Abstract: Examples are disclosed of systems and methods for developing personalized intervention strategies for advanced driver assistance systems (ADAS) based on in-cabin sensing data and related driving context information. In one embodiment, a method for a vehicle comprises, generating a driver profile of a driver of the vehicle, the driver profile including driving style data of the driver, the driving style data including at least a braking style; an acceleration style; a steering style; and one or more preferred cruising speeds of the driver; estimating a cognitive state of a driver of a vehicle; and adjusting one or more actuator controls of an ADAS based on the estimated cognitive state of the driver, the driver profile of the driver, and route/traffic info of the vehicle.

Abstract: Examples are disclosed for systems and methods for increasing a performance of a driver monitoring system (DMS) based on contextual information within a cabin of the vehicle. In one embodiment, a method comprises, during operation of a vehicle by a driver, collecting vehicle environment status information inside a cabin of the vehicle, the vehicle environment status information related to environmental factors that may impact a cognitive load of the driver and including at least one of information regarding one or more passengers of the vehicle; and information from one or more dashboard controls of the vehicle; and based on the vehicle environment status information and an estimated physiological state of the driver, adjusting one or more environmental controls of the vehicle.

Abstract: Disclosed herein are systems and methods for generating and displaying navigation guidance by utilizing data acquired by an advanced driver assistance system (ADAS) for driver behavior prediction and route planning. In embodiments, a method comprises generating navigation guidance based on a plurality of driver state events detected via an ADAS, and outputting the navigation guidance via a navigation system, wherein the navigation guidance comprises at least one of a map layer and a route recommendation.

Abstract: A map fusing method includes receiving a source graph and a target graph. The source graph is representative of a source map and the target graph is representative of a target map and includes nodes and edges that connect the nodes. The method further includes processing each of the source graph and the target graph in a graph convolutional layer to provide graph convolutional layer outputs related to the source graph and to the target graph, processing each of the graph convolutional layer outputs for the source graph and the target graph in a linear rectifying layer to output node feature maps related to the source graph and the target graph. The method further includes selecting pairs of node representations from the node feature maps related to the source graph and the target graph and concatenating the selected pairs to output selected and concatenated pairs of node representations.

Abstract: A method and system for updating or generating global maps are described, the system adapted to perform the steps of obtaining sensor data from one or more sensors of a vehicle, the sensor data describing a plurality of objects within an area surrounding the vehicle at a time or during a time interval; generating a local map based on the sensor data, the local map indicating relative positions of at least some of the plurality of objects to each other, and indicating an absolute position of one or more of the at least some of the plurality of objects; comparing the local map with a global map; updating the global map or generating a new global map based on the comparison.

Abstract: A map fusing method includes receiving a source graph and a target graph. The source graph is representative of a source map and the target graph is representative of a target map and includes nodes and edges that connect the nodes. The method further includes processing each of the source graph and the target graph in a graph convolutional layer to provide graph convolutional layer outputs related to the source graph and to the target graph, processing each of the graph convolutional layer outputs for the source graph and the target graph in a linear rectifying layer to output node feature maps related to the source graph and the target graph. The method further includes selecting pairs of node representations from the node feature maps related to the source graph and the target graph and concatenating the selected pairs to output selected and concatenated pairs of node representations.