Search

This paper investigates the application of Deep Reinforcement (DRL) Learning to address motion control challenges in drones for additive manufacturing (AM). Drone-based additive manufacturing promises flexible and autonomous material deposition in large-scale or hazardous environments. However, achieving robust real-time control of a multi-rotor aerial robot under varying payloads and potential disturbances remains challenging. Traditional controllers like PID often require frequent parameter re-tuning, limiting their applicability in dynamic scenarios. We propose a DRL framework that learns adaptable control policies for multi-rotor drones performing waypoint navigation in AM tasks. We compare Deep Deterministic Policy Gradient (DDPG) and Twin Delayed Deep Deterministic Policy Gradient (TD3) within a curriculum learning scheme designed to handle increasing complexity. Our experiments show TD3 consistently balances training stability, accuracy, and success, particularly when mass variability is introduced. These findings provide a scalable path toward robust, autonomous drone control in additive manufacturing.

Fiducial markers are widely used in various robotics tasks, facilitating enhanced navigation, object recognition, and scene understanding. Despite their advantages for robots and Augmented Reality (AR) applications, they often disrupt the visual aesthetics of environments because they are visible to humans, making them unsuitable for non-intrusive use cases. To address this gap, this paper presents "iMarkers"-innovative, unobtrusive fiducial markers detectable exclusively by robots equipped with specialized sensors. These markers offer high flexibility in production, allowing customization of their visibility range and encoding algorithms to suit various demands. The paper also introduces the hardware designs and software algorithms developed for detecting iMarkers, highlighting their adaptability and robustness in the detection and recognition stages. Various evaluations have demonstrated the effectiveness of iMarkers compared to conventional (printed) and blended fiducial markers and confirmed their applicability in diverse robotics scenarios., Comment: 12 pages, 10 figures, 2 tables

The classical picture of our Solar System being the archetypal outcome of planet formation has been rendered obsolete by the astonishing diversity of extrasolar-system architectures. From rare hot-Jupiters to abundant super-Earths and sub-Neptunes, most detected exoplanets have no analogs in our system, and their interior and atmospheric compositions remain largely unknown. Fortunately, new methodologies enable us to analyze exoplanet atmospheres, inferring their compositions, temperatures, dynamics, and even formation pathways. Specifically, ground-based high-resolution Doppler spectroscopy (HRDS) can disentangle spectral-line profiles of weak exo-atmospheric signals from the dominating features of Earth's atmosphere in the observed flux. For over a decade, HRDS has focused on hot Jupiters (close-orbiting gas giants) due to their high signal-to-noise ratio, which makes them ideal laboratories for advancing our knowledge. However, there have been concerns regarding potential biases in exo-atmospheric-detection methods, hindering comparative planetology. Here we propose a modeling framework based on extensive simulations of HRDS exo-atmospheric observations to systematically explore in-silico underlying biases in commonly-used pipelines, particularly under the presence of observational noise. Our findings show that exo-atmospheric detection-significances are highly contingent on details of the analysis-pipeline used, with different techniques responding differently to noise: A given technique may fail to recover a true-signal that is detected by another. Noise effects in the computed significances are non-trivial and pipeline-dependent. Statistical analyses provide a complementary tool to contextualize signal-significances, which will gain in relevance as we move towards studying the atmospheres of smaller, potentially habitable exoplanets with even weaker signals., Comment: 25 pages, 17 figures

Context. The detection of the He I 10830 A triplet in exoplanet atmospheres has opened a new window for probing planetary properties, including atmospheric escape. Unlike Lyman alpha, the triplet is less affected by ISM absorption. Sufficient XUV stellar irradiation may trigger the formation of the He I triplet via photoionization and posterior recombination processes in the planet atmospheres. Only a weak trend between stellar XUV and the planetary He I strength has been observed so far. Aims. We aim to confirm this mechanism for producing the He I absorption in exoplanetary atmospheres by examining a sample of planetary systems. Methods. We obtained homogeneous measurements of the planetary He I line EW and consistently computed the stellar XUV ionizing irradiation. We first derived new coronal models for the planet-host stars. We used updated data from the X-exoplanets database, archival X-ray spectra of M-type stars (including AU Mic and Proxima Cen), and new XMM-Newton X-ray data obtained for the CARMENES project. These data were complemented at longer wavelengths with publicly available HST, FUSE, and EUVE spectra. A total of 75 stars are carefully analyzed to obtain a new calibration between X-ray and EUV emission. Results. Two distinct relationships between stellar X-ray emission (5-100 A) and EUV_H (100-920 A) or EUV_He (100-504 A) radiation are obtained to scale the emission from late-type stellar coronae. A total of 48 systems with reported planetary He I 10830 A studies, exhibit a robust relationship between the planetary He I feature and the ionizing XUV_He received by the planet, corrected by stellar and planetary radii, and the planet's gravitational potential. Some outliers could be explained by a different atmospheric composition or the lack of planetary gaseous atmospheres. This relation may be used to predict the He I 10830 A absorption in exoplanet atmospheres., Comment: Accepted by A&A. 12 pages, 5 figures in the main body (42 pages, 22 figures, 21 tables including appendices)

