A driving assist system for a vehicle includes a driver monitoring system that includes a plurality of sensors disposed in a vehicle and sensing driver hand positions of a driver driving the vehicle. A control includes a processor operable to process data sensed by the sensors to determine the driver hand positions of the driver driving the vehicle. The control, responsive to processing of data sensed by the sensors and at least in part responsive to the determined sensed driver hand positions, is operable to determine a level of attentiveness of the driver. The driving assistance system of the vehicle operates to provide driving assistance of the vehicle responsive at least in part to the determined level of attentiveness of the driver.

An autonomous vehicle uses machine learning based models such as neural networks to predict hidden context attributes associated with traffic entities. The hidden context represents behavior of the traffic entities in the traffic. The machine learning based model is configured to receive a video frame as input and output likelihoods of receiving user responses having particular ordinal values. The system uses a loss function based on cumulative histogram of user responses corresponding to various ordinal values. The system identifies user responses that are unlikely to be valid user responses to generate training data for training the machine learning mode. The system identifies invalid user responses based on response time of the user responses.

Evasive steering assist (ESA) systems and methods for a vehicle utilize a set of vehicle perception systems configured to detect an object in a path of the vehicle, a driver interface configured to receive steering input from a driver of the vehicle via a steering system of the vehicle, a set of steering sensors configured to measure a set of steering parameters, and a controller configured to determine a set of driver-specific threshold values for the set of steering parameters, compare the measured set of steering parameters and the set of driver-specific threshold values to determine whether to engage/enable an ESA feature of the vehicle, and in response to engaging/enabling the ESA feature of the vehicle, command the steering system to assist the driver in avoiding a collision with the detected object.

The present subject matter refers to a method implemented in a behavior-based risk-profiling system. The method includes receiving at least one of a location and a driving-behavior metric of a user, determining a risk profile of the user by analyzing the received at least one of the location and the driving-behavior metric, and classifying the user based on the determined risk profile. The risk profile indicates a risk associated with a driving behavior.

A vehicle includes a controller programed to: collect a set of data related to a driver of the vehicle; predict a driving setting for the driver using the set of data and an initial student-T process (STP) machine learning (ML) model; generate an updated STP ML model based on the prediction of the driving setting as to the set of vehicle data; transmit incremental learning related to the updated STP ML model to a server; and receive, from the server, a personalized driving setting for the driver output from a cloud STP ML model trained by the incremental learning.

Methods and systems for tracking driver behavior across a variety of vehicles are described herein. One or more first performance metrics which indicate performance of a first vehicle when driven by a user may be determined. One or more second performance metrics indicating performance of a second vehicle when driven by the user may be determined. The first vehicle and the second vehicle may be compared to determine a vehicle difference. The performance metrics may be compared. One or more third performance metrics that predict performance of a third vehicle, different from the first vehicle and the second vehicle, when driven by the user may be determined based on the vehicle difference and the comparison. Whether to provide the user access to the third vehicle may be determined based on the one or more third performance metrics.

A controller and method for real-time customization of presentation features of a vehicle. A method includes collecting a first dataset about a knowledge level of an operator of the vehicle, wherein the first dataset is collected with respect to a feature of the vehicle; collecting, using at least one sensor, a second dataset regarding an external environment of the vehicle and a cabin of the vehicle; determining, based on the first dataset and the second dataset, a presentation feature from a plurality of presentation features associated with the feature of the vehicle; customizing the presentation feature based on at least the first dataset, wherein the customization is performed in real-time when the operator operates the vehicle; and presenting the presentation feature to the operator of the vehicle.

A learning model generating unit generates a learning model using a user ID of a user estimated by a driver estimating unit and driving attributes of the user, as training data. Specifically, a learning model generating unit generates a learning model in which the driving attributes are an explanatory variable and the user ID of a user is an objective variable. When various driving attributes are input to the driving behavior model, the user ID of a driver specified by the attributes is output.

A method for operating a vehicle includes obtaining personal data associated with a user of the vehicle, obtaining operating data for the vehicle, determining a driver behavior recommendation to reduce emissions of the vehicle based at least in part on the personal data and the operating data, and presenting the driver behavior recommendation on an interface.

A method for operating a hybrid vehicle includes obtaining propulsion switching data descriptive of a state of one or more vehicle systems for switching power flow of an internal combustion engine and an electric machine. The propulsion switching data may be used to provide a driver behavior recommendation and/or an actual environmental impact of the hybrid vehicle.