Monitoring operator condition using sensor data

A non-transitory computer-readable medium comprising instructions that, when executed by one or more processors, cause the one or more processors to perform a process for monitoring an operator of an asset, the process comprising:

• receiving training data, the training data comprising training sensor data associated with one or more tasks performed by a plurality of operators of different skill levels and under different performance impairments;
• training a machine learning model to recognize one or more operator conditions and asset statuses based on the received training data;
• receiving, from at least one asset sensor, asset data that indicates an operating status of the asset;
• receiving, from at least one biometric sensor, biometric data associated with the operator;
• determining, by the machine learning model, an operator condition of the operator has reached an impairment threshold based on the biometric data;
• identifying, by the machine learning model, at least one risk parameter in a current operation of the asset based on the operating status of the asset;
• and
• in response to determining the operator condition has reached the impairment threshold and the at least one risk parameter, sending, to the asset, a command that remotely shuts down operation of the asset.

A computing device for monitoring an operator of an asset, the computing device comprising:

• one or more processors;
• and
• a memory comprising instructions that, when executed by the one or more processors, cause the one or more processors to perform a process, the process comprising:
• receiving training data, the training data comprising training sensor data associated with one or more tasks performed by a plurality of operators of different skill levels and under different performance impairments;
• training a machine learning model to recognize one or more operator conditions and asset statuses based on the received training data;
• receiving, from at least one asset sensor, asset data that indicates an operating status of the asset;
• receiving, from at least one biometric sensor, biometric data associated with the operator;
• determining, by the machine learning model, an operator condition of the operator has reached an impairment threshold based on the biometric data;
• identifying, by the machine learning model, at least one risk parameter in a current operation of the asset based on the operating status of the asset;
• and
• in response to determining the operator condition has reached the impairment threshold and the at least one risk parameter, sending, to the asset, a command that remotely shuts down operation of the asset.