A vehicle for collecting image data of a target object for generating a classifier. The vehicle includes an image sensor and an electronic processor. The electronic processor is configured to determine a plurality of potential trajectories of the vehicle, determine, for each of the plurality of potential trajectories of the vehicle, a total number of views including the target object that would be captured by the image sensor as the vehicle moved along the respective trajectory, and determine a key trajectory of the vehicle from the plurality of potential trajectories based on the total number of views including the target of the key trajectory.

A method and system for target detection of a vehicle is proposed. In the method and system, when the vehicle is turning, a warning signal according to a risk level of collision is generated at the right timing as a risk level of collision between the host vehicle and the other vehicle behind the host vehicle may be accurately identified by correcting a driving path of the host vehicle and position of the other vehicle on the basis of a driving state of the host vehicle.

A host vehicle includes a rear image capturing device and a vehicle control device. The rear image capturing device captures an image of an area behind the host vehicle. The vehicle control device detects a lateral position of a following vehicle in the same lane as that in which the host vehicle travels, the following vehicle being reflected in the image captured by the rear image capturing device and traveling in the lane. The vehicle control device determines a lateral position of the host vehicle within a lane depending on the lateral position of the following vehicle within the same lane.

A method, apparatus, and system for executing a lane change is disclosed. That an ADV is in a lane changing region for an anticipated lane change into a neighboring target lane in a first direction is determined. The first direction is either a left direction or a right direction in a direction of travel of the ADV. A reference line is moved toward the target lane in the first direction at a predetermined rate while the reference line is kept within a current lane of the ADV. A gap in traffic for the anticipated lane change is searched for. Thereafter, in response to finding the gap in traffic for the anticipated lane change, the ADV is controlled to complete the lane change into the target lane.

A method, apparatus, and system for executing a lane change is disclosed. That an ADV is in a lane changing region for an anticipated lane change into a neighboring target lane in a first direction is determined. The first direction is either a left direction or a right direction in a direction of travel of the ADV. A reference line is moved toward the target lane in the first direction at a predetermined rate while the reference line is kept within a current lane of the ADV. A gap in traffic for the anticipated lane change is searched for. Thereafter, in response to finding the gap in traffic for the anticipated lane change, the ADV is controlled to complete the lane change into the target lane.

Provided are a vehicle lane-changing control method and a vehicle lane-changing control device. The method includes controlling a host vehicle to travel into a neighboring to-be-turned-into lane with a first control rule, acquiring a location relation between the host vehicle and a referential lane line in a real time manner. The referential lane line is located between the host vehicle and the to-be-turned-into lane. The method further includes determining whether the location relation meets a preset changing rule, and controlling an action of the host vehicle with a second control rule corresponding to the preset changing rule in a case that the location relation meets the preset changing rule.

A vehicle for collecting image data of a target object for generating a classifier. The vehicle includes an image sensor and an electronic processor. The electronic processor is configured to determine a plurality of potential trajectories of the vehicle, determine, for each of the plurality of potential trajectories of the vehicle, a total number of views including the target object that would be captured by the image sensor as the vehicle moved along the respective trajectory, and determine a key trajectory of the vehicle from the plurality of potential trajectories based on the total number of views including the target of the key trajectory.

Systems and method are provided for controlling a vehicle. In one embodiment, an obstacle management method includes receiving, via one or more sensing devices, sensor data relating to an environment associated with a vehicle, wherein the vehicle is substantially stationary and has an intended path corresponding to entering a traffic flow of a first lane. The method includes determining the presence of an obstacle that at least partially occludes a view of the first lane by a first sensing device of the one or more sensing devices, and positioning, with a processor, the vehicle with respect to the obstacle to improve the view of the first lane by the first sensing device without significantly obstructing the first lane. The first lane is then monitored via the first sensing device to determine when the intended path clear.

A host vehicle includes a rear image capturing device and a vehicle control device. The rear image capturing device captures an image of an area behind the host vehicle. The vehicle control device detects a lateral position of a following vehicle in the same lane as that in which the host vehicle travels, the following vehicle being reflected in the image captured by the rear image capturing device and traveling in the lane. The vehicle control device determines a lateral position of the host vehicle within a lane depending on the lateral position of the following vehicle within the same lane.

A method and system for target detection of a vehicle is proposed. In the method and system, when the vehicle is turning, a warning signal according to a risk level of collision is generated at the right timing as a risk level of collision between the host vehicle and the other vehicle behind the host vehicle may be accurately identified by correcting a driving path of the host vehicle and position of the other vehicle on the basis of a driving state of the host vehicle.