The outcomes demonstrate the efficacy of combining edge intelligence with closed-loop robotic control by confirming consistent behavior throughout simulation and limited physical testing.
Abstract
Robust perception, fast decision-making, and reliable closed-loop control under uncertainty are necessary for vision-based robotic manipulation in dynamic industrial settings. An edge-intelligent robotic manipulation framework for pick-and-place tasks is presented in this work. It combines perception, calibration, motion planning, and control into a single simulation-based closed-loop architecture. To lower latency and increase robustness in dynamic circumstances, the suggested system makes use of a lightweight CNN-based perception module, calibration-aware SE(3) transformation refinement, and edge-enabled execution logic. To improve generalization under occlusion, light change, and object pose uncertainty, a data-centric enrichment technique is employed. Using a Monte Carlo technique and several trials in various industrial contexts, the framework is assessed in a high-fidelity simulation environment. Task success rate, latency, and robustness under the same settings have all improved when compared to current robotic manipulation baselines. Furthermore, without claiming full industrial implementation, a small-scale qualitative real-world validation (18 grip trials) is carried out to evaluate transferability. The outcomes demonstrate the efficacy of combining edge intelligence with closed-loop robotic control by confirming consistent behavior throughout simulation and limited physical testing.
A deep examination of the vision-based object manipulation through collaborative robotics with respect to perception pipelines, object detection and recognition, pose estimation, grasp planning, and real time control integration is given.
Rahul Mehta· International Journal of Int...· 0 citations
Industry 4.0 has transformed conventional manufacturing into intelligent, automated, and connected production environments. Intelligent robotic pick-and-sort systems improve productivity, flexibility, product quality, and operational efficiency by overcoming the limitations of traditional rule-based automation. This paper presents an AI-enabled framework integrating computer vision, deep learning, robotic manipulation, edge computing, and the Industrial Internet of Things (IIoT) for dynamic manufacturing applications. Convolutional Neural Networks (CNNs) provide accurate object detection and classification, while intelligent motion planning and reinforcement learning optimize robotic grasping and movement. Sensor fusion, edge computing, and IIoT connectivity enable real-time monitoring, low-latency decision-making, and predictive maintenance, improving system reliability and reducing downtime. Performance is evaluated using object detection accuracy, sorting accuracy, processing time, throughput, energy efficiency, and overall system reliability. Compared with conventional automation, the proposed framework offers greater adaptability, higher sorting accuracy, and improved operational performance in dynamic production environments. The study concludes that intelligent robotic pick-and-sort systems are a key technology for smart factories, supporting flexible manufacturing, mass customization, and sustainable industrial production, with future opportunities in digital twins, explainable AI, cloud-edge intelligence, and collaborative human-robot systems.
Nandhini Ravi· International Journal of Int...· 0 citations
Visual perception plays a critical role in industrial assembly systems, where robotic actions are driven by image-based sensing under variable and data-dependent conditions. A key challenge in such systems lies in transforming unstructured visual inference outputs, including object detection and pose estimation results, into structured and executable control parameters that can be reliably grounded in physical execution. In practice, mismatches between perception outputs and downstream control interfaces often lead to execution errors and reduced system robustness in multi-stage assembly processes. To address this challenge, this paper proposes a vision-guided robotic action generation framework that explicitly models the data flow from visual perception to robotic action execution. The framework introduces a structured visual data extraction mechanism that interprets raw visual outputs into type-consistent, constraint-aware, and physically feasible motion parameters, enabling reliable perception-action coupling in industrial assembly systems. By decoupling visual interpretation from low-level control execution, the proposed approach improves modularity and robustness across heterogeneous hardware platforms and low-code industrial orchestration environments. The proposed framework is implemented and evaluated through an end-to-end, data-dependent toy vehicle assembly task involving multiple perception-driven operations. Experimental results demonstrate that the proposed method significantly improves perception-action alignment robustness, achieving higher phase-level execution reliability and an end-to-end assembly success rate of up to 94%, outperforming baseline approaches that lack explicit visual data alignment mechanisms.
