Aug 2026· International Journal of Engineering and Modern Technology· pp. 1· 0 citations
TL;DR
This review examines recent advances in the integration of Artificial Intelligence with Autonomous Mobile Robots (AMRs) for real-time material flow optimization in EV manufacturing ecosystems to identify key performance improvements in throughput, operational efficiency, and cost reduction attributed to AI-AMR integration.
Abstract
The rapid evolution of electric vehicle (EV) manufacturing has intensified the need for highly
adaptive, efficient, and intelligent material handling systems capable of operating in dynamic
production environments. This review examines recent advances in the integration of Artificial
Intelligence (AI) with Autonomous Mobile Robots (AMRs) for real-time material flow optimization
in EV manufacturing ecosystems. It explores how AI-driven perception, decision-making, and
predictive analytics enhance the operational capabilities of AMRs, enabling them to respond
autonomously to fluctuating production demands, layout constraints, and supply chain
uncertainties. The study synthesizes developments in machine learning algorithms, reinforcement
learning, computer vision, and digital twin technologies that collectively enable real-time route
optimization, task allocation, congestion avoidance, and energy-efficient navigation within smart
factories. Particular attention is given to the role of edge computing and Industrial Internet of
Things (IIoT) architectures in facilitating low-latency communication and decentralized
intelligence, which are critical for real-time responsiveness. The review also evaluates system
level integration challenges, including interoperability with Manufacturing Execution Systems
(MES), scalability, cybersecurity risks, and safety compliance in human-robot collaborative
environments. Furthermore, it highlights emerging trends such as swarm intelligence, multi-agent
coordination, and adaptive scheduling frameworks that are redefining material flow strategies in
EV production lines. By consolidating current research and industrial practices, this paper
identifies key performance improvements in throughput, operational efficiency, and cost reduction
attributed to AI-AMR integration. It also outlines future research directions, including the
development of explainable AI models, resilient control architectures, and sustainable energy
aware robotic systems. Overall, this review provides a comprehensive foundation for
understanding how AI-enabled AMRs are transforming material flow optimization and shaping
the next generation of intelligent EV manufacturing systems.
The findings show that machine learning, deep learning, computer vision, computer vision, reinforcement learning, knowledge-driven approaches, digital twins, and explainable AI contribute to improvements in predictive maintenance, quality inspection, production scheduling, adaptive safety, and collaborative decision-making.
Zaliha Baso, N. Yadav, P. Faujdar· Cureus Journal of Computer S...· 0 citations
The rapid advancement of Industry 4.0 has transformed conventional manufacturing into intelligent smart factories by integrating Industrial Internet of Things (IIoT), cyber-physical systems, cloud computing, and artificial intelligence (AI). As manufacturing environments become increasingly complex, traditional human-driven decision-making is insufficient for real-time production optimization. Autonomous Decision Support Systems (ADSS) address this challenge by combining AI, machine learning, digital twins, edge computing, and predictive analytics to enable intelligent, data-driven decision-making with minimal human intervention. This paper presents a scalable ADSS framework that integrates IIoT, edge-cloud computing, and digital twin technology for real-time monitoring, predictive maintenance, dynamic scheduling, and autonomous production optimization. The proposed architecture includes data acquisition, preprocessing, feature engineering, predictive analytics, decision optimization, autonomous execution, and continuous learning. Reinforcement learning and explainable AI improve decision accuracy, adaptability, and transparency, while federated learning enhances data privacy and reduces communication latency. Experimental results demonstrate significant improvements in production efficiency, equipment utilization, predictive maintenance, energy efficiency, quality control, and manufacturing responsiveness compared to conventional decision support systems. The proposed framework provides a scalable foundation for Industry 5.0, enabling sustainable, resilient, and intelligent manufacturing through seamless collaboration between human expertise and autonomous AI systems.
Jose Fernandez, Marta Silva· International Journal of Int...· 0 citations
Flexible manufacturing, characterized by high-mix, low-volume, and highly variable production, demands robotic systems with strong adaptability, dexterity, and intelligence that conventional offline-programmed industrial robots cannot provide. This paper presents a systematic review of key technologies for robot embodied intelligence oriented toward flexible manufacturing, organized around the closed loop of perception, decision-making, and execution. The purpose is to clarify the current research landscape, identify core technical bottlenecks, and outline future directions for embodied-intelligent manufacturing. Adopting a literature-analysis and comparative-review method, the study examines representative advances at three levels: multimodal environmental perception and real-time modeling, flexible adaptive precision manipulation, and intelligent decision-making for process planning and scheduling. The review finds that multimodal fusion and semantic SLAM are overcoming perception bottlenecks, that deep learning and force/position hybrid control are balancing flexible adaptability with high-precision operation, and that deep reinforcement learning and large models are advancing intelligent process planning. It concludes that data scarcity, model reliability, software-hardware integration, and ethical-legal standards remain the principal challenges to large-scale industrial deployment.
