Rockwell Collins, Inc.

Alexander Roup

Joshua R Bertram

Angus L McLean

Brian R Wolford

Vladislav Gavrilets

Bryan M Krawiec

Ian McElhenny

A system for providing maneuvering behaviors to a vehicle is disclosed. The system may include one or more controllers communicatively coupled to one or more vehicles. The one or more controllers may include one or more processors configured to execute one or more program instructions causing the one or more processors to: initiate one or more maneuver primitives in response to decision engine selection; receive a plurality of input parameters for the one or more maneuver primitives, the plurality of input parameters including one or more initialization definition input parameters, one or more goal definition input parameters, one or more navigation state input parameters, one or more design input parameters, and one or more vehicle performance envelope input parameters; and generate one or more control signals at one or more predetermined intervals of time to maneuver the one or more vehicles based on the decision engine selection.

System and method for providing maneuvering behaviors to a vehicle using maneuver primitives

A system includes a machine learning engine configured to receive training data including a plurality of input conditions associated with a state space and a plurality of response maneuvers associated with the state space and train a learning system using the training data and a reward function including a plurality of terms associated with a plurality of end state spaces, each term in the plurality of terms defines an end reward value for each end state space. A value function and policy are generated. The value function comprising a plurality of values, wherein each response maneuvers in the plurality of response maneuvers is associated with a value in the plurality of values related to transitioning from the state space to each end state space, the policy indicative of connections between the state spaces, plurality of values, and the respective end reward value for the plurality of end state spaces.

Systems and methods for practical autonomy decision controller

Safe practical autonomy is ensured by encapsulating an unreliable or untrusted machine learning algorithm within a control-based algorithm. A safety envelope is utilized to ensure that the machine learning algorithm does not output control signals that are beyond safe thresholds or limits. Secure practical autonomy is ensured by verification using digital certificates or cryptographic signatures. The verification may be for individual partitions of an autonomous system or apparatus. The partitions include trusted and untrusted partitions. Trusted partitions are verified for security, while untrusted partitions are verified for safety and security.

Safe and secure practical autonomy

Systems for mobile launch and retrieval of unmanned aircraft systems (UAS) include a rail-based, ground-based, or water-based mobile platform carrying a mobile station for launching and retrieving vertical take-off and landing (VTOL) or non-VTOL UAS while the platform is in motion, based on current position and weather conditions. The mobile platform may include facilities for communicating with the airborne UAS, stowing a retrieved UAS, and reloading/refitting a stowed UAS. The mobile platform may include positionable wake control devices and a partially positionable launch and retrieval mechanism for alleviating turbulence or crosswinds. The mobile platform may include long-range sensors for detecting or identifying obstacles near a rail-based platform that may interfere with the operating envelope of the launch and retrieval mechanisms. The launch and retrieval system may be intermodal and scalable either up or down as mission parameters demand.

Growing community of inventors

Centreville, VA, United States of America

Alexander Roup