Abstract
Software for robotic systems is becoming progressively more complex despite the existence of established software ecosystems like ROS, as the problems we delegate to robots become more and more challenging. Ensuring that the software works as intended is a crucial (but not trivial) task, although proper quality assurance processes are rarely seen in the open-source robotics community. This paper explains how we analyzed and improved a specialized path planner for steep-slope vineyards regarding its software dependability. The analysis revealed previously unknown bugs in the system, with a relatively low property specification effort. We argue that the benefits of similar quality assurance processes far outweigh the costs and should be more widespread in the robotics domain.

Abstract
The importance of agriculture and the production of fruits and vegetables has stood out mainly over the past few years, especially for the benefits for our health. In 2021, in the international year of fruit and vegetables, it is important to encourage innovation and evolution in this area, with the needs surrounding the different processes of the different cultures. This paper compares the performance between two datasets for robotics fruit harvesting using four deep learning object detection models: YOLOv4, SSD ResNet 50, SSD Inception v2, SSD MobileNet v2. This work aims to benchmark the Open Images Dataset v6 (OIDv6) against an acquired dataset inside a tomatoes greenhouse for tomato detection in agricultural environments, using a test dataset with acquired non augmented images. The results highlight the benefit of using self-acquired datasets for the detection of tomatoes because the state-of-the-art datasets, as OIDv6, lack some relevant characteristics of the fruits in the agricultural environment, as the shape and the color. Detections in greenhouses environments differ greatly from the data inside the OIDv6, which has fewer annotations per image and the tomato is generally riped (reddish). Standing out in the use of our tomato dataset, YOLOv4 stood out with a precision of 91%. The tomato dataset was augmented and is publicly available (See https://rdm.inesctec.pt/ and https://rdm.inesctec.pt/dataset/ii-2021-001).

Abstract
The agricultural sector plays a fundamental role in our society, where it is increasingly important to automate processes, which can generate beneficial impacts in the productivity and quality of products. Perception and computer vision approaches can be fundamental in the implementation of robotics in agriculture. In particular, deep learning can be used for image classification or object detection, endowing machines with the capability to perform operations in the agriculture context. In this work, deep learning was used for the detection of grape bunches in vineyards considering different growth stages: the early stage just after the bloom and the medium stage where the grape bunches present an intermediate development. Two state-of-the-art single-shot multibox models were trained, quantized, and deployed in a low-cost and low-power hardware device, a Tensor Processing Unit. The training input was a novel and publicly available dataset proposed in this work. This dataset contains 1929 images and respective annotations of grape bunches at two different growth stages, captured by different cameras in several illumination conditions. The models were benchmarked and characterized considering the variation of two different parameters: the confidence score and the intersection over union threshold. The results showed that the deployed models could detect grape bunches in images with a medium average precision up to 66.96%. Since this approach uses low resources, a low-cost and low-power hardware device that requires simplified models with 8 bit quantization, the obtained performance was satisfactory. Experiments also demonstrated that the models performed better in identifying grape bunches at the medium growth stage, in comparison with grape bunches present in the vineyard after the bloom, since the second class represents smaller grape bunches, with a color and texture more similar to the surrounding foliage, which complicates their detection.

Abstract
The world society needs to produce more food with the highest quality standards to feed the world population with the same level of nutrition. Microfarms and local food production enable growing vegetables near the population and reducing the operational logistics costs related to post-harvest food handling. However, it isn't economical viable neither efficient to have one person devoted to these microfarms task. To overcome this issue, we propose an open-source robotic solution capable of performing multitasks in small polyculture farms. This robot is equipped with optical sensors, manipulators and other mechatronic technology to monitor and process both biotic and abiotic agronomic data. This information supports the consequent activation of manipulators that perform several agricultural tasks: crop and weed detection, sowing and watering. The development of the robot meets low-cost requirements so that it can be a putative commercial solution. This solution is designed to be relevant as a test platform to support the assembly of new sensors and further develop new cognitive solutions, to raise awareness on topics related to Precision Agriculture. We are looking for a rational use of resources and several other aspects of an evolved, economically efficient and ecologically sustainable agriculture.

Abstract
This study analyzed the potential of proximal optical sensing as an effective approach for early disease detection. A compact, modular sensing system, combining direct UV–Vis spectroscopy with optical fibers, supported by a principal component analysis (PCA), was applied to evaluate the modifications promoted by the bacteria Xanthomonas euvesicatoria in tomato leaves (cv. cherry). Plant infection was achieved by spraying a bacterial suspension (108 CFU mL-1) until run-off occurred, and a similar approach was followed for the control group, where only water was applied. A total of 270 spectral measurements were performed on leaves, on five different time instances, including pre- and post-inoculation measurements. PCA was then applied to the acquired data from both healthy and inoculated leaves, which allowed their distinction and differentiation, three days after inoculation, when unhealthy plants were still asymptomatic.

Abstract
Thrombocytosis is a disorder with an excessive number of platelets in the blood, where total platelet counts (TPC) are crucial for diagnosis. This condition predisposes to blood vessels clotting and diseases such as stroke or heart attack. TPC is generally performed at the laboratory by flow cytometry with laser scattering or impedance detection. Due to the limited capacity of automated hematology in performing TPC quantification, a manual microscopy count is a very common quality assurance measure undertaken by clinical pathologists. Monitoring coagulation risk is key in many health conditions, and point-of-care platforms would simplify this procedure by taking platelet counts to the bedside. Spectroscopy has high potential for reagent-less point-of-care miniaturized technologies. However, platelets are difficult to detect in blood by standard spectroscopy analysis, due to their small size, low number when compared to red blood cells, and low spectral contrast to hemoglobin. In this exploratory research, we show that it is possible to perform TPC by advanced spectroscopy analysis, using a new processing methodology based on self-learning artificial intelligence. The results show that TPC can be measured by visible–near-infrared spectroscopy above the standard error limit of 61.19 × 109 cells/L (R2 = 0.7016), tested within the data range of 53 × 109 to 860 × 109 cells/L of dog blood. These results open the possibility for using spectroscopy as a diagnostic technology for the detection of high levels of platelets directly in whole blood, towards the rapid diagnosis of thrombocytosis and stroke prevention.