Self-correcting controller systems and methods of limiting the operation of neural networks to be within one or more conditions
Systems and methods for automatically self-correcting or correcting in real-time one or more neural networks after detecting a triggering event, or breaching boundary conditions are provided. Such a triggering event may indicate incorrect output signal or data being generated by the one or more neural networks. In particular, machine controllers of the invention limit the operations of neural networks to be within boundary conditions. Autonomous machines of the invention can be self-corrected after a breach of a boundary condition is detected. Autonomous land vehicles of the invention are capable of determining the timing of automatic transition to the manual control from automated driving mode. The controller of the invention filters and saves input-output data sets that fall within boundary conditions for later training of neural networks. The controllers of the invention include security architectures to prevent damages from virus attacks or system malfunctions.
1. A system, configured for self-correcting, for an autonomous machine having a plurality of sensors, the system comprising:
a first neural network with at least one hidden layer deployed on the autonomous machine, trained with a first training data set, and configured to generate first output data after processing a set of input data;
a first processor deployed remote from the autonomous machine coupled to the first neural network, including:
i) a detector adapted to receive the first output data and to determine whether the first output data breach a first predetermined condition;
ii) a neural network manager coupled to the first neural network and adapted to re-train the first neural network using a second training data set stored on the autonomous machine if the detector determines the first output data breach the first predetermined condition, wherein the second training data is different from the first training data set; and
a database management system coupled to the detector and constructed to receive and store the set of input data and the corresponding first output data if the detector determines the corresponding first output data does not breach the first predetermined condition, wherein the database management system is further adapted to retrieve the stored input data and the corresponding output data to form the second training data set.
2. The system of claim 1 , wherein the second training data set includes data generated by a sensor on the autonomous machine.
3. The system of claim 1 , the system further includes a second neural network with at least one hidden layer deployed on the autonomous machine, the second neural network structured and trained identical to the first neural network to generate a second output by processing the set of input data, wherein the first and second neural networks are executed simultaneously.
4. The system of claim 3 , wherein the first processor is further configured to operate only the second neural network if the detector determines the first output data breach the first predetermined condition.
5. The system of claim 1 , wherein the first predetermined condition is unchangeable after an initial installation onto the control system.
6. The system of claim 3 , further comprising a second processor configured to execute the first and second neural networks.
7. A method of controlling an autonomous machine using a system configured with one or more processors, the system configured for self-correcting, the method comprising:
generating first output data after processing a set of input data using a first neural network with at least one hidden layer on the autonomous machine, wherein the first neural network is trained with a first training data set;
processing the first output data and to determine whether the first output data breach a first predetermined condition;
storing the set of input data and the corresponding first output data if the detector determines the corresponding first output data does not breach the first predetermined condition;
retrieving the stored set of input data and the corresponding output data to form a second training data set; and
re-training the first neural network using the second training data set stored on the autonomous machine if the first output data is determined to breach the first predetermined condition, wherein the second training data is different from the first training data set.
8. The method of claim 7 , wherein the second training data set includes data generated by a sensor on the autonomous machine.
9. The method of claim 7 , further comprising:
executing, simultaneously with the first neural network, a second neural network with at least one hidden layer structured and trained identical to the first neural network to generate a second output by processing the input data from the input device.
10. The method of claim 9 , further comprising:
executing the first and second neural networks on a first thread on the one or more processors; and
executing the steps of processing the first output data and re-training the first neural network on a second thread of the one or more processors.
11. The method of claim 9 , further comprising:
executing the first neural network on a first thread on the one or more processors; and
executing the second neural network on a second thread of the one or more processors.
12. The method of claim 7 , wherein the first predetermined condition is unchangeable after an initial installation onto the control system.
13. A system, capable of self-correcting, for controlling an autonomous machine having a plurality of sensors, the system comprising:
a first neural network with at least one hidden layer deployed on the autonomous machine, trained with a first training data set, and configured to generate first output data after processing a set of input data;
a first processor coupled to the first neural network, including:
i) a detector means for receiving the first output data and to determine whether the first output data breach a first predetermined condition; and
ii) a neural network manager means coupled to the first neural network and for re-training the first neural network using a second training data set retrieved from a memory component on the autonomous machine if the detector determines the first output data breach the first predetermined condition, wherein the second training data is different from the first training data set; and
a database management system coupled to the detector, the database management system configured to receive and store the input data and the corresponding first output data if the detector determines the corresponding first output data does not breach the first predetermined condition, the database management system further configured to retrieve the stored input data and the corresponding output data to form the second training data set.
14. The system of claim 13 , wherein the second training data set includes data generated by a sensor on the autonomous machine.
15. The system of claim 13 , the system further comprises:
a second neural network with at least one hidden layer structured deployed on the autonomous machine and trained identical to the first neural network, the second neural network configured to generate a second output by processing the input data from the input device, wherein the first and second neural networks are executed simultaneously.