arXiv subjects

Omid Ghasemalizadeh

Publications and source records attributed to Omid Ghasemalizadeh.

12 recordsLinked to original sources

arXiv2025

Attribute-based Object Grounding and Robot Grasp Detection with Spatial Reasoning

Enabling robots to grasp objects specified through natural language is essential for effective human-robot interaction, yet it remains a significant challenge. Existing approaches often struggle with open-form language expressions and typically assume unambiguous target objects without duplicates. Moreover, they frequently rely on costly, dense pixel-wise annotations for both object grounding and grasp configuration. We present Attribute-based Object Grounding and Robotic Grasping (OGRG), a novel framework that interprets open-form language expressions and performs spatial reasoning to ground target objects and predict planar grasp poses, even in scenes containing duplicated object instances. We investigate OGRG in two settings: (1) Referring Grasp Synthesis (RGS) under pixel-wise full supervision, and (2) Referring Grasp Affordance (RGA) using weakly supervised learning with only single-pixel grasp annotations. Key contributions include a bi-directional vision-language fusion module and the integration of depth information to enhance geometric reasoning, improving both grounding and grasping performance. Experiment results show that OGRG outperforms strong baselines in tabletop scenes with diverse spatial language instructions. In RGS, it operates at 17.59 FPS on a single NVIDIA RTX 2080 Ti GPU, enabling potential use in closed-loop or multi-object sequential grasping, while delivering superior grounding and grasp prediction accuracy compared to all the baselines considered. Under the weakly supervised RGA setting, OGRG also surpasses baseline grasp-success rates in both simulation and real-robot trials, underscoring the effectiveness of its spatial reasoning design. Project page: https://z.umn.edu/ogrg

cs.RO↗

arXiv2025

POp-GS: Next Best View in 3D-Gaussian Splatting with P-Optimality

In this paper, we present a novel algorithm for quantifying uncertainty and information gained within 3D Gaussian Splatting (3D-GS) through P-Optimality. While 3D-GS has proven to be a useful world model with high-quality rasterizations, it does not natively quantify uncertainty or information, posing a challenge for real-world applications such as 3D-GS SLAM. We propose to quantify information gain in 3D-GS by reformulating the problem through the lens of optimal experimental design, which is a classical solution widely used in literature. By restructuring information quantification of 3D-GS through optimal experimental design, we arrive at multiple solutions, of which T-Optimality and D-Optimality perform the best quantitatively and qualitatively as measured on two popular datasets. Additionally, we propose a block diagonal covariance approximation which provides a measure of correlation at the expense of a greater computation cost.

cs.CV↗

arXiv2025

CSCPR: Cross-Source-Context Indoor RGB-D Place Recognition

We extend our previous work, PoCo, and present a new algorithm, Cross-Source-Context Place Recognition (CSCPR), for RGB-D indoor place recognition that integrates global retrieval and reranking into an end-to-end model and keeps the consistency of using Context-of-Clusters (CoCs) for feature processing. Unlike prior approaches that primarily focus on the RGB domain for place recognition reranking, CSCPR is designed to handle the RGB-D data. We apply the CoCs to handle cross-sourced and cross-scaled RGB-D point clouds and introduce two novel modules for reranking: the Self-Context Cluster (SCC) and the Cross Source Context Cluster (CSCC), which enhance feature representation and match query-database pairs based on local features, respectively. We also release two new datasets, ScanNetIPR and ARKitIPR. Our experiments demonstrate that CSCPR significantly outperforms state-of-the-art models on these datasets by at least 29.27% in Recall@1 on the ScanNet-PR dataset and 43.24% in the new datasets. Code and datasets will be released.

