Advanced flight processing system and/or method
The method can include: determining sensor information with an aircraft sensor suite; based on the sensor information, determining a flight command using a set of models; validating the flight command S 130 ; and facilitating execution of a validated flight command. The method can optionally include generating a trained model. However, the method S 100 can additionally or alternatively include any other suitable elements. The method can function to facilitate aircraft control based on autonomously generated flight commands. The method can additionally or alternatively function to achieve human-in-the-loop autonomous aircraft control, and/or can function to generate a trained neural network based on validation of autonomously generated aircraft flight commands.
1. An aircraft system comprising:
an autonomous computing system communicatively coupled to a sensor suite onboard an aircraft, the autonomous computing system comprising a set of pre-trained neural networks, wherein the autonomous computing system is configured to determine a flight command with the set of pre-trained neural networks based on sensor data from the sensor suite;
an aircraft computing system partitioned from the autonomous computing system and communicatively coupled to the autonomous computing system, the aircraft computing system comprising:
a pilot validation interface communicatively coupled to a flight management system (FMS), the pilot validation interface configured to:
facilitate pilot validation of the flight command in a human-interpretable format; and
in response to pilot validation of the flight command, automatically facilitate execution of the flight command via the flight management system (FMS),
wherein the autonomous computing system is onboard the aircraft and the aircraft computing system partitioned from the autonomous computing system by a firewall.
2. The aircraft system of claim 1 , wherein the sensor data comprises unstructured information, wherein the set of pre-trained neural networks are configured to autonomously determine the flight command in a predetermined, machine-readable format from the unstructured information.
3. The aircraft system of claim 2 , further comprising: an application programming interface (API) communicatively coupled to the autonomous computing system and the pilot validation interface, the API configured to:
receive the flight command from the autonomous computing system;
automatically validate adherence of the flight command to the predetermined, machine-readable data format; and
provide the flight command to the pilot validation interface based on the automatic validation of flight command adherence to the predetermined, machine-readable data format.
4. The aircraft system of claim 3 , wherein the API is further configured to automatically validate adherence of the flight command to the predetermined, machine-readable data format with a hash function or a checksum.
5. The aircraft system of claim 3 , wherein the API is further configured to automatically validate the flight command based on a flight envelope.
6. The aircraft system of claim 1 , wherein the human-interpretable format comprises a human-readable format, wherein the pilot validation interface comprises a display, wherein the pilot validation interface is configured to provide the flight command at the display in the human-readable format.
7. The aircraft system of claim 6 , wherein pilot validation comprises: automatic acceptance of the flight command based on satisfaction of a validation condition.
8. The aircraft system of claim 7 , wherein the validation condition comprises a pilot response time threshold.
9. The aircraft system of claim 1 , wherein the autonomous computing system comprises a multi-core processor.
10. The aircraft system of claim 1 , wherein the flight command comprises a resolution advisory.
11. The aircraft system of claim 1 , wherein the sensor data comprises an air traffic control (ATC) audio signal, wherein the autonomous computing system comprises:
a speech-to-text module configured to determine an utterance hypothesis from the ATC audio signal with a first pre-trained neural network of the set; and
a question-and-answer (Q/A) module configured to determine the flight command based on the utterance hypothesis using a plurality of natural language queries, wherein the question-and-answer (Q/A) module is configured to determine aircraft commands by querying the utterance hypothesis with a second pre-trained neural network of the set according to a structured sequence of the natural language queries.
12. The aircraft system of claim 1 , wherein the sensor suite comprises a set of time-of-flight sensors and the sensor data comprises time-of-flight data from the set of time-of-flight sensors, wherein the autonomous computing system is configured to:
identify features based on the time-of-flight data using a pre-trained neural network of the set; and
autonomously determine the flight command based on the identified features.
13. A method for control of an aircraft, the method comprising:
determining sensor information with a sensor suite of the aircraft;
based on the sensor information, determining a flight command with an autonomous computing system onboard the aircraft using a set of pre-trained models of the autonomous computing system;
receiving the flight command at an application program interface (API) which is partitioned from the autonomous computing system;
validating the flight command, comprising:
in response to receiving the flight command at the API, validating a format compliance of the flight command received at the API;
in response to validating the format compliance of the flight command received at the API, providing the flight command in a human-interpretable format at a pilot validation interface; and
based on the provision of the flight command in the human-interpretable format at the pilot validation interface, determining a pilot validation of the flight command using the pilot validation interface; and
in response to determining the pilot validation, automatically facilitating execution of the flight command.
14. The method of claim 13 , wherein the sensor information is unstructured, wherein the flight command comprises a predetermined machine-readable data structure, wherein validating format compliance comprises validating adherence to the predetermined machine-readable data structure.
15. The method of claim 13 , wherein determining the pilot validation comprises receiving a pilot confirmation at the pilot validation interface.
16. The method of claim 13 , wherein automatically facilitating execution of the flight command comprises providing the flight command to a flight management system (FMS) and executing the command via a flight control system (FCS).
17. The method of claim 14 , further comprising:
determining a second flight command with the autonomous computing system of the aircraft using the set of pre-trained models of the autonomous computing system;
receiving the second flight command at the API;
providing the second flight command at a pilot validation interface;
determining a pilot override of the second flight command with the pilot validation interface, the pilot override comprising a third flight command; and
in response to determining the pilot override, automatically facilitating execution of the third flight command.
18. The method of claim 17 , further comprising: updating at least one of the set of pre-trained models of the autonomous computing system based on the pilot override.
19. The method of claim 13 , wherein the sensor information comprises an air traffic control (ATC) audio signal, wherein determining the flight command comprises:
with a speech-to-text module of the autonomous computing system, determining an utterance hypothesis from the ATC audio signal using a first pre-trained neural network model of the set of pre-trained models; and
with a question-and-answer (Q/A) module of the autonomous computing system, determining the flight command based on the utterance hypothesis by querying the utterance hypothesis with a second pre-trained neural network model of the set of pre-trained models according to a structured sequence of the natural language queries.