Unmanned aerial vehicles (UAVs), known for their agile flight capabilities, require safe trajectory planning to achieve high-speed flights. This is necessary to swiftly evade obstacles and adapt trajectories under hard real-time constraints. These adjustments are essential to generate viable paths that prevent collisions while maintaining high speeds with minimal tracking errors. This paper addresses the challenge of enhancing the safety of agile trajectory planning. The proposed method combines a supervised learning approach, as teacher policy, with deep reinforcement learning (DRL), as student policy. Initially, we train the teacher policy using a path planning algorithm that prioritizes safety while minimizing jerk and flight time. Then, we use this policy to guide the learning of the student policy in various unknown environments. Testing in simulation demonstrates noteworthy advancements, including an 80% reduction in tracking error, a 31% decrease in flight time, a 19% increase in high-speed duration, and a success rate improvement from 50% to 100%, as compared to baseline methods.

The Internet of Things (IoT) is an environment that can be divided in three large layers: the sensor/actuator level where a wide variety of objects with different computing, sensors and communication capabilities resides, the communication layer with wireless technologies such as ZigBee, Bluetooth and emerging 6LoWPAN (e.g LoRa), and the intelligence layer, where computing analytics/decisions occur. IoT can be used for monitoring, inferring problems, decision making at a business level or actuating at the edge via IoT nodes. As the IoT sensor network grows, an enormous amount of data from multiple sources flows to the intelligence layer. In order to make decisions based on analytics over these data, the measurements need to be precise and accurate. Data fusion is an effective way to improve data quality, however, IoT environments are still evolving and the best way and location where data fusion should happen is an open problem. This paper presents one potential strategy for IoT sensor data fusion by implementing multi-sensor data fusion as microservices using a container platform built into an opensource IoT middleware based in a fog computing infrastructure which is can scale automatically as the influx of data from the IoT nodes grows. A number of data fusion tests were performed for different amounts of IoT nodes and sensor readings over ZigBee and LoRa using a specific data fusion algorithm. The results show that, the strategy can be effectively used in IoT heterogeneous environments.

The mapping of agricultural crops by capturing images obtained with UAVs enables fast environmental monitoring and diagnosis in large areas. Airborne monitoring in agriculture can a substantially impacts on the identification of diseases and produce accurate information on affected areas. The problem can be formulated as a classification task on aerial images with significant opportunities to impact other fields. This paper presents an active learning method through route planning for improvements in the knowledge on visited areas and minimization uncertainties about the classification of diseases in crops. Binary Logistic Regression and Gaussian Process were used for the detection of pathologies and map interpolation, respectively. A Bayesian optimization strategy is also proposed for the planning of an informative trajectory, which resulted in a maximized search for affected areas in an initially unknown environment.

One of the challenges in precision agriculture is the detection of diseased crops in agricultural environments. This paper presents a methodology to detect the Ceratocystis wilt disease in Eucalyptus crops. An unmanned aerial vehicle is used to obtain high-resolution RGB images of a predefined area. The methodology enables the extraction of visual features from image regions and uses several supervised machine learning (ML) techniques to classify regions into three classes: ground, healthy and diseased plants. Several learning techniques were compared using data obtained from a commercial Eucalyptus plantation. Experimental results show that the GP learning model is more reliable than the other learning methods for accurately identifying diseased trees.

When it comes to AGVs (Automated Guide Vehicles) working in intelligent warehouse systems it is necessary to take into account that the use of batteries may impact the performance of the overall system. They need to be recharged or changed, and the time required to execute these operations might interfere in the AGV availability. Therefore, it is necessary to carry out a battery management procedure to ensure that the batteries have sufficient charges to perform the desired tasks. This paper describes a method based on the Extended Kalman Filter (EKF) to estimate the Batteries State of Charge (SOC). The estimated consumption is compared with the SOC obtained by the EKF. A series of experiments using mini-robotic forklifts were performed to evaluate the method. The experimental results have shown its effectiveness using resistive loads. This methodology allowed estimating the battery consumption for a certain route of the mini-robotic forklift in the warehouse and verifying the load capacity available for the mini-robotic forklift to accomplish a task assigned by the warehouse routing system.