Abstract
To produce more food and tackle the labor scarcity, agriculture needs safer robots for repetitive and unsafe tasks (such as spraying). The interaction between humans and robots presents some challenges to ensure a certifiable safe collaboration between human-robot, a reliable system that does not damage goods and plants, in a context where the environment is mostly dynamic, due to the constant environment changes. A well-known solution to this problem is the implementation of real-time collision avoidance systems. This paper presents a global overview about state of the art methods implemented in the agricultural environment that ensure human-robot collaboration according to recognised industry standards. To complement are addressed the gaps and possible specifications that need to be clarified in future standards, taking into consideration the human-machine safety requirements for agricultural autonomous mobile robots.

Abstract
<p>The WATER4EVER Project (http://water4ever.eu/) was built on the premise that agriculture is by far the largest consumer of water, with about 70% of the diverted water being used in irrigation. Agriculture is also considered as a key source of diffuse pollution with inefficient practices resulting in high water and nutrient (particularly N and P) surpluses that are transferred to water bodies through diffuse processes (runoff and leaching), promoting eutrophication, with associated biodiversity loss. WATER4EVER aims thus to develop new monitoring strategies at the plot and catchment scales to provide detailed information of water and nutrient flow, and gain new insights on the connectivity between both scales. New monitoring strategies were developed and tested in agricultural fields in Portugal, Spain, Italy and Turkey and included: (i) crop physiological indicators assessment using static sensors for defining improved deficit irrigation strategies for woody crops; (ii) crop stress and productivity maps from measurements taken with a smart sensor mounted on a tractor and equipped with LIDAR 2D, normalized difference vegetation index (NDVI) and thermal cameras, and a GNSS receiver; (iii) leaf area index maps at 30 m resolution derived from ATCOR and Landsat 8 imagery data using the NDVI and the Soil Adjusted Vegetation Index (SAVI); (iv) soil moisture maps at 100 m resolution by combining the 10 m resolution synthetic-aperture radar (SAR) images from Sentinel 1 with the 10 m resolution NDVI computed from Sentinel 2 images, averaged into 100 m cells, and then by considering the backscatter difference with the driest day, or alternatively the backscatter difference between two consecutive dates; (v) soil moisture maps at 1 km resolution created with the DISaggregation based on a Physical And Theoretical scale CHange (DISPATCH) algorithm for the downscaling of the 40 km SMOS (Soil Moisture and Ocean Salinity) soil moisture data using land surface temperature (LST) and NDVI data; (vi) conventional monitoring techniques combined with modeling tools for assessing the impact of different soil managements (conventional tillage, tillage with grass trips, grass cover) on soil infiltration, soil water content, runoff and soil erosion of hillslope vineyards; (vii) an improved deterministic model for irrigation and fertigation management at the plot scale; and (viii) a decision support system for irrigation water management at the plot scale which integrated a deterministic model for irrigation scheduling and the NDVI computed from Sentinel 2 imagery data for crop growth monitoring. Preliminary results derived from the use of the innovative monitoring and mapping strategies, besides model applications are presented. The remote sensing products described above were also applied for catchment modeling validation of streamflow, which results fall outside the scope of this communication. WATER4EVER activities were thus wide and diverse, aimed at optimizing crop management practices which will help to promote the sustainability of different Mediterranean production systems.</p><p> </p><p>WATER4EVER is funded by the European Commission under the framework of the ERA-NET COFUND WATERWORKS 2015 Programme</p>

Abstract
The efficient application of phytochemical products in agriculture is a complex issue that demands optimised sprayers and variable rate technologies, which rely on advanced sensing systems to address challenges such as overdosage and product losses. This work developed a system capable of processing different tree canopy parameters to support precision fruit farming and environmental protection using intelligent spraying methodologies. This system is based on a 2D light detection and ranging (LiDAR) sensor and a Global Navigation Satellite System (GNSS) receiver integrated into a sprayer driven by a tractor. The algorithm detects the canopy boundaries, allowing spray only in the presence of vegetation. The spray volume spared evaluates the system's performance compared to a Tree Row Volume (TRV) methodology. The results showed a 28% reduction in the overdosage of spraying product. The second step in this work was calculating and adjusting the amount of liquid to apply based on the tree volume. Considering this parameter, the saving obtained had an average value for the right and left rows of 78%. The volume of the trees was also monitored in a georeferenced manner with the creation of a occupation grid map. This map recorded the trajectory of the sprayer and the detected trees according to their volume.

