LSTM-Enabled Level Curve Tracking in Scalar Fields Using Multiple Mobile Robots

In this work, we investigate the problem of level curve tracking in unknown scalar fields using a limited number of mobile robots. We design and implement a long short term memory (LSTM) enabled control strategy for a mobile sensor network to detect and track desired level curves. Based on the existing work of cooperative Kalman filter, we design an LSTM-enhanced Kalman filter that utilizes the sensor measurements and a sequence of past fields and gradients to estimate the current field value and gradient. We also design an LSTM model to estimate the Hessian of the field. The LSTM enabled strategy has some benefits such as it can be trained offline on a collection of level curves in known fields prior to deployment, where the trained model will enable the mobile sensor network to track level curves in unknown fields for various applications. Another benefit is that we can train using larger resources to get more accurate models, while utilizing a limited number of resources when the mobile sensor network is deployed in production. Simulation results show that this LSTM enabled control strategy successfully tracks the level curve using a mobile multi-robot sensor network.

MPC Based Feedback-Linearization Strategy of a Fixed-Wing UAV

This work proposes a xed-wing UAV (Ummaned Aerial Vehicle) control strategy based on feedback-linearization and model predictive control (MPC). The strategy makes use of the relationship between the applied control inputs of the UAV and the generalized forces and moments actuating on it. A linear model is obtained by the exact feedback-linearization technique, followed by the use of MPC to solve the trajectory tracking and the control allocation problems. The proposed controller is capable of actuating on the 6 DOF (Degrees of Freedom) of the UAV, avoiding inherited restrictions when the model is decoupled. The proposed strategy is applied in a curve tracking task. Simulations are performed using MATLAB software, and the results show the eciency of the proposed control strategy.

Covid-19 Transmission Trajectories–Monitoring the Pandemic in the Worldwide Context

The Covid-19 pandemic is developing worldwide with common dynamics but also with marked differences between regions and countries. These are not completely understood, but presumably, provide a clue to find ways to mitigate epidemics until strategies leading to its eradication become available. We describe an iteractive monitoring tool available in the internet. It enables inspection of the dynamic state of the epidemic in 187 countries using trajectories that visualize the transmission and removal rates of the epidemic and in this way bridge epi-curve tracking with modelling approaches. Examples were provided which characterize state of epidemic in different regions of the world in terms of fast and slow growing and decaying regimes and estimate associated rate factors. The basic spread of the disease is associated with transmission between two individuals every two-three days on the average. Non-pharmaceutical interventions decrease this value to up to ten days, whereas ‘complete lock down’ measures are required to stop the epidemic. Comparison of trajectories revealed marked differences between the countries regarding efficiency of measures taken against the epidemic. Trajectories also reveal marked country-specific recovery and death rate dynamics. The results presented refer to the pandemic state in May to July 2020 and can serve as ‘working instruction’ for timely monitoring using the interactive monitoring tool as a sort of ‘seismometer’ for the evaluation of the state of epidemic, e.g., the possible effect of measures taken in both, lock-down and lock-up directions. Comparison of trajectories between countries and regions will support developing hypotheses and models to better understand regional differences of dynamics of Covid-19.

Covid-19 trajectories – Monitoring pandemic in the worldwide context

BackgroundCovid-19 pandemic is developing worldwide with common dynamics but also with partly marked differences between regions and countries. They are not completely understood, but presumably, provide one clue to find ways to mitigate epidemics until exit strategies to its eradication become available.MethodWe provide a monitoring tool available at www.izbi.de. It enables inspection of the dynamic state of the epidemic in 187 countries using trajectories. They visualize transmission and removal rates of the epidemic and this way bridge epi-curve tracking with modelling approaches.ResultsExamples were provided which characterize state of epidemic in different regions of the world in terms of fast and slow growing and decaying regimes and estimate associated rate factors. Basic spread of the disease associates with transmission between two individuals every two-three days on the average. Non-pharmaceutical interventions decrease this value to up to ten days where ‘complete lock down’ measures are required to stop the epidemic. Comparison of trajectories revealed marked differences between the countries regarding efficiency of measures taken against the epidemic. Trajectories also reveal marked country-specific dynamics of recovery and death rates.ConclusionsThe results presented refer to the pandemic state in May 2020 and can serve as ‘working instruction’ for timely monitoring using the interactive monitoring tool as a sort of ‘seismometer’ for the evaluation of the state of epidemic, e.g., the possible effect of measures taken in both, lock-down and lock-up directions. Comparison of trajectories between countries and regions will support developing hypotheses and models to better understand regional differences of dynamics of Covid-19.