Forming friendship with peers from diverse backgrounds is key to children’s social emotional development. In this study, we explored the use of social robot, Haru, as mediator for remote communication in children group, to support connection and friendship building. We invited children from different countries aged from 10 to 15 to participate in two interaction sessions with peers from other countries, after which we conducted interviews with children from three countries, focusing on their experiences, and perceptions of the robot’s roles in the process. The findings indicated that social robot Haru effectively served as an icebreaker and entertainer; However, improvements are needed in conversation flow, transitions between different roles, and supporting children’s autonomy in guiding the conversation and the depth of their communication.

Robots are becoming increasingly pervasive in our lives, evolving from service and security robots to social robots that build bonds and personal relationship with their human counterparts. We are witnessing a growing trend of robots being embedded within various groups and demographics. This paper presents social robots that mediate relationships between individuals, groups, and society as a whole, which we refer to as embodied mediators. These embodied mediators cater not only to individual needs, but also to communal and societal needs. As we develop these new types of robots with the potential to significantly impact society, it is imperative to establish guiding principles that ensure their safe and beneficial integration. This paper proposes three principles for embodied mediation that consider social underpinnings and extend beyond theory and into practice through use case scenarios currently under development.

Recent studies have tried to approach through Socially Assistive Robotics (SAR) the challenge of supporting elderly individuals living alone. In this paper, we introduce a cognitive architecture for SAR, incorporating planned and reactive behaviors. We emphasize the role of generative AI to provide a high-level semantic understanding and reasoning over dynamic environments, allowing more natural and flexible interactions with the user. The architecture has been deployed using the TIAGo mobile robotic manipulator in a simulated kitchen environment.

Social robots for children have focused mainly on conventional education domains such as teaching language, science, and math, while applications focusing on the enhancement of cultural competency are quite scarce. In this paper, we present a prototype of a robot-mediation framework for cross-cultural communication. This framework paves the way for a social robot to act as a mediator between groups of schoolchildren from different countries. First, we conducted a participatory design activity by an interdisciplinary team, resulting in the extraction of the design, robot’s roles, and technical requirements. Based on these requirements, we built the robot-mediation system prototype. We conducted a pilot study using the system with groups of high school children in Japan and Australia and our results show the potential of the system to drive children’s interest in communicating, sharing, and discussing cultural themes with their remote peers through the social robot.

Autonomous navigation is essential for the successful integration of mobile robots in agricultural operations. In structured fields, where permanent crops are usually disposed in row patterns, perception-based navigation is typically used for achieving safe and efficient in-row operation, whereas map-based navigation and other techniques are applied for transitioning between rows and from/to the robot base station. However, execution and coordination of different strategies has been mostly achieved using finite state machines or rule-based implementations, limiting orchestration of complex behaviors and scalability. This work presents a modular reasoning architecture that leverages behavior trees and a topological representation of the environment for deploying agricultural robots, switching between operation modes (perception or map-based) according to their topological state and goal, and embedding recovery behaviors in the event of failure. The system has been validated with different robotic platforms (mobile robot and retrofitted tractor) and large scale pilots (apple orchards and table grape vineyards), resulting in successful autonomous spraying demonstrations.

Steep slope vineyards pose specific challenges for autonomous robot navigation, therefore requiring accurate, robust and scalable localization and mapping solutions for such goal. In addition, due to the unevenness of the terrain, the identification of traversable zones is crucial for a safe operation, thus requiring a dense scene representation that captures these details. For such reasons, a novel SLAM architecture is presented in this work, characterized by a multi-sensor based dual factor-graph framework that integrates in real time wheel odometry, IMU, LIDAR and GNSS measurements, as well as heading and attitude data, generating a dense 3D map in point cloud format. The proposed system was tested with datasets obtained from a real robot navigating in vineyards with different levels of steepness, and benchmarked with state-of-the-art 3D LIDAR SLAM techniques. The presented results demonstrate superior performance over the compared methods, while maintaining overall map consistency and accuracy when matched with a reference model.

