Apparatus, method, and computer program for collecting feature data
An apparatus for collecting feature data includes a memory configured to store map information including a probability distribution of reliability indicating how likely a feature related to travel of vehicles exists as a function of position; and one or more processors configured to store feature data indicating the position of the feature in the memory whenever receiving the feature data from any of one or more vehicles via a communication circuit, update the probability distribution of reliability indicating how likely the feature exists as a function of position, based on the position of the feature indicated by each of one or more pieces of received feature data, and transmit an instruction to stop collecting the feature data to the one or more vehicles via the communication circuit for a feature regarding which the extent of the updated probability distribution is not greater than a predetermined threshold.
1. A method for collecting feature data, comprising:
storing feature data indicating the position of a feature related to travel of vehicles in a memory whenever receiving the feature data from any of one or more vehicles via a communication circuit capable of communicating with the vehicles;
updating a probability distribution of reliability indicating how likely the feature exists as a function of position, based on the position of the feature indicated by each of one or more pieces of received feature data, the probability distribution being included in map information, wherein the function of the position indicates increasing reliability depending on distance to the feature decreasing;
transmitting an instruction to stop collecting the feature data to the one or more vehicles via the communication circuit when the extent of the updated probability distribution is not greater than a predetermined threshold; and
stopping collecting the feature data by a processor mounted on each of the one or more vehicles receiving the instruction to stop collecting the feature data,
wherein the probability distribution is expressed as a normal distribution, and
wherein the method further comprises at least one of:
determining, when a variance value in any direction of the updated probability distribution is equal to or less than a predetermined variance threshold, that the extent of the updated probability distribution is not greater than the predetermined threshold, and
determining, when reliability at an average position in the updated probability distribution is not less than a predetermined reliability threshold, that the extent of the updated probability distribution is not greater than the predetermined threshold.
2. The method according to claim 1 , wherein the feature data further includes information indicating the distance between a vehicle of the one or more vehicles that has generated the feature data and the position of the feature indicated by the feature data, and
the method further comprises increasing contribution of the feature data to update of the probability distribution as the distance decreases.