Abstract: A computer system comprising a processor device configured to select a candidate path for a first vehicle to travel is provided. The processor device is further configured to obtain, from at least one temperature sensor, heat sensor data indicative of heat distributed on a road surface of a road located ahead of the first vehicle in a driving direction of the first vehicle. The processor device is further configured to, based on the heat distributed on the road surface, identify at least one first path travelled by at least one second vehicle. The processor device is further configured to select a candidate path for the first vehicle to travel. The candidate path is selected out of the at least one first path.

Abstract: A method of controlling an autonomous vehicle, AV, which is navigable in an environment with at least one prohibited area and at least one calibration station. The AV comprises a state estimation system configured to output an estimated state including an estimated position of the AV, wherein the estimated state has a guaranteed accuracy while the AV is visiting the calibration station. According to an embodiment, the method comprises an assessment, on the basis of the AV's estimated state and the time elapsed since the AV's latest visit at one of the calibration stations, whether the AV is staying outside the prohibited area with a predetermined confidence level ?. If the assessment produces a negative result, a safety-oriented action is taken. The assessment may include an evaluation whether the AV is staying outside the prohibited area by a margin which includes a position uncertainty.

Abstract: A method for determining an error with anchor point detection for an at least partly autonomous vehicle is provided. The method comprises detecting a first anchor point. The method comprises obtaining a distance between the first anchor point and a second anchor point. The method comprises, based on the distance and a of the vehicle, estimating an expected time for the vehicle to detect the second anchor point. The method comprises establishing a time difference by comparing the expected time with a second time after the expected time or by detecting the second anchor point at a third time, and establishing the time difference by comparing the expected time with the third time. The method comprises, based on the established time difference, determining whether there is an error in detecting the first anchor point and/or the second anchor point.

Abstract: A method for quantifying vehicle path following performance, the method comprising; obtaining samples of path following performance (I), selecting a subset of the path following performance samples such that the selected samples follow a pre-determined statistical extreme value distribution, parameterizing the pre-determined statistical extreme value distribution based on the selected samples of path following performance, and quantifying vehicle path following performance based on the parameterized statistical extreme value distribution.

Abstract: A method of verifying a position of a vehicle using a vehicle-mounted device, the method including generating first position data for the vehicle-mounted device responsive to receiving data from a transponder-based localization system, generating second position data for the vehicle-mounted device responsive to receiving data from another localization system; and reporting verified vehicle position data for the vehicle, based on a comparison of the data from the other localization system with the data from the transponder-based localization system for the vehicle-mounted device.

Abstract: A computer-implemented method controls a vehicle to have predictable behaviour after an unexpected event occurs even if the event causes there to be no safe trajectories at that particular instant. The method comprises an automated driver system, ADS, of the vehicle determines there are no safe trajectories responsive to the occurrence of the unexpected event, and also responsive to the occurrence of the unexpected event, dynamically re-evaluates whether a current trajectory being followed by the vehicle meets a current set of safety criteria. A decision to follow the current re-evaluated trajectory path is then made possible removing one or more consequences of the occurrence of the event from the safety criteria used to re-evaluate the current trajectory whilst maintaining all other previous safety criteria. This allows the vehicles ADS to maintain the path of the current trajectory whilst possibly changing the behaviour of the vehicle along that path to slow it down.

Abstract: A method performed by a central unit for evaluating a performance of an obstacle detection system comprised in a first object within a set of two or more objects at a confined area. The first object is a vehicle. The central unit obtains pose data from each object in the set and obstacle detection data from at least the first object. The central unit determines a relative pose of the objects using the pose data from each object. The central unit the obstacle detection data from each object in the set to the determined relative pose of the objects. Based on the comparison, the central unit evaluates the performance of the obstacle detection system of the first object.

Abstract: A computer-implemented method for assisting one or more autonomous vehicles to drive in a road junction. The road junction comprises a plurality of traffic zones, including a central zone arranged for use by the one or more autonomous vehicles and one or more secondary vehicles and at least one edge zone for use by the one or more secondary vehicles for entering the central zone. The method comprises obtaining sensor data from a set of sensors arranged in the road junction for monitoring the plurality of traffic zones. The sensor data is indicative of objects present in the plurality of traffic zones. Based on the obtained sensor data, it is determined whether there are any objects present in the plurality of traffic zones. In response to determining that at least one object is present in the at least one edge zone indicating to the one or more autonomous vehicles that the road junction is occupied.

Abstract: A method for controlling a vehicle based on a quantified objection detection performance. The method includes obtaining samples of objection detection performance pii=1n-1, wherein the objection detection performance comprises a comparison of an estimated object state with a reference object state, selecting a subset of the objection detection performance samples such that the selected samples follow a pre-determined statistical extreme value distribution, parameterizing the pre-determined statistical extreme value distribution based on the selected samples of objection detection performance, quantifying objection detection performance based on the parameterized statistical extreme value distribution, and controlling the vehicle based on the quantified objection detection performance.

Abstract: The present disclosure relates to a control system for selectively controlling a vehicle, ensuring high integrity of decisions taken by the control system when controlling the vehicle. The present disclosure also relates to a corresponding computer implemented method and to a computer program product.

Abstract: A method for quantifying vehicle path following performance, the method comprising; obtaining samples of path following performance (I), selecting a subset of the path following performance samples such that the selected samples follow a pre-determined statistical extreme value distribution, parameterizing the pre-determined statistical extreme value distribution based on the selected samples of path following performance, and quantifying vehicle path following performance based on the parameterized statistical extreme value distribution.

Abstract: A method for determining if a vehicle control command for controlling a vehicle (1) associated with a current vehicle state precludes a future situation avoidance maneuver (SAM) by the vehicle. The method comprises obtaining one or more safe sets, wherein each safe set represents a range of vehicle states from which a future SAM can be initialized with prospect for success. The method also comprises obtaining the current vehicle state and the control command and predicting a future vehicle state based on the current vehicle state and on the control command. The method comprises comparing the predicted future vehicle state to the one or more safe sets and determining that the control command precludes the future SAM if the predicted future vehicle state is not comprised in any of the one or more safe sets.

Abstract: A method for quantifying road user behavior, the method comprising; obtaining samples of road user behavior selecting a subset of the road user behavior samples such that the selected samples follow a pre-determined statistical extreme value distribution, parameterizing the pre-determined statistical extreme value distribution based on the selected samples of road user behavior, and quantifying road user behavior based on the parameterized statistical extreme value distribution.

Abstract: A method for quantifying correctness of a vehicle model f(·). The method comprises obtaining prediction errors (A) by evaluating the model f(·) over a range of input parameters, determining a threshold ? such that the prediction errors in excess of the threshold ?, {?i:?i??}, follow a Generalized Pareto Distribution, GDP, and parameterizing a GDP based on the prediction errors in excess of the threshold ?{?i:?i?}. The method then quantifies correctness of the vehicle model f(·) based on the parameterized GDP.