Search

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

In this work we explore the application of AI to robotic welding. Robotic welding is a widely used technology in many industries, but robots currently do not have the capability to detect welding defects which get introduced due to various reasons in the welding process. We describe how deep-learning methods can be applied to detect weld defects in real-time by recording the welding process with microphones and a camera. Our findings are based on a large database with more than 4000 welding samples we collected which covers different weld types, materials and various defect categories. All deep learning models are trained in an unsupervised fashion because the space of possible defects is large and the defects in our data may contain biases. We demonstrate that a reliable real-time detection of most categories of weld defects is feasible both from audio and video, with improvements achieved by combining both modalities. Specifically, the multi-modal approach achieves an average Area-under-ROC-Curve (AUC) of 0.92 over all eleven defect types in our data. We conclude the paper with an analysis of the results by defect type and a discussion of future work., Comment: 21 pages

Having prior knowledge of an environment boosts the localization and mapping accuracy of robots. Several approaches in the literature have utilized architectural plans in this regard. However, almost all of them overlook the deviations between actual as-built environments and as-planned architectural designs, introducing bias in the estimations. To address this issue, we present a novel localization and mapping method denoted as deviations-informed Situational Graphs or diS-Graphs that integrates prior knowledge from architectural plans even in the presence of deviations. It is based on Situational Graphs (S-Graphs) that merge geometric models of the environment with 3D scene graphs into a multi-layered jointly optimizable factor graph. Our diS-Graph extracts information from architectural plans by first modeling them as a hierarchical factor graph, which we will call an Architectural Graph (A-Graph). While the robot explores the real environment, it estimates an S-Graph from its onboard sensors. We then use a novel matching algorithm to register the A-Graph and S-Graph in the same reference, and merge both of them with an explicit model of deviations. Finally, an alternating graph optimization strategy allows simultaneous global localization and mapping, as well as deviation estimation between both the A-Graph and the S-Graph. We perform several experiments in simulated and real datasets in the presence of deviations. On average, our diS-Graphs outperforms the baselines by a margin of approximately 43% in simulated environments and by 7% in real environments, while being able to estimate deviations up to 35 cm and 15 degrees.

For a multidimensional It\^o semimartingale, we consider the problem of estimating integrated volatility functionals. Jacod and Rosenbaum (2013) studied a plug-in type of estimator based on a Riemann sum approximation of the integrated functional and a spot volatility estimator with a forward uniform kernel. Motivated by recent results that show that spot volatility estimators with general two-side kernels of unbounded support are more accurate, in this paper, an estimator using a general kernel spot volatility estimator as the plug-in is considered. A biased central limit theorem for estimating the integrated functional is established with an optimal convergence rate. Unbiased central limit theorems for estimators with proper de-biasing terms are also obtained both at the optimal convergence regime for the bandwidth and when applying undersmoothing. Our results show that one can significantly reduce the estimator's bias by adopting a general kernel instead of the standard uniform kernel. Our proposed bias-corrected estimators are found to maintain remarkable robustness against bandwidth selection in a variety of sampling frequencies and functions., Comment: 80 pages

Language models of code have demonstrated state-of-the-art performance across various software engineering and source code analysis tasks. However, their demanding computational resource requirements and consequential environmental footprint remain as significant challenges. This work introduces ALPINE, an adaptive programming language-agnostic pruning technique designed to substantially reduce these models' computational overhead. The proposed method offers a pluggable layer that can be integrated with all Transformer-based models. With ALPINE, input sequences undergo adaptive compression throughout the pipeline, reaching a size up to $\times 3$ less their initial size, resulting in significantly reduced computational load. Our experiments on two software engineering tasks, defect prediction and code clone detection across three language models CodeBERT, GraphCodeBERT and UniXCoder show that ALPINE achieves up to a 50% reduction in FLOPs, a 58.1% decrease in memory footprint, and a 28.1% improvement in throughput on average. This led to a reduction in CO2 by up to $44.85$%. Importantly, it achieves the reduction in computation resources while maintaining up to 98.1% of the original predictive performance. These findings highlight the potential of ALPINE in making language models of code more resource-efficient and accessible while preserving their performance, contributing to the overall sustainability of adopting language models in software development. Also, it sheds light on redundant and noisy information in source code analysis corpora, as shown by the substantial sequence compression achieved by ALPINE.

