Abstract: A hydraulic block for a hydraulic unit for generating brake pressure and regulating brake pressure in a hydraulic vehicle power brake system. The hydraulic block includes a projection that extends the power cylinder bore which passes transversely through the hydraulic block on a large side of the hydraulic block and a projection that extends an anti-rotation guide of a power piston of a power brake pressure generator on an opposite large side of the hydraulic block.

Abstract: Systems for monitoring brake systems on railway assets include a load measuring device. The load measuring device includes an instrumented coupling configured to be connected to the rigging of a brake system of the railway asset; and to an underframe of the railway asset. The load measuring device also includes a data collection unit configured to process an output of a sensor of the instrumented coupling and, based on the sensor output, determine the force being transmitted between the brake rigging and the underframe.

Abstract: A control method for driving series mode of a hybrid vehicle is suitable for a four-wheel drive powertrain of a hybrid vehicle and can further improve a charging efficiency by implementing a second series mode, in which a vehicle is driven by a second motor for driving rear wheels, which is employed for a four-wheel drive powertrain of a hybrid vehicle, and an energy storage device is charged by power generation operation of a first motor connected to an engine through an engine clutch, beside a first series mode in which a vehicle is driven by the first motor and the energy storage device is charged by power generation operation of a third motor directly connected to the engine so that the first series mode or the second series mode may be selected in accordance with driver request power and charge power for the energy storage device.

Abstract: A system and method for power management of hybrid electric vehicles is provided. In some implementations, a plug-in series hybrid electric vehicle may include an engine, a motor/generator (MG), a traction motor, an energy storage device, and a controller. The controller is coupled to the engine and the MG to control operation of the engine and the MG such that a state-of-charge (SOC) of the energy storage device tracks a dynamic reference SOC profile during a trip and an average engine power (AEP) is maintained above a threshold. In some instances, maintaining AEP above a threshold supports emission control of the vehicle.

Abstract: A method of controlling an electrified vehicle may include determining a traveling environment level; determining a regenerative braking continuation range and a regenerative braking retention amount according to the traveling environment level when a preset deceleration condition is satisfied; and determining whether to maintain a regenerative braking amount as the regenerative braking retention amount based on whether a vehicle speed is included in the regenerative braking continuation range when the vehicle speed is lower than or equal to a preset regenerative braking termination vehicle speed.

Abstract: The control system includes a first controller and a second controller. The second controller includes a processor that processes the first command value by a program to output an operation command value for the motor, and a logic circuit having a circuit structure that monitors a state index indicating a state of the power controller and converts the operation command value output into the drive signal. The first controller is configured to, in a case where a failure of the processor is detected when the electrified vehicle is started up, determine whether a limp home mode is executable, based on the state index, and, in a case where a determination is made that the limp home mode is executable, output a second command value based on the limp home mode to the logic circuit instead of the first command value.

Abstract: A trailer sway control system for a vehicle includes: a front left active suspension actuator; a front right active suspension actuator; a rear left active suspension actuator; a rear right active suspension actuator; an actuator control module configured to: based on a hitch angle between (a) a first longitudinal axis of a trailer hitched to the vehicle and (b) a second longitudinal axis of the vehicle, determine target vertical forces for the front left active suspension actuator, the front right active suspension actuator, the rear left active suspension actuator, and the rear right active suspension actuator, respectively; and selectively adjust the front left active suspension actuator, the front right active suspension actuator, the rear left active suspension actuator, and the rear right active suspension actuator based on the target vertical forces, respectively.

Abstract: A method includes determining a desired yaw moment to be applied to an ego vehicle during travel. The method also includes identifying yaw moment changes that are achievable using different torque vectoring techniques supported by the ego vehicle. The method further includes selecting at least one of the torque vectoring techniques based on the identified yaw moment changes. In addition, the method includes using the at least one selected torque vectoring technique to obtain the desired yaw moment and create lateral movement of the ego vehicle during the travel. In some cases, a desired response time associated with the lateral movement of the ego vehicle may be used, where steering control provides a faster response time and torque vectoring control provides a slower response time. The at least one torque vectoring technique may be selected based on different energy efficiencies associated with different ones of the torque vectoring techniques.

