A map generation apparatus including a division line detection part, a feature point detection part and a microprocessor. The microprocessor is configured to perform generating a first map including position information of the division line detected by the division line detection part, generating a second map including position information of the feature points detected by the feature point detection part, and determining whether a position of the division line has changed, the determining including determining that the position of the division line has changed when a degree of difference between two first maps respectively generated at a first time point and a second time point after the first time point is a first predetermined degree or more and a degree of difference between two second maps respectively generated at the first time point and the second time point is a second predetermined degree or more.

Systems and methods are disclosed for identifying landmarks. A method for identifying a landmark may include initiating identification of a landmark based on one or more images from a camera, for use in autonomous vehicle navigation, the landmark including a traffic sign; initiating updating a road model with a location of the landmark; and initiating distribution of the road model with the location of the traffic sign to a plurality of autonomous vehicles.

Systems and methods evaluate navigation system capabilities. In one implementation, at least one processing device is programmed to acquire characteristics of one or more sensors included in the host vehicle; establish a testing domain, wherein the testing domain includes at least one mapped representation of a geographic region; and simulate operation of the one or more sensors relative to the testing domain. Based on the simulated operation of the one or more sensors, the at least one processing device may determine whether one or more regions exist within the geographic region where outputs of the one or more sensors are insufficient for ensuring that each navigational action implemented by the navigation system of the host vehicle will not result in an accident for which the host vehicle is at fault.

Aspects of the disclosure relate to generating map data. For instance, data generated by a perception system of a vehicle may be received. This data corresponds to a plurality of observations including observed positions of a passenger of the vehicle as the passenger approached the vehicle at a first location. The data may be used to determine an observed distance traveled by a passenger to reach a vehicle. A road edge distance between an observed position of an observation of the plurality of observations and a nearest road edge to the observed position may be determined. An inconvenience value for the first location may be determined using the observed distance and the road edge distance. The map data is then generated using the inconvenience value.

A processor operates to: acquire first information regarding a surrounding travel environment including a travel lane in which a subject vehicle travels, on the basis of detection information from an onboard sensor; refer to map information stored in a storage device to acquire second information regarding lanes of a road; determine whether or not a travel road to which the travel lane belongs is a predetermined specific road, on the basis of the first information; and when a determination is made that the travel road is the specific road, composite the first information and the second information to generate travel environment information.

An approach is provided for detecting and/or verifying a traffic incident (e.g., a road closure) on one of nearby paths that are susceptible to location sensor errors, digital map errors, and/or map mis-matching errors. The approach involves, for example, determining sensor data collected from one or more sensors of one or more devices traveling on either road link of the at least two road links connected at an intersection point. The approach also involves aggregating the sensor data to said either road link of at least two road links. The approach further involves filtering the sensor data based on a distance threshold from the intersection point. The approach further involves determining a traffic incident on said either road link based on the filtered sensor data.

A method, apparatus and computer program product are provided for learning to generate maps from raw geospatial observations from sensors traveling within an environment. Methods may include: receiving a plurality of sequences of geospatial observations from discrete trajectories; refining a summary entity set representation through iteration over discrete trajectories; determining a drive offset for each of the discrete trajectories based on a comparison of the summary entity set representation to a drive entity set for each of the discrete trajectories; aligning the discrete trajectories to generate aligned geospatial observations based, at least in part, on the drive offset for a respective discrete trajectory; concatenating the aligned geospatial observations; processing the concatenated, aligned geospatial observations using at least one Set Transformer; and generating, from the at least one Set Transformer, map geometries including objects from the geospatial observations.

A method, apparatus and computer program product are provided for learning to generate maps from raw geospatial observations from sensors traveling within an environment. Methods may include: processing geospatial observations from discrete trajectories through an iterative attention model incorporating a Gated Recurrent Unit gating pattern to obtain a feature summary; determining a drive offset for each of the discrete trajectories based on the feature summary; aligning the discrete trajectories to generate aligned geospatial observations based, at least in part, on the drive offset for a respective discrete trajectory; concatenating the aligned geospatial observations; processing the concatenated, aligned geospatial observations using at least one Set Transformer; generating, from the at least one Set Transformer, map geometries including objects from the geospatial observations; and providing for at least one of navigational assistance or at least semi-autonomous vehicle control based on the map geometries.

A system and related method determines implicit lane boundaries by generating a bird's eye view of a portion of a road having a first lane and a second lane from environment data having information related to the road, overlaying a grid having cells onto the bird's eye view of the portion of the road, determining cells of the grid that form at least portions of the first lane of the road, determining cells of the grid that form at least portions of the second lane of the road, and determining a probability for one or more cells of the grid indicating a likelihood that a vehicle will travel upon portions of the road represented by the cells of the grid when traveling from the first lane to the second lane. The probability for one or more cells of the grid may be generated by a neural network trained with training data.

Disclosed are a vehicle control system and a driving method of a vehicle using the vehicle control system. The vehicle control system includes a vehicle controller that controls driving of a vehicle and one or more processors that process data related to the driving of the vehicle, receive information about a longitudinal gradient and a transverse gradient of the vehicle from a server, and control a driving speed, and an Advanced Driver Assistant System (ADAS), and/or set a landmark, based on the information on the longitudinal gradient and the transverse gradient.