Variability can be the pathway to understanding the physical processes in astrophysical jets, however, the high-cadence observations required to test particle acceleration models are still missing. Here we report on the first attempt to produce continuous, >24 hour polarization light curves of blazars using telescopes distributed across the globe and the rotation of the Earth to avoid the rising Sun. Our campaign involved 16 telescopes in Asia, Europe, and North America. We observed BL Lacertae and CGRaBS J0211+1051 for a combined 685 telescope hours. We find large variations in the polarization degree and angle for both sources in sub-hour timescales as well as a ~180 degree rotation of the polarization angle in CGRaBS J0211+1051 in less than two days. We compared our high-cadence observations to Particle-In-Cell magnetic reconnection and turbulent plasma simulations. We find that although the state of the art simulation frameworks can produce a large fraction of the polarization properties, they do not account for the entirety of the observed polarization behavior in blazar jets., Comment: 20 pages, 15 figures, 2 tables, accepted for publication in A&A. The data used in the paper are available here: https://doi.org/10.7910/DVN/IETSXS

Photoacoustic spectroscopys (PAS)-based methane (CH4) detectors have garnered significant attention with various developed systems using near-infrared (NIR) laser sources, which requires high-energy and narrow-linewidth laser sources to achieve high-sensitivity and low-concentration gas detection. The anti-resonant hollow-core fiber (ARHCF) lasers in the NIR and mid-infrared (MIR) spectral domain show a great potential for spectroscopy and high-resolution gas detection. In this work, we demonstrate the generation of a frequency-comb-like Raman laser with high pulse energy spanning from ultraviolet (UV) (328 nm) to NIR (2065 nm wavelength) based on a hydrogen (H2)-filled 7-ring ARHCF. The gas-filled ARHCF fiber is pumped with a custom-laser at 1044 nm with ~100 {\mu}J pulse energy and a few nanoseconds duration. Through stimulated Raman scattering process, we employ the sixth-order Stokes as case example located at ~1650 nm to demonstrate how the developed high-energy and narrow-linewidth laser source can effectively be used to detect CH4 in the NIR-II region using the photoacoustic modality. We report the efficient detection of CH4 with sensitivity as low as ~550 ppb with an integration time of ~40 s. In conclusion, the main goal of this work is to demonstrate and emphasize the potential of the gas-filled ARHCF laser technology for compact next-generation spectroscopy across different spectral regions., Comment: 18 pages, 7 figures

A novel high-frequency market-making approach in discrete time is proposed that admits closed-form solutions. By taking advantage of demand functions that are linear in the quoted bid and ask spreads with random coefficients, we model the variability of the partial filling of limit orders posted in a limit order book (LOB). As a result, we uncover new patterns as to how the demand's randomness affects the optimal placement strategy. We also allow the price process to follow general dynamics without any Brownian or martingale assumption as is commonly adopted in the literature. The most important feature of our optimal placement strategy is that it can react or adapt to the behavior of market orders online. Using LOB data, we train our model and reproduce the anticipated final profit and loss of the optimal strategy on a given testing date using the actual flow of orders in the LOB. Our adaptive optimal strategies outperform the non-adaptive strategy and those that quote limit orders at a fixed distance from the midprice., Comment: A preprint of this paper was distributed under the title of "Market Making with Stochastic Liquidity Demand: Simultaneous Order Arrival and Price Change Forecasts". The present paper extends the results in the referred preprint, which will remain as an unpublished manuscript

Gradient boosted decision trees have achieved remarkable success in several domains, particularly those that work with static tabular data. However, the application of gradient boosted models to signal processing is underexplored. In this work, we introduce gradient boosted filters for dynamic data, by employing Hammerstein systems in place of decision trees. We discuss the relationship of our approach to the Volterra series, providing the theoretical underpinning for its application. We demonstrate the effective generalizability of our approach with examples., Comment: 9 pages, 12 figures. Submitted to ICML 2024 and subsequently rejected for insufficient evaluation

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.

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

In this paper, we report on a multicore fiber-based (MCF) temperature sensor that operates in a wide thermal range and that is robustly packaged to withstand harsh environments. To develop the sensor, the fundamentals concerning the effect of temperature on such fibers have been analyzed in detail to predict the most temperature sensitive MCF geometry. Thanks to it, the device, which operates in reflection mode and consists of a short segment of strongly coupled MCF fusion spliced to a standard single mode fiber, shows higher sensitivity than other devices with identical configuration. Regarding its packaging, it consists of an inner ceramic and two outer metallic tubes to provide rigidity and protection against impacts or dirt. The device was calibrated for a thermal range from 25 C to 900 C and a K-type thermocouple was used as reference. Our results suggest that the manufactured optical thermometer is as accurate as the electronic one, reaching a sensitivity up to 29.426 pm/C with the advantage of being passive, compact and easy to fabricate and interrogate. Therefore, we believe this device is appealing for industrial applications that require highly sensitive temperature sensing in very demanding environments, and that the analysis included in this work could be analogously applied to develop sensitivity-optimized devices for other parameters of interest.

