Robotic Arm C‐Space Trajectory Planning Using Large‐Scale Digital Twin Parallelism and Safety‐Prioritisable Optimal Search Algorithm

IET Cyber-Systems and Robotics · 2025-01-01 · 1 citations

ABSTRACT This paper proposes a trajectory planning approach based on the configuration space (C‐space) generated from large‐scale digital twinning. Leveraging GPU‐based parallelism, the C‐space of a multi‐degree‐of‐freedom (multi‐DoF) manipulator in a complex task space with obstacles can be mapped out through extensive simulation of motion and collision of multiple virtual robot arms known as digital twins. An optimal search algorithm is incorporated with artificial potential field generated in the C‐space to allow the prioritising of safety in accordance with the varying risks associated with the obstacles by means of variable repulsive potential. To extend the high‐degree path to smooth and continuous joint trajectories, a spline operation is applied. Finally, a 7‐DOF physical manipulator is deployed for the execution of the planned trajectory in a task space filled with obstacles. Results demonstrated a 16.3% improvement in success rate achieved by utilising the safety‐prioritisable search algorithm. With this unified formulation of the control and planning problem in the C‐space, the kinematics complexity of a large DOF manipulator in obstacle‐present task space could be truly relieved from the joint control loop. This simplification, in turn, opens up prospective work in dynamic reconstruction of the C‐space.

QRIVAS: Quadruped Robot-Based Intelligent Visual Acquisition System for Bridge Component Inspection

Journal of Field Robotics · 2025-11-10

ABSTRACT Bridge inspection constitutes a critical yet labor‐intensive task in civil infrastructure maintenance, often requiring access to confined, structurally complex environments. Conventional manual inspection suffers from low efficiency and high operational risks, and the robotic solutions encounter limitations in GNSS‐denied and low illumination environments with texture‐deficient surfaces. This study proposes QRIVAS (quadruped robot based intelligent visual acquisition system), an autonomous framework for structural component image acquisition without relying on prior maps to reduce the workload for manual close‐proximity inspection. QRIVAS integrates 3D LiDAR SLAM with real‐time semantic segmentation, enabling reliable navigation and precise structural component identification. In this paper, we focus on the exploration and inspection of bridge column—a representative and critical structural component of bridge systems. Experimental validation across simulated concrete railway viaducts and physical laboratory‐scale bridge models (1:3 scale) shows that QRIVAS achieved 100% navigation success rate in simulation environments and 96.7% average task navigation success rate across six bridge columns in laboratory‐scale bridge specimen. Compared to existing research, QRIVAS shows consistent performance improvements across varying tolerance conditions (25 cm and 50 cm radius), maintaining robust operation under both flat concrete floor and rough artificial grass terrain conditions. This work demonstrates the potential of AI‐driven robotic systems to transform traditional infrastructure maintenance practices.

PMesh——Pressure-Informed Human Mesh Recovery for Bedridden Individuals

2025-07-14

Human Mesh Recovery (HMR) for bedridden individuals offers an intuitive way to visualize the 3D postures of patients confined to bed. By integrating HMR with pressure maps, it is possible to analyze the pressure distribution across various body parts, aiding in the prevention of bedsores or pressure ulcers and in monitoring sleep postures. However, existing HMR methods based on pressure maps face limitations in performance and practical deployment due to a lack of targeted model architecture design and the heterogeneity among sensors. Moreover, methods relying on visual modalities not only lack access to authentic pressure distribution data but are also more susceptible to occlusions and involve more complex deployment processes. In response to these challenges, we introduce PMesh, an innovative HMR method that relies solely on pressure modality. This method utilizes specifically designed modules to enhance HMR performance in bedridden subjects. Additionally, we have developed an annotation-free framework named PMeshFIT, which incorporates an RGB-guided fine-tuning strategy. PMeshFIT enables rapid adaptation of PMesh to new, unlabeled pressure maps, facilitating better deployment in complex real-world scenarios. Extensive experiments demonstrate that PMesh’s recovery performance exceeds the current pressure-based state-of-the-art methods by at least 12.11% in terms of MPJPE(Mean Per Joint Position Error). Furthermore, the PMeshFIT fine-tuning method has proven effective, enhancing the practical utility of our approach in clinical settings.

Extraction of effective response for controlled-source electromagnetic data based on clustering analysis

Applied Geophysics · 2025-06-20

Two-Stage Multi-stained Cell Analysis with the Segment Anything Model for Pathological Image Segmentation

Lecture notes in computer science · 2025-01-01 · 1 citations

Is LLM an Overconfident Judge? Unveiling the Capabilities of LLMs in Detecting Offensive Language with Annotation Disagreement

2025-01-01 · 4 citations

Large Language Models (LLMs) have become essential for offensive language detection, yet their ability to handle annotation disagreement remains underexplored.Disagreement samples, which arise from subjective interpretations, pose a unique challenge due to their ambiguous nature.Understanding how LLMs process these cases, particularly their confidence levels, can offer insight into their alignment with human annotators.This study systematically evaluates the performance of multiple LLMs in detecting offensive language at varying levels of annotation agreement.We analyze binary classification accuracy, examine the relationship between model confidence and human disagreement, and explore how disagreement samples influence model decision-making during few-shot learning and instruction finetuning.Our findings reveal that LLMs struggle with low-agreement samples, often exhibiting overconfidence in these ambiguous cases.However, utilizing disagreement samples in training improves both detection accuracy and model alignment with human judgment.These insights provide a foundation for enhancing LLM-based offensive language detection in real-world moderation tasks.