Abstract: A method for provision image recordings in a vehicle. The method include: ascertaining a first image recording of a first image sensor of the vehicle and at least one further image recording of at least one further image sensor of the vehicle; carrying out a merging of the first image recording and the at least one further image recording for a reduction of an amount of data for providing the relevant information, the merging taking place based on a selection from the surrounding regions, whereby at least one merged image recording is obtained; initiating at least one transmission of the merged image recording within the vehicle and at least to a central control device of the vehicle, whereby the merged image recording is supplied to a processing for performing the vehicle function.

Abstract: An automatic parking system which controls a vehicle so as to cause the vehicle to be moved to a parking place and accommodated in a parking frame provided in the parking place includes a route where magnetic marker is laid so as to be detectable by using a magnetic sensor array provided to the vehicle, RFID tag providing tag information capable of identifying laying position of the magnetic marker, and a control server device which identifies a vehicle position based on the laying positions of the magnetic markers, allowing highly-accurate identification of the position of the vehicle to be forwarded and allowing operation with high reliability.

Abstract: A system is provided. The system includes a first vehicle controller , a second vehicle controller, and a remote server. The first vehicle controller is programmed to: a) detect an obstacle, b) activate at least one rear-facing sensor to capture a recording of the obstacle; and c) transmit the recording of the obstacle and a location of the first vehicle. The remote server is programmed to a) determine and store a first location of the obstacle, b) subsequent to storing the first location of the obstacle, c) receive a current location of the second vehicle, and d) compare the current location of the second vehicle to the stored first location of the obstacle. The second vehicle controller is programmed to: a) receive the information about the obstacle and b) adjust operation of the second vehicle to avoid the obstacle.

Abstract: A low clearance detection system for a vehicle. In one example, the system includes a first sensor configured to detect an object in front of the vehicle and generate an object clearance signal. The system includes a second sensor configured to detect a load height of a load of the vehicle and generate a load height signal. The system includes a third sensor configured to detect a distance between the third sensor to a ground surface and to generate a ground reference signal. The system also includes an electronic processor configured to receive the object clearance signal, the load height signal, and the ground reference signal. The electronic processor determines an object clearance threshold, a clearance height of the load, and a load collision condition when the clearance height exceeds the object clearance threshold. In response to determining the load collision condition, the electronic processor controls a vehicle system.

Abstract: A device for controlling driving of a vehicle includes a sensor for acquiring state information of the vehicle during autonomous driving, a processor that performs emergency braking when a risk of collision of the vehicle is predicted based on the obtained state information of the vehicle, stores a vehicle event when the vehicle event occurs after the emergency braking is performed, and transitions to a driving mode for resolving the vehicle event when the risk of collision is resolved, and storage for storing an algorithm for an operation of the processor.

Abstract: A vehicle control apparatus includes a host vehicle position recognizer, a moving object recognizer, a map database, an influence recognizer configured to recognize an influence of a moving object around the host vehicle traveling along a target path of the host vehicle, and a vehicle controller configured to decelerate the host vehicle to avoid collision with the moving object based on the influence. Map information includes area information regarding a plurality of areas on the map for specifying the moving object that is a target of recognizing the influence. When the host vehicle position satisfies predetermined host vehicle position conditions set in advance for each area, the influence recognizer recognizes the influence of the moving object present in the area where the host vehicle position satisfies the host vehicle position conditions, based on the host vehicle position, the area information, and the recognition result from the moving object recognizer.

Abstract: A method of automatically controlling a motor vehicle may involve generating environment data and the data being taken as a basis for determining a concealed region of a field of view. A reference point on a boundary between the concealed region and an unconcealed region of the field of view is determined, and at least two risk zones, each risk zone having the reference point as the centre, may be determined. A risk zone of the risk zones (Sa, Sb, Sc) may be assigned a risk characteristic, and the motor vehicle may be controlled on the basis of the risk characteristics.

Abstract: A method for ascertainment of an approximate object position of a dynamic object in the surroundings of a vehicle. The method includes: detecting sensor data; ascertaining a present reflection origin position of a static or dynamic object as a function of the detected sensor data; detecting a camera image; recognition of the dynamic object as a function of the detected camera image; and ascertaining a present estimated position of the recognized dynamic object relative to the vehicle as a function of the detected camera image. When a position distance between the ascertained estimated position of the recognized dynamic object and the ascertained reflection origin position is less than or equal to a distance threshold value, a classification of the present reflection origin position as belonging to the recognized dynamic object takes place as a function of the underlying sensor data for the ascertainment of the reflection origin position.

