Electrical scooter alert

1. A method for electrical scooter alert, the method comprises:

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, a electrical scooter within the environment;

predicting, using a machine leaning process and based in the situation, a future behavior of the electrical scooter and an impact of the future behavior of the electrical scooter on a future progress of the vehicle; and

responding to the predicting; and

wherein the machine learning is trained by a training process that comprises:

generating electrical scooter identifiers based on a first set of tagged sensed information units and a second set of untagged sensed information units;

monitoring behaviors of electrical scooters at multiple situations to provide monitoring results, wherein the monitoring comprises detecting one or more electrical scooter identifiers within sensed information units obtained during one or more monitoring periods; and

generating, based on the monitoring results, situation behavioral information indicative of behaviors of electrical scooters at different situations.

2. The method according to claim 1 wherein the responding to the predicting is responsive to a probability distribution of potential future behaviors of the electrical scooter.

3. The method according to claim 1 wherein the responding is responsive to an existence of at least one potential relevant future behavior of the electrical scooter, wherein each of the at least potential relevant future behavior of the electrical scooter (a) has probability of occurrence that exceeds a threshold, and (b) impacts the future progress of the vehicle when occurs.

4. The method according to claim 1 wherein the responding is selected out of generating a human perceivable information about the predicting, requesting an autonomous module to drive the vehicle based on the predicting; proposing a route of the vehicle; storing an outcome of the predicting; activating a driving mode in response to the outcome of the predicting; activating safety measures in response to the outcome of the predicting; and generating a human perceivable alert outside the vehicle.

5. The method according to claim 1 comprising classifying the electrical scooters to classes; and wherein the training process comprises generating situation behavioral information indicative of behaviors of electrical scooters of different classes at different situations.

6. The method according to claim 1 wherein the generating of the electrical scooter identifiers comprises generating signatures of the electrical scooters.

7. The method according to claim 6 comprising clustering the signatures of electrical scooters to generate electrical scooter classes.

8. A non-transitory computer readable medium for electrical scooter alert, the non-transitory computer readable medium comprises:

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, a electrical scooter within the environment;

predicting, using a machine leaning process and based in the situation, a future behavior of the electrical scooter and an impact of the future behavior of the electrical scooter on a future progress of the vehicle; and

responding to the predicting; and

wherein the machine learning is trained by a training process that comprises:

generating electrical scooter identifiers based on a first set of tagged sensed information units and a second set of untagged sensed information units;

monitoring behaviors of electrical scooters at multiple situations to provide monitoring results, wherein the monitoring comprises detecting one or more electrical scooter identifiers within sensed information units obtained during one or more monitoring periods; and

generating, based on the monitoring results, situation behavioral information indicative of behaviors of electrical scooters at different situations.

9. The non-transitory computer readable medium according to claim 8 wherein the responding to the predicting is responsive to a probability distribution of potential future behaviors of the electrical scooter.

10. The non-transitory computer readable medium according to claim 8 wherein the responding is responsive to an existence of at least one potential relevant future behavior of the electrical scooter, wherein each of the at least potential relevant future behavior of the electrical scooter (a) has probability of occurrence that exceeds a threshold, and (b) impacts the future progress of the vehicle when occurs.

11. The non-transitory computer readable medium according to claim 8 wherein the responding is selected out of generating a human perceivable information about the predicting, requesting an autonomous module to drive the vehicle based on the predicting; proposing a route of the vehicle; storing an outcome of the predicting; activating a driving mode in response to the outcome of the predicting; activating safety measures in response to the outcome of the predicting; and generating a human perceivable alert outside the vehicle.

12. The non-transitory computer readable medium according to claim 8 that stores instructions for classifying the electrical scooters to classes; and wherein the training process comprises generating situation behavioral information indicative of behaviors of electrical scooters of different classes at different situations.

13. The non-transitory computer readable medium according to claim 8 wherein the generating of the electrical scooter identifiers comprises generating signatures of the electrical scooters.

14. The non-transitory computer readable medium according to claim 13 that stores instructions for clustering the signatures of electrical scooters to generate electrical scooter classes.