The carbon isotope ratio ($^{12}\mathrm{C}/^{13}\mathrm{C}$) is a potential tracer of giant planet and brown dwarf formation. The GQ Lup system, hosting the K7 T Tauri star GQ Lup A and its substellar companion GQ Lup B, offers a unique opportunity to investigate this ratio in a young system. We aim to characterise the atmosphere of GQ Lup B, determining its temperature, chemical composition, spin, surface gravity, and $^{12}\mathrm{C}/^{13}\mathrm{C}$, while also measuring the same ratio for its host star, GQ Lup A. High-resolution K-band spectra of GQ Lup were obtained using CRIRES+ at the VLT. We modelled the starlight contribution from GQ Lup A and fitted GQ Lup B\'s spectrum with atmospheric models from petitRADTRANS. The $^{12}\mathrm{C}/^{13}\mathrm{C}$ ratio for GQ Lup A was derived using isotope-sensitive PHOENIX models. Atmospheric analysis of GQ Lup B revealed abundances of H$_2$O, $^{12}$CO, $^{13}$CO, HF, Na, Ca, and Ti, along with a C/O ratio of $0.50 \pm 0.01$, consistent with the solar value. The carbon isotope ratio was measured as $^{12}\mathrm{C}/^{13}\mathrm{C} = 53^{+7}_{-6}$ for GQ Lup B and $^{12}\mathrm{C}/^{13}\mathrm{C} = 51^{+10}_{-8}$ for GQ Lup A. Strong veiling of the photospheric lines of GQ Lup A was identified and accounted for. The similar $^{12}\mathrm{C}/^{13}\mathrm{C}$ values in GQ Lup A and B suggest a common origin from a shared material reservoir, supporting formation via disc fragmentation or gravitational collapse., Comment: Accepted for publication in A&A, 20 pages, 14 figures

High-resolution spectroscopic characterization of young super-Jovian planets enables precise constraints on elemental and isotopic abundances of their atmospheres. As part of the ESO SupJup Survey, we present high-resolution spectral observations of two wide-orbit super-Jupiters in YSES 1 (or TYC 8998-760-1) using the upgraded VLT/CRIRES+ (R~100,000) in K-band. We carry out free atmospheric retrieval analyses to constrain chemical and isotopic abundances, temperature structures, rotation velocities, and radial velocities. We confirm the previous detection of 13CO in YSES 1 b at a higher significance of 12.6{\sigma}, but point to a higher 12CO/13CO ratio of 88+/-13 (1{\sigma} confidence interval), consistent with the primary's isotope ratio 66+/-5. We retrieve a solar-like composition in YSES 1 b with a C/O=0.57+/-0.01, indicating a formation via gravitational instability or core accretion beyond the CO iceline. Additionally, the observations lead to detections of H2O and CO in the outer planet YSES 1 c at 7.3{\sigma} and 5.7{\sigma}, respectively. We constrain the atmospheric C/O ratio of YSES 1 c to be either solar or subsolar (C/O=0.36+/-0.15), indicating the accretion of oxygen-rich solids. The two companions have distinct vsini, 5.34+/-0.14 km/s for YSES 1 b and 11.3+/-2.1 km/s for YSES 1 c, despite their similar natal environments. This may indicate different spin axis inclinations or effective magnetic braking by the long-lived circumplanetary disk around YSES 1 b. YSES 1 represents an intriguing system for comparative studies of super-Jovian companions and linking present atmospheres to formation histories., Comment: 25 pages, 11 figure, accepted for publication in AJ. The extracted CRIRES+ spectra of the YSES-1 system can be found at https://doi.org/10.5281/zenodo.13664032

Understanding the relationships between geometric structures and semantic concepts is crucial for building accurate models of complex environments. In indoors, certain spatial constraints, such as the relative positioning of planes, remain consistent despite variations in layout. This paper explores how these invariant relationships can be captured in a graph SLAM framework by representing high-level concepts like rooms and walls, linking them to geometric elements like planes through an optimizable factor graph. Several efforts have tackled this issue with add-hoc solutions for each concept generation and with manually-defined factors. This paper proposes a novel method for metric-semantic factor graph generation which includes defining a semantic scene graph, integrating geometric information, and learning the interconnecting factors, all based on Graph Neural Networks (GNNs). An edge classification network (G-GNN) sorts the edges between planes into same room, same wall or none types. The resulting relations are clustered, generating a room or wall for each cluster. A second family of networks (F-GNN) infers the geometrical origin of the new nodes. The definition of the factors employs the same F-GNN used for the metric attribute of the generated nodes. Furthermore, share the new factor graph with the S-Graphs+ algorithm, extending its graph expressiveness and scene representation with the ultimate goal of improving the SLAM performance. The complexity of the environments is increased to N-plane rooms by training the networks on L-shaped rooms. The framework is evaluated in synthetic and simulated scenarios as no real datasets of the required complex layouts are available., Comment: Submitted to ICRA 2025

