Recent advances in aerial robotics have enabled the use of multirotor vehicles for autonomous payload transportation. Resorting only to classical methods to reliably model a quadrotor carrying a cable-slung load poses significant challenges. On the other hand, purely data-driven learning methods do not comply by design with the problem’s physical constraints, especially in states that are not densely represented in training data. In this work, we explore the use of physics-informed neural networks to learn an end-to-end model of the multirotor-slung-load system and, at a given time, estimate a sequence of the future system states. An LSTM encoder-decoder with an attention mechanism is used to capture the dynamics of the system. To guarantee the cohesiveness between the multiple predicted states of the system, we propose the use of a physics-based term in the loss function, which includes a discretized physical model derived from first principles together with slack variables that allow for a small mismatch between expected and predicted values. To train the model, a dataset using a real-world quadrotor carrying a slung load was curated and is made available. Prediction results are presented and corroborate the feasibility of the approach. The proposed method outperforms both the first principles physical model and a comparable neural network model trained without the physics regularization proposed.

The expected behavior of industrial automation systems can be defined and modeled, but since not every event is predicted at design time, additional care has to be taken during the operation to handle situations such as exceptions, failures and new production orders. Another remark is also the limitation of modeling languages used in the control to permit the intervention of higher grade decision mechanisms. This paper discusses the application of decision support system for Petri net based processes to control automation components and devices. The decision mechanisms are used for path planning, production scheduling and preventive maintenance, to support the description of processes in Petri nets formalism. As such, the same Petri nets designed for the control are also used as analytical information input to the decision support system and for the detection process options that require decision. The solution provides a dynamic complement to the static modeling and operational flexibility. Experiments were done in a real service-oriented industrial factory-cell to prove the specified approach.