Abstract: A computer-implemented method for estimating a road geometry of a road upon which a vehicle is traveling and related aspects are disclosed. The disclosed embodiments provide a model-based technique for estimating a road model having an arbitrary number of lanes on a road as well as any entrance lanes (i.e. on-ramp or slip roads) and exit lanes (i.e. off ramps or off-slip roads). In more detail, the herein disclosed embodiments utilize a Bayesian approach to multi-lane tracking in various traffic scenarios, such as e.g. highway scenarios. The employed model-based algorithm estimates the lane center curves of multi-lane roads based on vehicle motion data (e.g. speed, angular velocity) and perception data (e.g. camera output, lidar output, radar output, etc.) that includes detected road features (e.g. lane markers, road edges, road barriers, guard rails, road markers, etc.) or other objects (e.g. other road users).

Abstract: The invention relates to a method for determining a representation of one or more road objects of a road for a vehicle traveling on the road. The method includes, for each time step out of a plurality of consecutive time steps, encoding images output from the one or more cameras of a vehicle using machine-learning algorithms trained to output image features of road objects depicted in an image provided as input to the machine-learning algorithms. The method further includes transforming a plurality of image features included in the encoded images to a Bird's Eye View (BEV) representation of the plurality of image features. The method also includes decoding the BEV representation to extract a set of object embeddings using transformer-based machine-learning algorithms. Further, the method includes outputting a position and class of each road object of the one or more road objects by decoding the extracted set of object embeddings.

Abstract: A computer-implemented method for estimating a road geometry of a road upon which a vehicle is traveling and related aspects are disclosed. The disclosed embodiments provide a model-based technique for estimating a road model having an arbitrary number of lanes on a road as well as any entrance lanes (i.e. on-ramp or slip roads) and exit lanes (i.e. off ramps or off-slip roads). In more detail, the herein disclosed embodiments utilize a Bayesian approach to multi-lane tracking in various traffic scenarios, such as e.g. highway scenarios. The employed model-based algorithm estimates the lane center curves of multi-lane roads based on vehicle motion data (e.g. speed, angular velocity) and perception data (e.g. camera output, lidar output, radar output, etc.) that includes detected road features (e.g. lane markers, road edges, road barriers, guard rails, road markers, etc.) or other objects (e.g. other road users).

Abstract: A system for adjusting a road boundary of a two dimensional virtual representation of a road for path planning of an autonomous vehicle includes a retrieval unit to retrieve a measured position and measured heading angle of the vehicle with respect to a reference. The system also includes an uncertainty unit to receive the measured position, the measured heading angle and map data of the road, and to determine a position uncertainty value and a heading angle uncertainty value representing an amount of uncertainty in the vehicle position and heading angle, respectively, on the road based on the input. The system also includes an adjustment unit to adjust a width and a heading angle of a drivable portion of the two dimensional virtual representation of the road, wherein the adjustment of the width and heading angle is based on the position uncertainty value and the heading angle uncertainty value, respectively.

Abstract: A system for adjusting a road boundary of a two dimensional virtual representation of a road for path planning of an autonomous vehicle includes a retrieval unit to retrieve a measured position and measured heading angle of the vehicle with respect to a reference. The system also includes an uncertainty unit to receive the measured position, the measured heading angle and map data of the road, and to determine a position uncertainty value and a heading angle uncertainty value representing an amount of uncertainty in the vehicle position and heading angle, respectively, on the road based on the input. The system also includes an adjustment unit to adjust a width and a heading angle of a drivable portion of the two dimensional virtual representation of the road, wherein the adjustment of the width and heading angle is based on the position uncertainty value and the heading angle uncertainty value, respectively.

Abstract: An onboard perception system of a vehicle is contemplated. The system may include a state assessment unit adapted to at least assess a state of a first external object located in a vicinity of the vehicle hosting the onboard perception system, at least a first sensor assembly for assessing sound information, and an evaluation means adapted to evaluate a change in the state of the first external object by using the assessed sound information.

Abstract: A method for reducing the risk of a collision between a vehicle and at least a first external object is contemplated. The risk of a collision may be reduced with use of a collision avoidance system having a detection unit adapted to issue a control signal in the event it detects a collision involving a first external object in a vicinity of the host vehicle, and an action unit adapted to operate the collision avoidance system such that an emergency maneuver can be initiated by the collision avoidance system at an earlier stage if the control signal is issued, as compared to when no control signal is issued.

Abstract: An onboard perception system of a vehicle is contemplated. The system may include a state assessment unit adapted to at least assess a state of a first external object located in a vicinity of the vehicle hosting the onboard perception system, at least a first sensor assembly for assessing sound information, and an evaluation means adapted to evaluate a change in the state of the first external object by using the assessed sound information.

Abstract: A method for reducing the risk of a collision between a vehicle and at least a first external object is contemplated. The risk of a collision may be reduced with use of a collision avoidance system having a detection unit adapted to issue a control signal in the event it detects a collision involving a first external object in a vicinity of the host vehicle, and an action unit adapted to operate the collision avoidance system such that an emergency manoeuvre can be initiated by the collision avoidance system at an earlier stage if the control signal is issued, as compared to when no control signal is issued.