This letter proposes an anti-disturbance control scheme for rotor drones to counteract voltage drop (VD) disturbance caused by voltage drop of the battery, which is a common case for long-time flight or aggressive maneuvers. Firstly, the refined dynamics of rotor drones considering VD disturbance are presented. Based on the dynamics, a voltage drop observer (VDO) is developed to accurately estimate the VD disturbance by decoupling the disturbance and state information of the drone, reducing the conservativeness of conventional disturbance observers. Subsequently, the control scheme integrates the VDO within the translational loop and a fixed-time sliding mode observer (SMO) within the rotational loop, enabling it to address force and torque disturbances caused by voltage drop of the battery. Sufficient real flight experiments are conducted to demonstrate the effectiveness of the proposed control scheme under VD disturbance.

The well-known generalization problem hinders the application of artificial neural networks in continuous-time prediction tasks with varying latent dynamics. In sharp contrast, biological systems can neatly adapt to evolving environments benefiting from real-time feedback mechanisms. Inspired by the feedback philosophy, we present feedback neural networks, showing that a feedback loop can flexibly correct the learned latent dynamics of neural ordinary differential equations (neural ODEs), leading to a prominent generalization improvement. The feedback neural network is a novel two-DOF neural network, which possesses robust performance in unseen scenarios with no loss of accuracy performance on previous tasks. A linear feedback form is presented to correct the learned latent dynamics firstly, with a convergence guarantee. Then, domain randomization is utilized to learn a nonlinear neural feedback form. Stemming from residual neural networks (He et al., 2016), neural ordinary differential equation (neural ODE) (Chen et al., 2018) emerges as a novel learning strategy aiming at learning the latent dynamic model of an unknown system. Recently, neural ODEs have been successfully applied to various scenarios, especially continuous-time missions (Liu & Stacey, 2024; Verma et al., 2024; Greydanus et al., 2019; Cranmer et al., 2020). However, like traditional neural networks, the generalization problem limits the application of neural ODEs in real-world applications. Traditional strategies like model simplification, fit coarsening, data augmentation, and transfer learning have considerably improved the generalization performance of neural networks on unseen tasks (Rohlfs, 2022). However, these strategies usually reduce the Figure 1: Neural network architectures.

This paper provides a simulated laboratory for making use of Reinforcement Learning (RL) for chemical discovery. Since RL is fairly data intensive, training agents `on-the-fly' by taking actions in the real world is infeasible and possibly dangerous. Moreover, chemical processing and discovery involves challenges which are not commonly found in RL benchmarks and therefore offer a rich space to work in. We introduce a set of highly customizable and open-source RL environments, ChemGymRL, based on the standard Open AI Gym template. ChemGymRL supports a series of interconnected virtual chemical benches where RL agents can operate and train. The paper introduces and details each of these benches using well-known chemical reactions as illustrative examples, and trains a set of standard RL algorithms in each of these benches. Finally, discussion and comparison of the performances of several standard RL methods are provided in addition to a list of directions for future work as a vision for the further development and usage of ChemGymRL.