Abstract: A system includes multiple charging stations, multiple fleet electric vehicles, and a computer. The charging stations are provided at a facility. The fleet electric vehicles are charged by the charging stations per a schedule. The fleet electric vehicles are operational to perform multiple tasks on multiple routes dispersed over multiple days. The computer is in communication with the charging stations and is operational to generate the schedule to charge the fleet electric vehicles over the multiple days with a two-stage process. The schedule is based on a first number of the charging stations ready to charge, a second number of the fleet electric vehicles ready to be charged, a plurality of state-of-charges in the fleet electric vehicles upon arrival and already present at the facility, and a plurality of energy consumption levels associated with the plurality of routes.

Abstract: An example method of generating a neural network control policy for a vehicle includes obtaining a performance objective parameter associated with a control system of a vehicle, obtaining a policy optimizing algorithm corresponding to the performance objective parameter, defining a system state space, a control action space, and a disturbance space, each associated with the control system, generating a neural network control policy, based on the system state space, the control action space, and the disturbance space, wherein the neural network control policy has a non-linear H-infinity robustness guarantee, and automatically controlling at least one vehicle component according to the neural network control policy.

Abstract: An example method of generating a neural network control policy for a vehicle includes obtaining a performance objective parameter associated with a control system of a vehicle, obtaining a policy optimizing algorithm corresponding to the performance objective parameter, defining a system state space, a control action space, and a disturbance space, each associated with the control system, generating a neural network control policy, based on the system state space, the control action space, and the disturbance space, wherein the neural network control policy has a non-linear H-infinity robustness guarantee, and automatically controlling at least one vehicle component according to the neural network control policy.

Abstract: A system for managing a fleet of electric vehicles and respective fleet drivers includes a command unit having a processor and tangible, non-transitory memory on which instructions are recorded. The command unit is adapted to obtain input variables, including respective fleet tasks and their priority status. Route data for the respective fleet tasks is obtained. The command unit is adapted to obtain an objective function defined by a plurality of influence factors having respective weights. The command unit is adapted to obtain optimal charging schedules respectively for the electric vehicles and match the respective fleet tasks to the electric vehicles and the respective fleet drivers, based in part on the objective function, input variables and the route data. The influence factors may include energy cost optimization, timeliness of task completion and minimizing range anxiety. In some embodiments, the respective weights of the influence factors are designated by a fleet manager.

Abstract: A system for predicting energy consumption by a vehicle during a trip has a controller adapted to receive a route plan for the trip. The controller has a processor and tangible, non-transitory memory on which instructions are recorded. The system has a plurality of machine learning modules, including a behavior predictor, a driving consumption predictor and an auxiliary consumption predictor. The controller is adapted to predict a total energy consumed by the vehicle during the trip by executing the plurality of machine learning modules. The driving consumption predictor is adapted to predict a primary energy consumed for propelling the vehicle based in part on the route plan. The auxiliary consumption predictor is adapted to predict a secondary energy consumed by the vehicle for non-propulsion purposes. The behavior predictor is adapted to predict an average vehicle speed based at least partially on traffic conditions.

Abstract: The concepts described herein relate to methods, systems, and analytical techniques to achieve a cloud-based electrified vehicle energy usage system that includes a cloud-based server that is operative to receive vehicle-specific electric energy-related data from a plurality of connected electrified vehicles, and correlate the vehicle-specific electric energy-related data to a road segment. A data analysis is executed for the vehicle-specific electric energy-related data for the plurality of connected electrified vehicles for the road segment, and a crowd-sourced electrified vehicle energy usage report is generated for the road segment based upon the data analysis.

Abstract: A system for adaptive in-drive updating, for a vehicle travelling on a route, includes a controller having a processor and tangible, non-transitory memory. The vehicle is carrying a load. The controller is adapted to obtain one or more dynamic parameters pertaining to the load. A plurality of adaptive predictors is selectively executable by the controller at a timepoint during the route at which a completed portion of the route has been traversed by the vehicle and a remaining portion remains untraversed. The plurality of adaptive predictors includes a speed predictor configured to generate a global speed profile. The plurality of adaptive predictors includes a driving consumption predictor is configured to predict a driving consumption profile for the remaining portion of the route based in part on the dynamic parameter, the route features, the global speed profile, and a past drive consumption.

Abstract: A method that includes obtaining demand data, consumer data, and historical demand data, the demand data represents a demand of consumers for a supply over a past time period in a geographic zone. The demand data includes a recent time segment having unreliable demand information. The consumer data. The method further includes, based on the demand data, estimating a scalar of the demand, and, based on the historical demand data, modeling a standardized model demand profile of mean demand over multiple past time periods. Further, the method includes producing a short-term demand prediction of the consumers of the supply over a portion of a forthcoming time period. The short-term demand prediction is based, at least in part, on the standardized model demand profile, the demand data, and the consumer data.

Abstract: The concepts described herein relate to methods, systems, and analytical techniques to achieve a cloud-based electrified vehicle energy usage system that includes a cloud-based server that is operative to receive vehicle-specific electric energy-related data from a plurality of connected electrified vehicles, and correlate the vehicle-specific electric energy-related data to a road segment. A data analysis is executed for the vehicle-specific electric energy-related data for the plurality of connected electrified vehicles for the road segment, and a crowd-sourced electrified vehicle energy usage report is generated for the road segment based upon the data analysis.