Longxiang Huang, Jiaxin Dai, Tao Wang et al.· International Conference on...· 0 citations
An intelligent vision-based autonomous robotic framework that integrates deep learning-based object detection with hybrid adaptive navigation for dynamic environments is proposed in this research. The proposed system addresses the challenges of real-time perception and robust navigation in unstructured settings by combining a convolutional neural network (CNN) for object detection with a hybrid control mechanism for motion planning. The CNN, implemented using a state-of-the-art architecture such as YOLO, processes visual input to identify obstacles and target objects, providing critical environmental awareness. Moreover, the hybrid navigation strategy merges reactive obstacle avoidance, achieved through algorithms like the Vector Field Histogram (VFH), with adaptive path planning using Rapidly-exploring Random Trees (RRT) to ensure both immediate collision avoidance and long-term goal convergence. The integration of these components enables the robotic system to dynamically adjust its navigation policy in response to environmental changes, thereby improving robustness and adaptability. The novelty of our approach lies in the seamless fusion of vision-based perception and adaptive control, which enhances the system’s capability to operate in complex, dynamic scenarios. Experimental validation demonstrates the effectiveness of the framework in real-world applications, highlighting its potential for deployment in autonomous vehicles, service robotics, and industrial automation. The proposed method offers a scalable and efficient solution for autonomous systems requiring high levels of situational awareness and adaptive decision-making.
K. A.· International Journal on Rob...· 0 citations
Industry 4.0 has transformed modern manufacturing, where industrial robots must operate continuously under dynamic and uncertain conditions such as vibrations, part tolerances, tool wear, thermal effects, and human–robot interaction. These disturbances can cause deviations between planned and executed paths, leading to assembly errors and reduced product quality. Therefore, real-time path correction has become essential for adaptive and high-precision robotic operations. Traditional robots rely on offline programming and open-loop control, which perform well in structured environments but struggle with real-time uncertainties like moving objects, conveyor variations, and sensor noise. Closed-loop systems enhanced with real-time sensory feedback address these challenges; however, single-sensor approaches are insufficient. Vision sensors provide rich spatial data but suffer from latency and lighting sensitivity, force–torque sensors offer precise contact feedback without global context, and inertial sensors are fast but prone to drift. This paper proposes a sensor-fusion-based framework for real-time path correction in assembly-line robots. Vision, force–torque, and inertial sensors are integrated using a Kalman filter for accurate state estimation, combined with a Model Predictive Control (MPC) strategy to generate real-time corrective motion commands. The system is validated through simulation and experimental pick-and-place and precision insertion tasks. Results demonstrate significant improvements in positional accuracy, force control, and task performance compared to single-sensor and open-loop methods, achieving sub-millimeter path correction accuracy and robustness to object movement and conveyor speed variations. The proposed approach enhances the reliability and adaptability of robotic assembly systems in smart manufacturing environments.
Chen Wei, Liu Fang· International Journal of Int...· 0 citations
Complex and dynamic environment autonomy, the ability to navigate complex and dynamic environments autonomously in real-time and with limited computational power, will persist as a basic challenge to mobile robotic systems. As a solution to this problem, this paper presents an alternative minimum-cost deep learning format using optimization, which combines a Modified Rime Optimization Algorithm (M-RIME) and a lightweight SqueezeNet-based navigation network. The given strategy is supposed to increase the depth of perception, precision of motion control, and computational efficiency at the same time. To begin with, an end-to-end navigation model that uses SqueezeNet is created to concurrently map raw red–green–blue observations to continuous motion commands to facilitate the perception–action interface. Subsequently, the M-RIME algorithm is improved with adaptive exploration–exploitation balancing and an adaptive mutation operator that greatly enhance convergence speed, global exploration, and the stability of solutions. The presented optimizer is used to improve the performance of the SqueezeNet model by automatically optimizing its hyperparameters within an offline optimization system, which improves navigation and retains its real-time functionality. Multi-frame and multi-measurement simulation experiments are performed in complex indoor navigation environments, where success rate, collision rate, navigation time, path length, and frames per second are adopted as quantitative and qualitative metrics to evaluate the suggested framework. The findings show that the optimized SqueezeNet is not only much better than the baseline model and other state-of-the-art optimization frameworks in terms of success rates of navigation, smoother trajectories, lower rates of collisions, and high-quality real-time optimization but also significantly better. In addition, convergence analysis establishes the effectiveness and precision of the suggested M-RIME algorithm in a high-dimensional optimization setting. On the whole, the presented framework will offer a good and scalable choice for autonomous navigation in real-time and can serve as an excellent basis for future developments aimed at temporal modeling, practical applications of autonomous driving, and multi-sensor fusion-driven robotic perception systems.
Jiangjun Ruan, Mei Wang, Lu Peng et al.· AIP Advances· 0 citations