RGB-D cameras supply rich and dense visual and spatial information for various robotics tasks such as scene understanding, map reconstruction, and localization. Integrating depth and visual information can aid robots in localization and element mapping, advancing applications like 3D scene graph generation and Visual Simultaneous Localization and Mapping (VSLAM). While point cloud data containing such information is primarily used for enhanced scene understanding, exploiting their potential to capture and represent rich semantic information has yet to be adequately targeted. This paper presents a real-time pipeline for localizing building components, including wall and ground surfaces, by integrating geometric calculations for pure 3D plane detection followed by validating their semantic category using point cloud data from RGB-D cameras. It has a parallel multi-thread architecture to precisely estimate poses and equations of all the planes detected in the environment, filters the ones forming the map structure using a panoptic segmentation validation, and keeps only the validated building components. Incorporating the proposed method into a VSLAM framework confirmed that constraining the map with the detected environment-driven semantic elements can improve scene understanding and map reconstruction accuracy. It can also ensure (re-)association of these detected components into a unified 3D scene graph, bridging the gap between geometric accuracy and semantic understanding. Additionally, the pipeline allows for the detection of potential higher-level structural entities, such as rooms, by identifying the relationships between building components based on their layout., Comment: 6 pages, 5 figures. 3 tables

Robots navigating indoor environments often have access to architectural plans, which can serve as prior knowledge to enhance their localization and mapping capabilities. While some SLAM algorithms leverage these plans for global localization in real-world environments, they typically overlook a critical challenge: the "as-planned" architectural designs frequently deviate from the "as-built" real-world environments. To address this gap, we present a novel algorithm that tightly couples LIDAR-based simultaneous localization and mapping with architectural plans under the presence of deviations. Our method utilizes a multi-layered semantic representation to not only localize the robot, but also to estimate global alignment and structural deviations between "as-planned" and as-built environments in real-time. To validate our approach, we performed experiments in simulated and real datasets demonstrating robustness to structural deviations up to 35 cm and 15 degrees. On average, our method achieves 43% less localization error than baselines in simulated environments, while in real environments, the as-built 3D maps show 7% lower average alignment error

Transmission spectroscopy presents one of the most successful approaches for investigating the atmospheres of exoplanets. We analyzed the near-infrared high-resolution transmission spectrum of a hot Saturn, HD 149026 b, taken using CARMENES spectrograph ($\mathcal{R}\sim80,400$). We found evidence of H$_2$O at an S/N of $\sim$4.8. We also performed grid search using a Bayesian framework and constrained the orbital velocity $K_\mathrm{p}$ and rest velocity $V_{\mathrm{rest}}$ to $158.17^{+8.31}_{-7.90}$ $\mathrm{km\ s}^{-1}$ and $2.57^{+0.54}_{-0.57}$ $\mathrm{km\ s}^{-1}$, respectively. Whilst the retrieved $K_\mathrm{p}$ value is consistent with theoretical prediction, the retrieved $V_{\mathrm{rest}}$ value is highly red-shifted ($>$3-$\sigma$). This might be an indication of either anomalous atmospheric dynamics at play or an orbit with non-zero eccentricity. Additionally, we searched for HCN but no successful detection has been made possibly due to the relatively low S/N dataset. The detection of H$_2$O and subsequent abundance retrieval, coupled with analysis of other species such as CO at the $K$-band, for example, might help us to get some information about the atmospheric C/O ratio and metallicity, which in turn could give us some insight into the planet formation scenario., Comment: 22 pages, 15 figures, 1 table. Accepted for publication at AJ

It has been proposed that the distinct formation and evolution of exoplanets and brown dwarfs may affect the chemical and isotopic content of their atmospheres. Recent work has indeed shown differences in the $^{12}$C/$^{13}$C isotope ratio, provisionally attributed to the top-down formation of brown dwarfs and the core accretion pathway of super-Jupiters. The ESO SupJup Survey aims to disentangle the formation pathways of isolated brown dwarfs and planetary-mass companions using chemical and isotopic tracers. The survey uses high-resolution spectroscopy with the recently upgraded VLT/CRIRES$^+$ spectrograph, covering a total of 49 targets. Here, we present the first results: an atmospheric characterisation of DENIS J0255-4700, an isolated brown dwarf near the L-T transition. We analyse its K-band spectrum using a retrieval framework where the radiative transfer code petitRADTRANS is coupled to PyMultiNest. Gaussian Processes are employed to model inter-pixel correlations and we adopt an updated parameterisation of the PT-profile. Abundances of CO, H$_2$O, CH$_4$, and NH$_3$ are retrieved for this fast-rotating L-dwarf. The ExoMol H$_2$O line list provides a significantly better fit than that of HITEMP. A free-chemistry retrieval is strongly favoured over equilibrium chemistry, caused by an under-abundance of CH$_4$. The free-chemistry retrieval constrains a super-solar C/O-ratio of $\sim0.68$ and a solar metallicity. We find tentative evidence ($\sim3\sigma$) for the presence of $^{13}$CO, with a constraint on the isotope ratio of $\mathrm{^{12}C/^{13}C}=184^{+61}_{-40}$ and a lower limit of $\gtrsim97$, suggesting a depletion of $^{13}$C compared to the interstellar medium ($\sim68$). High-resolution, high signal-to-noise K-band spectra provide an excellent means to constrain the chemistry and isotopic content of sub-stellar objects, as is the main objective of the ESO SupJup Survey., Comment: Submitted to A&A