Abstract: In various examples, control policies for controlling agents may be learned from demonstrations capturing joint states of entities navigating through the environment. A control policy may be learned mapping joint states to control actions, where the joint states are between agents, and the control actions are of at least one of the agents. The control policy may be learned to define the mappings as control invariant sets of the joint sates and the control actions. The control policy may be used to determine one or more functions that compute, based at least on a joint state between entities, output indicating a likelihood of collision between the entities operating in accordance with the control policy. Using the output, current and/or potential states of the environment may be evaluated to determine control operations for a machine, such as a vehicle.

Abstract: The invention relates to a method and a device for regulating the speed of an autonomous vehicle, referred to as ego vehicle, comprising an adaptive cruise control, said method comprising the steps of activating (201) said adaptive cruise control, receiving (202) information relating to said target vehicle, referred to as target information, receiving (203) information relating to said ego vehicle, referred to as ego vehicle information, determining (204) an inter-vehicle time, determining (205) an alert signal from said target information and said ego vehicle information, determining conditions (206) for substituting (207) a target acceleration for a setpoint acceleration of said cruise control.

Abstract: Example embodiments relate to techniques for adjusting vehicle behavior based on ambient ground relative wind estimations. An onboard computing system may receive wind data from one or multiple wind sensors positioned onboard a vehicle. The wind data can indicate a direction and a speed of wind propagating in the vehicle's environment. The computing system can also receive navigation data that represents a direction and a speed of the vehicle and then estimate an ambient ground relative wind speed based on the navigation data and the wind data. The computing system can adjust the behavior of the vehicle based on the ambient ground relative wind speed. For instance, the computing system may compare the speed of the ambient ground relative wind to a predefined behavior threshold curve and adjust the behavior of the vehicle based on the comparison.

Abstract: A vehicle speed control system comprising: a thermometer measuring a temperature of a tire; and a control device controlling a speed of a vehicle on the basis of a measured temperature of the tire obtained by the thermometer.

Abstract: A system controls a vehicle. The vehicle implements at least one control application using a variable measured by at least one sensor of a perception system installed in the vehicle. The control system includes an adaptive controller to dynamically activate one or more elementary controllers of a set of elementary controllers including at least two elementary controllers, each elementary controller can apply a control function of a vehicle parameter acting on actuators of the vehicle, the control functions being separate, based on a precision indicator of the perception system determined according to a real-time value of the variable.

Abstract: Disclosed is a vehicle that may include a frame to support a power system, such as an engine, and one or more surface supports, such as wheels, to support the frame. The engine may include an internal combustion engine and a fuel supply system therefore. The engine may provide power to drive the wheels.

Abstract: A method for controlling a braking system of a motor vehicle that includes a plurality of wheels, at least one electric motor as a drive, a service brake and a vehicle dynamic control system. The wheels can be braked by a deceleration torque applied by the service brake and at least partially by a deceleration torque (ME) applied by the electric motor where slippage which arises as a result of braking and/or of intervention by the vehicle dynamic control system is regulated at least primarily through adjustment of the deceleration torque applied by the electric motor. When necessary, a drive torque is applied to regulate slippage or to cause a locked wheel to rotate by the electric motor.

Abstract: Systems, methods, and vehicles for classifying driving behavior of a target vehicle are provided. The systems include a controller programmed to identify a target vehicle associated with a pseudo-id, obtain a first tag representing first driving behavior of the target vehicle during a first period of time along with the pseudo-id based on first motion data of the target vehicle, obtain a second tag representing second driving behavior of the target vehicle during a second period of time along with the pseudo-id based on second motion data of the target vehicle, the second period of time being after the first period of time, and classify driving behavior of the target vehicle based on interpretation of the first tag and the second tag.

Abstract: A vehicle assistance device includes an object sensing unit that detects an object around an own vehicle included in a range viewable through a monitoring area set in a part of a field-of-view range of a driver, sensed object information extraction unit and an additional information generation unit that generate additional information regarding the object detected, a driver's line-of-sight sensing unit that detects a line of sight of the driver, a mirror gaze determination unit that determines that movement of the line of sight of the driver detected has stopped in the monitoring area, and an additional information voice generation and output unit that outputs by voice the additional information generated by the additional information generation unit at a time point when stop of the line-of-sight movement is determined.

Abstract: Systems, methods, and vehicles for correcting driving behavior of a driver of a vehicle are provided. The systems include a controller programmed to identify a repetitive movement pattern of a driver of a vehicle at a predetermined location based on accumulated driving data of the vehicle, implement digital twin simulation of the vehicle using the repetitive movement pattern and the digital twin simulation of another object to identify a potential conflict between the vehicle and the another object, and inform the driver of the vehicle about predetermined driving behavior in response to identifying the potential conflict.