The present work deals with a curvature sensor that consists of two segments of asymmetric multicore fiber (MCF) fusion spliced with standard single mode fiber (SMF). The MCF comprises three strongly coupled cores; one of such cores is at the geometrical center of the MCF. The two segments of MCF are short, have different lengths (less than 2 cm each), and are rotated 180 degrees with respect to each other. The fabrication of the sensor was carried out with a fusion splicing machine that has the means for rotating optical fibers. It is demonstrated that the sensor behaves as two SMF-MCF-SMF structures in series, and consequently, it has enhanced sensitivity. The device proposed here can be used to sense the direction and amplitude of curvature by monitoring either wavelength shifts or intensity changes. In the latter case, high curvature sensitivity was observed. The device can also be used for the development of other highly sensitive sensors to monitor, for example, vibrations, force, pressure, or any other parameter that induces periodic or local curvature or bending to the MCF segments.

We report on a compact, highly sensitive all-fiber accelerometer suitable for low frequency and low amplitude vibration sensing. The sensing elements in the device are two short segments of strongly coupled asymmetric multicore fiber (MCF) fusion spliced at 180{\deg} with respect to each other. Such segments of MCF are sandwiched between standard single mode fibers. The reflection spectrum of the device exhibits a narrow spectrum whose height and position in wavelength changes when it is subjected to vibrations. The interrogation of the accelerometer was carried out by a spectrometer and a photodetector to measure simultaneously wavelength shift and light power variations. The device was subjected to a wide range of vibration frequencies, from 1 mHz to 30 Hz, and accelerations from 0.76 mg to 29.64 mg, and performed linearly, with a sensitivity of 2.213 nW/mg. Therefore, we believe the accelerometer reported here may represent an alternative to existing electronic and optical accelerometers, especially for low frequency and amplitude vibrations, thanks to its compactness, simplicity, cost-effectiveness, implementation easiness and high sensitivity.

Motivation. Large language models (LLMs) have exhibited remarkable proficiency in diverse software engineering (SE) tasks. Handling such tasks typically involves acquiring foundational coding knowledge on large, general-purpose datasets during a pre-training phase, and subsequently refining on smaller, task-specific datasets as part of a fine-tuning phase. Problem statement. While intra-dataset code duplication examines the intersection between the training and test splits within a given dataset and has been addressed in prior research, inter-dataset code duplication, which gauges the overlap between different datasets, remains largely unexplored. If this phenomenon exists, it could compromise the integrity of LLM evaluations because of the inclusion of fine-tuning test samples that were already encountered during pre-training, resulting in inflated performance metrics. Contribution. This paper explores the phenomenon of inter-dataset code duplication and its impact on evaluating LLMs across diverse SE tasks. Study design. We conduct an empirical study using the CodeSearchNet dataset (CSN), a widely adopted pre-training dataset, and five fine-tuning datasets used for various se tasks. We first identify the intersection between the pre-training and fine-tuning datasets using a deduplication process. Next, we pre-train two versions of LLMs using a subset of CSN: one leaky LLM and one non-leaky LLM. Finally, we fine-tune both models and compare their performances using leaky fine-tuning test samples. Results. Our findings reveal a potential threat to the evaluation of LLMs across multiple SE tasks, stemming from the inter-dataset code duplication phenomenon. We also demonstrate that this threat is accentuated by the chosen fine-tuning technique. Furthermore, we provide evidence that open-source models could be affected by inter-dataset duplication.

Artificial intelligence (AI) has acquired notorious relevance in modern computing as it effectively solves complex tasks traditionally done by humans. AI provides methods to represent and infer knowledge, efficiently manipulate texts and learn from vast amount of data. These characteristics are applicable in many activities that human find laborious or repetitive, as is the case of the analysis of scientific literature. Manually preparing and writing a systematic literature review (SLR) takes considerable time and effort, since it requires planning a strategy, conducting the literature search and analysis, and reporting the findings. Depending on the area under study, the number of papers retrieved can be of hundreds or thousands, meaning that filtering those relevant ones and extracting the key information becomes a costly and error-prone process. However, some of the involved tasks are repetitive and, therefore, subject to automation by means of AI. In this paper, we present a survey of AI techniques proposed in the last 15 years to help researchers conduct systematic analyses of scientific literature. We describe the tasks currently supported, the types of algorithms applied, and available tools proposed in 34 primary studies. This survey also provides a historical perspective of the evolution of the field and the role that humans can play in an increasingly automated SLR process., Comment: 25 pages, 3 figures, 1 table, journal paper

