Abstract: Systems and methods for correcting mapping information inaccuracies are described. In some aspects, the method includes receiving terrestrial data captured in an area of interest, and detecting features in the terrestrial data identifying ground points in the area of interest. The method also includes correlating the ground points with ground control points in the area of interest to determine a correspondence, and computing an aggregate of positional differences between corresponding points. The method further includes generating a report indicating a quality of the terrestrial data captured in the area of interest based on the aggregate.

Abstract: A method for checking the plausibility of a lateral acceleration and further input variables of a transmission shifting program includes measuring, over a defined route section, a lateral acceleration signal, calculating a mean value of the measured lateral acceleration signal, and calculating, based on the further input variables, a plurality of n?2 different lateral acceleration sensor reference variables. The different lateral acceleration sensor reference variables are calculated by a lateral acceleration reference model for the defined route section. The method further includes determining, for each respective lateral acceleration sensor reference variable, a respective mean value of a calculated lateral acceleration, determining deviations of the mean value of the measured lateral acceleration and the mean values of the calculated lateral accelerations, and evaluating, based on a magnitude of the deviations, whether or not the measured lateral acceleration and the further input variables are plausible.

Abstract: Provided is a control apparatus for a vehicle, the control apparatus being configured to determine a road surface ? state of a road in front of the vehicle based on an image of a front region of the vehicle, and change a magnitude of an amount of reduction in a braking force per unit time in accordance with the determined road surface ? state in braking force cancel control executed after hill-hold control

Abstract: Embodiments of this application provide a target road segment speed prediction method, apparatus, a server, and a non-transitory computer-readable medium. In the method, a first moving speed on a target road segment at a first time point is obtained. A plurality of second moving speeds on the target road segment at each of a plurality of time points before the first time point is obtained. A mean historical speed on the target road segment at the first time point during previous time cycles is obtained. A speed prediction feature of the target road segment at a second time point is determined. A moving speed on the target road segment at the second time point is predicted according to the speed prediction feature of the target road segment at the second time point and a pre-trained road segment speed prediction model.

Abstract: A map generation device extracts, by inputting an image in which a road is represented to a classifier that outputs, for each pixel of the image, a type of a feature object on the road represented by the pixel, a pixel representing a boundary feature object that represents a boundary of a lane among feature objects on the road, calculates a Voronoi boundary by Voronoi-dividing the image with each pixel representing the boundary feature object as a generating point, detects each of the calculated Voronoi boundaries as one lane, and generates map information representing each of the detected lanes.

Abstract: A method may include determining a location of an unmanned aerial vehicle (UAV); generating a set of mission plans based on the location of the UAV, each mission plan including respective mission plan parameters; receiving a selection of a mission plan of the set of mission plans; obtaining mission plan parameters for the selected mission plan; and transmitting the obtained mission plan parameters to the UAV to configure the UAV according to the obtained mission parameters.

Abstract: Aspects of the disclosure provide for controlling an autonomous vehicle. For instance, a first probability distribution may be generated for the vehicle at a first future point in time using a generative model for predicting expected behaviors of objects and a set of characteristics for the vehicle at an initial time expected to be perceived by an observer. Planning system software of the vehicle may be used to generate a trajectory for the vehicle to follow. A second probability distribution may be generated for a second future point in time using the generative model based on the trajectory and a set of characteristics for the vehicle at the first future point expected to be perceived by the observer. A surprise assessment may be generated by comparing the first probability distribution to the second probability distribution. The vehicle may be controlled based on the surprise assessment.

Abstract: A method (200) for detecting the clearance of a brake (100) of a motor vehicle, in particular a utility motor vehicle, includes the following steps: reading measurement signals of a wear sensor (115) disposed on the brake (100), determining an output signal value that is representative of the non-actuated state of the brake from the measurement signals, determining an event signal value that is representative of the braking state of the brake from the measurement signals, and determining the clearance from the difference between the event signal value and the output signal value, wherein the measurement signals of the wear sensor are examined for the presence of a characteristic signal oscillation that arises as a result of bringing into contact the brake lining with the counterpart thereof that is to be braked. A controller (10) carries out the method on a brake (100).

Abstract: Systems and methods for training machine-learned models are provided. A method can include receiving a rasterized image associated with a training object and generating a predicted trajectory of the training object by inputting the rasterized image into a first machine-learned model. The method can include converting the predicted trajectory into a rasterized trajectory that spatially corresponds to the rasterized image. The method can include utilizing a second machine-learned model to determine an accuracy of the predicted trajectory based on the rasterized trajectory. The method can include determining an overall loss for the first machine-learned model based on the accuracy of the predictive trajectory as determined by the second machine-learned model. The method can include training the first machine-learned model by minimizing the overall loss for the first machine-learned model.

Abstract: A rotary-wing aircraft and system for flying a rotary-wing aircraft. The aircraft includes a servo system for actuating a rotor of the aircraft. A hydraulic system provides hydraulic power to the servo system, and a sensor measures a parameter of the hydraulic system. A processor determines a condition of the hydraulic system from the parameter and enforces an effective flight envelop based on the condition of the hydraulic system in order to fly the aircraft within the effective flight envelope.

