A method for child forward collision warning, the method may include sensing sensed information about an environment of a vehicle; detecting, based on the sensed information, a situation related to the environment; detecting, based on the sensed information, one or more children within the environment; classifying each child of the one or more children to a class; predicting, using a machine leaning process, a future behavior of the one or more children and an impact of the future behavior of the one or more children on a future progress of the vehicle; wherein the predicting of each child of the one or more children is responsive to a class of the child and to the situation; and responding to the predicting.