Abstract
This study presents a novel approach to cope with the human behaviour uncertainty during Human-Robot Collaboration (HRC) in dynamic and unstructured environments, such as agriculture, forestry, and construction. These challenging tasks, which often require excessive time, labour and are hazardous for humans, provide ample room for improvement through collaboration with robots. However, the integration of humans in-the-loop raises open challenges due to the uncertainty that comes with the ambiguous nature of human behaviour. Such uncertainty makes it difficult to represent high-level human behaviour based on low-level sensory input data. The proposed Fuzzy State-Long Short-Term Memory (FS-LSTM) approach addresses this challenge by fuzzifying ambiguous sensory data and developing a combined activity recognition and sequence modelling system using state machines and the LSTM deep learning method. The evaluation process compares the traditional LSTM approach with raw sensory data inputs, a Fuzzy-LSTM approach with fuzzified inputs, and the proposed FS-LSTM approach. The results show that the use of fuzzified inputs significantly improves accuracy compared to traditional LSTM, and, while the fuzzy state machine approach provides similar results than the fuzzy one, it offers the added benefits of ensuring feasible transitions between activities with improved computational efficiency.

Abstract
The manual monitoring of refilling stations in industrial environments can lead to inefficiencies and errors, which can impact the overall performance of the production line. In this paper, we present an unsupervised detection pipeline for identifying refilling stations in industrial environments. The proposed pipeline uses a combination of image processing, pattern recognition, and deep learning techniques to detect refilling stations in visual data. We evaluate our method on a set of industrial images, and the findings demonstrate that the pipeline is reliable at detecting refilling stations. Furthermore, the proposed pipeline can automate the monitoring of refilling stations, eliminating the need for manual monitoring and thus improving industrial operations' efficiency and responsiveness. This method is a versatile solution that can be applied to different industrial contexts without the need for labeled data or prior knowledge about the location of refilling stations.

Abstract
This paper describes the implementation of a distributed data acquisition network based on the 80C592 microcontroller from Intel. Each Station is connected in a hierarchical way to form a tree topology. The lower level network stations, designated by Slaves, are dedicate to the data acquisition and the generation of control signals. The upper level, Masters, are responsible for the communications control. Both networks uses a CAN - Controller Area Network - Bus, for Data Transferring, and the global Network is also connected to a PC, via CAN. A device router, NetManager, was implemented to support total intrinsic requirements at the communication level. This type of connection allows total configuration from a personal computer, PC, in which runs a software application developed for Windows(TM) environments. The tests performed at the laboratory, with transmission rates varying from 40Kbits/s to 1Mbits/s, showed that the communications were performed without errors for cable lengths of 1100m to 40m, respectively. This system is now being installed in a set of environmental chambers and greenhouses located on UTAD, where it will be monitored and controlled the air temperatures and humidities, the CO2 and ammonia concentrations and the radiation level.

Abstract

Abstract
Recent developed button heat pulse probes (BHPP) demonstrated a great potential for soil water content measurements. This new probe compared to conventional heat pulse probes (HPP), does not use needles, and measurement accuracy is significantly improved. This new design, with the possibility to assembly the probe and electronics in the same package, with low-cost, and with less power consumption compared to conventional HPP, make it suitable to be connected to wireless data acquisition systems in precision agriculture. The probe was tested in agar to demonstrate the potential advantages of the button heat pulse sensor for soil water content measurements. It was possible to have an 0.5 °C temperature rise with only 156mW of power consumption, a ten times power reduction in heat-pulse soil water content measurements. These tests showed the potential use of the button heat pulse sensor for the determination of soil water content. © 2010 IEEE.

Abstract
This work describes the development and implementation of a grid of self-powered multi-functional probes (MFPz) for small-scale measurements of different soil properties, as being part of a wireless sensor network. The measurement principle is based on the heat-pulse method for soil moisture and water flux measurements and in a Wenner array for soil electrical conductivity. To promote the deployment of these sensing devices across large areas, such as irrigation fields, the ZigBee standard has been adopted as a multi-hop, ad-hoc network enabler. The core of the MTPz device is a wireless microcontroller (with a built-in ZigBee stack) that builds upon an IEEE 802.15.4 radio device. A 7.2Ah NiHM battery that is charged by a solar panel powers the MFPz device. Experimental results have proofed the reliability of the MFPz, regarding power consumption, connectivity and data agreement with known soil samples, as a cost-effective solution for environment monitoring.