Abstract: Systems and methods for reducing vehicle collisions based on driver risk groups are provided. A plurality of vehicle operators may be classified into a driver risk group based on one or more attributes (e.g., location, workplace, school, demographic, hobby, interest, etc.) shared by the plurality of vehicle operators. Vehicle sensor data (e.g., speed data, acceleration data, braking data, cornering data, following distance data, turn signal data, seatbelt use data, etc.) associated with each of the plurality of vehicle operators of the driver risk group may be analyzed. Based on the analysis of the vehicle sensor data, one or more indicia of safe driving behavior associated with the driver risk group may be identified. In response to a third-party query regarding a vehicle operator in the driver risk group, an indication of the safe driving behavior associated with the driver risk group may be provided to the third party.

Abstract: A vehicle control system may include a sensor network sensing vehicle attitude information and a controller operably coupled to the sensor network to determine, based on the vehicle attitude information, movement of a center of gravity of the vehicle relative to an axis of rotation of the vehicle. The controller may further determine a modification to a torque application of the vehicle based on the movement of the center of gravity of the vehicle relative to the axis of rotation of the vehicle.

Abstract: System, methods, and computer-readable media for extrinsically calibrating sensors on an autonomous vehicle (AV) by leveraging map data. By leveraging offline data, such as the map data on the AV, the extrinsic calibration of the sensors may be performed on road to update or check previous calibrations. Static objects are determined in the scene by leveraging a map with a semantic map layer and sensors are extrinsically calibrating using a portion of a set of static points associated with the determined static objects by determining relative positions and angles the sensors.

Abstract: The subject technology is related to autonomous vehicles (AV) and, in particular, to an environmental and electromagnetic seal for autonomous vehicle control systems. The AV includes an autonomous driver system computer (ADSC) fixed to an interior surface of the AV and configured to control the electronic drivetrain, the ADSC including at least one port for connecting with an AV and an elastic conductive cover for selectively sealing the at least port one. The elastic conductive cover comprises a hooking member with an opening that is rotatably connected to the ADSC, cannot be independently removed from the ADSC, and includes an inner surface having at least one extended member with a sealing member that is configured to seal a port of the at least one port.

Abstract: A computer-implemented method provides for terminating a scenario-based test process of a driver assistance system. The test process comprises a cycle and includes determining critical test cases and parameter combinations thereof. The method includes: performing at least one test of the driver assistance system after each iteration n of the cycle and determining a set of critical test cases; establishing, on that basis, a distance between a first set of critical test cases in the iteration n and a second set of critical test cases from the iteration n?1 or a distance between the first set of critical test cases in the iteration n and a predefined set of critical test cases; and terminating or continuing the cycle of the test process on the basis of a difference between the distance between the first set and the second set and a preset limit.

Abstract: Disclosed herein are systems, methods, and computer program products for selectively using vehicle trajectories. The methods comprise: receiving a vehicle trajectory (VT) prior to being used to generate motion commands (MCs) for a vehicle; identifying software and/or hardware components of the vehicle that produced data used to generate VT; determining whether a fault condition exists that is associated with VT based on (i) a detection that the software/hardware component(s) did or did not experience a fault or operational condition of a type while producing the data used to generate VT and/or (ii) a detection that VT would or would not cause violation of limit(s) for an operational parameter of the vehicle; selecting VT when the fault condition does not exist or another VT when the fault condition does exist; and causing the motion commands to be generated using VT or the another VT which was selected.

Abstract: The present technology is effective to cause at least one processor to instruct an autonomous vehicle to navigate a specific course and to record diagnostic measurements while navigating the specific course, receive the diagnostic measurements from the autonomous vehicle, and analyze the diagnostic measurements from the autonomous vehicle in a context provided by a collection of diagnostic measurement data collected from a fleet of similar autonomous vehicles navigating the specific course.

Abstract: The subject disclosure relates to estimating a chassis frame of an autonomous vehicle. A process of the disclosed technology can include receiving a position for each of a plurality of sensors on an autonomous vehicle, determining an ideal chassis point in relation to a constellation of model sensors in a CAD model associated with the autonomous vehicle, generating a constellation of the plurality of sensors based on the positions of the plurality of sensors in relation to the ideal chassis point, minimizing distortion between measured values associated with the constellation of the plurality of sensors and ideal values associated with the constellation of model sensors, determining an estimated real chassis point based on the minimized distortion between the measured values and the ideal values, and calibrating at least one of the plurality of sensors based on the estimated real chassis point.

