Abstract: Example methods, apparatuses, and/or articles of manufacture are disclosed that may be implemented, in whole or in part, using one or more computing devices to estimate an execution latency of a candidate neural network in a neural network architecture search (NAS) process.

Abstract: Example methods, apparatuses, and/or articles of manufacture are disclosed that may be implemented, in whole or in part, using one or more computing devices to update parameters of an estimator to estimate and/or predict an execution latency of a neural network in a neural network architecture search (NAS) process.

Abstract: A normalized driver performance comparison framework can include predicting a plurality of scenarios of a ground vehicle. A Monte Carlo simulation can be utilized to determine results using the predicted plurality of scenarios and one or more predictive models. Best and worst possible scenarios and associated efficiency for an observed scenario can be determined based on the Monte Carlo simulation results. The efficiency for the observed scenario can be normalized as a function of the best and worst efficiencies.

Abstract: A ground vehicle control system including a plurality of sensors and one or more predictive controllers. The sensors can be configured to detect environment information and vehicle operating information. The one or more predictive controllers can be configured to self-train for an energy consumption solution based on one or more control parameters including the environment information and the vehicle operating information.

Abstract: Presented systems and methods facilitate efficient and effective performance of vehicle operations. In one embodiment, a system comprises a user interface, a processor, and a memory. The user interface is configured to convey information associated with operation of a vehicle to and from a user, wherein the information associated with the operation of the vehicle includes information associated with a performance objective. Information associated with the operation of the vehicle can include metric information that expresses a characteristic corresponding to the performance objective. The metric information can be associated with various aspects (e.g., current, future, etc.) of the vehicle operation. Processing by the processor can include comparative analysis of actual performance of the vehicle operation to target values associated with the vehicle operation. The user interface can include a performance indicator.

Abstract: Techniques for utilizing a Monte Carlo model to perform pre-training of a ground vehicle controller. A sampled distribution of actions and corresponding states can be utilized to train a reinforcement learning controller policy, learn an action-value function, or select a set of control parameters with a predetermined loss.

Abstract: Reinforcement learning based ground vehicle control techniques adapted to reduce energy consumption, braking, shifting, travel distance, travel time, and or the like. The reinforcement learning techniques can include training a reinforcement learning controller based on a simulated ground vehicle environment during a simulation mode, and then further training the reinforcement learning controller based on a ground vehicle environment during an operating mode of a ground vehicle.

Abstract: Ground vehicle control techniques adapted to reduce energy consumption, braking, shifting, travel distance, travel time, and or the like. The techniques can generate a target speed window and a target vehicle performance plan for controlling operation of a ground vehicle along a current and one or more upcoming segments of a roadway responsive to the dynamic driving environment.

Abstract: Ground vehicle control techniques adapted to reduce energy consumption, braking, shifting, travel distance, travel time, and or the like. The techniques can generate a target speed window and a target vehicle performance plan for controlling operation of a ground vehicle along a current and one or more upcoming segments of a roadway responsive to the dynamic driving environment.

Abstract: Ground vehicle control techniques adapted to reduce energy consumption, braking, shifting, travel distance, travel time, and or the like. The techniques can generate a target speed window and a target vehicle performance plan for controlling operation of a ground vehicle along a current and one or more upcoming segments of a roadway responsive to the dynamic driving environment.

Abstract: A normalized driver performance comparison framework can include predicting a plurality of scenarios of a ground vehicle. A Monte Carlo simulation can be utilized to determine results using the predicted plurality of scenarios and one or more predictive models. Best and worst possible scenarios and associated efficiency for an observed scenario can be determined based on the Monte Carlo simulation results. The efficiency for the observed scenario can be normalized as a function of the best and worst efficiencies.

Abstract: A ground vehicle control system including a plurality of sensors and one or more predictive controllers. The sensors can be configured to detect environment information and vehicle operating information. The one or more predictive controllers can be configured to self-train for an energy consumption solution based on one or more control parameters including the environment information and the vehicle operating information.

Abstract: Presented systems and methods facilitate efficient and effective performance of vehicle operations. In one embodiment, a system comprises a user interface, a processor, and a memory. The user interface is configured to convey information associated with operation of a vehicle to and from a user, wherein the information associated with the operation of the vehicle includes information associated with a performance objective. Information associated with the operation of the vehicle can include metric information that expresses a characteristic corresponding to the performance objective. The metric information can be associated with various aspects (e.g., current, future, etc.) of the vehicle operation. Processing by the processor can include comparative analysis of actual performance of the vehicle operation to target values associated with the vehicle operation. The user interface can include a performance indicator.

Abstract: Reinforcement learning based ground vehicle control techniques adapted to reduce energy consumption, braking, shifting, travel distance, travel time, and or the like. The reinforcement learning techniques can include training a reinforcement learning controller based on a simulated ground vehicle environment during a simulation mode, and then further training the reinforcement learning controller based on a ground vehicle environment during an operating mode of a ground vehicle.

Abstract: Techniques for utilizing a Monte Carlo model to perform pre-training of a ground vehicle controller. A sampled distribution of actions and corresponding states can be utilized to train a reinforcement learning controller policy, learn an action-value function, or select a set of control parameters with a predetermined loss.

Abstract: A navigation system having a navigation module configured to plot a first route. A display is controlled by the navigation module to display the first route. A touch surface is configured to receive a touch input by a user corresponding to a second route, which is a modification of the first route, for entry to the navigation module. The navigation module is configured to plot the second route and control the display to display the second route.

Abstract: Systems and methods for multi-step vehicle entry authorization utilizing biometric data are disclosed. A proximity/contact sensor attached to a vehicle receives a device ID from a wearable device of a user. A biometric sensor receives biometric data of the user. A control module accesses a user database storing authorized user information and determines whether the user is authorized for the vehicle based on the device ID, the biometric data, and the user database. The control module unlocks the vehicle in response to a determination that the user is authorized for the vehicle.

Abstract: A low fuel notification system for use in association with a vehicular navigation system is operable to generate and provide notifications to the vehicle operator of low fuel conditions and provide information regarding available refueling stations based on the station's location and the vehicle's estimated driving range.

Abstract: A low fuel notification system for use in association with a vehicular navigation system is operable to generate and provide notifications to the vehicle operator of low fuel conditions and provide information regarding available refueling stations based on the station's location and the vehicle's estimated driving range.