Abstract: Data describing operation of a vehicle is provided to a deep neural network. A vehicle wheel impact event is determined based on output of the deep neural network. Alternatively or additionally, it is possible to determine the wheel impact event based on output of a threshold based algorithm that compares vehicle acceleration and the velocity to one or more thresholds.

Abstract: A vehicle such as a hybrid electric vehicle (HEV) and method of operation, which include controller(s) coupled to a communication unit, configured to respond to a trip signal, and in response, to generate a driver notification to adjust vehicle performance parameters, such as acceleration, speed, braking, and others. The driver notification is generated to reduce fuel and/or battery consumption, and according to a recommendation signal that is received from and generated by a remote fleet server, and in response to instantaneous vehicle operating conditions that are communicated in real-time from the vehicle to the remote server. The recommendation signal includes a fuel and/or a battery consumption estimate, among other data. The vehicle controller is also responsive to detecting the one or more adjusted vehicle performance parameters, and to generate and store one or more estimate errors, which are respective differences between the estimates and actual fuel and battery consumption.

Abstract: Data describing operation of a vehicle is provided to a deep neural network. A vehicle wheel impact event is determined based on output of the deep neural network. Alternatively or additionally, it is possible to determine the wheel impact event based on output of a threshold based algorithm that compares vehicle acceleration and the velocity to one or more thresholds.