Aircraft control system failure event search

A method for use with a computing device, the method comprising:

• receiving a specification of a search space over a plurality of inputs to an aircraft control system;
• performing a Monte Carlo tree search (MCTS) to identify an adversarial branch of the search space, wherein performing the MCTS includes, in each of a plurality of partitioning steps:
• computing a plurality of discrete branches of the search space at least in part by:
• computing a plurality of sample objective function values of a partitioning objective function for different respective sample input values of the inputs included in a current-iteration portion of the search space;
• estimating a probability density function of the partitioning objective function over the current-iteration portion of the search space based at least in part on the sample objective function values;
• and
• partitioning the current-iteration portion of the search space into the discrete branches based at least in part on the probability density function, wherein:
• the discrete branches each include a respective temporal sequence of event nodes that indicate a plurality of temporally ordered events and have corresponding estimated event probabilities;
• and
• the plurality of event probabilities include a plurality of failure event probabilities of a respective plurality of failure events;
• at a multi-agent system model that includes a plurality of supervised learning models, recomputing the estimated event probabilities associated with each of a plurality of event nodes included in the discrete branches;
• and
• recomputing the current-iteration portion of the search space based at least in part on the failure event probabilities;
• generating a graphical representation of the adversarial branch, wherein the graphical representation includes an aircraft operator training scenario presented via a flight simulator application program;
• outputting the graphical representation for display at a display device;
• receiving user feedback via a user-controlled agent included in the multi-agent system model, wherein the user feedback includes simulated aircraft control instructions received from the flight simulator application program in response to user inputs and aircraft control logic;
• and
• updating the plurality of discrete branches based at least in part on the user feedback.

A computing system of one or more computing devices comprising:

• one or more processing devices configured to:
• receive a specification of a search space over a plurality of inputs to an aircraft control system;
• discretize one or more of the plurality of inputs;
• perform a Monte Carlo tree search (MCTS) to identify an adversarial branch of the search space, wherein:
• the adversarial branch has a highest failure event probability among a plurality of discrete branches computed in a plurality of partitioning steps;
• and
• performing the MCTS includes, in each of the plurality of partitioning steps:
• computing the discrete branches of the search space at least in part by:
• computing a plurality of sample objective function values of a partitioning objective function for different respective sample input values of the inputs included in a current-iteration portion of the search space;
• estimating a probability density function of the partitioning objective function over the current-iteration portion of the search space based at least in part on the sample objective function values;
• and
• partitioning the current-iteration portion of the search space into the discrete branches based at least in part on the probability density function, wherein:
• the discrete branches each include a respective temporal sequence of event nodes that indicate a plurality of temporally ordered events and have corresponding estimated event probabilities;
• and
• the plurality of event probabilities include a plurality of failure event probabilities of a respective plurality of failure events;
• at a multi-agent system model that includes a plurality of supervised learning models, recomputing the estimated event probabilities associated with each of a plurality of event nodes included in the discrete branches;
• and
• recomputing the current-iteration portion of the search space based at least in part on the failure event probabilities;
• output a graphical representation of the adversarial branch, wherein the graphical representation includes an aircraft operator training scenario presented via a flight simulator application program;
• output the graphical representation for display at a display device;
• receive user feedback via a user-controlled agent included in the multi-agent system model, wherein the user feedback includes simulated aircraft control instructions received from the flight simulator application program in response to user inputs and aircraft control logic;
• and
• update the plurality of discrete branches based at least in part on the user feedback.