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

In this work, we develop a high energy laser at 1.4 {\mu}m wavelength through the 1st order vibrational Raman Stokes generation in a nitrogen (N2) filled nodeless anti-resonant hollow core fiber (ARHCF), pumped using a custom-made 1060 nm Yb-doped narrow-linewidth fiber laser with 3.7 ns pulse duration and 98 {\mu}J pulse energy. The maximum Raman energy of 26.5 {\mu}J is achieved at 15 bar N2 pressure, corresponding to a quantum efficiency of 45% and peak power of 8.03 kW with 3.3 ns pulse width. This Raman laser has a narrow linewidth of 0.16 nm, and it is tunable over ~2 nm range by thermally tuning the laser diode seed wavelength of the pump fiber laser. This work provides a promising alternative for developing high energy and narrow-linewidth lasers outside the gain spectral regions of rare earth ion doped fibers., Comment: 6 pages

Many methods for estimating integrated volatility and related functionals of semimartingales in the presence of jumps require specification of tuning parameters for their use in practice. In much of the available theory, tuning parameters are assumed to be deterministic and their values are specified only up to asymptotic constraints. However, in empirical work and in simulation studies, they are typically chosen to be random and data-dependent, with explicit choices often relying entirely on heuristics. In this paper, we consider novel data-driven tuning procedures for the truncated realized variations of a semimartingale with jumps based on a type of random fixed-point iteration. Being effectively automated, our approach alleviates the need for delicate decision-making regarding tuning parameters in practice and can be implemented using information regarding sampling frequency alone. We show our methods can lead to asymptotically efficient estimation of integrated volatility and exhibit superior finite-sample performance compared to popular alternatives in the literature.

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

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

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

We consider again stationary solutions to the spherically symmetric Einstein--Maxwell--Klein--Gordon system, commonly known as ``charged boson stars'', originally studied by Jetzer and Van Der Bij. We construct families of charged boson stars in the ground state, for different values of the charge parameter $q$, and different values of the central scalar field. Following Jetzer and Van Der Bij, one can define a critical value for the charge $q=q_c$ that corresponds to the value for which the Coulomb repulsion of the bosonic particles exactly cancels their newtonian gravitational attraction. We confirm the claim made by Pugliese et al. that super-critical solutions exist for a limited range of charges above the critical value $q>q_c$ (though we find an even smaller range of $q$ for which this is possible). Our analysis indicates, however, that all such super-critical solutions are gravitationally unbound, and are therefore expected to be unstable. One of the main results of our analysis is the fact that, even though we do find a family of slightly super-critical solutions in the sense that $q>q_c$, there are no super-critical solutions in the sense that the total charge $Q$ is larger than the total mass $M$ of the system.

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.

Fiducial markers can encode rich information about the environment and can aid Visual SLAM (VSLAM) approaches in reconstructing maps with practical semantic information. Current marker-based VSLAM approaches mainly utilize markers for improving feature detections in low-feature environments and/or for incorporating loop closure constraints, generating only low-level geometric maps of the environment prone to inaccuracies in complex environments. To bridge this gap, this paper presents a VSLAM approach utilizing a monocular camera along with fiducial markers to generate hierarchical representations of the environment while improving the camera pose estimate. The proposed approach detects semantic entities from the surroundings, including walls, corridors, and rooms encoded within markers, and appropriately adds topological constraints among them. Experimental results on a real-world dataset collected with a robot demonstrate that the proposed approach outperforms a traditional marker-based VSLAM baseline in terms of accuracy, given the addition of new constraints while creating enhanced map representations. Furthermore, it shows satisfactory results when comparing the reconstructed map quality to the one reconstructed using a LiDAR SLAM approach., Comment: 7 pages, 6 figures

In this paper, we tackle the problem of Unmanned Aerial (UA V) path planning in complex and uncertain environments by designing a Model Predictive Control (MPC), based on a Long-Short-Term Memory (LSTM) network integrated into the Deep Deterministic Policy Gradient algorithm. In the proposed solution, LSTM-MPC operates as a deterministic policy within the DDPG network, and it leverages a predicting pool to store predicted future states and actions for improved robustness and efficiency. The use of the predicting pool also enables the initialization of the critic network, leading to improved convergence speed and reduced failure rate compared to traditional reinforcement learning and deep reinforcement learning methods. The effectiveness of the proposed solution is evaluated by numerical simulations.