5G New Radio Time of Arrival (ToA) data has the potential to revolutionize indoor localization for micro aerial vehicles (MAVs). However, its performance under varying network setups, especially when combined with IMU data for real-time localization, has not been fully explored so far. In this study, we develop an error state Kalman filter (ESKF) and a pose graph optimization (PGO) approach to address this gap. We systematically evaluate the performance of the derived approaches for real-time MAV localization in realistic scenarios with 5G base stations in Line-Of-Sight (LOS), demonstrating the potential of 5G technologies in this domain. In order to experimentally test and compare our localization approaches, we augment the EuRoC MAV benchmark dataset for visual-inertial odometry with simulated yet highly realistic 5G ToA measurements. Our experimental results comprehensively assess the impact of varying network setups, including varying base station numbers and network configurations, on ToA-based MAV localization performance. The findings show promising results for seamless and robust localization using 5G ToA measurements, achieving an accuracy of 15 cm throughout the entire trajectory within a graph-based framework with five 5G base stations, and an accuracy of up to 34 cm in the case of ESKF-based localization. Additionally, we measure the run time of both algorithms and show that they are both fast enough for real-time implementation.

The integration of Unmanned Aerial Vehicles (UAVs) into Search and Rescue (SAR) missions presents a promising avenue for enhancing operational efficiency and effectiveness. However, the success of these missions is not solely dependent on the technical capabilities of the drones but also on their acceptance and interaction with humans on the ground. This paper explores the effect of human-centric factor in UAV trajectory planning for SAR missions. We introduce a novel approach based on the reinforcement learning augmented with Analytic Hierarchy Process and novel similarity-based experience replay to optimize UAV trajectories, balancing operational objectives with human comfort and safety considerations. Additionally, through a comprehensive survey, we investigate the impact of gender cues and anthropomorphism in UAV design on public acceptance and trust, revealing significant implications for drone interaction strategies in SAR. Our contributions include (1) a reinforcement learning framework for UAV trajectory planning that dynamically integrates multi-objective considerations, (2) an analysis of human perceptions towards gendered and anthropomorphized drones in SAR contexts, and (3) the application of similarity-based experience replay for enhanced learning efficiency in complex SAR scenarios. The findings offer valuable insights into designing UAV systems that are not only technically proficient but also aligned with human-centric values.

Ground-based high-resolution spectra provide a powerful tool for characterising exoplanet atmospheres. However, they are greatly hampered by the dominating telluric and stellar lines, which need to be removed prior to any analysis. Such removal techniques ("preparing pipelines") deform the spectrum, hence a key point is to account for this process in the forward models used in retrievals. We develop a formal derivation on how to prepare froward models for retrievals, in the case where the telluric and instrumental deformations can be represented as a matrix multiplied element-wise with the data. We also introduce the notion of "Bias Pipeline Metric" (BPM), that can be used to compare the bias potential of preparing pipelines. We use the resulting framework to retrieve simulated observations of 1-D and 3-D exoplanet atmospheres and to re-analyse high-resolution ($\mathcal{R} \approx 80\,400$) near infrared (0.96--1.71 $\mu$m) CARMENES transit data of HD~189733~b. We compare these results with those obtained from a CCF analysis. With our fiducial retrieval, we find a blueshift of the absorption features of $-5.51^{+0.66}_{-0.53}$ km$\cdot$s$^{-1}$. In addition, we retrieve a H$_2$O $\log_{10}$(VMR) of $-2.39^{+0.12}_{-0.16}$ and a temperature of $660^{+6}_{-11}$ K. We are also able to put upper limits for the abundances of CH$_4$, CO, H$_2$S, HCN and NH$_3$, consistent with a sub-solar metallicity atmosphere enriched in H$_2$O. We retrieve a broadened line shape, consistent with rotation- and wind-induced line broadening. Finally, we find a lower limit for the pressure of an opaque cloud consistent with a clear atmosphere, and find no evidence for hazes., Comment: 40 pages, 25 figures, accepted in The Astronomical Journal

Aerial robots play a vital role in various applications where the situational awareness of the robots concerning the environment is a fundamental demand. As one such use case, drones in GPS-denied environments require equipping with different sensors (e.g., vision sensors) that provide reliable sensing results while performing pose estimation and localization. In this paper, reconstructing the maps of indoor environments alongside generating 3D scene graphs for a high-level representation using a camera mounted on a drone is targeted. Accordingly, an aerial robot equipped with a companion computer and an RGB-D camera was built and employed to be appropriately integrated with a Visual Simultaneous Localization and Mapping (VSLAM) framework proposed by the authors. To enhance the situational awareness of the robot while reconstructing maps, various structural elements, including doors and walls, were labeled with printed fiducial markers, and a dictionary of the topological relations among them was fed to the system. The VSLAM system detects markers and reconstructs the map of the indoor areas enriched with higher-level semantic entities, including corridors and rooms. Another achievement is generating multi-layered vision-based situational graphs containing enhanced hierarchical representations of the indoor environment. In this regard, integrating VSLAM into the employed drone is the primary target of this paper to provide an end-to-end robot application for GPS-denied environments. To show the practicality of the system, various real-world condition experiments have been conducted in indoor scenarios with dissimilar structural layouts. Evaluations show the proposed drone application can perform adequately w.r.t. the ground-truth data and its baseline., Comment: 8 pages, 7 figures, 3 tables