Building information modeling (BIM) has been increasingly adopted by construction project managers, as it covers the entire building life cycle and allows better coordination among different specialities. Mobile robots, on the other hand, are becoming the next frontier on automation of construction processes, and can largely exploit the geometric and semantic information provided by BIM models for many of their tasks. This work, in the context of the COBOLLEAGUE European project, presents a BIM-based interface that processes 3D building information, appending structural data to the pose-graph of a simultaneous localization and mapping (SLAM) system used by a mobile robot. This enables the robot to access a 3D map of the reference model and to determine its own pose in the construction environment, saving time and being able to perform autonomous navigation without previously exploring the map. Also, the methodology presented enables tracking the construction state and flagging u pdates t o t he r eference model as well, a relevant feature for the construction industry. Results from simulations with publicly available models and real tests at an industrial site indicate a coherent mapping and consistent robot localization over time.

Vineyard protection is a key task for winegrowers to maximize crop yield. Control of plagues, fungi and other threats are recurrent tasks in winery. This project is focused on the improvement of plague control tasks, specifically on the distribution and placement of pheromone dispensers for matting disruption, currently a labour-intensive and time consuming task. The operators walk through the vineyard hanging the dispensers in a regular distribution pattern. Grape project aims to automate the dispenser distribution in the vineyard using an outdoor autonomous ground platform with a robotic arm. Furthermore our platform is used to monitor the vineyard status and retrieve this information to the producer in order to to provide timely and precise information from the field.

This paper presents an unprecedented set of data in a challenging underground environment: the visitable sewers of Barcelona. To the best of our knowledge, this is the first data set involving ground and aerial robots in such scenario: the sewer inspection autonomous robot (SIAR) ground robot and the autonomous robot for sewer inspection aerial platform. These platforms captured data from a great variety of sensors, including sequences of red green blue-depth (RGB-D) images with their onboard cameras. The set consists of 14 logs of experiments that were obtained in more than 10 different days and in four different locations. The complete length of the experiments in the data set exceeds 5 km. In addition, we provide the users with a partial ground-truth and baselines of the localization of the platforms, which can be used for testing their localization and simultaneous localization and mapping (SLAM) algorithms. We also provide details on the setup and execution of each mission and a partial labeling of the elements found in the sewers. All the data were recorded by using the rosbag tool from robot operating system framework. Our goal is to make the data available to the scientific community as a benchmark to test localization, SLAM and classification algorithms in underground environments. The data set are available at .

Global Navigation Satellite Systems (GNSS) have been commonly used as a source for global localization in autonomous systems, including autonomous vehicles and robots. Different GNSS-based techniques exist to compute the position, velocity and time (PVT) of a moving rover, differing in the level of precision and complexity. The expected performance for each technique is well-studied but it is highly-dependant on the surrounding conditions and local effects such as occlusion or multipath. This paper presents the results after evaluating multiconstellation single-frequency data obtained from an extensive field campaign carried out in the port of Thessaloniki over several months, as part of the European GSA project LOGIMATIC. The paper, furthermore, focuses on the GNSS performance in container terminals, considered different from common urban and suburban scenarios and a potentially challenging environment due to the presence of containers, cranes, hangars and proximity to water. Analysis results show that the accuracy of the standalone PVT estimation methods for GPS and Galileo separately matched the expected performance numbers, with Galileo slightly outperforming GPS. The analysis also illustrated the effects of multipath and signal denial when operating in the proximity of cranes and hangars. Furthermore, the application of EGNOS/SBAS introduced a significant improvement, demonstrating the added value of EGNOS and Galileo over a traditional GPS only solution in these scenarios.

