87191 research outputs found
Sort by
Recognizing Robotic Components in Complex Environment
No full textModern robotic applications demand precise visual perception to enable intelligent interaction with dynamic environments. In complex robotic working scenarios-such as multi-arm coordination in industrial automation, collaborative robotic assistants in healthcare, and humanoid robots interacting with humans-accurate robotic arm segmentation is critical for avoiding collisions, improving motion planning, and enhancing manipulation precision. Despite its importance, this challenge has been largely overlooked in the field, with no publicly available datasets specifically designed for robotic arm segmentation. To bridge this gap, we introduce the Robotic Arm Segmentation Dataset (RASD), a manually curated dataset comprising 3,269 images covering diverse robotic arms in various environments. Additionally, we propose a novel segmentation framework that refines the output of a pre-trained segmentation model by integrating spatial and semantic information. Our method employs a Large Vision Model (LVM) to enhance spatial awareness through a textual prompt: "Where is the robotic arm in the image?". The extracted spatial and semantic features are then fused within a refined UNet, which takes an initial coarse segmentation mask as input and progressively refines it through a structured encoder-decoder process. Experimental results demonstrate that incorporating spatial-semantic fusion significantly improves seg-mentation accuracy compared to standard pre-trained models. By addressing a critical yet underexplored problem, our work contributes to safer and more intelligent robotic perception, paving the way for enhanced robotic autonomy in complex real-world scenarios
Risk, Artificial Intelligence, and the Governance of Migration: A Critical Discourse Analysis of the EU AI Act
No full textThe EU Artificial Intelligence Act represents one of the most ambitious regulatory frameworks to date, entailing policy regarding innovation, competitiveness, and the protection of fundamental rights. However, regulatory discourse surrounding AI is neither politically nor ideologically neutral. Through the employment of Critical Discourse Analysis, this paper explicates the discursive construction of ‘risk objects’ within the EU AI Act, focusing on the dilemmatic rhetorical constructions regarding AI governance, human rights, and migration management. The analysis highlights that while the Act positions AI misuse as a primary threat to fundamental rights, it simultaneously frames migrants and refugees as high-risk subjects; legitimising AI applications within border control and migration governance, and reproducing a discursive ideological dilemma. As a result, the Act employs securitisation rhetoric within rights-based governance frameworks, authorising algorithmic interventions that disproportionately target marginalised populations. The findings contribute to critical debates on AI governance by highlighting how risk-based regulatory frameworks function as instruments of power, reproducing existing socio-political asymmetries under the guise of harm prevention and ethical oversight within digital governance
Joint noise detection and L 2 , p -norm metric in least squares twin SVM for robust multiclass classification
No full textModelling of turbulence induced quasi-static aberrations at extremely large telescope scales
No full textA simulation has been used to explore the decay rates of time-averaged atmospheric turbulence residuals under frozen flow conditions. We have used our model to show that there is a significant variation in the power-law exponent when individual Zernike modes within the same azimuthal pair are considered. We have shown via simulation that the characteristic time-scale needed for a time-averaged Zernike mode to achieve a specified residual wavefront variance is dependent upon wind direction, meaning that both the and wind velocity profiles can have a large effect on the modal variance of observed quasi-static aberrations. Results are presented for both a single layer atmospheric model and an ESO standard 35 layer model – with wind directions and ground layer speeds taken from on-sky data. We model a 39 m telescope, demonstrating that for low order modes averaging to a threshold of at 550 nm may take thousands of seconds, which is substantially longer than the typical update rates of telescope control systems
Gravitational potential drives the concentration dependence of the stellar mass–halo mass relation
No full textWe investigate the origin of the scatter in the stellar mass–halo mass (SMHM) relation using the colibre cosmological hydrodynamical simulations. At fixed halo mass, we find a clear positive correlation between stellar mass and halo concentration, particularly in low-mass haloes between and , where all halo properties are computed from the corresponding dark-matter-only simulation. Two scenarios have been proposed to explain this trend: the earlier formation of higher-concentration haloes allows more time for star formation, or the deeper gravitational potential wells of higher-concentration haloes enhance baryon retention. To distinguish between them, we examine correlations between halo concentration, stellar mass, stellar age, and stellar metallicity. While, at fixed halo mass, halo concentration correlates with stellar age, stellar age itself shows only a weak correlation with stellar mass, indicating that early formation alone cannot account for the concentration-dependence in the scatter of the SMHM relation. In contrast, both stellar metallicity and halo concentration exhibit correlations with stellar mass. The connection between halo concentration and stellar metallicity persists even when simultaneously controlling for both halo mass and stellar mass. These results support the scenario in which the deeper gravitational potentials in higher-concentration haloes suppress feedback-driven outflows, thereby enhancing both baryon and metal retention
Scalable and Robust Multiband Modeling of AGN Light Curves in Rubin-LSST
No full textThe Vera C. Rubin Observatory’s Legacy Survey of Space and Time (LSST) will monitor tens of millions of active galactic nuclei (AGNs) for a period of 10 yr with an average cadence of 3 days in six broad photometric bands. This unprecedented data set will enable robust characterizations of AGN UV/optical variability across a wide range of AGN physical properties. However, existing tools for modeling AGN light curves are not yet capable of fully leveraging the volume, cadence, and multiband nature of LSST data. We present EzTaoX, a scalable light-curve modeling tool designed to take advantage of LSST’s multiband observations to simultaneously characterize AGN UV/optical stochastic variability and measure interband time delays. EzTaoX achieves a speed increase of ∼102–104× on CPUs over current tools with similar capabilities, while maintaining equal or better accuracy in recovering simulated variability properties. This performance gain enables continuum time-delay measurements for all AGNs discovered by LSST—both in the Wide Fast Deep survey and the Deep Drilling Fields—thereby opening new opportunities to probe AGN accretion-flow geometries. In addition, EzTaoX’s multiband capability allows for robust characterization of AGN stochastic variability down to hourly timescales, facilitating the identification of accreting low-mass AGNs—such as those residing in dwarf galaxies—through their distinctive variability signatures
Uncertainty-aware calibrated 3D human motion forecasting with latent conformal prediction
No full text3D human motion forecasting aims to predict the future dynamics of observed human movements, with applications ranging from autonomous driving to robotics. Estimating the uncertainty of each individual prediction is crucial for risk-bounded planning and control to ensure safety. However, generative model-based approaches struggle with uncertainty quantification due to their implicit probabilistic representations. To address this, we propose an uncertainty-aware probabilistic forecasting framework that parameterize complex human motions using invertible networks and forecast parameters of the future human motion distribution. This explicit probabilistic representation offers effective uncertainty quantification based on probability density. Additionally, to transform heuristic notions of uncertainty into statistically grounded estimates, we introduce a copula-based latent conformal prediction method for calibrating the predicted distribution. Experiments demonstrate the strong predictive performance of our approach in both deterministic and diverse setup, and validate the effectiveness of the uncertainty estimates
Data sources:
Access Repository Dashboard
Do you manage Open Research Online? Become a CORE Member to access insider analytics, issue reports and manage access to outputs from your repository in the CORE Repository Dashboard! 👇