cs.CV↗

arXiv2024

PoCo: Point Context Cluster for RGBD Indoor Place Recognition

We present a novel end-to-end algorithm (PoCo) for the indoor RGB-D place recognition task, aimed at identifying the most likely match for a given query frame within a reference database. The task presents inherent challenges attributed to the constrained field of view and limited range of perception sensors. We propose a new network architecture, which generalizes the recent Context of Clusters (CoCs) to extract global descriptors directly from the noisy point clouds through end-to-end learning. Moreover, we develop the architecture by integrating both color and geometric modalities into the point features to enhance the global descriptor representation. We conducted evaluations on public datasets ScanNet-PR and ARKit with 807 and 5047 scenarios, respectively. PoCo achieves SOTA performance: on ScanNet-PR, we achieve R@1 of 64.63%, a 5.7% improvement from the best-published result CGis (61.12%); on Arkit, we achieve R@1 of 45.12%, a 13.3% improvement from the best-published result CGis (39.82%). In addition, PoCo shows higher efficiency than CGis in inference time (1.75X-faster), and we demonstrate the effectiveness of PoCo in recognizing places within a real-world laboratory environment.

cs.CV↗

arXiv2024

Modeling Uncertainty in 3D Gaussian Splatting through Continuous Semantic Splatting

In this paper, we present a novel algorithm for probabilistically updating and rasterizing semantic maps within 3D Gaussian Splatting (3D-GS). Although previous methods have introduced algorithms which learn to rasterize features in 3D-GS for enhanced scene understanding, 3D-GS can fail without warning which presents a challenge for safety-critical robotic applications. To address this gap, we propose a method which advances the literature of continuous semantic mapping from voxels to ellipsoids, combining the precise structure of 3D-GS with the ability to quantify uncertainty of probabilistic robotic maps. Given a set of images, our algorithm performs a probabilistic semantic update directly on the 3D ellipsoids to obtain an expectation and variance through the use of conjugate priors. We also propose a probabilistic rasterization which returns per-pixel segmentation predictions with quantifiable uncertainty. We compare our method with similar probabilistic voxel-based methods to verify our extension to 3D ellipsoids, and perform ablation studies on uncertainty quantification and temporal smoothing.

cs.RO↗

arXiv2024

Correspondence-Free SE(3) Point Cloud Registration in RKHS via Unsupervised Equivariant Learning

This paper introduces a robust unsupervised SE(3) point cloud registration method that operates without requiring point correspondences. The method frames point clouds as functions in a reproducing kernel Hilbert space (RKHS), leveraging SE(3)-equivariant features for direct feature space registration. A novel RKHS distance metric is proposed, offering reliable performance amidst noise, outliers, and asymmetrical data. An unsupervised training approach is introduced to effectively handle limited ground truth data, facilitating adaptation to real datasets. The proposed method outperforms classical and supervised methods in terms of registration accuracy on both synthetic (ModelNet40) and real-world (ETH3D) noisy, outlier-rich datasets. To our best knowledge, this marks the first instance of successful real RGB-D odometry data registration using an equivariant method. The code is available at {https://sites.google.com/view/eccv24-equivalign}

cs.CV↗

arXiv2023

Tabletop Transparent Scene Reconstruction via Epipolar-Guided Optical Flow with Monocular Depth Completion Prior

Reconstructing transparent objects using affordable RGB-D cameras is a persistent challenge in robotic perception due to inconsistent appearances across views in the RGB domain and inaccurate depth readings in each single-view. We introduce a two-stage pipeline for reconstructing transparent objects tailored for mobile platforms. In the first stage, off-the-shelf monocular object segmentation and depth completion networks are leveraged to predict the depth of transparent objects, furnishing single-view shape prior. Subsequently, we propose Epipolar-guided Optical Flow (EOF) to fuse several single-view shape priors from the first stage to a cross-view consistent 3D reconstruction given camera poses estimated from opaque part of the scene. Our key innovation lies in EOF which employs boundary-sensitive sampling and epipolar-line constraints into optical flow to accurately establish 2D correspondences across multiple views on transparent objects. Quantitative evaluations demonstrate that our pipeline significantly outperforms baseline methods in 3D reconstruction quality, paving the way for more adept robotic perception and interaction with transparent objects.