Collaborative Simultaneous Localization and Mapping (CSLAM) is critical to enable multiple robots to operate in complex environments. Most CSLAM techniques rely on raw sensor measurement or low-level features such as keyframe descriptors, which can lead to wrong loop closures due to the lack of deep understanding of the environment. Moreover, the exchange of these measurements and low-level features among the robots requires the transmission of a significant amount of data, which limits the scalability of the system. To overcome these limitations, we present Multi S-Graphs, a decentralized CSLAM system that utilizes high-level semantic-relational information embedded in the four-layered hierarchical and optimizable situational graphs for cooperative map generation and localization in structured environments while minimizing the information exchanged between the robots. To support this, we present a novel room-based descriptor which, along with its connected walls, is used to perform inter-robot loop closures, addressing the challenges of multi-robot kidnapped problem initialization. Multiple experiments in simulated and real environments validate the improvement in accuracy and robustness of the proposed approach while reducing the amount of data exchanged between robots compared to other state-of-the-art approaches. Software available within a docker image: https://github.com/snt-arg/multi_s_graphs_docker, Comment: 8 pages paper presented to IEEE RA-L

Context: High-resolution spectrographs fed by adaptive optics (AO) provide a unique opportunity to characterize directly imaged exoplanets. Observations with such instruments allow us to probe the atmospheric composition, spin rotation, and radial velocity of the planet, thereby helping to reveal information on its formation and migration history. The recent upgrade of the Cryogenic High-Resolution Infrared Echelle Spectrograph (CRIRES+) at the VLT makes it a highly suitable instrument for characterizing directly imaged exoplanets. Aims: In this work, we report on observations of $\beta$ Pictoris b with CRIRES+ and use them to constrain the planets atmospheric properties and update the estimation of its spin rotation. Methods: The data were reduced using the open-source \textit{pycrires} package. We subsequently forward-modeled the stellar, planetary, and systematic contribution to the data to detect molecules in the planet's atmosphere. We also used atmospheric retrievals to provide new constraints on its atmosphere. Results: We confidently detected water and carbon monoxide in the atmosphere of $\beta$ Pictoris b and retrieved a slightly sub-solar carbon-to-oxygen ratio, which is in agreement with previous results. The interpretation is hampered by our limited knowledge of the C/O ratio of the host star. We also obtained a much improved constraint on its spin rotation of $19.9 \pm 1.0$ km/s, which gives a rotation period of $8.7 \pm 0.8$ hours, assuming no obliquity. We find that there is a degeneracy between the metallicity and clouds, but this has minimal impact on the retrieved C/O, $v\sin{i}$, and radial velocity. Our results show that CRIRES+ is performing well and stands as a highly useful instrument for characterizing directly imaged planets., Comment: Accepted for publication in A&A

Recently, a set of graph-based tools have been introduced for the identification of singular events of O3, NO2 and temperature time series, as well as description of their dynamics. These are based on the use of the Visibility Graphs (VG). In this work, an improvement of the original approach is proposed, being called Upside-Down Visibility Graph (UDVG). It adds the possibility of investigating the singular lowest episodes, instead of the highest. Results confirm the applicability of the new method for describing the multifractal nature of the underlying O3, NO2, and temperature. Asymmetries in the NO2 degree distribution are observed, possibly due to the interaction with different chemicals. Furthermore, a comparison of VG and UDVG has been performed and the outcomes show that they describe opposite subsets of the time series (low and high values) as expected. The combination of the results from the two networks is proposed and evaluated, with the aim of obtaining all the information at once. It turns out to be a more complete tool for singularity detection in photochemical time series, which could be a valuable asset for future research., Comment: 35 pages, 7 figures

In this work, an analysis of multifractal parameters of daily precipitation series over the Iberian Peninsula was performed in two 30-year periods to explore whether these properties follow any pattern. Fluctuations of precipitation series show three different scaling regions. Only two distinct regimes for small and large timescales can be confirmed, while intermediate scales are part of a transition region. It is also observed a certain degree of multifractality, which is higher for small timescales. At these scales, there is a high persistence which follows the spatial gradient of the annual precipitation. Moreover, multifractal parameters of the precipitation are modified according to complex spatial and temporal patterns. Only persistence uniformly decreases in the last period. Other relevant findings are the changes in the asymmetry of multifractal spectra in the eastern belt at larger timescales, which might be related to the change in the behavior of the Mediterranean cyclones., Comment: 12 pages, 8 figures

Recent works on SLAM extend their pose graphs with higher-level semantic concepts like Rooms exploiting relationships between them, to provide, not only a richer representation of the situation/environment but also to improve the accuracy of its estimation. Concretely, our previous work, Situational Graphs (S-Graphs+), a pioneer in jointly leveraging semantic relationships in the factor optimization process, relies on semantic entities such as Planes and Rooms, whose relationship is mathematically defined. Nevertheless, there is no unique approach to finding all the hidden patterns in lower-level factor-graphs that correspond to high-level concepts of different natures. It is currently tackled with ad-hoc algorithms, which limits its graph expressiveness. To overcome this limitation, in this work, we propose an algorithm based on Graph Neural Networks for learning high-level semantic-relational concepts that can be inferred from the low-level factor graph. Given a set of mapped Planes our algorithm is capable of inferring Room entities relating to the Planes. Additionally, to demonstrate the versatility of our method, our algorithm can infer an additional semantic-relational concept, i.e. Wall, and its relationship with its Planes. We validate our method in both simulated and real datasets demonstrating improved performance over two baseline approaches. Furthermore, we integrate our method into the S-Graphs+ algorithm providing improved pose and map accuracy compared to the baseline while further enhancing the scene representation.