Abstract
To tackle wildfires and improve forest biomass management, cost effective and reliable mowing and pruning robots are required. However, the development of visual perception systems for forestry robotics needs to be researched and explored to achieve safe solutions. This paper presents two main contributions: an annotated dataset and a benchmark between edge-computing hardware and deep learning models. The dataset is composed by nearly 5,400 annotated images. This dataset enabled to train nine object detectors: four SSD MobileNets, one EfficientDet, three YOLO-based detectors and YOLOR. These detectors were deployed and tested on three edge-computing hardware (TPU, CPU and GPU), and evaluated in terms of detection precision and inference time. The results showed that YOLOR was the best trunk detector achieving nearly 90% F1 score and an inference average time of 13.7ms on GPU. This work will favour the development of advanced vision perception systems for robotics in forestry operations.

Abstract
Robotics in agriculture faces several challenges, such as the unstructured characteristics of the environments, variability of luminosity conditions for perception systems, and vast field extensions. To implement autonomous navigation systems in these conditions, robots should be able to operate during large periods and travel long trajectories. For this reason, it is essential that simultaneous localization and mapping algorithms can perform in large-scale and long-term operating conditions. One of the main challenges for these methods is maintaining low memory resources while mapping extensive environments. This work tackles this issue, proposing a localization and mapping approach called VineSLAM that uses a topological mapping architecture to manage the memory resources required by the algorithm. This topological map is a graph-based structure where each node is agnostic to the type of data stored, enabling the creation of a multilayer mapping procedure. Also, a localization algorithm is implemented, which interacts with the topological map to perform access and search operations. Results show that our approach is aligned with the state-of-the-art regarding localization precision, being able to compute the robot pose in long and challenging trajectories in agriculture. In addition, we prove that the topological approach innovates the state-of-the-art memory management. The proposed algorithm requires less memory than the other benchmarked algorithms, and can maintain a constant memory allocation during the entire operation. This consists of a significant innovation, since our approach opens the possibility for the deployment of complex 3D SLAM algorithms in real-world applications without scale restrictions.

Abstract
Purpose: Visual perception enables robots to perceive the environment. Visual data is processed using computer vision algorithms that are usually time-expensive and require powerful devices to process the visual data in real-time, which is unfeasible for open-field robots with limited energy. This work benchmarks the performance of different heterogeneous platforms for object detection in real-time. This research benchmarks three architectures: embedded GPU-Graphical Processing Units (such as NVIDIA Jetson Nano 2 GB and 4 GB, and NVIDIA Jetson TX2), TPU-Tensor Processing Unit (such as Coral Dev Board TPU), and DPU-Deep Learning Processor Unit (such as in AMD-Xilinx ZCU104 Development Board, and AMD-Xilinx Kria KV260 Starter Kit). Methods: The authors used the RetinaNet ResNet-50 fine-tuned using the natural VineSet dataset. After the trained model was converted and compiled for target-specific hardware formats to improve the execution efficiency.Conclusions and Results: The platforms were assessed in terms of performance of the evaluation metrics and efficiency (time of inference). Graphical Processing Units (GPUs) were the slowest devices, running at 3 FPS to 5 FPS, and Field Programmable Gate Arrays (FPGAs) were the fastest devices, running at 14 FPS to 25 FPS. The efficiency of the Tensor Processing Unit (TPU) is irrelevant and similar to NVIDIA Jetson TX2. TPU and GPU are the most power-efficient, consuming about 5 W. The performance differences, in the evaluation metrics, across devices are irrelevant and have an F1 of about 70 % and mean Average Precision (mAP) of about 60 %.