cs.RO↗

arXiv2016

Systolic Pressure in Different Percents of Stenosis at Major Arteries

- Modeling Human cardiovascular system is always an important issue. One of the most effective methods is using lumped model to reach to a complete model of human cardiovascular system. Such modeling with advanced considerations is used in this paper. Some of these considerations are as follow: Exact simulating of ventricles as pressure suppliers, peristaltic motion of descending arteries as additional suppliers, and dividing each vessel into more than one compartment to reach more accurate answers. Finally a circuit with more than 150 RLC segments and different elements is made. Then the verification of our complex circuit is done and at the end, obstruction as an important abnormality is investigated. For this aim different percents of obstruction in vital arteries are considered and the results are brought as different graphs at the end. According to physiological texts the citation of our simulation and its results are obvious. To earn productive information about arteries characteristics a 36-vessels model was chosen from biological sources.

physics.med-ph↗

arXiv2014

Beat Pressure and Comparing it with Ascending Aorta Pressure in Normal and Abnormal Conditions

Lumped method (Electrical analogy) is a quick and easy way to model human cardiovascular system. In this paper Lumped method is used for simulating a complete model. It describes a 36-vessel model and cardiac system of human body with details that could show hydrodynamic parameters of cardiovascular system. Also this paper includes modeling of pulmonary, atrium, left and right ventricles with their equivalent circuits. Exact modeling of right and left ventricles pressure with division of ascending aorta into 27 segments increases the accuracy of our simulation. In this paper we show that a calculated pressure for aorta from our complex circuit is near to measured pressure by using advanced medical instruments. Also it is shown that pressure graph from brachial is so near to aortic pressure because of this its pressure signal is usable instead of aortic pressure. Furthermore, obstruction in ascending aorta, brachial and its effects has been showed in different figures.

physics.med-ph↗

arXiv2014

Exact Modeling of Cardiovascular System Using Lumped Method

Electrical analogy (Lumped method) is an easy way to model human cardiovascular system. In this paper Lumped method is used for simulating a complete model. It describes a 36-vessel model and cardiac system of human body with details that could show hydrodynamic parameters of cardiovascular system. Also this paper includes modeling of pulmonary, atrium, left and right ventricles with their equivalent circuits. Exact modeling of right and left ventricles pressure increases the accuracy of our simulation. In this paper we show that a calculated pressure for aorta from our complex circuit is near to measured pressure by using advanced medical instruments.

physics.med-ph↗

arXiv2014

Semi-active Suspension Control using Modern Methodology: Comprehensive Comparison Study

Semi-active suspensions have drawn particular attention due to their superior performance over the other types of suspensions. One of their advantages is that their damping coefficient can be controlled without the need for any external source of power. In this study, three control approaches are implemented on a quarter-car model using MATLAB/Simulink. The investigated control methodologies are Acceleration Driven Damper, Power Driven Damper, and H_infinity Robust Control. The three controllers are known as comfort-oriented approaches. H_infinity Robust Control is an advanced method that guarantees transient performance and rejects external disturbances. It is shown that H_infinity with the proposed modification, has the best performance although its relatively high cost of computation could be potentially considered as a drawback.

eess.SY↗

arXiv2013

Rotor Bearing System Analysis Using the Transfer Matrix Method with Thickness Assumption of Disk and Bearing

One of the methods to find the natural frequencies of rotating systems is the application of the transfer matrix method. In this method the rotor is modeled as several elements along the shaft which have their own mass and moment of inertia. Using these elements, the entire continuous system is discretized and the corresponding differential equation can be stated in matrix form. The bearings at the end of the shaft are modeled as equivalent spring and dampers which are applied as boundary conditions to the discretized system. In this paper the dynamics of a rotor-bearing system is analyzed, considering the gyroscopic effect. The thickness of the disk and bearings is also taken into account. Continuous model is used for shaft. Results Show that, the stiffness of the shaft and the natural frequencies of the system increase, while the amplitude of vibration decreases as a consequence of increasing the thickness of the bearing.

physics.class-ph↗