Method, control arrangement and machine learning based system for proactively acting on situations involving an increased traffic accident risk

摘要

Method (600) for creating an artificial intuition functionality, capable of proactively act on situations involving an increased traffic accident risk. The method (600) comprises: collecting (601) vehicle environmental data via at least one sensor (110a, 110b, 110c) in a manned vehicle (100a, 100b); detecting (602) a precautious driver action/ reaction, indicating an increased traffic accident risk; labelling (604) the vehicle environmental data at the moment when the precautious driver action/ reaction, is detected (602); extracting (605) vehicle environmental data to be used for learning, based on the labelled (604) vehicle environmental data; creating (606) an artificial intuition functionality, capable of proactively act on situations involving an increased traffic accident risk, by training a machine learning based system (200), based on the extracted (605) vehicle environmental data; and implementing (607) the created (606) artificial intuition functionality in a control arrangement (510) of an autonomous vehicle (500).