Autonomous vehicle capable of precise position correction based on collaborative cognition and method for correcting the same

An autonomous vehicle capable of precise position correction based on collaborative cognition, comprising:

• a sensor module composed of a predetermined sensor for detecting an object;
• a communication module receiving a shared message from at least one of a first vehicle (another connected vehicle (CV) or another connected automated vehicle (CAV)) and a road infrastructure device capable of V2X communication existing on the road, receiving the shared message including driving status information of the other CV when the first vehicle is the other CV, and receiving the driving status information of the other CAV and the shared message about a second vehicle (the second vehicle is a vehicle in which the V2X communication is not possible) recognized by the other CAV;
• a memory storing a program for estimating and correcting object information based on the shared message and sensing data of the sensor module;
• and
• a processor executing a program stored in the memory to estimate object information from the sensing data, calculating an estimated error by comparing the estimated object information and the shared message, and setting a radius (when the first vehicle is another CV, it means the reference radius, and when the first vehicle is another CAV, it means a recognition radius) based on the first vehicle corresponding to an estimated error application radius,
• wherein the processor is configured to comprehensively determine the radius based on distance information between the autonomous vehicle and the first vehicle, cognitive accuracy for the first vehicle, and the estimated error,
• wherein the radius defines a target area for selecting the second vehicle to which position correction is to be applied,
• wherein the target area is configured as one of a circular area, a peanut-shaped area, or an area partially extended outward from the circular area,
• wherein the processor is configured to calculate the estimated error through an interpolation method using a plurality of estimated error values configured in a two-dimensional or three-dimensional surface form,
• wherein the processor is configured to use the estimated error for position correction only when the estimated error satisfies a predetermined threshold value.