Estimating danger from future falling cargo

1. A method for estimating a future fall of a cargo conveyed by a monitored vehicle, the method comprising:

receiving, by a monitoring vehicle, one or more future falling cargo predictors for multiple types of cargo that were learnt by applying a machine learning process;

sensing, by at least one sensor of the monitoring vehicle, to provide monitoring results;

determining, by a processor that belongs to the monitoring vehicle, a cargo class carried by the monitored vehicle;

estimating, by the processor of the monitoring vehicle, and based on the cargo class and a future falling cargo predictor associated with the cargo class, whether the cargo conveyed by the monitored vehicle will fall before the monitoring vehicle will pass the monitored vehicle; and

responding to the estimating, wherein the responding comprises amending, autonomously, a driving pattern of the monitoring vehicle during an autonomous driving of the vehicle.

2. The method according to claim 1 , wherein the future falling cargo predictor associated with the cargo class is indicative of a behavior of a vehicle conveying the cargo that contributes to the future fall of cargo; and wherein the estimating is based, at least in part, on the behavior of the monitored vehicle.

3. The method according to claim 1 , wherein the future falling cargo predictor associated with the cargo class is indicative of an attribute of a road that contributes to the future fall of the cargo; and wherein the estimating is based, at least in part, on a road over which the monitored vehicle is driving or is about to drive.

4. A non-transitory computer readable medium for estimating a future fall of a cargo conveyed by a monitored vehicle, the non-transitory computer readable medium stores instructions for:

receiving, by a monitoring vehicle, one or more future falling cargo predictors for multiple types of cargo that were learnt by applying a machine learning process;

sensing, by at least one sensor of the monitoring vehicle, to provide monitoring results;

determining, by a processor that belongs to the monitoring vehicle, a cargo class carried by the monitored vehicle;

estimating, by the processor that belongs to the monitoring vehicle, and based on the cargo class and a future falling cargo predictor associated with the cargo class, whether the cargo conveyed by the monitored vehicle will fall before the monitoring vehicle will pass the monitored vehicle; and

responding to the estimating, wherein the responding comprises amending, autonomously, a driving pattern of the monitoring vehicle during an autonomous driving of the vehicle.

5. The non-transitory computer readable medium according to claim 4 , wherein the future falling cargo predictor associated with the cargo class is indicative of a behavior of a vehicle conveying the cargo that contributes to a future falling of cargo; and wherein the estimating is based, at least in part, on the behavior of the monitored vehicle.

6. The non-transitory computer readable medium according to claim 4 , wherein the future falling cargo predictor associated with the cargo class is indicative of an attribute of a road that contributes to the future fall of the cargo; and wherein the estimating is based, at least in part, on a road over which the monitored vehicle is driving or is about to drive.

7. The non-transitory computer readable medium according to claim 4 wherein the one or more future falling cargo predictors were generated by receiving, by a computerized system, sensed information related to driving sessions of multiple vehicles; applying a machine learning process on the sensed information to detect actual or estimated cargo falling events; and generating the one or more future falling cargo predictors for multiple types of cargo.

8. The method according to claim 1 wherein the applying of the machine learning process comprises applying the machine learning process on sensed information related to driving sessions of multiple vehicles; wherein the applying of the machine learning process comprises detecting actual or estimated cargo falling events and generating the one or more future falling cargo predictors for multiple types of cargo.

9. The method according to claim 8 further comprising estimating, from the sensed information related to driving sessions of multiple vehicles, an impact of the actual or estimated cargo falling events related to at least some of the multiple types of cargo.

10. The method according to claim 9 further comprising responding to the estimating.

11. The method according to claim 8 , further comprising determining suggested vehicle behavior in response to the actual or estimated cargo falling events related to the at least some of the multiple types of cargo.

12. The method according to claim 8 , further comprising detecting a behavior of a vehicle conveying a cargo of a certain type that contributes to falling of the cargo of the certain type; and associating an indication of the behavior with a future falling cargo predictor for the certain type.

13. The method according to claim 1 , wherein the applying of the machine learning process comprises training the machine learning process with samples of cargos of the multiple types and with samples of cases where the cargos of the multiple types fell.

14. The method according to claim 8 , wherein the applying of the machine learning process comprises identifying spatial relationships between cargo of the multiple types and vehicles conveying the cargo of the multiple types and an outcome of the conveying of the cargo of the multiple types.