MAIN RESEARCH AREAS
Vision Based Control and Navigation
During a previous research project on Autonomous Aerial Refueling (AAR), Machine Vision (MV) techniques were developed to augment/replace the GPS receiver during the final phase of the docking. MV-based algorithms are implemented to detect the relative position and orientation between the UAV and the tanker. Within this effort, techniques and algorithms for the visualization of the tanker aircraft in a Virtual Reality (VR) setting, acquisition of the tanker image, Feature Extraction (FE) from the acquired image, Feature Matching (FM) of the features, as well as the tanker-UAV Pose Estimation (PE) have been developed and extensively tested in closed loop simulations. A study related to the use of passive markers as compared to feature extraction for the problem of estimating in real time the UAV-tanker relative position and orientation vectors was also performed.
Another ongoing research effort at the FCSL involves the use of optical flow information for UAV collision avoidance and to regulate the dead-reckoning drift of the inertial navigation system. An extensive comparison study involving 9 different optical flow algorithms was performed using a number of different real-world videos with images rotating or translating at known speeds as well as images taken from Virtual Reality environments. In addition, several sets of flight data with synchronized video, inertial, GPS, pressure, and range measurements have been collected. It is anticipated that leveraging this data could lead to several applications such as autonomous takeoff/landing within a GNSS-denied environment and aircraft ground collision avoidance.
Mammarella M., Campa G., Napolitano M.R., Fravolini M.L. "Comparison of Point
Matching Algorithms for the UAV Aerial Refueling Problem", Machine Vision and Applications, Vol. 21, No. 3,pp. 241-251, 2010, Springer ISSN 0932-8092
Mammarella, M., Campa, G., Napolitano, M.R., Fravolini, M.L., Perhinschi, M.G., and Gu, Y., “Machine Vision / GPS Integration Using EKF for the UAV Aerial Refueling Problem,” Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on, Vol. 38, No. 6, pp.791-801, November, 2008.
Effland, J., Seanor, B., Gu, Y., Napolitano, M., “Application of Machine Vision in Unmanned Aerial Systems for Autonomous Target Tracking”, AIAA Guidance, Navigation, and Control Conference, AIAA 2008-7251, August 18-21, 2008, Honolulu, HI, USA.
Mammarella, M., Campa, G., Fravolini, M., Gu, Y., Seanor, B., Napolitano, M., “A Comparison of Optical Flow algorithms for Real Time Aircraft Guidance and Navigation”, AIAA Guidance, Navigation, and Control Conference, AIAA 2008-7494, August 18-21, 2008, Honolulu, HI, USA.
Campa, G., Napolitano, M. R., Fravolini, M. L., "A Simulation Environment for Machine Vision Based Aerial Refueling for UAV", IEEE Transaction on Aerospace and Electronic Systems, Vol.44, No 4, October 2008.
Mammarella, M., Campa, G., Napolitano, M. R., Fravolini, M. L., Dell’Aquila, R., Brunori, V., Perhinschi M. G., "Comparison of Point Matching Algorithms for the UAV Aerial Refueling Problem", Submitted to: Machine Vision and Applications, November 2007, Accepted March 2008. Published online 12 June 2008
Vendra, S., Campa, G., Napolitano, M. R., Mammarella, M., Fravolini, M., L., Perhinschi M. G., "Addressing Corner Detection Issues for Machine Vision based UAV Aerial Refueling", Machine Vision and Application, pp 261-273, Volume 18, Number 5, October, 2007.
Fravolini, M. L., Campa, G., Napolitano, M. R., "Evaluation of Machine Vision Algorithms for Autonomous Aerial Refueling for Unmanned Aerial Vehicles", AIAA Journal of Aerospace Computing, Information and Communication, Vol. 4, No. 9, September 2007.