The vehicle control method can include: determining a vehicle state based on a set of vehicle state inputs; determining a command based on the vehicle state; and controlling the vehicle according to the command. The method can optionally include updating a vehicle model based on a control outcome. However, the method S100 can additionally or alternatively include any other suitable elements. The method can function to determine longitudinal vehicle control based on a set of vehicle state inputs (e.g., a limited set of inputs—such as without direct knowledge of a throttle input, etc.). Additionally or alternatively, the vehicle control method can function to infer driving intent based on vehicle state measurements and/or translate inferred driving intent into low-latency vehicle control. Additionally or alternatively, the system can function to autonomously augment longitudinal propulsion, autonomously augment vehicle braking, and/or facilitate autonomous (longitudinal) vehicle control.

An apparatus for controlling a fuel cell of an environment-friendly vehicle, a system including the same, and a method thereof are provided. The apparatus includes a storage storing information mapping an amount of additional output of a fuel cell according to air density and a current battery state of a high voltage battery depending on a drive mode and a processor that controls an amount of output of the fuel cell in response to a required amount of output of a motor, the amount of output of the fuel cell being varied according to the air density, the current battery state, and the drive mode based on the information mapping the amount of additional output.

Disclosed are a method of improving fuel efficiency of a fuel cell electric vehicle, and an apparatus and a system therefor. The method includes collecting navigation information and vehicle speed information, calculating a coasting line when a specified event point is detected based on the navigation information, determining whether deceleration is necessary by comparing a current traveling speed with a coasting line speed corresponding to a current location, and changing a criterion for determining whether to enter a fuel cell stop (FC STOP) state when the deceleration is necessary as a determination result.

An acceleration slip regulation method includes determining a current control phase of a vehicle in an acceleration slip regulation state, determining a current road surface adhesion coefficient of the vehicle, determining, based on the current control phase and the current road surface adhesion coefficient, maximum torque allowed by a road surface, obtaining demand torque received by a drive motor of the vehicle and a wheel slip rate of the vehicle, and outputting adaptive feedforward torque for acceleration slip regulation based on the maximum torque allowed by the road surface, the demand torque, and the wheel slip rate, where the adaptive feedforward torque is used to perform the acceleration slip regulation on the vehicle.

A method for controlling cooling of a traction battery in an electric vehicle where the method comprises determining a battery temperature profile for a segment of a planned route based on route information describing a route from a starting point to a destination and based on a current battery status and determining a battery cooling profile for the segment of the route based on the battery temperature profile. By means of the route information and the state of the battery, the battery cooling profile can be determined in order to minimize the power required for cooling the battery. Since the route information can provide information relating to a range of parameters which influence the power consumption along the route, the cooling needs of the battery can also be estimated for the route as a whole.

An operating system for a vehicle having an electric vehicle (EV) drivetrain and a plurality of electrically-powered accessories is described. A controller determines, via a navigation system, a target off-road trail segment, and characterizes the subject vehicle, ambient conditions, and the target off-road trail segment to determine an estimated consumption of electric energy for the vehicle to operate over the target off-road trail segment. The EV drivetrain and the electrically-powered accessories are controlled during operation of the vehicle on the off-road trail segment based upon the estimated consumption of electric energy for the subject vehicle. This is done to minimize a likelihood of a low SOC event for the DC power source for the trail segment and to avoid a low battery state at a location that is distal from a charging station.

A method of analyzing data related to a driving range estimation of a vehicle includes collecting attribute data related to the driving range estimation of the vehicle, analyzing a correlation between the attribute data and a driving range of the vehicle, generating a vehicle driving range estimation model based on the analyzed correlation, and analyzing a sensitivity between the vehicle driving range estimation model and the attribute data.

When a route searching command is input, a control unit searches for a provisional route disregarding remaining energy. Next, a finding unit finds charging lanes and charging spots near the provisional route and a calculation unit calculates a charging lane traveling distance and a spot charging usage amount. Then, a searching unit searches for charging lane information, and the like, the first route that restrains charging up cost and uses charging lanes and searches for, on the basis of the spot charging usage amount, charging spot information, and the like, the second route that restrains charging up cost and uses charging spots. A generation unit generates information about the retrieved routes that includes charging up cost and the expected time required. which is presented by a presentation unit. Accordingly, it is possible to find routes including charging plans that use charging lanes and charging spots and to enhance user convenience.

An energy management system for an electric autonomous vehicle comprises a battery and a controller comprising a processor and a non-transitory computer-readable medium. The system comprises a pre-allocation input mechanism transmitting an input signal to the processor relating to a travel destination for the vehicle. The system comprises a navigation module receiving a wireless signal from a satellite network relating to a current location of the vehicle. The system comprises an autonomous input mechanism powered by the battery and transmitting an autonomous signal to the processor relating to dynamic conditions for autonomous operation of the vehicle. The processor determines a route between the current location and the travel destination, performs autonomous operation of the vehicle along the route, and selectively powers or tunes the usage of the at least one autonomous input mechanism with the battery during autonomous operation of the vehicle.

The present invention provides specific systems, methods and algorithms based on artificial intelligence expert system technology for determination of preferred routes of travel for electric vehicles (EVs). The systems, methods and algorithms provide such route guidance for battery-operated EVs in-route to a desired destination, but lacking sufficient battery energy to reach the destination from the current location of the EV. The systems and methods of the present invention disclose use of one or more specifically programmed computer machines with artificial intelligence expert system battery energy management and navigation route control. Such specifically programmed computer machines may be located in the EV and/or cloud-based or remote computer/data processing systems for the determination of preferred routes of travel, including intermediate stops at designated battery charging or replenishing stations. Expert system algorithms operating on combinations of expert defined parameter subsets for route selection are disclosed. Specific fuzzy logic methods are also disclosed based on defined potential route parameters with fuzzy logic determination of crisp numerical values for multiple potential routes and comparison of those crisp numerical values for selection of a particular route. Application of the present invention systems and methods to autonomous or driver-less EVs is also disclosed.