Navaminda Kasatriyadhiraj Royal Air Force Academy (NKRAFA) won the Autonomous Aerial Vehicle Challenge (AAVC) 2023. This paper describes the architecture, design, implementation, and testing of an unmanned aircraft system that ultimately won the challenge. The mission of the challenge was to search for a mannequin target, acquire a geolocated coordinate of the target, and then drop a payload as close to the target as possible. The scoring was based on the level of autonomy in each phase of the mission. During the competition, NKRAFA was able to fly the mission autonomously from takeoff to landing. NKRAFA earned a full score and only missed the extra points. The mission was completed within 8 min out of the 25 min allotted time. Our multirotor aircraft was operated according to the two-internal pilot operational concept — where the first internal pilot will be responsible for the flight aspect of the operation, while the second internal pilot will be responsible for the mission aspect of the operation. The hardware architecture also reflected this concept. There were two onboard computers and two ground control stations. Our mission software components included a YOLO v4 object detector, the target candidate filter, the Extended Kalman Filter states estimator, the geolocation, and the mission manager. The paper will also discuss emergency procedures, our experiences from flight testing, and the results of the competition.

A system using aerial vehicles to autonomously locate and retrieve ground packages of various colors and shapes within a designated area was developed. This system was notable for its use of an innovative rotor configuration that offered a higher degree of control compared to traditional designs. To accurately identify and track the packages, a multi-sensor approach combining vision and Light Detection and Ranging technologies was implemented, integrating data into an extended Kalman filter framework for precise position and velocity estimates. An electro-permanent magnet was employed to securely grab and release the packages, which have a ferrous material. The process of path planning and collision avoidance was conducted in a decentralized manner, leveraging a shared global map among the airborne vehicles. This paper details system technical design, including the integration of various technologies, and shares insights and outcomes derived from its application.

Unmanned Aircraft Systems (UASs) have become increasingly important assets for naval and maritime law enforcement operations. In response to the ever-increasing demand for autonomous systems, this paper presents a design, development, integration, and flight testing of an unmanned rotorcraft system capable of operating with a moving ship. The system was developed initially by playing back ship motion data in a simulation environment. Ship motion prediction, relative guidance, operator control interface, and landing flight management system were developed and tested against simulated sea state motion. The system was then flight tested using a 15-kg electric helicopter operating off a US Naval Academy’s yard patrol craft. The craft was instrumented with IMU and GPS for the craft’s own state estimation. The craft was also used as a moving-base station for Real-time Kinematic (RTK) relative positioning. The flight operation was done in the Chesapeake Bay. Autonomous capabilities including takeoff, landing, station-keeping, and maneuvering relative to a moving ship were successfully demonstrated.