Abstract: An autonomous agent of a team of autonomous agents (e.g., semi- or fully autonomous vehicles) includes a self-simulator incorporating a faster than real time (FTRT) processing environment for online simulation of each agent of the team. Based on the current mission status and one or more action sets determining the behaviors of the autonomous agents, the behaviors of each agent of the team are projected forward within the FTRT environment to determine mission status metrics relevant to the effectiveness of a particular action set towards optimal completion of mission objectives currently assigned to the team. Based on the mission status metrics, the self-simulator can select and provide an action set for optimized completion of mission objectives. For example, the self-simulator can recommend switching to a different preloaded action set or, in some cases, construct an optimized action set selected from multiple preloaded action sets tested in the FTRT environment.

Abstract: A mission system for autonomous vehicle (AV) team coordination and a method of using the same are disclosed. A controller included on an AV shares mission data between two or more AVs, and in response to communication denial, generates estimated navigation trajectories for teammate AVs. A simulation outputs estimated navigation states for the teammate AVs. The estimated navigation states are identical or substantially identical to navigation states otherwise generated by controllers included on the teammate AVs. The estimated navigation trajectories are generated based on the estimated navigation states.

Abstract: A mission system for autonomous vehicle (AV) team coordination and a method of using the same are disclosed. A controller included on an AV shares mission data between two or more AVs, and in response to communication denial, generates estimated navigation trajectories for teammate AVs. A simulation outputs estimated navigation states for the teammate AVs. The estimated navigation states are identical or substantially identical to navigation states otherwise generated by controllers included on the teammate AVs. The estimated navigation trajectories are generated based on the estimated navigation states.

Abstract: A system and method for multi-asset collaborative operations by a team of autonomous vehicles (AV) implements a multi-level hierarchical mission planning and autonomy stack aboard each member AV of the team. Mission-level and team-level layers of the stack, either independently or in collaboration with other members of the AV team. receive high-level mission goals, spawn mission objectives for the fulfillment of received goals, and assign the mission objectives to specific member AVs or sub-teams thereof. Asset-level action planning modules translate the assigned mission objectives into default trajectories including component action and payload sequences for execution by the AV. An asset-level guidance playbook executes the default trajectories via high-rate control commands directly to vehicle and payload control systems.

Abstract: A method for occupancy map synchronization in multi-vehicle networks may include receiving three-dimensional perception sensor (3DPS) data. The method may include generating a data message including an occupancy map (OM) octree. The OM octree may be generated from an occupancy map constructed from the 3DPS data. The method may include reducing at least one of a messaging time or a messaging size of the data message including the OM octree. The method may include transmitting the data message including the OM octree via a leader vehicle controller communicatively coupled to a leader vehicle. The method may include receiving the data message comprising the OM octree via a follower vehicle controller communicatively coupled to the follower vehicle. The method may include generating a local occupancy map from the data message comprising the OM octree via the follower vehicle controller.

Abstract: A method for occupancy map synchronization in multi-vehicle networks may include receiving three-dimensional perception sensor (3DPS) data. The method may include generating a data message including an occupancy map (OM) octree. The OM octree may be generated from an occupancy map constructed from the 3DPS data. The method may include reducing at least one of a messaging time or a messaging size of the data message including the OM octree. The method may include transmitting the data message including the OM octree via a leader vehicle controller communicatively coupled to a leader vehicle. The method may include receiving the data message comprising the OM octree via a follower vehicle controller communicatively coupled to the follower vehicle. The method may include generating a local occupancy map from the data message comprising the OM octree via the follower vehicle controller.

Abstract: A memory subsystem includes a memory controller operable to generate first control signals according to a standard interface. A memory interface adapter is coupled to the memory controller and is operable responsive to the first control signals to develop second control signals adapted to be applied to a memory subsystem to access desired storage locations within the memory subsystem.