, and an error correction loop between a second logic block and the first logic block. The controller also executes a control action with respect to the vehicle using the corrected energy consumption, including changing a logic state of the vehicle.

Abstract: A system configured to receive baseline map data from a remote map-data source, and determine whether the baseline map data is sufficient for present mobile navigation-unit function, yielding a map-sufficiency determination. If the map-sufficiency determination is affirmative, using the baseline map data for the present mobile navigation-unit function. If the map-sufficiency determination is negative, the system predicts navigation-unit movement, obtains based on the navigation-unit movement predicted, supplemental map data, and uses the baseline map data and the supplemental map data for the present mobile navigation-unit function.

Abstract: A vehicle includes drive wheels, an energy source having an available energy, a torque-generating device powered by the energy source to provide an input torque, a transmission configured to receive the input torque and deliver an output torque to the set of drive wheels, and a controller. The controller, as part of a programmed method, predicts consumption of the available energy along a predetermined travel route using onboard data, offboard data, and a first logic block, and also corrects the predicted energy consumption using the onboard data, offboard data, and an error correction loop between a second logic block and the first logic block. The controller also executes a control action with respect to the vehicle using the corrected energy consumption, including changing a logic state of the vehicle.

Abstract: A system having a resource-availability module configured to cause the processing unit to determine whether a resource scarcity condition exists in connection with providing map data to a mobile navigation unit. The system also includes a tuning-parameter module configured to cause the processing unit to, in response to determining that the resource scarcity condition exists, determine a tuning parameter to use in preparing map data to provide to the mobile navigation unit. The system further includes an encoding module configured to cause the processing unit to encode map data based on the tuning parameter, and a map-data-delivery module configured to cause the processing unit to provide or make available the encoded map data to the mobile navigation unit.

Abstract: A system configured to receive baseline map data from a remote map-data source, and determine whether the baseline map data is sufficient for present mobile navigation-unit function, yielding a map-sufficiency determination. If the map-sufficiency determination is affirmative, using the baseline map data for the present mobile navigation-unit function. If the map-sufficiency determination is negative, the system predicts navigation-unit movement, obtains based on the navigation-unit movement predicted, supplemental map data, and uses the baseline map data and the supplemental map data for the present mobile navigation-unit function.

Abstract: A system having a resource-availability module configured to cause the processing unit to determine whether a resource scarcity condition exists in connection with providing map data to a mobile navigation unit. The system also includes a tuning-parameter module configured to cause the processing unit to, in response to determining that the resource scarcity condition exists, determine a tuning parameter to use in preparing map data to provide to the mobile navigation unit. The system further includes an encoding module configured to cause the processing unit to encode map data based on the tuning parameter, and a map-data-delivery module configured to cause the processing unit to provide or make available the encoded map data to the mobile navigation unit.

Abstract: A modified clay is provided, which includes a layered clay material intercalated with a modifier having a conjugated double bond and capable of producing free radicals when heated. A clay-polymer composite is also provided, which includes a polymer material and the modified clay, wherein the modified clay is dispersed in the polymer material and at least partially exfoliated. The modifier is capable of producing free radicals when heated to scavenge free radicals generated from thermal cracking or burning of the polymer material to prevent further thermal cracking of the polymer material.

Abstract: A mobile computing apparatus simulates the performance of a virtual vehicle using the route, driving behavior and loading experience of a baseline vehicle. The baseline vehicle is instrumented and operational data is collected, forming a data set. The apparatus includes simulator logic configured to construct a duty cycle from the data set representative of the operation of the baseline vehicle during travel along the route (e.g., a loading duty cycle). The data set includes route data with distance and vehicle speed information, engine data associated with the engine, and operational element data. The logic defines a virtual vehicle that is the same as the baseline vehicle but that includes a virtual operational element, such as a transmission, that is different than that in the baseline vehicle. The logic determines a performance characteristic, such as fuel economy, of the virtual vehicle using the constructed duty cycle.

