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.

A vehicle idling stop control device has switches that detect an operation of opening a driver's door and an unbuckling of a driver's seat belt as disembarkation operations by a driver. When a disembarkation operation performed by the driver is detected during an idling stop, the idling stop is cancelled and the engine is restarted upon detecting a disembarkation operation performed by a driver during the idling stop. Also, restarting of the idling stop is prevented due to ending of the disembarkation operation performed by the driver until after the vehicle starts traveling. Thus, unnecessary automatic stopping and automatic restarting of the engine are thereby avoided when the vehicle sets off without the driver actually exiting the vehicle.

A method for predicting an ego-lane for a vehicle. The method includes: receiving at least one image captured by at last one camera sensor of the vehicle, which depicts a lane that may be used by a vehicle; ascertaining a center line of the lane, which extends through a center of the lane, by implementing a trained neural network on the captured image, the neural network being trained via regression to ascertain a center line of a lane, which extends in a center of the lane, based on captured images of the lane; outputting a plurality of parameters, which describe the center line of the lane, via the neural network; generating the center line based on the parameters of the center line; identifying the center line of the lane as the ego-lane of the vehicle; and providing the ego-lane.

One or more outputs from a planning module of an ADV are received. Data of a driving environment of the ADV is received. A performance of the planning module is evaluated by determining a score of the performance of the planning module based on the data of the driving environment and the one or more outputs from the planning module. Whether the one or more outputs from the planning module violates at least one of a set of safety rules is determined. The score is determined being larger than a predetermined threshold in response to determining that the one or more outputs from the planning module violate at least one of the set of safety rules. Otherwise, the score is determined based on a machine learning model. The planning module is modified by tuning a set of parameters of the planning module based on the score.

A system, method, and computer-readable medium having instructions stored thereon to enable an ego vehicle having an autonomous driving function to estimate and traverse a curved segment of highway utilizing radar sensor data. The radar sensor data may comprise stationary reflections and moving reflections. The ego vehicle may utilize other data, such as global positioning system data, for the estimation and traversal. The estimation of the curvature may be refined based upon a lookup table or a deep neural network.

The application disclose an autonomous-driving-based control method performed by a computer device. The method includes: acquiring scene information of a target vehicle; determining a current lane changing scene type of the target vehicle according to the scene information; recognizing, when the current lane changing scene type is a mandatory lane changing scene type, a first lane for completing a navigation travel route, and, when the first lane satisfies a lane changing safety check condition, controlling the target vehicle to perform lane changing operation according to the first lane. The second lane for optimizing the travel time is recognized according to the scene information when the current lane changing scene type is the free lane changing scene type. When the second lane satisfies the lane changing safety check condition, the target vehicle is controlled to perform lane changing operation according to the second lane.

A high-definition map creation method includes: obtaining point cloud data collected with respect to a target region, the point cloud data including K frames of point clouds and an initial pose of each frame of point cloud, K being an integer greater than 1; associating the K frames of point clouds with each other in accordance with the initial pose to obtain a first point cloud relation graph of the K frames of point clouds; performing point cloud registration on the K frames of point clouds in accordance with the first point cloud relation graph and the initial pose to obtain a target relative pose of each frame of point cloud in the K frames of point clouds; and splicing the K frames of point clouds in accordance with the target relative pose to obtain a point cloud map of the target region.

A method of processing an image, an electronic device, and a storage medium, which relate to the artificial intelligence field, in particular to fields of computer vision and intelligent transportation technologies. The method includes: determining at least one key frame image in a scene image sequence captured by a target camera; determining a camera pose parameter associated with each key frame image in the at least one key frame image, according to a geographic feature associated with the key frame image; and projecting each scene image in the scene image sequence to obtain a target projection image according to the camera pose parameter associated with the key frame image, so as to generate a scene map based on the target projection image. The geographic feature associated with any key frame image indicates localization information of the target camera at a time instant of capturing the corresponding key frame image.

Systems and methods are disclosed for estimating slipperiness of a road surface. This estimate may be obtained using an image sensor mounted on a vehicle. The estimated road slipperiness may be utilized when calculating a risk index for the road, or for an area including the road. If a predetermined threshold for slipperiness is exceeded, corrective actions may be taken. For instance, warnings may be generated to human drivers that are in control of driving vehicle, and autonomous vehicles may automatically adjust vehicle speed based upon road slipperiness detected.

In one embodiment, an exemplary method includes the operations of receiving, at a profiling application, a record file recorded by the ADV for a driving scenario in an area, and a high definition map matching the area; extracting planning messages and perception messages from the record file; and aligning the planning message and the perception messages based on their timestamps. The method further includes calculating an individual performance score for each planning cycle of the ADV for the driving scenario based on the planning messages; calculating a weight for each planning cycle based on the perception messages and the high definition map; and then calculating a weighted score for the driving scenario based on individual performance scores and their corresponding weights.