Southwest Research Institute

Christopher I Mentzer

Kristopher Charles Kozak

Marc Christopher Alban

Edmond M DuPont

Samuel E Slocum

Omar D Medjaouri

Kevin J Alley

Jason C Gassaway

Richard D Garcia

Ryan D Lamm

George T McWilliams, Iii

A motion prediction system for predicting the motion of a random animate subject. A first neural network is a markerless motion capture network, trained to receive video data of the subject and to process the video data to generate a time sequence of musculoskeletal motion capture data. A second neural network is a motion prediction network, trained to receive the musculoskeletal motion capture data and to process the data to generate a prediction of the subject's location based on position change in position of joints and/or muscles.

Markerless motion capture of animate subject with prediction of future motion

An unmanned vehicle system, having at least one autonomous ground vehicle (A-GV) and at least one remote controlled aerial vehicle (RC-AV). The A-GV autonomously navigates across the ground, and on-board perception sensors, whose field of view that contains at least a portion of the ground ahead of the direction of travel of the ground vehicle as well as the RC-GV. The RC-AV flies in response to commands received from the control system of the A-GV. The RC-AV has on-board in-sky perception sensors having a field of view that contains at least a portion of the ground path to be followed by the ground vehicle. The control system of the A-GV locate the aerial vehicle, receives perception data from the on-ground perception sensors and the in-sky perception sensors, and uses combined perception data to determine a ground path for itself and for the RC-AV.

Unmanned ground/aerial vehicle system having autonomous ground vehicle that remotely controls one or more aerial vehicles

The present disclosure relates to a method and system for simulating an unmanned aerial vehicle (UAV) and simulating an environment in which the UAV may be flying. A plurality of visual sensors, e.g., cameras, positioned on the UAV, may be simulated. A UAV simulator is configured to simulate the UAV and a graphical simulator is configured to simulate the environment. The UAV simulator may be configured to: estimate pitch, roll and/or groundspeed based, at least in part, on outputs from the visual sensors, determine a position and/or an orientation of the simulated UAV in the simulated environment based, at least in part, on the estimate(s) and provide the position and/or orientation to the graphical simulator. The graphical simulator may be configured to display the simulated UAV at the position and/or orientation in the simulated environment and/or to display the simulated camera view(s).

Optical state estimation and simulation environment for unmanned aerial vehicles

Growing community of inventors

San Antonio, TX, United States of America

Christopher I Mentzer