Abstract: A mobile computing apparatus simulates the performance of a virtual vehicle using the route, driving behavior and loading experience of a baseline vehicle. The baseline vehicle is instrumented and operational data is collected, forming a data set. The apparatus includes simulator logic configured to construct a duty cycle from the data set representative of the operation of the baseline vehicle during travel along the route (e.g., a loading duty cycle). The data set includes route data with distance and vehicle speed information, engine data associated with the engine, and operational element data. The logic defines a virtual vehicle that is the same as the baseline vehicle but that includes a virtual operational element, such as a transmission, that is different than that in the baseline vehicle. The logic determines a performance characteristic, such as fuel economy, of the virtual vehicle using the constructed duty cycle.

Abstract: A continuously variable transmission mechanically coupled with an automated mechanical transmission is adjusted during a shifting process. At the completion of the shifting process, an engine mechanically coupled with the automated mechanical transmission is provided a fueling pulse. Additionally, the speed of an output shaft of the automated mechanical transmission is filtered by a second order variable time constant low pass filter.

Abstract: A modified clay is provided, which includes a layered clay material intercalated with a modifier having a conjugated double bond and capable of producing free radicals when heated. A clay-polymer composite is also provided, which includes a polymer material and the modified clay, wherein the modified clay is dispersed in the polymer material and at least partially exfoliated. The modifier is capable of producing free radicals when heated to scavenge free radicals generated from thermal cracking or burning of the polymer material to prevent further thermal cracking of the polymer material.

Abstract: A method is disclosed for computing clutch engagement characteristics of a friction clutch system in a vehicle powertrain. A dynamic model of the system is used under conditions that cause clutch slipping. Algebraic equations defining a functional relationship between clutch torque and an engagement angle have characteristic parameters that are estimated using a non-linear least squares technique. The non-linear least squares technique repetitively minimizes the difference between a measured clutch output speed and a clutch output speed from the system dynamic model for the same inputs until a small insignificant error is reached. Parameter estimates are used to update each engagement characteristic.

Abstract: A continuously variable transmission mechanically coupled with an automated mechanical transmission is adjusted during a shifting process. At the completion of the shifting process, an engine mechanically coupled with the automated mechanical transmission is provided a fueling pulse. Additionally, the speed of an output shaft of the automated mechanical transmission is filtered by a second order variable time constant low pass filter.

Abstract: A method is disclosed for estimating clutch engagement characteristics of a friction clutch system in a vehicle powertrain. A dynamic model of the system is used under conditions that cause clutch slipping. Algebraic equations defining a functional relationship between clutch torque and an engagement angle have characteristic parameters that are estimated using a non-linear least squares technique. A non-linear least squares technique iteratively minimizes the difference between a measured output clutch disk speed and an output clutch disk speed from the system dynamic model for the same inputs until a small insignificant error is reached. Parameter estimates are used to compile an estimated clutch engagement characteristic.

Abstract: A method is disclosed for estimating clutch engagement characteristics of a friction clutch system in a vehicle powertrain. A dynamic model of the system is used under conditions that cause clutch slipping. Algebraic equations defining a functional relationship between clutch torque and an engagement angle have characteristic parameters that are estimated using a non-linear least squares technique. A non-linear least squares technique iteratively minimizes the difference between a measured output clutch disk speed and an output clutch disk speed from the system dynamic model for the same inputs until a small insignificant error is reached. Parameter estimates are used to compile an estimated clutch engagement characteristic.

Abstract: A control for a vehicle drive line system (10) including an automated vehicle master clutch (14) drivingly interposed in between a fuel-controlled engine (12) and the input shaft (20) of a mechanical transmission. At sensed idle conditions (THL<REF and OS<REF), the engine (12) is commanded to generate an output torque (T.sub.FW) equal to a selected idle drive torque (T.sub.IDLE) at idle speed (ES=IDLE), the engine is commanded to rotate at idle speed and the clutch, preferably a wet clutch, is caused to engage with a torque capacity equal to the idle drive torque.