A method for determining hard example sensor data inputs for training a task neural network is described. The task neural network is configured to receive a sensor data input and to generate a respective output for the sensor data input to perform a machine learning task. The method includes: receiving one or more sensor data inputs depicting a same scene of an environment, wherein the one or more sensor data inputs are taken during a predetermined time period; generating a plurality of predictions about a characteristic of an object of the scene; determining a level of inconsistency between the plurality of predictions; determining that the level of inconsistency exceeds a threshold level; and in response to the determining that the level of inconsistency exceeds a threshold level, determining that the one or more sensor data inputs comprise a hard example sensor data input.

An approach is provided for identifying partitions associated with erratic pedestrian behaviors and their correlations to points of interest. For example, the approach involves receiving sensor data associated with a geographic area. The approach also involves based on the sensor data, determining pedestrian-behavior parameter(s) respectively for partition(s). Each respective partition of the partition(s) represents a respective subarea of the geographic area, a respective time period, or a combination thereof. The approach further involves identifying at least one erratic partition from the partition(s) based on determining that a respective pedestrian-behavior parameter associated with the at least one erratic partition deviates from a baseline pedestrian-behavior parameter by at least a threshold extent. The approach further involves determining a correlation of the at least one erratic partition to at least one map feature of a geographic database. The approach further involves providing the correlation as an output.

An object recognition apparatus includes at least one processor and at least one memory communicably coupled to the processor. The processor sets one or more object presence regions in each of which an object is likely to be present, on the basis of observation data of a distance sensor. The processor estimates an attribute of the object that is likely to be present in each of the one or more object presence regions. The processor sets, on the basis of the attribute of the object, a level of processing load to be spent on object recognition processing to be executed for each of the one or more object presence regions by using at least image data generated by an imaging device. The processor performs, for each of the one or more object presence regions, the object recognition processing corresponding to the set level of the processing load.

An object recognition apparatus includes at least one processor and at least one memory communicably coupled to the processor. The processor sets one or more object presence regions in each of which an object is likely to be present, on the basis of observation data of a distance sensor. The processor estimates an attribute of the object that is likely to be present in each of the one or more object presence regions. The processor sets, on the basis of the attribute of the object, a level of processing load to be spent on object recognition processing to be executed for each of the one or more object presence regions by using at least image data generated by an imaging device. The processor performs, for each of the one or more object presence regions, the object recognition processing corresponding to the set level of the processing load.

Aspects of the disclosure provide for automatically generating labels for sensor data. For instance, first sensor data, for a vehicle may be identified. This first sensor data may have been captured by a first sensor of the vehicle at a first location during a first point in time and may be associated with a first label for an object. Second sensor data for the vehicle may be identified. The second sensor data may have been captured by a second sensor of the vehicle at a second location at a second point in time outside of the first point in time. The second location is different from the first location. A determination may be made as to whether the object is a static object. Based on the determination that the object is a static object, the first label may be used to automatically generate a second label for the second sensor data.

A method for illuminating vehicle surroundings of a motor vehicle that comprises an illumination device and a detection device, wherein the illumination device is set up to illuminate at least part of a solid angle region of the vehicle surroundings with different illumination patterns, in particular with visible light, wherein the illumination patterns each predefine illumination intensities for different solid angle subregions of the solid angle region, comprising the steps of: illuminating the vehicle surroundings with a first of the illumination patterns by means of the illumination device, detecting a light pattern that results from the illumination of the vehicle surroundings with the first illumination pattern by means of the detection device, selecting a second of the illumination patterns on the basis of the detected light pattern, and illuminating the vehicle surroundings with the second illumination pattern by means of the illumination device.

An information processing apparatus includes an input interface, a processor, and an output interface. The input interface obtains observation data obtained from an observation space. The processor detects a subject image of a detection target from the observation data, calculates a plurality of individual indices indicating degrees of reliability, each of which relates to at least identification information or measurement information regarding the detection target, and also calculates an integrated index, which is obtained by integrating a plurality of calculated individual indices. The output interface outputs the integrated index.

An information processing apparatus includes an input interface, a processor, and an output interface. The input interface obtains observation data obtained from an observation space. The processor detects a subject image of a detection target from the observation data, calculates a plurality of individual indices indicating degrees of reliability, each of which relates to at least identification information or measurement information regarding the detection target, and also calculates an integrated index, which is obtained by integrating a plurality of calculated individual indices. The output interface outputs the integrated index.

This application discloses a method and an apparatus for detecting a complexity of a traveling scenario of a vehicle, comprising: obtaining a travelling speed of the vehicle and a travelling speed of a target vehicle; determining, based on the traveling speed of the vehicle and the traveling speed of the target vehicle, a dynamic complexity of a traveling scenario in which the vehicle is located; determining static information of each static factor in the traveling scenario in which the vehicle is currently located; obtaining, based on the static information of each static factor, a static complexity of the traveling scenario in which the vehicle is located; and obtaining, based on the dynamic complexity and the static complexity, a comprehensive complexity of the traveling scenario in which the vehicle is located.

This application discloses a method and an apparatus for detecting a complexity of a traveling scenario of a vehicle, comprising: obtaining a travelling speed of the vehicle and a travelling speed of a target vehicle; determining, based on the traveling speed of the vehicle and the traveling speed of the target vehicle, a dynamic complexity of a traveling scenario in which the vehicle is located; determining static information of each static factor in the traveling scenario in which the vehicle is currently located; obtaining, based on the static information of each static factor, a static complexity of the traveling scenario in which the vehicle is located; and obtaining, based on the dynamic complexity and the static complexity, a comprehensive complexity of the traveling scenario in which the vehicle is located.