Hrl Laboratories, LLC

Tiffany Hwu

Steven W Skorheim

David J Huber

Jaehoon Choe

Myana Anderson

Described is a system for improving machine operation performance. The system assigns and displays, on an interface having multiple interactive controls, a performance score for each skill of a sequential task in a simulation of operation of a machine. Based on the performance scores, one or more skills to improve with targeted training are identified and displayed on the interface. A training scenario of skills to perform via the interactive controls in a subsequent simulation is recommended to improve the performance scores. Following performance of the training scenario in the subsequent simulation, the system assigns and displays, on the interface, a new performance score for each skill performed. The training scenario is adapted based on the new performance scores.

Human machine teaching system for sequential task training

A pilot support system includes: a processing circuit; and memory storing instructions that, when executed by the processing circuit, cause the processing circuit to: receive input data regarding a current state of a vehicle; encode the input data to generate encoded input data; supply the encoded input data to a trained statistical model; compute a current context of the vehicle based on the input data using the trained statistical model; compute one or more pilot feedback indicators based on the current context using the trained statistical model; and provide the one or more pilot feedback indicators to a cockpit of the vehicle.

Neural network-based system for flight condition analysis and communication

Described is a system for human-machine teaching for vehicle operation. The system determines currently enabled status reporting modes on a vehicle interface of a vehicle. The currently enabled status reporting modes are compared to a set of preferred status reporting modes of previous users. Based on the comparison, a status reporting mode is selected. A current operational status of the vehicle is reported to a current user, via the vehicle interface, using the selected status reporting mode. The system then determines preferred solutions of previous users to address the current operational status of the vehicle. Suggestions to address the current operational status of the vehicle based on the preferred solutions are reported to the user via the vehicle interface. A vehicle action corresponding to a solution selected by the current user is implemented via a vehicle component.

Bidirectional machine teaching interface for human-machine co-pilots

Described is a system for multimodal machine-aided comprehension analysis. The system can be implemented in an augmented reality headset that, in conjunction with a processor, generates an initial scene graph of a scene proximate the user. Items and labels are presented, with the headset tracking eye movements of the user as the user gazes upon the subject labels, item labels, and relationship labels. A resulting scene graph (having relationship triplets) is generated based on the eye movements of the user and an amount of time the user spends gazing upon each of the display components. A comprehension model is generated by estimating a user's comprehension of the relationship triplets, with a knowledge model being generated based on a known knowledge graph and the comprehension model. Cues are then presented to the user based on the comprehension and knowledge models to assist the user in their comprehension of the scene.

Growing community of inventors

San Diego, CA, United States of America

Tiffany Hwu