Reinforcement Learning for Orientation Estimation Using Inertial Sensors with Performance Guarantee

This paper presents a deep reinforcement learning (DRL) algorithm for orientation estimation using inertial sensors combined with a magnetometer. Lyapunov’s method in control theory is employed to prove the convergence of orientation estimation errors. The estimator gains and a Lyapunov function are parametrised by deep neural networks and...

The effect of processing parameters on the formation of epoxy/UF resin microcapsules

Epoxy E-51/UF resin microcapsules were prepared by traditional two-stepped in situ polymerization method and processing parameters affecting the final microcapsules’ shape and size were carefully studied in the aim to obtain microcapsule with ideally spherical shape and uniform size. It’s found the polycarboxylate surfactant of SMA (styrene...

Self-encapsulation of epoxy resin by a controlled interface curing process in epoxy/water emulsion

The microcapsules of epoxy E-51 resin encapsulated by cured itself were prepared by interfacial curing reaction, in which ethylenediamine (EDA) was employed as curing agent and sulfonated copolymer of styrene and maleic anhydride (SMA) as emulsifying agent. It’s found the morphology of microcapsules strongly depend on reaction time and EDA...

Hopcount in the NICE Application Layer Multicast Protocol