Method and apparatus for recognizing shape of road for vehicles

摘要

An example of recognition of the shape of a road where a vehicle travels is provided. An object type as to whether an object is a moving or stationary object is determined according to a relative speed of the object and a speed of the vehicle. Object-unit data effective for recognizing a road shape is extracted according to the determination. The object-unit data is used for forming data of a roadside object group, based on which a road edge is recognized. A series of the processes is repeatedly performed at a predetermined cycle. After the extraction process, a data addition process is performed to add object-unit data obtained in the extraction process of the previous cycle to object-unit data obtained in the extraction process of the present cycle. In a recognition process, a road edge is recognized according to the object-unit data obtained in the data addition process.

主权项

1. A road-shape recognition method for vehicles, comprising:
detecting, by a turn calculator mounted in a vehicle, a turning condition of the vehicle; calculating, by a curvature calculator mounted in the vehicle, a curvature of a travelling road where the vehicle travels, from the turning condition of the vehicle and a speed of the vehicle; detecting, by a radar mounted in the vehicle, a distance to a reflector and an angle to the reflector relative to a vehicle's width direction on the basis of a reflected wave that is a reflection of a transmitted wave radiated over a predetermined angular range in the vehicle's width direction; calculating, by an object recognizing unit mounted in the vehicle, a relative position of the object on the basis of the detected distance and the angle in the vehicle's width direction; calculating, by a lane probability calculator mounted in the vehicle, a first lane probability that is a probability that an object to be recognized is on the same lane where the vehicle to which the method is applied travels, on the basis of the calculated curvature of the travelling road where the vehicle travels and the calculated relative position of the object relative to the vehicle; determining, by the object recognizing unit, an object type as to whether each of objects is a moving object or a stationary object, according to a relative speed of the object and a speed of the vehicle; recognizing, by a road-shape recognizing unit mounted in the vehicle, a road shape ahead of the vehicle according to extracted stationary object data effective for recognizing a road shape, while extracting the stationary object data using the relative position of the object and the determined object type; determining, by a same-lane determining unit mounted in the vehicle, a second lane probability that the object is on the same lane where the vehicle travels, according to the recognized road shape ahead of the vehicle and a degree of the recognition, the road shape being recognized according to a distance to the object and an angle to the object in a vehicle's width direction; calculating, by a correction value calculator mounted in the vehicle, a correction value used for correcting the first lane probability in conformity with the determination of the second lane probability; and determining, by the lane probability calculator, whether or not there is a difference between the calculated curvature of the travelling road where the vehicle travels and a curvature of the recognized road shape ahead of the vehicle to correct the first lane probability using the correction value when there is no difference, or not to correct the first lane probability using the correction value when there is a difference.