Abstract: A vehicle information processing system includes a vehicle information processing device mounted on a vehicle, a first external information processing device provided outside the vehicle, a plurality of vehicle control applications configured to output control commands to control target devices of the vehicle, and an arbitration unit provided in at least one of the vehicle information processing device and the first external information processing device. The vehicle control applications are installed in at least one of the vehicle information processing device and the first external information processing device. The arbitration unit is configured to arbitrate the control commands for a predetermined one of the control target devices to determine one control command. The control commands for the predetermined one of the control target devices are obtained by the vehicle control applications.

Abstract: A voice instruction approval device includes: a change receiving unit that receives a change instruction given by voice; a presentation unit that presents information; an approval request instruction unit that gives the presentation unit a presentation instruction of an approval request requesting an approval operation for executing the change instruction; an approval operation receiving unit that receives the approval operation by an occupant; a presentation monitoring unit that monitors whether the presentation unit is in a state in which the approval request is able to be presented; a determination unit that determines to reject the change instruction when the presentation unit is in a state in which the approval request is not able to be presented; a re-operation instruction unit that gives the presentation unit a presentation instruction of a re-operation when the presentation unit cannot present the approval request.

Abstract: By an automate driving control device, a presentation control device, a non-transitory computer-readable storage medium storing an automated driving control device or a presentation control program, an offset control is executed and the execution is limited or, whether to execute the offset control is recognized and notification related to the offset control is performed.

Abstract: An example operation includes one or more of: detecting that a plurality of wireless devices are located in a vehicle; pairing a wireless device of the plurality of wireless devices and a head unit of the vehicle, when the wireless device is receiving or transmitting audio; and transmitting the audio through the head unit of the vehicle.

Abstract: Systems and methods for learning and managing robot user interfaces are disclosed herein. One embodiment generates, based on input data including information about past interactions of a particular user with a robot and with existing HMIs of the robot, a latent space using one or more encoder neural networks, wherein the latent space is a reduced-dimensionality representation of learned behavior and characteristics of the particular user, and uses the latent space as input to train a decoder neural network associated with (1) a new HMI distinct from the existing HMIs or (2) a particular HMI among the existing HMIs to alter operation of the particular HMI. The trained first decoder neural network is deployed in the robot to control, at least in part, operation of the new HMI or the particular HMI in accordance with the learned behavior and characteristics of the particular user.

Abstract: The driving evaluation display device acquires an evaluation result of a driving operation of a driver based on operation data regarding the driving operation during traveling, and causes an evaluation image indicating the acquired evaluation result to be displayed on a display unit provided forward of a driver's seat. The evaluation image is displayed in conjunction with the start of the driving operation by the driver, and the display mode of at least a part of the evaluation image changes based on the evaluation result of the driving operation.

Abstract: Provided are a method and apparatus for providing a driver interface. The method of providing a driver interface may include, based on a state of a vehicle, determining a main interface configured to display information regarding a vehicle operation service, and generating the determined main interface, wherein the generating of the main interface may include determining a before-starting-work interface as the main interface, in response to the state of the vehicle being switched to a moving-to-workplace state, determining a moving-to-workplace interface as the main interface, and in response to the state of the vehicle being switched to a standby-for-dispatch state, determining a standby-for-dispatch interface as the main interface.

Abstract: A vehicle presentation control device, which is usable in a vehicle capable of performing autonomous driving, includes a processor. The processor distinguishably specifies, as an autonomous driving start requirement to be satisfied for a start of autonomous driving without monitoring obligation, at least a driver requirement, which is a requirement highly likely to be solved by a driver, or an environmental requirement, which is a requirement less likely to be solved by the driver. The processor starts, as requirement presentation that presents information about requirement necessary for the start of autonomous driving, driver requirement presentation, which indicates that the driver requirement is necessary for the start of autonomous driving, before the start of autonomous driving, in response to the specified autonomous driving start requirement being the driver requirement.

Abstract: Systems and methods are provided for increasing driver awareness of external audible and visual alerts. The external alerts may be detected by external sensors of a vehicle. Systems may use internal sensors to determine whether a driver of the vehicle appears aware of the external alert or whether the external alert is detectable inside the vehicle. If the driver does not appear aware of the external alert, or the external alert is not detectable inside the vehicle, the vehicle may broadcast an internal alert to the driver. The internal alert may be one or more of a visual alert, an audible alert, or a tactile alert.

