DETERMINING DRIVING FEATURES USING CONTEXT-BASED NARROW AI AGENTS SELECTION
A method for determining driving related features of a vehicle, which may include repeating, during each time interval out of multiple time intervals of a period: obtaining sensed information during at least a part of the time interval; selecting, based on a predefined decision, a selected sub-set of narrow artificial intelligence (AI) agents; and calculating one or more driving related feature. The calculating may include applying the selected sub-set of narrow AI agents on the sensed information.
1 . A method for determining driving related features of a vehicle, the method comprises:
repeating, during each time interval out of multiple time intervals of a period:
obtaining sensed information during at least a part of the time interval;
selecting, based on a predefined decision, a selected sub-set of narrow artificial intelligence (AI) agents; and
calculating one or more driving related feature, wherein the calculating comprises applying the selected sub-set of narrow AI agents on the sensed information.
2 . The method according to claim 1 wherein the period comprises multiple repetitions of a sub-period; wherein each sub-period comprises N time intervals, N being a positive integer that exceeds one; wherein the method comprises applying a n'th sub-set of narrow AI agents during an n'th time intervals of different sub-periods, n ranged between 1 and N.
3 . The method according to claim 2 wherein a most frequently selected sub-set of narrow AI agents comprises a narrow AI agent allocated for detection of road users selected out of vehicles and pedestrians.
4 . The method according to claim 3 wherein a less frequently selected sub-set of narrow AI agents comprises a narrow AI agent allocated for lane detection.
5 . The method according to claim 3 wherein a less frequently selected sub-set of narrow AI agents comprises a narrow AI agent allocated for traffic light detection.
6 . The method according to claim 1 wherein the applying the selected sub-set of narrow AI agents on the sensed information provides at least one narrow AI output; and wherein the calculating further comprises processing the at least one narrow AI output to provide the one or more driving related feature.
7 . The method according to claim 1 comprising autonomously driving the vehicle based on the at least one driving related feature.
8 . The method according to claim 1 comprising performing an advance driver assistance system (ADAS) operation based on the at least one driving related feature.
9 . The method according to claim 1 wherein the obtaining of the sensed information during at least the part of the time interval comprises applying a field of view associated with the time interval.
10 . The method according to claim 1 wherein the obtaining of the sensed information during at least the part of the time interval comprises focusing on a certain range of detection associated with the time interval.
11 . The method according to claim 1 wherein the obtaining of the sensed information during at least the part of the time interval comprises acquiring the sensed information at a rate that is associated with the time interval.