arXiv subjects

Mohammad Eskandari

Publications and source records attributed to Mohammad Eskandari.

6 recordsLinked to original sources

arXiv2026

Autonomous VR-Based Risk Detection for Situational Awareness in Dangerous Settings

In high-risk environments such as disaster response, situational awareness depends not only on detecting hazards but also on communicating them clearly to human operators. Vision Language Models (VLMs) have shown strong potential for scene understanding in safety-critical settings, yet their value as part of human-facing robotic systems remains underexplored. We present a VR-based Human Robot Interaction framework for studying how VLM-assisted robots can support situational awareness in simulated hazardous environments. In our system, a robot explores a virtual scene and queries a VLM to identify potential hazards and annotate user-facing points of interest. These annotations are presented to a human operator through an immersive VR interface. This framework enables controlled evaluation of both robotic hazard identification and the communication of safety-critical information to users. Results from our study indicate that the annotated VR interface was preferred over the unannotated baseline and that participants reported high clarity, usefulness, and comfort when interacting with the system. These findings suggest that combining VLM-based robotic perception with immersive visualization is a promising approach for supporting situational awareness in hazardous settings.

cs.RO↗

arXiv2026

Hazard or Anomaly? Evaluating VLMs for Understanding Dangers and Discrepancies

Modern safety-critical systems increasingly rely on human-robot interaction to reduce disaster risk and support decision-making during emergencies. Vision-Language Models (VLMs) are promising for these settings because they can interpret complex scenes and communicate safety-relevant information, but they still require careful evaluation to ensure reliable safety reasoning. In particular, current evaluations often frame danger recognition as a binary decision (Safe/Unsafe), making it unclear whether a model is identifying true physical hazards or merely reacting to unusual scene elements. We address this limitation by introducing an explicit distinction between hazard and anomaly, and by separately recognizing hazardous and anomalous states. We evaluate several state-of-the-art VLMs across two datasets and multiple prompting strategies to test whether this distinction changes model behavior. Our results show that VLMs frequently misinterpret anomalousness as hazardousness, revealing an over-reliance on contextual irregularity as a proxy for danger. We further show that explicitly separating anomaly from hazard provides a more informative evaluation of VLM safety reasoning and exposes failure modes that binary safety judgments can obscure. Our public dataset is available on Roboflow https://app.roboflow.com/vlm-in-context-anomaly-and-hazard-detection/camera-ready-roman-ds.

cs.CV↗

arXiv2025

Electromagnetic Investigation of Crosstalk in Bent Microstrip Lines with Partial and Apertured Shielding: Simulations and Measurements

This paper presents an electromagnetic investigation of the crosstalk between two bent microstrip lines (MLs) separated by a perforated planar shield. As an extension of our previous study, the effects of various discontinuities in either the MLs or the shield along the coupling path are analyzed through numerical simulations and validated by measurements. The underlying electromagnetic mechanisms are also discussed. Furthermore, multimodal wave theory in a rectangular waveguide is applied to predict crosstalk behavior when the shield contains an aperture. This study aims to conceptually elucidate complex crosstalk phenomena that are difficult to model using circuit theory, and successful predictions of crosstalk behavior are presented for different problem cases.

physics.app-ph↗

arXiv2024

A Modal Analysis of Electromagnetic Fields Coupling into an Open-Ended Waveguide Mounted on a Finite Flange: Evaluation of a Rectangular Waveguide with a Square Flange

This paper presents a modal analysis based on the reciprocity theorem to calculate the coupled/penetrated fields into an open-ended waveguide mounted on a finite flange. Although there is no limitation on the geometry and type of the external source, an infinitesimal dipole is chosen to produce a plane wave incident to the waveguide aperture. The proposed method relates the amplitude of each penetrated mode into the waveguide to the far-field radiation components of that mode from the waveguide aperture. The accuracy of the final result depends on the accuracy of the calculated radiated fields. The radiated field components are calculated considering the reflected fields due to the aperture and the diffracted fields due to the flange edges. For the first time, the impact of a finite flange on the penetrated fields into a waveguide is discussed comprehensively. The geometry of a rectangular waveguide mounted on a thick square flange is selected to be evaluated. The effects of changing the main parameters of the geometry on the penetrated fields are discussed rigorously in various examples. Our results are compared with 3D full-wave simulations, and an excellent agreement was found between the results while our analytical approach showing a 60 times faster performance. In addition, we compared our results with the measurement reported in a previous study.

physics.app-ph↗

arXiv2022

Design of a broadband and polarization insensitive THz absorber based on two layers of periodic arrays of graphene disks

In this paper, we analytically design a simple configuration of a broadband THz and polarization-insensitive absorber. The mentioned absorber consists of two layers of graphene disks, and the transmission line model is considered for the whole of the proposed absorber's structure to design it accurately. Therefore, the input admittance of the designed absorber is obtained by the transmission line model. Also, the real part of the input admittance is approximately tuned to be matched to the free space admittance. In contrast, the imaginary part of it is closely adjusted to zero around the central frequency of the THz absorber. Using only just two layers of Periodic Arrays of Graphene Disks (PAGDs) with one kind of dielectric as the material of substrates, it causes that the absorption of the structure can be achieved higher than 90 % by the Finite Element Method (FEM). Normalized bandwidth has reached up to 75.4% in 5 THz as the central frequency of the device. As the next step, we use the CST studio software to validate our designed absorber, and it will show that the numerical results will have the best matching with the analytical method.

physics.optics↗

arXiv2020

Design of a Broadband and Polarization Insensitive THz Absorber Based on Two Layers of Periodic Arrays of Graphene Disks

In this paper, we analytically design a simple configuration of a broadband THz and polarization-insensitive absorber. The mentioned absorber consists of two layers of graphene disks, and the transmission line model is considered for the whole of the proposed absorber's structure to design it accurately. Therefore, the input admittance of the designed absorber is obtained by the transmission line model. Also, the real part of the input admittance is approximately tuned to be matched to the free space admittance. In contrast, the imaginary part of it is closely adjusted to zero around the central frequency of the THz absorber. Using only just two layers of Periodic Arrays of Graphene Disks (PAGDs) with one kind of dielectric as the material of substrates, it causes that the absorption of the structure can be achieved higher than 90% by the Finite Element Method (FEM). Normalized bandwidth has reached up to 75.4% in 5 THz as the central frequency of the device. As the next step, we use the CST studio software to validate our designed absorber, and it will show that the numerical results will have the best matching with the analytical method.

physics.optics↗