Unmanned Aerial Vehicles (UAV) are becoming an essential tool for evaluating the status and the changes in forest ecosystems. This is especially important in Japan due to the sheer magnitude and complexity of the forest area, made up mostly of natural mixed broadleaf deciduous forests. Additionally, Deep Learning (DL) is becoming more popular for forestry applications because it allows for the inclusion of expert human knowledge into the automatic image processing pipeline. In this paper we study and quantify issues related to the use of DL with our own UAV-acquired images in forestry applications such as: the effect of Transfer Learning (TL) and the Deep Learning architecture chosen or whether a simple patch-based framework may produce results in different practical problems. We use two different Deep Learning architectures (ResNet50 and UNet), two in-house datasets (winter and coastal forest) and focus on two separate problem formalizations (Multi-Label Patch or MLP classification and semantic segmentation). Our results show that Transfer Learning is necessary to obtain satisfactory outcome in the problem of MLP classification of deciduous vs evergreen trees in the winter orthomosaic dataset (with a 9.78% improvement from no transfer learning to transfer learning from a a general-purpose dataset). We also observe a further 2.7% improvement when Transfer Learning is performed from a dataset that is closer to our type of images. Finally, we demonstrate the applicability of the patch-based framework with the ResNet50 architecture in a different and complex example: Detection of the invasive broadleaf deciduous black locust (Robinia pseudoacacia) in an evergreen coniferous black pine (Pinus thunbergii) coastal forest typical of Japan. In this case we detect images containing the invasive species with a 75% of True Positives (TP) and 9% False Positives (FP) while the detection of native trees was 95% TP and 10% FP.

In this chapter we present the Autonomous Robot for Sewer Inspection (ARSI), a robotic system designed to make the work of inspection brigades safer and more efficient. ARSI uses an autonomous Micro Air Vehicle (MAV) to collect HD imagery and structural data in the sewers, while operators remain on the surface to supervise missions. Our compact quadrotor design is lightweight and robust, with a flight autonomy of 15 min and a payload capacity of 1 kg. It can be deployed without any special equipment, and operates in sewer tunnels as narrow as 80 cm. The sensor payload collects inspection data as well as inputs for the onboard software, allowing the ARSI MAV to follow pre-planned inspection paths autonomously. User-friendly interfaces are provided to plan, execute, and monitor sewer inspections. Data collected by the MAV onboard sensors is processed by our offline algorithms to generate detailed 3D models of the sewers, and perform automatic visual and structural analysis. Our data analysis software allows ARSI users to review all information and generate inspection reports for their clients. Our system was tested and validated during rigorous field tests in the city of Barcelona, Spain.

Tree counting and classification tasks in forestry are often addressed by costly, in terms of labour and money, field surveys carried on manually by forestry experts. Consequently, computer vision techniques have been used to automatically detect tree tops and classify them in terms of species or plant health status. The success of the algorithms are highly dependent on the data, and most significantly in its quantity and in the number of challenges it presents. In this work we used Unmanned Aerial Vehicles to acquired extremely challenging data from natural Japanese mixed forests. In a first step, six common clustering algorithms were used for tree top detection. Furthermore, we also assessed the usability of five different deep learning architectures to classify tree tops corresponding to trees in different degrees of affectation from a parasite infestation. Data covering an area of 40 ha are used in extensive experiments resulting in a detection accuracy of over 80% with high location accuracy and up to 90% with lower accuracy. Classification results produced by our algorithms reached error rates as low as 0.096 for classification. Data acquisition and runtime considerations show that this techniques is useful to process real forest data.

Counting trees is a common problem in forest applications often solved by performing field studies that are exceedingly cost-intensive in time and manpower. Consequently, many researchers have used computer vision techniques to automatically detect trees by finding tree tops. The success of these algorithms is highly dependent on the data that they are used on. We present a study using data acquired by ourselves in a natural mixed forest using an Unmanned Aerial Vehicle (UAV). Given the particularly challenging nature of our data, we developed a pre-processing step aimed at preparing the data so that it could be used with six common clustering algorithms to detect tree tops. Extensive experiments using data covering over 40 ha is presented and tree detection accuracy, tree counting metrics and computation and use time considerations are taken into account. Our algorithms detect over 80% with high location accuracy and up to 90% with lower accuracy. Tree counting errors range from 8% to 14% for most methods. Data Acquisition and runtime considerations show how this techniques are ready to have an immediate impact in the processing of real forest data.

