Coverage Path Planning and Point-of-Interest Detection Using Autonomous Drone Swarms.

Unmanned Aerial Vehicles (UAVs) or drones presently are enhanced with miniature sensors that can provide information relative to their environment. As such, they can detect changes in temperature, orientation, altitude, geographical location, electromagnetic fluctuations, lighting conditions, and more. Combining this information properly can help produce advanced environmental awareness; thus, the drone can navigate its environment autonomously. Wireless communications can also aid in the creation of drone swarms that, combined with the proper algorithm, can be coordinated towards area coverage for various missions, such as search and rescue. Coverage Path Planning (CPP) is the field that studies how drones, independently or in swarms, can cover an area of interest efficiently. In the current work, a CPP algorithm is proposed for a swarm of drones to detect points of interest and collect information from them. The algorithm's effectiveness is evaluated under simulation results. A set of characteristics is defined to describe the coverage radius of each drone, the speed of the swarm, and the coverage path followed by it. The results show that, for larger swarm sizes, the missions require less time while more points of interest can be detected within the area. Two coverage paths are examined here-parallel lines and spiral coverage. The results depict that the parallel lines coverage is more time-efficient since the spiral increases the required time by an average of 5% in all cases for the same number of detected points of interest.

Improving the Accuracy of Low-Cost Sensor Measurements for Freezer Automation.

In this work, a regression method is implemented on a low-cost digital temperature sensor to improve the sensor's accuracy; thus, following the EN12830 European standard. This standard defines that the maximum acceptable error regarding temperature monitoring devices should not exceed 1 °C for the refrigeration and freezer areas. The purpose of the proposed method is to improve the accuracy of a low-cost digital temperature sensor by correcting its nonlinear response using simple linear regression (SLR). In the experimental part of this study, the proposed method's outcome (in a custom created dataset containing values taken from a refrigerator) is compared against the values taken from a sensor complying with the EN12830 standard. The experimental results confirmed that the proposed method reduced the mean absolute error (MAE) by 82% for the refrigeration area and 69% for the freezer area-resulting in the accuracy improvement of the low-cost digital temperature sensor. Moreover, it managed to achieve a lower generalization error on the test set when compared to three other machine learning algorithms (SVM, B-ELM, and OS-ELM).