Zheng-Yang Chen· Advances in Engineering Inno...· 0 citations
The rapid advancement of artificial intelligence (AI), autonomous robotics, and distributed computing has significantly improved the capabilities of multi-robot systems (MRS) across applications such as warehouse automation, disaster response, healthcare, precision agriculture, intelligent transportation, and smart manufacturing. A key challenge in these systems is dynamic task allocation, where robots must efficiently assign and reassign tasks in response to changing environments, communication constraints, resource limitations, and robot failures. Conventional approaches often face limitations in scalability, computational efficiency, and adaptability.This paper proposes an AI-based dynamic task allocation framework that integrates machine learning, reinforcement learning, swarm intelligence, and optimization techniques to enable intelligent and adaptive decision-making in heterogeneous multi-robot systems. The framework considers robot capabilities, task priorities, battery levels, communication quality, travel distance, and workload balancing to optimize real-time task allocation. Reinforcement learning supports adaptive policy learning, while swarm intelligence enables decentralized cooperation. Graph-based task modeling and utility-based optimization further improve resource utilization and minimize execution time, energy consumption, and task conflicts.Experimental evaluation using metrics such as task completion rate, response time, energy efficiency, workload distribution, and scalability demonstrates that the proposed framework outperforms conventional scheduling methods by providing improved adaptability, fault tolerance, and operational efficiency. The proposed approach offers a scalable and intelligent solution for next-generation multi-robot collaboration in Industry 5.0 and cyber-physical systems.
Alexey Lyapunov· International Journal of Int...· 0 citations
Unmanned Aerial Vehicles (UAVs) are used in numerous practical applications in industry, science, and ecology; however, the large-scale use of UAVs is hampered by the limited onboard energy capacity. Increasing the energy efficiency of UAVs has thus become one of the most important tasks in UAV research. This review examines approaches to energy optimization of UAVs using algorithms and artificial intelligence (AI). It evaluates and compares algorithms and methods used to optimize energy efficiency of trajectory planning, adaptive speed control, battery management in mission planning, and navigation that accounts for environmental characteristics. It differs from those focusing on hardware solutions by highlighting optimization problems where energy usage is considered the key target for optimization and not a limiting constraint. The analyzed methods have been categorized into five groups, including classical optimization, metaheuristics, machine learning (ML), reinforcement learning (RL), and hybrid approaches. Key approaches such as RL, Model Predictive Control, evolutionary algorithms, and data-driven energy modeling have been outlined and compared with regard to energy-model accuracy, type of validation, scalability, and deployment readiness. Additionally, it emphasizes practical aspects such as the accuracy of energy modeling, real-time capabilities, scalability to multiple UAVs, and robustness to environmental uncertainty. Finally, this review provides directions for future research that will help develop sustainable, intelligent, and energy-efficient UAVs.
Wojciech Skarka, Rukhseena Ashfaq, Arun Winglin Amaladoss et al.· Energies· 0 citations
: Affected by global extreme climates, ice-covering disasters occur frequently, posing a significant threat to the safe and stable operation of power transmission lines, wind turbine generators, high-speed railway contact nets, and airport infrastructure. The traditional ice removal methods generally have problems such as high risks associated with high-altitude operations, low ice-removal efficiency, and insufficient adaptability to extreme conditions. Based on this, this paper comprehensively reviews the research progress and engineering applications of AI-enabled intelligent de-icing robots, thereby providing theoretical guidance and technical support for future technology optimization and large-scale engineering applications. Focusing on the “perception–decision–execution” technical framework of intelligent de-icing robots, the key technologies, including multi-source information fusion perception, intelligent ice-condition identification, autonomous path planning and motion control, reinforcement learning-based decision-making, and composite de-icing actuators, are comprehensively analyzed. Typical engineering applications in power transmission lines, wind turbine blades, high-speed railway catenary systems, and civil aviation airports are also reviewed and evaluated. The integration of artificial intelligence technologies significantly enhances the environmental perception, autonomous decision-making, and adaptability of intelligent de-icing robots under complex operating conditions, enabling the transition from manual operation to autonomous de-icing. These technologies effectively improve operational safety, efficiency, and intelligence levels. At present, intelligent de-icing robots have been successfully applied in the power, transportation, and renewable energy sectors, demonstrating promising engineering performance. Intelligent de-icing robots have become an important technological approach for improving the anti-icing and de-icing capabilities of critical infrastructures and exhibit broad application prospects. However, significant challenges remain in complex environments, adaptability to extreme operating conditions, energy supply and endurance, and the establishment of technical
