Abstract: The present disclosure relates to methods, systems, a vehicle and a computer-readable storage medium and a computer program product. The method includes obtaining a baseline risk model generated based on one or more risk-associated parameters. The method further includes obtaining sensor data from a sensor system of a vehicle. The method further includes estimating one or more risk values associated with the one or more risk-associated parameters based on the obtained sensor data and generating, based on the one or more estimated risk values, an adopted risk model. Further, the method includes provisioning the generated adopted risk model for determining an acceptable risk model for forming a driving policy of an ADS.

Abstract: A method for closed-loop evaluation of path planning modules for a vehicle equipped with an Automated Driving System (ADS) is disclosed. The method includes obtaining a candidate path from each of a plurality of path planning modules of the ADS. The method further includes determining a fulfilment of convergence criteria by the obtained candidate paths by comparing the obtained candidate paths with each other and determining a level of convergence between the candidate paths. If the convergence criteria is fulfilled, one of the obtained candidate paths is selected and the vehicle is controlled so to execute the selected candidate path. If the convergence criteria is not fulfilled, determining an exposure need of each path planning module in view of a predicted scene or scenario in the surrounding environment of the vehicle that the vehicle is expected to be exposed to while executing any one of the obtained candidate paths.

Abstract: A method for generating training data for a machine learning (ML) algorithm configured for identification of an unknown traffic object present on a road is disclosed. The method includes obtaining sensor data from a sensor system of an ego vehicle travelling on the road, the sensor data including one or more images of a surrounding environment of the vehicle and speed information of the ego vehicle and/or speed of at least one external vehicle. The method further includes determining a presence of the unknown traffic object in the surrounding environment of the ego vehicle and determining a change of speed of the ego vehicle and/or of the at least one external vehicle. In an instance of a co-occurrence of the determined change of speed and the determined presence of the unknown traffic object, the method includes selecting one or more images of the at least one unknown traffic object.

Abstract: A method for handling one or more items in an item storage in a communication network. The method includes initiating a procedure for handling one or more items in an item storage based on an input related to a user in the communication network, and selecting a position related to an item of the one or more items based on the input. Further, the method includes guiding the user to the selected position via triggering a guiding indication associated with the selected position, and detecting a pattern change in a registered pattern, wherein the pattern change is due to movement of an item associated with the selected position or movement of another item. Upon detection of the pattern change, a confirmation indication is sent for confirming handling of the item back to the user.

Abstract: A method for updating a perception function of a vehicle having an Automated Driving System (ADS) is disclosed. The ADS has a self-supervised machine-learning (ML) algorithm for reconstructing an ingested image and a ML algorithm for an in-vehicle perception module for detecting one or more objects or free-space areas depicted in an ingested image. At first, an image of a scene in a surrounding environment of the vehicle is obtained. The obtained image is processed to obtain an output image with one or more detected objects or free-space areas. Then, an evaluation dataset is formed accordingly. The evaluation dataset and the obtained image is processed to obtain a reconstruction error value for each evaluation image and an evaluation image with highest reconstruction error value is selected among plurality of evaluation images. Using the obtained image and the selected evaluation image, the ML algorithm for the in-vehicle perception module is updated.

Abstract: A computer-implemented method and a device for controlling a lane support system of a vehicle are disclosed. The method includes obtaining data indicative of a driver of the vehicle being in an inattentive state, and determining an intended path of the driver at a point in time when the driver enters the inattentive state. The method further includes determining an unintended lateral deviation from the intended path by computing a function representative of a lateral deviation from the intended path of the driver. Moreover, the function is dependent upon at least one of a change in steering wheel angle, and a change in road geometry along the vehicle's traveling direction while the driver is in the inattentive state. When the determined unintended lateral deviation violates a threshold value, activating the lane support system to output a warning to the driver and/or to execute an intervention.