Optimizing Variable Admittance Control for Remote Ultrasound Scanning Under Uncertain Environment

IEEE Access · 2025-01-01 · 2 citations

Precise force control in remote robotic ultrasound systems is critical for optimizing image quality and ensuring patient safety. However, conventional admittance control strategies face limitations in achieving high-precision force tracking during interaction while maintaining accurate position tracking in free motion. To address this challenge, we propose an adaptive variable admittance approach integrated with a novel coarse-to-fine force control strategy, which requires online estimation of environmental properties. The environmental information is estimated by a fusion algorithm that combines force and position data from sensors with confidence scores derived from ultrasound images. Furthermore, a compensation term is introduced to the variable stiffness control law to mitigate estimation uncertainties, thereby enhancing force tracking accuracy. Additionally, an energy tank mechanism is implemented to guarantee system passivity under varying damping and stiffness conditions. The effectiveness of the proposed method was experimentally validated using a teleoperated ultrasound system, tested on both a vascular phantom model and human upper limb. The proposed controller demonstrated stable force tracking performance while maintaining compliance throughout the interaction process. The force tracking errors were maintained within ranges of 0.2 N and 0.4 N with standard deviation of 0.02 N and 0.2 N for the phantom and human experiments, respectively.

A Generalizable Telerobotic Solution for Undisrupted Man-Robot Workflow Coupling via Shape-Variable Virtual Fixture

IEEE Access · 2025-01-01

This paper introduces a generalizable telerobotic solution for the coupling between manual and machine workflow tracks to facilitate the incorporation of personnel-required procedures in lab automation processes. The proposed shape-variable virtual fixture can be generalized for providing synchronized dexterous guidance during human interaction with a robotized automation process without disrupting the automated workflow. Accuracy performance evaluation showed that the use of our proposed shape-variable virtual fixture reduced positioning and orientation errors by 50%. Stability and transparency are validated by evaluation of the force profiles during the teleoperation process while interacting with the environment. User experience test based on the NASA-TLX evaluation also indicates reduced workload and task complexity experienced by the subjects of informed consent, suggesting better usability with our proposed method. This study demonstrates the feasibility and usability of the proposed telerobotic approach using shape-variable virtual fixtures for generalized man-robot collaborated workflows. It is envisioned that the work would pave a path for the realization of safer and more intuitive human-robot collaboration while maintaining the efficiency of the ever-increasing task complexity in modern smart laboratories.

UniSVG: A Unified Dataset for Vector Graphic Understanding and Generation with Multimodal Large Language Models

2025-10-25

Unlike bitmap images, scalable vector graphics (SVG) maintain quality when scaled, frequently employed in computer vision and artistic design in the representation of SVG code. In this era of proliferating AI-powered systems, enabling AI to understand and generate SVG has become increasingly urgent. However, AI-driven SVG understanding and generation (U&G) remain significant challenges. SVG code, equivalent to a set of curves and lines controlled by floating-point parameters, demands high precision in SVG U&G. Besides, SVG generation operates under diverse conditional constraints, including textual prompts and visual references, which requires powerful multi-modal processing for condition-to-SVG transformation. Recently, the rapid growth of Multi-modal Large Language Models (MLLMs) have demonstrated capabilities to process multi-modal inputs and generate complex vector controlling parameters, suggesting the potential to address SVG U&G tasks within a unified model. To unlock MLLM's capabilities in the SVG area, we propose an SVG-centric dataset called UniSVG, comprising 525k data items, tailored for MLLM training and evaluation. To our best knowledge, it is the first comprehensive dataset designed for unified SVG generation (from textual prompts and images) and SVG understanding (color, category, usage, etc.). As expected, learning on the proposed dataset boosts open-source MLLMs' performance on various SVG U&G tasks, surpassing SOTA close-source MLLMs like GPT-4V. We release dataset, benchmark, weights, codes and experiment details on https://ryanlijinke.github.io/.

Power Adaptation-Enabled Admittance Control for Stable and Safe Actuated Interaction in Unmodeled Environment

IEEE Robotics and Automation Letters · 2025-01-27 · 1 citations

Pin-based shape display is a type of interactive interface researched in the field of human-robot interaction (HRI) for physical shape rendering through a grid of linear motion actuators. Some researchers have enabled it with the abilities of manipulating objects and interacting with humans. This important expansion of usages in pin-based shape display to dynamic shape rendering imposes a potential challenge in interacting with unmodeled environment dynamics consisting of humans or other objects in a safe and stable way. We have previously introduced admittance control to the pin-based shape rendering in an attempt to regulate the relation between the motions of pins and the external force applied by the unmodeled environment. Despite the functional realization, there is a need for a safe and stable interaction as the admittance controller may lead to excessive power output. To overcome this, one approach is to apply the energy-based control method to the admittance controller. Bounded energy is allocated to the admittance controller, and bounded power is introduced to limit the power output of the pin-based shape rendering. However, these boundaries are difficult to estimate. Especially for the power boundary, which needs to be dynamically adjusted to balance the safety and quick interaction response of the system. To address the above issues, we introduce a power adaptation method to the admittance controller in pin-based shape rendering. Experiments with previously developed pin-based shape rendering are used to validate the benefit of the power adaption method. The results support the fact that the proposed method has better performance in terms of safety and interaction response, demonstrating the potential to introduce higher-level planning frameworks.