Abstract: The present invention relates to determination of a state of a vehicle on a road portion. The vehicle includes an Automated Driving System (ADS) feature. At first, map data associated with the road portion, positioning data indicating a pose of the vehicle on the road, and sensor data of the vehicle are obtained. Then, a plurality of filters for the road portion are initialized. Further, one or more sensor data point(s) in the obtained sensor data is associated to a corresponding map-element of the obtained map data to determine one or more normalized similarity score(s). Now, based on the determined one or more normalized similarity score(s), one or more multivariate time-series data are also determined and provided as input to a trained machine-learning algorithm. Then, one of the initialized filters is selected by the machine learning algorithm to indicate a current state of the vehicle on the road portion.

Abstract: A method performed by a vehicle pose assessment system for supporting determining a pose of a vehicle in view of a digital map. The approach provided by the method alleviates finding lane segments of the digital map corresponding to current sensor detections, which in turn may support accurate and/or improved vehicle localization. An apparatus and computer storage medium for supporting determining a pose of a vehicle in view of a digital map are also provided.

Abstract: The present disclosure relates to a method for determining a state of a vehicle on a road portion having two or more lanes. The method comprises obtaining map data associated with the road portion and positioning data indicating a position of the vehicle on the road and a sensor data from a sensor system of the vehicle. The method further comprises initializing a filter per lane of the road portion based on the obtained map data, the obtained positioning data, and the obtained sensor data, wherein each filter indicates an estimated state of the vehicle on the road portion. Then, selecting one of the initialized filters using a trained machine-learning algorithm, configured to use the obtained map data, the positioning data, the sensor data, and each estimated state as indicated by each filter as input and to output a current state of the vehicle on the road portion.

Abstract: The present disclosure relates to a method for determining a vehicle pose, predicting a pose (xk, yk, ?k) of vehicle on a map based on sensor data acquired by a vehicle localization system, transforming a set of map road references of a segment of a digital map from a global coordinate system to an image-frame coordinate system of a vehicle-mounted camera based on map data and predicted pose of the vehicle. The transformed set of map road references form a set of polylines in image-frame coordinate system. Identifying a set of corresponding image road reference features in an image acquired by vehicle mounted camera, where each identified road references feature defines a set of measurement coordinates (xi, yi) in image-frame. Projecting each of identified set of image road reference features onto formed set of polylines in order to obtain a set of projection points.