Control transfer of a vehicle
A method for detecting obstacles, the method may include receiving, from a plurality of vehicles, and by an I/O module of a computerized system, visual information acquired during executions of vehicle maneuvers that are suspected as being obstacle avoidance maneuvers; determining, based at least on the visual information, at least one visual obstacle identifier for visually identifying at least one obstacle; and transmitting to one or more of the plurality of vehicles, the at least one visual obstacle identifier.
1. A method for finding a trigger for human intervention in a control of a vehicle, the method comprises:
receiving, from a plurality of vehicles, and by an I/O module of a computerized system that is located outside the plurality of vehicles, visual information acquired during situations that are suspected as situations that require human intervention in the control of the vehicle;
determining, based at least on the visual information, what amounts to the trigger for human intervention, wherein the human intervention comprises handing over a control of a vehicle from an autonomous driving manager of the vehicle to a human driver; and
transmitting, by the computerized system, to the vehicle of the trigger visual information that represents the trigger;
receiving by a processing circuitry of the vehicle the trigger visual information;
acquiring, by a visual sensor of the vehicle, images of an environment of the vehicle;
searching, by the processing circuit of the vehicle, images of the environment of the vehicle for a situation that is identified by the trigger visual information; and
when finding the situation that is identified by the trigger visual information then triggering the human intervention in the control of the vehicle.
2. The method according to claim 1 wherein the determining of what amounts to the at least one trigger for human intervention is based on an outcome of an unsupervised learning process.
3. The method according to claim 1 wherein the determining of what amounts to the at least one trigger for human intervention is responsive to at least one human intervention policy of the at least one vehicle.
4. The method according to claim 1 wherein the determining of what amounts to the at least one trigger for human intervention comprises determining a complexity of the situation.
5. The method according to claim 1 wherein the determining of what amounts to the at least one trigger for human intervention comprises determining a danger level associated with the situation.
6. The method according to claim 1 wherein the determining what amounts to is responsive to statistics of maneuvers executed by different vehicles during a same situation that is suspected as a situation that requires human intervention in the control of at least one of the plurality of vehicles.
7. The method according to claim 1 comprising generating or receiving movement information of entities included in the visual information; and wherein the determining of what amounts to the at least one trigger is also responsive to the movement information.
8. The method according to claim 7 wherein the movement information represents entity movement functions of the entities, wherein the method comprises estimating, based on the entity movement functions, a future movement of the entities.
9. The method according to claim 1 wherein the determining is also based on verification information indicative of whether a maneuver related to a situation that is suspected as requiring human intervention in the control of a vehicle is actually related to a situation that actually requires human intervention in the control of the vehicle.
10. A non-transitory computer readable medium that stores instructions for:
receiving, from a plurality of vehicles, and by an I/O module of a computerized system that is located outside the plurality of vehicles, visual information acquired during situations that are suspected as situations that require human intervention in a control of the vehicle;
determining, based at least on the visual information, of what amounts to the at least one trigger for human intervention, wherein the human intervention comprises handing over a control of a vehicle from an autonomous driving manager of the vehicle to a human driver; and
transmitting, by the computerized system, to the vehicle of the, trigger visual information that represents the trigger;
receiving by a processing circuitry of the vehicle the trigger visual information;
acquiring, by a visual sensor of the vehicle, images of an environment of the vehicle;
searching, by the processing circuit of the vehicle, images of the environment of the vehicle for a situation that is identified by the trigger visual information; and
when finding the situation that is identified by the trigger visual information then triggering the human intervention in the control of the vehicle.
11. The non-transitory computer readable medium according to claim 10 wherein the determining of what amounts to the at least one trigger for human intervention is executed in an unsupervised manner.
12. The non-transitory computer readable medium according to claim 10 wherein the determining of what amounts to the at least one trigger for human intervention is responsive to at least one human intervention policy of the at least one vehicle.
13. The non-transitory computer readable medium according to claim 10 wherein the determining of what amounts to the at least one trigger for human intervention comprises determining a complexity of the situation.
14. The non-transitory computer readable medium according to claim 10 wherein the determining of what amounts to the at least one trigger for human intervention comprises determining a danger level associated with the situation.
15. The non-transitory computer readable medium according to claim 10 wherein the determining of what amounts to the at least one trigger for human intervention is responsive to statistics of maneuvers executed by different vehicles during a same situation that is suspected as a situation that requires human intervention in the control of at least one of the plurality of vehicles.
16. The non-transitory computer readable medium according to claim 10 that stores instructions for generating or receiving movement information of entities included in the visual information; and wherein the determining of what amounts to the at least one trigger is also responsive to the movement information.
17. The non-transitory computer readable medium according to claim 16 wherein the movement information represents entity movement functions of the entities; wherein the non-transitory computer readable medium stores instructions for estimating, based on the entity movement functions, a future movement of the entities.
18. The non-transitory computer readable medium according to claim 17 that stores instructions for wherein the determining is also based on verification information indicative of whether a maneuver related to a situation that is suspected as requiring human intervention in the control of a vehicle is actually related to a situation that actually requires human intervention in the control of the vehicle.
19. The method according to claim 1 wherein the trigger visual information is generated based on visual information acquired by at least one visual sensor during an execution of at least vehicle maneuver that is suspected as being an obstacle avoidance maneuver.