Methods and systems are provided for adjusting clutch pressures and electric machine torques as a function of a stability metric threshold(s) in order to balance performance and charging of an onboard energy storage device. In one example, a method comprises during an upshift of a transmission from a first gear to a second gear, adjusting a clutch pressure of the transmission to adjust slippage of a clutch in response to a vehicle stability control parameter exceeding a threshold. In this way, torque delivered to a transmission output shaft may be reduced, which may increase vehicle stability.

A device for controlling an engine clutch in an environmentally-friendly vehicle, wherein the engine clutch is disposed between an engine and a driving motor and is configured to selectively connect the engine to the driving motor, includes: a transmission configured to receive a driving force that is transmitted from at least one of the engine and the driving motor by release or engagement of the engine clutch; and a controller configured to control the engine clutch based on a gear of the transmission when the failure of the engine clutch is detected and configured to charge a battery using the engine.

A vehicle comprises an autonomous driving system and a vehicle platform that controls the vehicle in response to a command received from the autonomous driving system. In the present vehicle, when the autonomous driving system issues a first command to request the vehicle platform to provide deceleration to stop the vehicle and a first signal indicates 0 km/h or a prescribed velocity or less, the autonomous driving system issues a second command to request the vehicle platform to maintain stationary. And after brake hold control is finished, a second signal indicates standstill. Until the second signal indicates standstill, the first command continues to request the vehicle platform to provide deceleration.

A processing server detects an incident of a vehicle by analyzing one of position information about the vehicle, image information about the periphery of the vehicle, and traveling data about the vehicle, which are acquired from the vehicle, and selects a new function corresponding to the detected incident. Then, the processing server gives notice of the proposal for the new function to the vehicle, as an estimated timing when a user having encountered the incident has cooled down while the user's memory about the incident is clear.

A method of releasing a stuck vehicle, in which a stuck situation is recognized and a rocking-free process is initiated and continued until the rocking-free process is suppressed. The rocking-free process is suppressed either after the activation of a parking brake of the vehicle, which was inactive at the beginning of and during the rocking-free process, for a predetermined time interval, or after the registration of a limit value of a deflection of a drive pedal of the vehicle and after the limit value of the deflection of the drive pedal is maintained or exceeded for a predetermined time interval, or after a vehicle speed falls to almost zero km/h, a minimum actuation of a drive pedal of the vehicle is registered, the vehicle speed is maintained for a predetermined time interval and the minimum actuation is maintained for the predetermined time interval.

The provided are a federated reinforcement learning (FRL) end-to-end autonomous driving control system and method, as well as vehicular equipment, based on complex network cognition. An FRL algorithm framework is provided, designated as FLDPPO, for dense urban traffic. This framework combines rule-based complex network cognition with end-to-end FRL through the design of a loss function. FLDPPO employs a dynamic driving guidance system to assist agents in learning rules, thereby enabling them to navigate complex urban driving environments and dense traffic scenarios. Moreover, the provided framework utilizes a multi-agent FRL architecture, whereby models are trained through parameter aggregation to safeguard vehicle-side privacy, accelerate network convergence, reduce communication consumption, and achieve a balance between sampling efficiency and high robustness of the model.

A vehicle comprises an autonomous driving system and a vehicle platform that controls the vehicle in response to a command received from the autonomous driving system. In the present vehicle, when the autonomous driving system issues a first command to request the vehicle platform to provide deceleration to stop the vehicle and a first signal indicates 0 km/h or a prescribed velocity or less, the autonomous driving system issues a second command to request the vehicle platform to maintain stationary. And after brake hold control is finished, a second signal indicates standstill. Until the second signal indicates standstill, the first command continues to request the vehicle platform to provide deceleration.

A remote parking control system and a fail-safe method thereof may include at least one controller and a remote parking control apparatus that performs braking control according to motor reverse torque control and transmission stage control, when a braking controller among the at least one controller fails, upon remote parking control.

The provided are a federated reinforcement learning (FRL) end-to-end autonomous driving control system and method, as well as vehicular equipment, based on complex network cognition. An FRL algorithm framework is provided, designated as FLDPPO, for dense urban traffic. This framework combines rule-based complex network cognition with end-to-end FRL through the design of a loss function. FLDPPO employs a dynamic driving guidance system to assist agents in learning rules, thereby enabling them to navigate complex urban driving environments and dense traffic scenarios. Moreover, the provided framework utilizes a multi-agent FRL architecture, whereby models are trained through parameter aggregation to safeguard vehicle-side privacy, accelerate network convergence, reduce communication consumption, and achieve a balance between sampling efficiency and high robustness of the model.

Methods and systems are provided for reducing vehicle movement during standstill. In one example, a method for a hybrid or electric vehicle may include monitoring a requested torque of an electric machine and a clutch position, predicting a torque at an output shaft by multiplying the requested torque and clutch position, and operating the hybrid or electric vehicle in a default state in response to an indication of a predicted torque exceeding a threshold torque.