Automatically validating of signatures for object detection
A method that is automatically validating of signatures for object detection, the method includes automatically evaluating, by a controller, a signature being generated by an adaptable artificial intelligence (AI) system and stored in a memory, by determining whether the signature introduced an error in a previously accurate detection of an object; and triggering a response to address an outcome of the evaluating with respect to a problem found during the automatically evaluating.
1. A method that is automatically validating of signatures for object detection, the method comprises:
automatically evaluating, by a controller, a signature being generated by an adaptable artificial intelligence (AI) system and stored in a memory, by determining whether the signature introduced an error in a previously accurate detection of an object; and
triggering a response to address an outcome of the evaluating with respect to a problem found during the automatically evaluating;
wherein the signature is a candidate signature that was generated, following a detection of an error associated with an erroneous signature, by an error resolving part of the adaptable AI system; and
wherein the response comprises not replacing the erroneous signature by the candidate signature when finding that the signature candidate did introduce the error in the previously accurate detection of the object.
2. The method according to claim 1 , wherein the automatically evaluating comprises concurrently evaluating the signature and additional signatures being generated by the adaptable AI system.
3. The method according to claim 1 wherein the evaluation of the signature further comprising determining whether the signature accurately identifies objects that are similar to an object associated with the signature.
4. The method according to claim 1 wherein an automatically evaluating of the signature is triggered with a storing of the signature in the memory.
5. The method according to claim 1 wherein automatically evaluating is performed as part of a verification and validation process used in automotive testing.
6. The method according to claim 1 , wherein the signatures are indicative of an environment of a vehicle.
7. The method according to claim 6 , wherein the automatically evaluating is executed during a driving of the vehicle.
8. The method according to claim 1 wherein the response comprises not replacing the erroneous signature by the candidate signature when finding that the signature fails to accurately identify objects that are similar to an object associated with the signature.
9. A method that is automatically validating of signatures for object detection, the method comprises:
automatically evaluating, by a controller, a signature being generated by an adaptable artificial intelligence (AI) system and stored in a memory, by determining whether the signature introduced an error in a previously accurate detection of an object; and
triggering a response to address an outcome of the evaluating with respect to a problem found during the automatically evaluating;
wherein the signature is a candidate signature that was generated, following a detection of an error associated with an erroneous signature, by an error resolving part of the adaptable AI system; and
wherein the response comprises (a) replacing the erroneous signature by the candidate signature when finding that the signature candidate did not introduce the error in the previously accurate detection of the object, and (b) generating a routing rule for routing a sensed information unit (SIU) to the error resolving part of the adaptive AI system, when the other part of the adaptable AI system generates the erroneous signature following a reception of the SIU.
10. A non-transitory computer readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to automatically validating of signatures for object detection, comprising:
automatically evaluating, by a controller, a signature being generated by an adaptable artificial intelligence (AI) system and stored in a memory, by determining whether the signature rendered another previously accurate signature in the memory to be erroneous for a detection of an object; and
triggering a response to address an outcome of the evaluating with respect to a problem found during the automatically evaluating;
wherein the signature is a candidate signature that was generated, following a detection of an error associated with an erroneous signature, by an error resolving part of the adaptable AI system; and
wherein the response comprises not replacing the erroneous signature by the candidate signature when finding that the signature candidate did introduce the error in the previously accurate detection of the object.
11. The non-transitory computer readable medium according to claim 10 , wherein an automatically evaluating of the signature is triggered with a storing of the signature in the memory.
12. The non-transitory computer readable medium according to claim 10 , wherein automatically evaluating is performed as part of a verification and validation process used in automotive testing.
13. The non-transitory computer readable medium according to claim 10 wherein the response comprises not replacing the erroneous signature by the candidate signature when finding that the signature fails to accurately identify objects that are similar to an object associated with the signature.
14. A non-transitory computer readable medium storing instructions that, when executed by at least one processor, cause the at least one processor to automatically validating of signatures for object detection, comprising:
automatically evaluating, by a controller, a signature being generated by an adaptable artificial intelligence (AI) system and stored in a memory, by determining whether the signature rendered another previously accurate signature in the memory to be erroneous for a detection of an object; and
triggering a response to address an outcome of the evaluating with respect to a problem found during the automatically evaluating;
wherein the signature is a candidate signature that was generated, following a detection of an error associated with an erroneous signature, by an error resolving part of the adaptable AI system;
wherein the response comprises (a) replacing the erroneous signature by the candidate signature when finding that the signature candidate did not introduce the error in the previously accurate detection of the object, and (b) generating a routing rule for routing a sensed information unit (SIU) to the error resolving part of the adaptive AI system, when the other part of the adaptable AI system generates the erroneous signature following a reception of the SIU.