In this study, we investigate the human perception of gender and bias toward non-humanoid robots. As robots increasingly integrate into various sectors beyond industry, it is essential to understand how humans engage with non-humanoid robotic forms. This research focuses on the role of anthropomorphic cues, including gender signals, in influencing human robot interaction and user acceptance of non-humanoid robots. Through three surveys, we analyze how design elements such as physical appearance, voice modulation, and behavioral attributes affect gender perception and task suitability. Our findings demonstrate that even non-humanoid robots like Spot, Mini-Cheetah, and drones are subject to gender attribution based on anthropomorphic features, affecting their perceived roles and operational trustworthiness. The results underscore the importance of balancing design elements to optimize both functional efficiency and user relatability, particularly in critical contexts.

This paper presents a Hierarchical Reinforcement Learning methodology tailored for optimizing CubeSat task scheduling in Low Earth Orbits (LEO). Incorporating a high-level policy for global task distribution and a low-level policy for real-time adaptations as a safety mechanism, our approach integrates the Similarity Attention-based Encoder (SABE) for task prioritization and an MLP estimator for energy consumption forecasting. Integrating this mechanism creates a safe and fault-tolerant system for CubeSat task scheduling. Simulation results validate the Hierarchical Reinforcement Learning superior convergence and task success rate, outperforming both the MADDPG model and traditional random scheduling across multiple CubeSat configurations.

Situational Graphs (S-Graphs) merge geometric models of the environment generated by Simultaneous Localization and Mapping (SLAM) approaches with 3D scene graphs into a multi-layered jointly optimizable factor graph. As an advantage, S-Graphs not only offer a more comprehensive robotic situational awareness by combining geometric maps with diverse hierarchically organized semantic entities and their topological relationships within one graph, but they also lead to improved performance of localization and mapping on the SLAM level by exploiting semantic information. In this paper, we introduce a vision-based version of S-Graphs where a conventional \ac{VSLAM} system is used for low-level feature tracking and mapping. In addition, the framework exploits the potential of fiducial markers (both visible as well as our recently introduced transparent or fully invisible markers) to encode comprehensive information about environments and the objects within them. The markers aid in identifying and mapping structural-level semantic entities, including walls and doors in the environment, with reliable poses in the global reference, subsequently establishing meaningful associations with higher-level entities, including corridors and rooms. However, in addition to including semantic entities, the semantic and geometric constraints imposed by the fiducial markers are also utilized to improve the reconstructed map's quality and reduce localization errors. Experimental results on a real-world dataset collected using legged robots show that our framework excels in crafting a richer, multi-layered hierarchical map and enhances robot pose accuracy at the same time., Comment: 16 pages, 6 figures, 2 tables

3D scene graphs hierarchically represent the environment appropriately organizing different environmental entities in various layers. Our previous work on situational graphs extends the concept of 3D scene graph to SLAM by tightly coupling the robot poses with the scene graph entities, achieving state-of-the-art results. Though, one of the limitations of S-Graphs is scalability in really large environments due to the increased graph size over time, increasing the computational complexity. To overcome this limitation in this work we present an initial research of an improved version of S-Graphs exploiting the hierarchy to reduce the graph size by marginalizing redundant robot poses and their connections to the observations of the same structural entities. Firstly, we propose the generation and optimization of room-local graphs encompassing all graph entities within a room-like structure. These room-local graphs are used to compress the S-Graphs marginalizing the redundant robot keyframes within the given room. We then perform windowed local optimization of the compressed graph at regular time-distance intervals. A global optimization of the compressed graph is performed every time a loop closure is detected. We show similar accuracy compared to the baseline while showing a 39.81% reduction in the computation time with respect to the baseline., Comment: 4 pages, 3 figures, IROS 2023 Workshop Paper

HD235088 (TOI-1430) is a young star known to host a sub-Neptune-sized planet candidate. We validated the planetary nature of HD235088 b with multiband photometry, refined its planetary parameters, and obtained a new age estimate of the host star, placing it at 600-800 Myr. Previous spectroscopic observations of a single transit detected an excess absorption of He I coincident in time with the planet candidate transit. Here, we confirm the presence of He I in the atmosphere of HD235088 b with one transit observed with CARMENES. We also detected hints of variability in the strength of the helium signal, with an absorption of $-$0.91$\pm$0.11%, which is slightly deeper (2$\sigma$) than the previous measurement. Furthermore, we simulated the He I signal with a spherically symmetric 1D hydrodynamic model, finding that the upper atmosphere of HD235088 b escapes hydrodynamically with a significant mass loss rate of (1.5-5) $\times$10$^{10}$g s$^{-1}$, in a relatively cold outflow, with $T$=3125$\pm$375 K, in the photon-limited escape regime. HD235088 b ($R_{p}$ = 2.045$\pm$0.075 R$_{\oplus}$) is the smallest planet found to date with a solid atmospheric detection - not just of He I but any other atom or molecule. This positions it a benchmark planet for further analyses of evolving young sub-Neptune atmospheres., Comment: Accepted for publication in A&A. 17 pages, 18 figures