Abstract: A lidar system is described herein. The lidar system includes a transmitter that is configured to emit a frequency-modulated lidar signal. The lidar system further includes processing circuitry that is configured to compute a distance between the lidar system and an object based upon the frequency-modulated lidar signal, the processing circuitry configured to compute the distance with a first resolution when the distance is at or beneath a predefined threshold, the processing circuitry configured to compute the distance with a second resolution when the distance is above the predefined threshold, wherein the first resolution is different from the second resolution.

Abstract: Disclosed are systems and methods relating to determining geographic locations of vehicle ways which are employed by vehicles for movement and/or parking. A classifier may be defined for identifying portions of the vehicle ways via machine learning techniques and processing of historical telematic data.

Abstract: Disclosed are systems and methods relating to determining geographic locations of vehicle ways which are employed by vehicles for movement and/or parking. A classifier may be defined for identifying portions of the vehicle ways via machine learning techniques and processing of historical telematic data.

Abstract: Various systems and methods for updating a current probability density function. The PDF includes a list of objects within a location. First information is received from a first remote device at a first position within the location. The first information includes a vehicle identification, a first PDF of the objects. Second information is received from a second remote device at a second position within the location. The second information includes a vehicle identification, a second PDF of the objects. A first rank for the first PDF is determined based on locations of the objects in the first PDF compared to locations of the objects in the current PDF. A second rank for the second PDF is determined. The first PDF and the second PDF are combined using the first rank and the second rank into a combined PDF. The current PDF based on the combined PDF.

Abstract: Methods described herein relate to iteratively refining parameters of a localization framework for different data sources. Methods may include: receiving a map data set from a data source; applying an offset to the map data to generate an offset map data set; applying a localization framework between the map data set and the offset map data set to generate a localized data set; recovering offset data from the localized data set; iteratively tuning parameters of the localization framework in response to the offset data from the localized data set failing to correspond with the applied offset until offset data recovered from the localized data set corresponds to the applied offset; receiving sensor data from at least one sensor of a vehicle; applying the localization framework to the sensor data to locate the vehicle within a mapped region.

Abstract: A system may determine that an upcoming pass is a final pass associated with loading a machine. The system may compute, based on determining that the upcoming pass is the final pass, a trigger time associated with causing a trigger signal to be transmitted. The trigger time may be computed based on a final pass completion time that identifies a time at which the final pass is expected to be completed. The trigger time may be prior to the final pass completion time. The system may cause the trigger signal to be transmitted at the trigger time. The system may cause, based on a receipt of the trigger signal, a transition of the machine from an idle state to a ready state to be initiated. The transition from the idle state to the ready state may be caused to be initiated prior to a time at which the final pass, associated with loading the machine, is completed.

Abstract: A lidar system is described herein. The lidar system includes a transmitter that is configured to emit a frequency-modulated lidar signal. The lidar system further includes processing circuitry that is configured to compute a distance between the lidar system and an object based upon the frequency-modulated lidar signal, the processing circuitry configured to compute the distance with a first resolution when the distance is at or beneath a predefined threshold, the processing circuitry configured to compute the distance with a second resolution when the distance is above the predefined threshold, wherein the first resolution is different from the second resolution.

Abstract: A headlight control system controls a headlight of a moving object. The moving object includes the headlight including a plurality of light emission units, and an imaging unit configured to capture images of circumstances in front. The headlight control system includes an irradiation pattern controller configured to perform control for changing at least one of presence or absence of light emission and a degree of light emission of each of the light emission units to change an irradiation pattern of the headlight to one of a plurality of irradiation patterns, an imaging controller configured to perform control such that the imaging unit captures the images of the circumstances in front for each of the irradiation patterns to acquire captured images, and a learning unit configured to learn an irradiation pattern suitable for the circumstances in front based on captured images captured for each of the irradiation patterns.

Abstract: The present invention has an object of determining feasibility of lowering a driving automation level of an automated driving vehicle, based on a driving load considering a relationship with surrounding vehicles. An automatic-driving-level lowering feasibility determination apparatus according to the present invention includes: a surrounding vehicle information obtainment unit obtaining surrounding vehicle information; a driving load calculator calculating, based on the surrounding vehicle information, a driving load value indicating a magnitude of a driving load on the subject vehicle; a driving-automation-level lowering feasibility determination unit determining feasibility of lowering a driving automation level of the subject vehicle, based on the driving load value; and an output controller outputting, to an automated driving control device, a result of the feasibility determined by the driving-automation-level lowering feasibility determination unit.

Abstract: Provided is an electric motor vehicle including a secondary battery, an electric motor, and a control device that controls an input to and an output from the secondary battery. Using an SOC of the secondary battery, the control device calculates a first OCV that is an OCV based on an assumption of absence of a change in voltage due to polarization. Using a voltage and a current of the secondary battery, the control device calculates a second OCV that is an OCV including a change in voltage due to polarization. When a voltage difference between the first OCV and the second OCV resulting from discharging of the secondary battery is large, the control device augments a limit value of electricity input into the secondary battery to be higher than a limit value when the voltage difference is small.