Unmanned Systems Technology 025 | iXblue DriX I Maintenance I UGVs I IDEX 2019 I Planck Aero Shearwater I Sky Power hybrid system I Delph Dynamics RH4 I GCSs I StreetDrone Twizy I Oceanology Americas 2019

An engineer in the US is using an underwater unmanned vehicle to develop a new control approach using goal-driven autonomy, or GDA (writes Nick Flaherty). GDA solves problems using autonomous agents that can assess the environment around them and change a UUV’s mission plan accordingly. The agents, aware of the set goal, generate and carry out plans to achieve that goal while monitoring the vehicle’s performance. The GDA algorithm directs the focus of the activities, allowing the agents to become more self-sufficient in achieving the mission. The research will investigate novel AI and machine learning techniques to make these agents adaptive and capable of operating robustly in complex and uncertain environments such as underwater. “The vehicle must be capable of self-adapting to changes in the environment that were not foreseen by the vehicle’s developers,” said the engineer behind the work, Prof Hector Munoz-Avila at Lehigh University in Bethlehem, Pennsylvania. Such changes can include underwater obstacles, comms problems, turbulent water and hydrothermal vents. Any of these changes can affect either the UUV’s sensors, the propulsion mechanisms or both. A lack of adaptability can lead to a catastrophic failure that could result in the total loss of the vehicle, so the UUV must reliably self- diagnose and take actions to adjust its mission accordingly. In this case, the agent will first try to assess the nature of the discrepancy between the vehicle’s expectations and the events it is currently observing. After that, the UUV will undertake controlled actions that can include actuation changes such as reducing its speed or changing its direction. Control has a new goal Underwater systems Goal-driven autonomy allows a UUV’s mission to be changed autonomously (Courtesy of Mary Anne Lynch)