Path planning is a basic capability of autonomous mobile robots. Former approaches in path planning exploit only the given geometric information from the environment without leveraging the inherent semantics within the environment. The recently presented S-Graphs constructs 3D situational graphs incorporating geometric, semantic, and relational aspects between the elements to improve the overall scene understanding and the localization of the robot. But these works do not exploit the underlying semantic graphs for improving the path planning for mobile robots. To that aim, in this paper, we present S-Nav a novel semantic-geometric path planner for mobile robots. It leverages S-Graphs to enable fast and robust hierarchical high-level planning in complex indoor environments. The hierarchical architecture of S-Nav adds a novel semantic search on top of a traditional geometric planner as well as precise map reconstruction from S-Graphs to improve planning speed, robustness, and path quality. We demonstrate improved results of S-Nav in a synthetic environment., Comment: 6 pages, 4 figures

This paper explores the potential of 5G new radio (NR) Time-of-Arrival (TOA) data for indoor drone localization under different scenarios and conditions when fused with inertial measurement unit (IMU) data. Our approach involves performing graph-based optimization to estimate the drone's position and orientation from the multiple sensor measurements. Due to the lack of real-world data, we use Matlab 5G toolbox and QuaDRiGa (quasi-deterministic radio channel generator) channel simulator to generate TOA measurements for the EuRoC MAV indoor dataset that provides IMU readings and ground truths 6DoF poses of a flying drone. Hence, we create twelve sequences combining three predefined indoor scenarios setups of QuaDRiGa with 2 to 5 base station antennas. Therefore, experimental results demonstrate that, for a sufficient number of base stations and a high bandwidth 5G configuration, the pose graph optimization approach achieves accurate drone localization, with an average error of less than 15 cm on the overall trajectory. Furthermore, the adopted graph-based optimization algorithm is fast and can be easily implemented for onboard real-time pose tracking on a micro aerial vehicle (MAV).

In this paper, we propose a solution for graph-based global robot simultaneous localization and mapping (SLAM) using architectural plans. Before the start of the robot operation, the previously available architectural plan of the building is converted into our proposed architectural graph (A-Graph). When the robot starts its operation, it uses its onboard LIDAR and odometry to carry out an online SLAM relying on our situational graph (S-Graph), which includes both, a representation of the environment with multiple levels of abstractions, such as walls or rooms, and their relationships, as well as the robot poses with their associated keyframes. Our novel graph-to-graph matching method is used to relate the aforementioned S-Graph and A-Graph, which are aligned and merged, resulting in our novel informed Situational Graph (iS-Graph). Our iS-Graph not only provides graph-based global robot localization, but it extends the graph-based SLAM capabilities of the S-Graph by incorporating into it the prior knowledge of the environment existing in the architectural plan, Comment: 4 Page Workshop paper for ICRA 2023. arXiv admin note: substantial text overlap with arXiv:2303.02076

Collaborative Simultaneous Localization and Mapping (CSLAM) is a critical capability for enabling multiple robots to operate in complex environments. Most CSLAM techniques rely on the transmission of low-level features for visual and LiDAR-based approaches, which are used for pose graph optimization. However, these low-level features can lead to incorrect loop closures, negatively impacting map generation.Recent approaches have proposed the use of high-level semantic information in the form of Hierarchical Semantic Graphs to improve the loop closure procedures and overall precision of SLAM algorithms. In this work, we present Multi S-Graphs, an S-graphs [1] based distributed CSLAM algorithm that utilizes high-level semantic information for cooperative map generation while minimizing the amount of information exchanged between robots. Experimental results demonstrate the promising performance of the proposed algorithm in map generation tasks., Comment: Presented as a candidate to the Distributed Graph Algorithms for Robotics Workshop at ICRA23

