This paper presents a computational architecture to facilitate autonomous decision-making under uncertainty for safe operation of drone-like vehicles. The proposed framework is based on identifying and predicting the occurrence of various risk-factors that affect the safe operation of such vehicles and estimating the likelihood of occurrence of these risk-factors. This analysis is then used to select trajectories for the operation of the vehicle. Feasible trajectories are classified into four different categories: nominal and safe, off-nominal but safe, unsafe and abort the mission, and unsafe and ditch the vehicle. An important challenge in the operation of drones is that there are several sources of uncertainty that affect their operation; these sources of uncertainty arise from wind conditions, imprecise future power-demands, inexact future trajectories, etc. Therefore, it is important to develop a decision-making framework that can incorporate all these sources of uncertainty and make decisions that are robust to the presence of such uncertainty. Potential risk-factors such as dynamic obstacles, battery drain, etc. are identified and the likelihood of occurrence of these risk-factors are predicted preemptively and proactively in order to facilitate risk-informed safety-assured decision-making.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.