Abstract: A method for managing an Operational Design Domain (ODD) expansion for an Automated Driving System (ADS) of a vehicle is disclosed. The method includes: obtaining a plurality of scenario parameters defining the environment of the vehicle, wherein each scenario parameter corresponds to a respective condition of the ODD; in response to the plurality of scenario parameters fulfilling the plurality of ODD conditions: allowing the ADS to be activated or to remain active; if not: querying a logic formula based on the obtained plurality of scenario parameters, such that if at least one soft constraint of the logical formula is satisfied without violating any hard constraints of the logical formula, and allowing the ADS to be activated in a degraded mode by limiting one or more variable state parameters of the ADS to conform to the determined set of values of the one or more variable state parameters.

Abstract: An assessment system obtains a state of the vehicle, and identifies lane segments void from road users. Input having data associated with the lane segments, data associated with the road users states and historic data associated with the road users states and/or lane segments, is encoded into respective states-related data associated with the road users states and segment-related data associated with dynamic start and end boundaries of the lane segments. One or more neural networks encode the road users states in view of the lane segments spatially and temporally, and output spatial- and temporal-processed respective states-related data and segment-related data. The output data associated with one or more of the road users (target road users) is fed to at least a first behavior-predicting neural network to predict and output data indicating predicted near-future behavior of the target road users in view of one or more of the lane segments.

Abstract: The present invention relates to methods and systems for safety and/or performance monitoring of an Automated Driving System (ADS). The method comprises obtaining a plurality of Performance Indicators (PIs) generated by each of a plurality of ADS-equipped vehicles based one or more driving sessions, wherein the plurality of PIs are of at least one PI-type. The method further comprises modelling each PI-type of the obtained PIs based on an Extreme Value Theory (EVT) model, wherein each modelled PI-type is indicative of a probability for exceeding a PI-value for that PI-type, and evaluating each modelled PI-type against a corresponding predefined requirement. Then, if the evaluation fails, determining that the ADS has violated one or more safety or quality requirements, and transmitting a first signal indicative of the violated one or more safety or quality requirements to an ADS management system and/or a second signal to the plurality of ADS-equipped vehicles.

Abstract: An image frames handling system for reconstruction of image frames obtained by an image capturing device of an Automated Driving System, ADS, of a vehicle at an entity. The image system stores in a surrounding state data buffer obtained object-level environmental data indicating states of vehicle surroundings derived from perception data output from an onboard perception system; stores image frames of vehicle surroundings captured by the capturing device in an image data buffer; processes the image data buffer to determine motions of objects in the image frames and respective values of the motions; extracts key image frames from the image data buffer and pixels having motion values exceeding a predeterminable level from non-key image frames of the image data buffer; transfers the extracted key image frames and the extracted pixels; and reconstructs at the entity interpolated image frames at the predeterminable frame rate based on the selected data.

Abstract: A driving mode transitioning system and method for supporting transitioning to an unsupervised autonomous driving mode of an Automated Driving System, ADS, of a vehicle. The driving mode transitioning system obtains vehicle situational data indicating a state of vehicle surroundings along with position and heading of the vehicle; determines based on the obtained vehicle situational data, that unsupervised driving conditions of an unsupervised driving mode-related driving policy pertinent an unsupervised autonomous driving mode of the ADS, are complied with; determines that the ADS has active a supervised driving mode; implements the unsupervised driving mode-related driving policy to govern the supervised driving mode; and enables the unsupervised autonomous driving mode to be activated for the ADS, when positioning and/or velocity of the vehicle has reached compliance with unsupervised dynamic driving conditions of the unsupervised driving mode-related driving policy.

Abstract: The present disclosure relates to a method performed by a buffer resources prioritizing system for storage prioritization in an event buffer configured to continuously collect operational data of an Automated Driving System, ADS, of a vehicle. The buffer resources prioritizing system obtains sensor data of one or more sensors onboard the vehicle. The buffer resources prioritizing system further determines, at least partly based on the sensor data, current ADS-related operational conditions at least comprising states of vehicle surroundings and internal states of the vehicle. Moreover, the buffer resources prioritizing system determines an upcoming scene predicted to evolve from the current operational conditions. Furthermore, the buffer resources prioritizing system deduces based on assessment of the predicted scene, a storage priority score thereof reflecting predicted relevance of freezing event data of the predicted scene in the event buffer.