Abstract: A system for adaptive in-drive updating, for a vehicle travelling on a route, includes a controller adapted to obtain a pre-drive energy consumption prediction for the route, via an energy consumption predictor. An in-drive updating module is selectively executable by the controller at a timepoint during the route at which a completed portion of the route has been traversed and a remaining portion remains untraversed. The controller is adapted to obtain an actual energy consumption for segments in the completed portion of the route. The controller is adapted to obtain at least one modification factor based on a comparison of the actual energy consumption and the pre-drive energy consumption prediction for the segments in the completed portion of the route. The pre-drive energy consumption prediction for the remaining portion of the route is adjusted based on the modification factor.

Abstract: A system for adaptive in-drive updating, for a vehicle travelling on a route, includes a controller having a processor and tangible, non-transitory memory. The vehicle is carrying a load. The controller is adapted to obtain one or more dynamic parameters pertaining to the load. A plurality of adaptive predictors is selectively executable by the controller at a timepoint during the route at which a completed portion of the route has been traversed by the vehicle and a remaining portion remains untraversed. The plurality of adaptive predictors includes a speed predictor configured to generate a global speed profile. The plurality of adaptive predictors includes a driving consumption predictor is configured to predict a driving consumption profile for the remaining portion of the route based in part on the dynamic parameter, the route features, the global speed profile, and a past drive consumption.

Abstract: An economy advisory system includes a circuit and a display. The circuit is configured to receive a route plan remainder of a vehicle and receive a plurality of consumption factor values of the vehicle while the vehicle traverses the route plan. The plurality of consumption factor values is controllable by a driver of the vehicle. The circuit is further configured to modify the plurality of consumption factor values based upon a plurality of modification factor values, calculate a plurality of potential range changes of the vehicle based on the route plan remainder and the plurality of consumption factor values as modified, and identify a group that has at least one of the plurality of potential range changes and a corresponding at least one of the plurality of modification factor values. The display is in communication with the circuit and is configured to present the group to the driver.

Abstract: A system for managing a fleet of electric vehicles and respective fleet drivers includes a command unit having a processor and tangible, non-transitory memory on which instructions are recorded. The command unit is adapted to obtain input variables, including respective fleet tasks and their priority status. Route data for the respective fleet tasks is obtained. The command unit is adapted to obtain an objective function defined by a plurality of influence factors having respective weights. The command unit is adapted to obtain optimal charging schedules respectively for the electric vehicles and match the respective fleet tasks to the electric vehicles and the respective fleet drivers, based in part on the objective function, input variables and the route data. The influence factors may include energy cost optimization, timeliness of task completion and minimizing range anxiety. In some embodiments, the respective weights of the influence factors are designated by a fleet manager.

Abstract: A system for adaptive in-drive updating, for a vehicle travelling on a route, includes a controller adapted to obtain a pre-drive energy consumption prediction for the route, via an energy consumption predictor. An in-drive updating module is selectively executable by the controller at a timepoint during the route at which a completed portion of the route has been traversed and a remaining portion remains untraversed. The controller is adapted to obtain an actual energy consumption for segments in the completed portion of the route. The controller is adapted to obtain at least one modification factor based on a comparison of the actual energy consumption and the pre-drive energy consumption prediction for the segments in the completed portion of the route. The pre-drive energy consumption prediction for the remaining portion of the route is adjusted based on the modification factor.

Abstract: A system for predicting energy consumption by a vehicle during a trip has a controller adapted to receive a route plan for the trip. The controller has a processor and tangible, non-transitory memory on which instructions are recorded. The system has a plurality of machine learning modules, including a behavior predictor, a driving consumption predictor and an auxiliary consumption predictor. The controller is adapted to predict a total energy consumed by the vehicle during the trip by executing the plurality of machine learning modules. The driving consumption predictor is adapted to predict a primary energy consumed for propelling the vehicle based in part on the route plan. The auxiliary consumption predictor is adapted to predict a secondary energy consumed by the vehicle for non-propulsion purposes. The behavior predictor is adapted to predict an average vehicle speed based at least partially on traffic conditions.

Abstract: An assistance system for a vehicle capable of automated operation has a controller having a processor and tangible, non-transitory memory on which instructions are recorded. The vehicle is located on a first lane in a vicinity of one or more neighboring vehicles, the first lane merging with a second lane at a merging trajectory location. The controller is adapted to selectively execute a leader determination module when a distance of the vehicle to the merge starting point is less than a threshold value. This includes determining an estimated arrival time of the vehicle to a merge starting point of the merging trajectory location. The controller is adapted to select a leader vehicle from the neighboring vehicles based in part on their respective estimated arrival times to the merge starting point. Operation of the vehicle is controlled based in part on the leader vehicle.

Abstract: A method, system and computer program product for efficiently utilizing a heat-pump based HVAC system with an auxiliary heating system. Possible actions (e.g., cooling, off, heat-pump heating and auxiliary heating) are selected over a period of time (e.g., three days). The effects of selecting actions are recorded in terms of a data set of tuples. A regression is fitted to model a transition function separately for each of the possible actions using the data set of tuples. A model is selected to fit a regression using regression features (e.g., historic indoor temperatures). An action (e.g., off) to take is determined using a lookahead planning approach during a don't care period (period of time occupants do not care about the inside temperature) for every time-step within the don't care period until an end of the don't care period, where the effects of the actions continue to be recorded.