Method, machine readable medium, device, and vehicle for determining a route connecting a plurality of destinations in a road network, method, machine readable medium, and device for training a machine learning module

A method for determining a route connecting a plurality of destinations in a road network, the method comprising:

• receiving input information, which comprises information on routing distances between two destinations of each pair of destinations among the plurality of destinations in the road network, wherein a routing distance between two destinations of each pair is a road distance measured from one destination of the pair to the other destination of the pair on the road network;
• inputting the input information into a trained machine learning module;
• determining, by the trained machine learning module, a route connecting the plurality of destinations in the road network based on an overall routing distance of candidate routes connecting the plurality of destinations;
• and
• generating output information on the determined route,
• wherein the information on the routing distances comprises a matrix with mutual routing distances between two destinations of each pair of the plurality of destinations, and a mutual routing distance between two destinations of at least one pair is asymmetric.