Predicting AI models for autonomous driving per road segment

1 . A method of predictability of artificial intelligence models for activation using localization, the method comprises:

obtaining, by a computerized system of a vehicle, cross-statistical data relating to (a) an activation of a first set of artificial intelligence models, with an autonomous driving application, in association with a first road segment indication of a first road segment in a driving path of the vehicle and with respect to one or more first driving scenarios, and to (b) an activation of a second set of artificial intelligence models in association with a second road segment indication of a second road segment in the driving path of the vehicle and with respect to one or more second driving scenarios;

analyzing, the cross-statistical data with respect to one or more first artificial intelligence models of the first set currently activated in association with the first road segment; and

predicting, based on analysis of the cross-statistical data, an artificial intelligence model for activation in a driving of the vehicle when approaching the second road segment;

wherein the artificial intelligence models of the first set and of the second set are trained each, in a scenario-level learning by using sensed data captured in an environment of the vehicle, to provide a scenario-level decision making in accordance with a driving scenario, and further, by collecting special-purpose data relating directly to a specified road segment indication and reflecting behavioral data of drivers captured along a specified road segment, to provide a special-purpose decision making that is adaptive to the specified road segment indication, in accordance with the driving scenario.

2 . The method according to claim 1 , wherein the predicting involves determining the artificial intelligence model for activation in the driving of the vehicle upon receiving the second road segment indication.

3 . The method according to claim 1 , further comprising obtaining an indication regarding the currently activated one or more first artificial intelligence models of the first set.

4 . The method according to claim 1 , wherein the predicted artificial intelligence model is of the second set of artificial intelligence models.

5 . The method according to claim 1 , wherein the obtaining of the cross-statistical data comprises:

collecting first information regarding the activation of the first set of artificial intelligence models during a learning period;

collecting second information regarding the activation of the second set of artificial intelligence models during the learning period; and

processing the first information in accordance with the second information to provide the cross-statistical data.

6 . The method according to claim 1 , wherein the analyzing and the predicting are executed in a real time driving of the vehicle, with the activation of the first set of artificial intelligence models.

7 . The method according to claim 1 , wherein the cross-statistical is generated by applying a pattern analysis that is indicative of activation patterns of artificial intelligence models.

8 . The method according to claim 1 , further comprising uploading the predicted artificial intelligence model to a cache memory module of the vehicle, in association with the second road segment indication.

9 . A system of predictability of artificial intelligence models for activation using localization, the system comprising at least one processing device configured to:

obtain cross-statistical data relating to (a) an activation of a first set of artificial intelligence models, with an autonomous driving application, in association with a first road segment indication of a first road segment in a driving path of a vehicle and with respect to one or more first driving scenarios, and to (b) an activation of a second set of artificial intelligence models in association with a second road segment indication of a second road segment in the driving path of the vehicle and with respect to one or more second driving scenarios;

analyze the cross-statistical data with respect to one or more first artificial intelligence models of the first set currently activated in association with the first road segment; and

predict based on analysis of the cross-statistical data, an artificial intelligence model for activation in a driving of the vehicle when approaching the second road segment;

wherein the artificial intelligence models of the first set and of the second set are trained each, in a scenario-level learning by using sensed data captured in an environment of the vehicle, to provide a scenario-level decision making in accordance with a driving scenario, and further, by collecting special-purpose data relating directly to a specified road segment indication and reflecting behavioral data of drivers captured along a specified road segment, to provide a special-purpose decision making that is adaptive to the specified road segment indication, in accordance with the driving scenario.

10 . The system according to claim 9 , wherein the at least one processing device is further configured to upload the predicted artificial intelligence model to a cache memory module of the vehicle, in association with the second road segment indication.

11 . A non-transitory computer readable medium of artificial intelligence models for activation using localization that stores instructions that, when executable by at least one processing device, cause the device to:

obtain cross-statistical data relating to (a) an activation of a first set of artificial intelligence models, with an autonomous driving application, in association with a first road segment indication of a first road segment in a driving path of a vehicle and with respect to one or more first driving scenarios, and to (b) an activation of a second set of artificial intelligence models in association with a second road segment indication of a second road segment in the driving path of the vehicle and with respect to one or more second driving scenarios;

analyze the cross-statistical data with respect to one or more first artificial intelligence models of the first set currently activated in association with the first road segment; and

predict based on analysis of the cross-statistical data, an artificial intelligence model for activation in a driving of the vehicle when approaching the second road segment;

wherein the artificial intelligence models of the first set and of the second set are trained each, in a scenario-level learning by using sensed data captured in an environment of the vehicle, to provide a scenario-level decision making in accordance with a driving scenario, and further, by collecting special-purpose data relating directly to a specified road segment indication and reflecting behavioral data of drivers captured along a specified road segment, to provide a special-purpose decision making that is adaptive to the specified road segment indication, in accordance with the driving scenario.

12 . The non-transitory computer readable medium according to claim 11 , wherein the predicting involves determining the artificial intelligence model for activation in the driving of the vehicle upon receiving the second road segment indication.

13 . The non-transitory computer readable medium according to claim 11 , further storing instructions that, when executable by the at least one processing device, cause the device to obtain an indication regarding the currently activated one or more first artificial intelligence models of the first set.

14 . The non-transitory computer readable medium according to claim 11 , wherein the predicted artificial intelligence model is of the second set of artificial intelligence models.

15 . The non-transitory computer readable medium according to claim 11 , wherein the obtaining of the cross-statistical data comprises:

collecting first information regarding the activation of the first set of artificial intelligence models during a learning period;

collecting second information regarding the activation of the second set of artificial intelligence models during the learning period; and

processing the first information in accordance with the second information to provide the cross-statistical data.

16 . The non-transitory computer readable medium according to claim 11 , wherein the analyzing and the predicting are executed in a real time driving of the vehicle, with the activation of the first set of artificial intelligence models.

17 . The non-transitory computer readable medium according to claim 11 , wherein the cross-statistical data is generated by applying a pattern analysis that is indicative of activation patterns of artificial intelligence models.

18 . The non-transitory computer readable medium according to claim 11 , further storing instructions that, when executable by the at least one processing device, cause the device to upload the predicted artificial intelligence model to a cache memory module of the vehicle, in association with the second road segment indication.