Characterisation of atmospheres undergoing photo-evaporation is key to understanding the formation, evolution, and diversity of planets. However, only a few upper atmospheres that experience this kind of hydrodynamic escape have been characterised. Our aim is to characterise the upper atmospheres of the hot Jupiters HAT-P-32 b and WASP-69 b, the warm sub-Neptune GJ 1214 b, and the ultra-hot Jupiter WASP-76 b through high-resolution observations of their HeI triplet absorption. In addition, we also reanalyse the warm Neptune GJ 3470 b and the hot Jupiter HD 189733 b. We used a spherically symmetric 1D hydrodynamic model coupled with a non-local thermodynamic equilibrium model. Comparing synthetic absorption spectra with observations, we constrained the main parameters of the upper atmosphere of these planets and classify them according to their hydrodynamic regime. Our results show that HAT-P-32 b photo-evaporates at (130$\pm$70)$\times$10$^{11}$ gs$^{-1}$ with a hot (12 400$\pm$2900 K) upper atmosphere; WASP-69 b loses its atmosphere at (0.9$\pm$0.5)$\times$10$^{11}$ gs$^{-1}$ and 5250$\pm$750 K; and GJ 1214 b, with a relatively cold outflow of 3750$\pm$750 K, photo-evaporates at (1.3$\pm$1.1)$\times$10$^{11}$ gs$^{-1}$. For WASP-76 b, its weak absorption prevents us from constraining its temperature and mass-loss rate significantly; we obtained ranges of 6000-17 000\,K and 23.5$\pm$21.5$\times$10$^{11}$ gs$^{-1}$. Our reanalysis of GJ 3470 b yields colder temperatures, 3400$\pm$350 K, but practically the same mass-loss rate as in our previous results. Our reanalysis of HD 189733 b yields a slightly higher mass-loss rate, (1.4$\pm$0.5)$\times$10$^{11}$ gs$^{-1}$, and temperature, 12 700$\pm$900 K compared to previous estimates. Our results support that photo-evaporated outflows tend to be very light.

In this paper, an adaptive super-twisting controller is designed for an agile maneuvering quadrotor unmanned aerial vehicle to achieve accurate trajectory tracking in the presence of external disturbances. A cascaded control architecture is designed to determine the desired accelerations using the proposed controller and subsequently used to compute the desired orientation and angular rates. The finite-time convergence of sliding functions and closed-loop system stability are analytically proven. Furthermore, the restrictive assumption on the maximum variation of the disturbance is relaxed by designing a gain adaptation law and low-pass filtering of the estimated equivalent control. The proper selection of design parameters is discussed in detail. Finally, the effectiveness of the proposed method is evaluated by high-fidelity software-in-the-loop simulations and validated by experimental studies., Comment: We are working on a new version of this paper and revising some technical parts. We will replace the new version as soon as it is carefully revised

In this paper, we propose a solution for legged robot localization using architectural plans. Our specific contributions towards this goal are several. Firstly, we develop a method for converting the plan of a building into what we denote as an architectural graph (A-Graph). When the robot starts moving in an environment, we assume it has no knowledge about it, and it estimates an online situational graph representation (S-Graph) of its surroundings. We develop a novel graph-to-graph matching method, in order to relate the S-Graph estimated online from the robot sensors and the A-Graph extracted from the building plans. Note the challenge in this, as the S-Graph may show a partial view of the full A-Graph, their nodes are heterogeneous and their reference frames are different. After the matching, both graphs are aligned and merged, resulting in what we denote as an informed Situational Graph (iS-Graph), with which we achieve global robot localization and exploitation of prior knowledge from the building plans. Our experiments show that our pipeline shows a higher robustness and a significantly lower pose error than several LiDAR localization baselines., Comment: 8 pages, 5 Figures, IROS 2023 conference

In this paper, we investigate requirements to prepare an application for Specific Operations Risk Assessment (SORA), regulated by European Union Aviation Safety Agency (EASA) to obtain flight authorization for Unmanned Aerial Vehicles (UAVs) operations and propose some perspectives to automate the approach based on our successful application. Preparation of SORA requires expert knowledge as it contains technicalities. Also, the whole process is an iterative and time-consuming one. It is even more challenging for higher-risk operations, such as those in urban environments, near airports, and multi- and customized models for research activities. SORA process limits the potential socio-economic impacts of innovative UAV capabilities. Therefore, in this paper, we present a SORA example, review the steps and highlight challenges. Accordingly, we propose an alternative workflow, considering the same steps, while addressing the challenges and pitfalls, to shorten the whole process. Furthermore, we present a comprehensive list of preliminary technical procedures, including the pre/during/post-flight checklists, design and installation appraisal, flight logbook, operational manual, training manual, and General Data Protection Regulation (GDPR), which are not explicitly instructed in SORA manual. Moreover, we propose the initial idea to create an automated SORA workflow to facilitate obtaining authorization, which is significantly helpful for operators, especially the scientific community, to conduct experimental operations.

This paper presents an integrated approach that combines trajectory optimization and Artificial Potential Field (APF) method for real-time optimal Unmanned Aerial Vehicle (UAV) trajectory planning and dynamic collision avoidance. A minimum-time trajectory optimization problem is formulated with initial and final positions as boundary conditions and collision avoidance as constraints. It is transcribed into a nonlinear programming problem using Chebyshev pseudospectral method. The state and control histories are approximated by using Lagrange polynomials and the collocation points are used to satisfy constraints. A novel sigmoid-type collision avoidance constraint is proposed to overcome the drawbacks of Lagrange polynomial approximation in pseudospectral methods that only guarantees inequality constraint satisfaction only at nodal points. Automatic differentiation of cost function and constraints is used to quickly determine their gradient and Jacobian, respectively. An APF method is used to update the optimal control inputs for guaranteeing collision avoidance. The trajectory optimization and APF method are implemented in a closed-loop fashion continuously, but in parallel at moderate and high frequencies, respectively. The initial guess for the optimization is provided based on the previous solution. The proposed approach is tested and validated through indoor experiments.