Abstract: The subject technology is related to autonomous vehicles (AV) and, in particular, to calibrating multiple sensors of an AV in an undefined training area. An example method includes instructing the AV to pilot itself in an undefined training area subject to at least one constraint, wherein the AV is instructed to pilot itself along a path until the AV has overlapped at least a portion of the path, and at a location at which the AV has overlapped at least the portion of the path, determining that first returns from a previous LIDAR scan overlaps with second returns from a subsequent LIDAR scan taken when the AV has overlapped at least the portion of the path. Initially, the AV does not include a location reference to identify locations of objects in the undefined training area and a plurality of sensors of the AV are uncalibrated with respect to each other.

Abstract: Assistance can be provided to AV users through projection of graphical figures. A system may receive a request for assistance from a user of an AV. The system assigns the request to an agent who can assist the user. The system further provides a graphical representation (e.g., an avatar) of the agent to a device that can project the graphical representation to the user. The user can have a conversation with the graphical representation, e.g., based on information provided by the agent. The system can also provide an audio filter to the device for modifying an audio content presented by the device so that the modified audio content appears as if it is made by the graphical representation. The device may be a part of the AV or a client device of the user that can present VR, AR, or MR content. The device may be mobile.

Abstract: A method of representation learning for object detection from unlabeled point cloud sequences is described. The method includes detecting moving object traces from temporally-ordered, unlabeled point cloud sequences. The method also includes extracting a set of moving objects based on the moving object traces detected from the sequence of temporally-ordered, unlabeled point cloud sequences. The method further includes classifying the set of moving objects extracted from on the moving object traces detected from the sequence of temporally-ordered, unlabeled point cloud sequences. The method also includes estimating 3D bounding boxes for the set of moving objects based on the classifying of the set of moving objects.

Abstract: Embodiments are disclosed for reducing unauthorized modifications of object detection systems of motor vehicles. As an example, a method comprises: generating a cryptographic signature for an output of nodes of a fully connected layer of a neural network of an object detection system of a vehicle, the cryptographic signature based in part on a first private key stored in a reply-protected memory block (RPMB), the output at least partially describing a detected object; and, responsive to verifying the cryptographic signature, adjusting vehicle operation based on the detected object. In this way, outputs of the neural network may be verified, so that unauthorized modifications are detected, and system accuracy increases.

Abstract: A computer-implemented method for updating a perception function of a vehicle having an Automated Driving System (ADS) is disclosed. The ADS has a machine-learning algorithm for: generating an attention map or a feature map based on one or more ingested images and for providing one or more in-vehicle perception functions based on one or more ingested images. The method comprises obtaining one or more images of a scene in a surrounding environment of the vehicle, and updating one or more model parameters of the self-supervised machine-learning algorithm in accordance with a self-supervised machine learning process based on the obtained one or more images. The method further comprises generating a first output comprising an attention map or a feature map by processing the obtained one or more images by using the self-supervised machine-learning algorithm, and generating a supervisory signal for a supervised learning process based on the first output.

Abstract: A method for operating a transportation vehicle wherein an image capturing unit is used to generate an optical image of an upcoming roadway lying ahead in the direction of travel of the transportation vehicle. The image is used to ascertain an ego lane of the roadway assigned to the transportation vehicle and an upcoming profile of the ego lane. At least one item of meta information that influences the detection of the ego lane and/or of the upcoming profile of the ego lane is captured. Swarm data pertaining to the roadway are retrieved from a database, a comparison lane of the roadway and a comparison profile of the comparison lane are derived from the swarm data, and the at least one item of meta information, the upcoming profile and the comparison profile are used to ascertain an uncertainty factor for the image from the image capturing unit.

Abstract: A method for operation of narrow artificial intelligence (AI) agents for at least partially autonomous driving, the method includes: (a) receiving, by multiple perception modules, multi-domain information about elements affecting a vehicle; wherein each one of the multiple perception module is associated with a dedicated domain of the multi-domain information; (b) generating, by the multiple perception modules, class signatures that are indicative of classes of the elements of the multi-domain information; (c) determining a multi-domain identifier that identifies the generated class signatures of the multiple perception modules; and (d) identifying, based on the multi-domain identifier, one or more narrow AI agents that are relevant to a processing of at least a part of the multi-domain information.