Some manufacturing sectors require handling very large pieces, such as airplane fuselages and wings in the aeronautic industry. This presents a challenge that is usually overcome by manual and tedious handling of these large parts or the use of mechanically attached Automated Guided Vehicles (AGVs). In this paper, we show the implementation and testing of a wireless (detached) cooperative transportation solution, with no need of mechanical attachment between AGVs. Inspired by the mutual tidal locking of astronomical bodies, we derive the expressions for coordinated movements between AGVs, allowing to maintain their relative distance and orientation for cooperative transportation. We provide details on the implemented system pipeline and validation with two research robots and subsequently with two industrial AGVs, designed and manufactured by Aritex in Spain, demonstrating coordinated movements with alignment errors in the scale of millimeter/below degree in real tests. This solution overcomes the need for mechanical attachments, does not depend on specific details or configurations of the vehicles and could reduce the number of robots required, enabling the cost-efficient use of medium and small size AGVs in the cooperative transportation of large parts.

We acknowledge financial support from the Spanish Science Ministry (MINECO) through projects EB-SLAM (DPI2017-89564-P) and Maria de Maeztu Seal of Excellence (MDM-2016-0656); and from the European GNSS Agency Grant LOGIMATIC (H2020-Galileo-2015-1-687534).

This chapter describes how the different ICARUS unmanned search and rescue tools have been evaluated and validated using operational benchmarking techniques. Two large‐scale simulated disaster scenarios were organized: a simulated shipwreck and an earthquake response scenario. Next to these simulated response scenarios, where ICARUS tools were deployed in tight interaction with real end users, ICARUS tools also participated to a real relief, embedded in a team of end users for a flood response mission. These validation trials allow us to conclude that the ICARUS tools fulfil the user require‐ ments and goals set up at the beginning of the project.

Unmanned aerial platforms are a means to gather efficiently valuable aerial information to support the crisis manager for further tactical planning and deployment. They can provide continuous support to the coordinators and operators by scanning blocked sectors or establish an communication network. This chapter describes how aerial platforms were tailored to search and rescue (SAR) requirements, including the localisation and tracking of victims. In order to meet the end user demands, complementary platforms are proposed. A small long‐endurance solar aeroplane is used to provide the largest and fastest area coverage at the highest view, and therefore enabling the mapping functionality and potential detection of victims with operation times span up to a day. Complementary to the aeroplane, two rotary‐wing systems were deployed. A large coaxial‐quadrotor was used for outdoor delivery task and detailed close range inspection. Its ability to fly close to the terrain enables a thorough search for victims in a well‐defined sector. A smaller multicopter was used for inspection of the indoor environment. It is able for victim detection in collapsed buildings. Thus, autonomous functionality for precise localisation and positioning was developed to decrease the operator workload.

Precision agriculture is a key topic in robotics. The incursion of robots in the agriculture domain has become a reality in recent years. Nowadays, robotics is not only used for crop monitoring like for instance the use of aerial robots for growth control. Robots are increasingly playing key role in the daily life of the farmers and producers. Heavy tasks like pruning, seeding or even precise harvesting are the target topics of the robotics in agriculture. In this paper we present the ongoing work of GRAPE project, founded by Echord++ program from European Commission. GRAPE (Ground Robot for vineyArd Monitoring and ProtEction) consists in the automatic pheromone dispenser distribution for matting disruption in vineyards using an autonomous ground robot equipped with a robotic arm. GRAPE focuses on developing the on-board intelligence and the required algorithms, using commercial hardware. The consortium of the project is composed by Eurecat Technology Center [5], University Politecnico di Milano [13] and Vitirover [18].