Abstract: A method for determining whether an automatic collision avoidance steering maneuver for a vehicle equipped with an automated driving system should be executed is disclosed.

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: 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 includes 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 includes 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: An annotation handling system for in an on edge-based manner training a supervised or semi-supervised perception model on edge of a vehicle equipped with an ADS. The annotation handling system stores while the vehicle is being driven, sensor data; selects annotation-eligible data out of the sensor data; generates a learning model candidate by annotating an event in the annotation-eligible data using a perception learning model; generates at least a first corroboration candidate by annotating the event based on perception predictions of the event derived from radar- and/or lidar-based sensor data of the obtained sensor data and/or based on identifying the event in a digital map; determines when one or more of the at least first corroboration candidate match the learning model candidate fulfilling corroboration criteria, an annotation of the event based on the learning model candidate and the first corroboration candidate; and updates the perception model based on the annotation.

Abstract: A method for calibrating a set of extrinsic parameters of a camera mounted on a vehicle is disclosed. The method includes: obtaining a sequence of images, wherein each image depicts a portion of a surrounding environment of the vehicle determining a set of feature points in the sequence of images; determining an area representing a sky in the sequence of images; removing a subset of feature points belonging to the area representing the sky, thereby forming an updated set of feature points; determining a first motion trajectory of the vehicle based on the updated set of feature points; obtaining a second motion trajectory of the vehicle which is based on motion data obtained from other sensors of the vehicle; and calibrating the camera by adjusting the set of extrinsic parameters of the camera based on a difference between the first motion trajectory and the second motion trajectory.

Abstract: The present invention relates to a method for training artificial neural network configured for 3D lane detection based on unlabelled image data from camera. The method includes generating a first set of 3D lane boundaries in first coordinate system based on first image, generating a second set of 3D lane boundaries in second coordinate system based on second image, transforming at least one of the second set of 3D lane boundaries and first set of 3D lane boundaries based on positional data associated with first image and second image, evaluating the first set of 3D lane boundaries against second set of 3D lane boundaries in common coordinate system in order to find matching lane pairs of first set of 3D lane boundaries and second set of 3D lane boundaries, and updating one or more model parameters of an artificial neural network based on a spatio-temporal consistency loss.

Abstract: The present invention relates to a method for alerting drivers and/or autonomous vehicles of high risk scenarios. The method includes obtaining positional data of a vehicle, where the positional data is indicative of geographical position and heading of the vehicle. The method further includes obtaining environmental data of the vehicle, where the environmental data is indicative of state of the surrounding environment of the vehicle. The method includes determining, by means of trained model, accident intensity for upcoming road portion for the vehicle, the trained model being configured to determine accident intensity associated with the upcoming road portion based on the obtained environmental data and the obtained positional data. Then, if the determined accident intensity exceeds threshold, the method comprises transmitting signal indicating approaching high risk scenario to a Human-Machine-Interface, HMI, of the vehicle and/or to a control system of the vehicle.

Abstract: A path-adapting system for precautionary path planning of a host vehicle. The path-adapting system determines conditions of a liquid and/or solid loose material in the air and/or on the road surface in vicinity of the host vehicle, determines movement attributes in relation to the host vehicle of at least a first object in host vehicle surroundings, determines based on the conditions and movement attributes, at least a first estimated upcoming host vehicle position occurring at an estimated upcoming at least first time instance at which the at least first detected object is estimated to direct the material onto the host vehicle and/or the host vehicle is estimated to direct the material onto the at least first detected object, and determines a driving path, altering for the at least first time instance the at least first estimated upcoming host vehicle position to a modified host vehicle position.