The quantified requirements of industrial robots enabled by EAI4I are analyzed and recent research progress is reviewed, covering core technologies for single- and multi-robot systems, dedicated hardware platforms, high-fidelity simulators, task-specific datasets, representative industrial application scenarios, and critical deployment challenges.
Abstract
Industrial robots underlie modern manufacturing automation, yet conventional deterministic control based on fixed trajectories and offline programming struggles under high-mix and flexible production. Embodied artificial intelligence (EAI) offers a promising alternative by coupling perception, reasoning, and action within closed-loop physical interaction, enabling industrial robots to adapt behaviors online rather than execute predefined tasks. Yet, general-purpose EAI remains difficult to deploy in industrial environments due to stringent requirements on precision, real-time performance, reliability, and safety. These challenges have motivated increasing interest in embodied artificial intelligence for industry (EAI4I). This paper presents a systematic survey of EAI4I from an industrial robotics perspective. Specifically, we first analyze the quantified requirements of industrial robots enabled by EAI4I. Afterwards, recent research progress is reviewed, covering core technologies for single- and multi-robot systems, dedicated hardware platforms, high-fidelity simulators, task-specific datasets, representative industrial application scenarios, and critical deployment challenges. Finally, promising directions toward EAI4I are discussed.
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
Modern manufacturing faces increasing demands for flexibility, customization, and productivity under dynamic conditions. Multi-robot systems offer a promising solution by enabling cooperative execution of complex tasks, such as assembly and cooperative manipulation. In this context, Multi-Agent Reinforcement Learning (MARL) has emerged as a promising paradigm to enhance coordination and adaptability in industrial settings. MARL enables multiple agents to learn and interact in shared environments to achieve common goals within complex and dynamic industrial processes. In this paper, a deep analysis of MARL applied to industrial multi-robot systems based on a systematic review is presented, with particular focus on cooperative manipulation tasks. Following PRISMA guidelines, we analyze a total of 30 articles published between 2016 and 2026, selected independently by two of the authors from an initial pool of 102 records retrieved from Scopus and Web of Science. These articles were used to address five key questions regarding MARL algorithms, control architectures, industrial applications and validation practices. These research questions seek to examine gaps and trends at the research level which are important for the development of multi-agent control technologies. This review shows a clear prevalence of model-free algorithms under Centralized Training with Decentralized Execution (CTDE) architectures, with validation mainly performed in simulation. Despite promising results and high potential for impact, critical gaps remain in scalability, reproducibility, and sim-to-real transfer, limiting real deployment in manufacturing environments. To address these challenges and fill current gaps, we outline actionable research directions, such as hybrid MARL approaches, standardized industrial benchmarks, digital twin pipelines, and safety-aware deployment strategies, to accelerate MARL adoption in industrial environments.
Francisco J. Huertos, Oihane Bañales, Pedro Álvarez et al.· Robotics· 0 citations
Industrial robots are fundamental to smart manufacturing, performing high-precision and high-speed tasks with minimal human intervention. However, maintaining optimal performance remains challenging due to equipment degradation, changing production demands, and dynamic operating conditions. Traditional maintenance approaches often fail to detect faults in real time, resulting in increased downtime, maintenance costs, and reduced productivity. Digital Twin (DT) technology addresses these challenges by creating a real-time virtual replica of industrial robots integrated with IIoT, cloud computing, edge analytics, artificial intelligence (AI), machine learning (ML), and cyber-physical systems (CPS).This study proposes a Digital Twin-Based Performance Optimization Framework that combines real-time data acquisition, AI-driven predictive analytics, virtual simulation, and adaptive control within a unified architecture. The framework enables continuous synchronization between physical robots and their virtual twins, supporting predictive maintenance, fault detection, motion optimization, and energy-efficient operation. Machine learning, deep learning, and reinforcement learning algorithms enhance anomaly detection, predictive diagnostics, and adaptive trajectory planning. A hierarchical optimization engine further improves robot kinematics, actuator performance, energy utilization, and cycle-time efficiency, while cloud-edge collaboration ensures scalable and low-latency decision-making. The proposed framework is expected to improve robot availability, predictive maintenance accuracy, energy efficiency, production throughput, and fault diagnosis while reducing operational risks and unplanned downtime. It provides a scalable foundation for intelligent, self-optimizing Industry 4.0 manufacturing systems and next-generation AI-enabled industrial robotics.
L. Martínez, Mark Richardson· International Journal of Int...· 0 citations
Industry 5.0 represents a paradigm shift from fully automated production toward intelligent, human-centric manufacturing environments where collaborative robots, artificial intelligence (AI), edge computing, digital twins, Industrial Internet of Things (IIoT), and cyber-physical systems (CPS) operate in harmony with human workers. Unlike Industry 4.0, which primarily emphasized automation and productivity, Industry 5.0 focuses on resilience, sustainability, worker well-being, and personalized manufacturing. This study presents a comprehensive research framework for Industry 5.0-oriented human-centric robotic manufacturing systems by integrating collaborative robotics, AI-assisted decision-making, adaptive sensing, real-time monitoring, and intelligent manufacturing analytics. The proposed framework enables seamless interaction between human operators and robotic systems while ensuring operational safety, productivity, flexibility, and energy efficiency. A detailed literature review identifies current advancements, research gaps, and technological challenges associated with human-robot collaboration. The research methodology introduces an intelligent architecture incorporating multi-modal sensing, AI-based decision support, digital twin simulation, and adaptive robotic control. Comparative performance metrics demonstrate improvements in production efficiency, safety compliance, response time, and system adaptability. The findings indicate that Industry 5.0 technologies significantly enhance manufacturing performance while promoting sustainable and worker-centered industrial environments. The study concludes with future research directions involving explainable artificial intelligence, federated learning, autonomous collaborative robots, and resilient cyber-physical manufacturing ecosystems.
Narendra Karmarkar, Iyengar P. K.· International Journal of Int...· 0 citations
The study concludes that Generative AI offers a promising foundation for scalable, adaptive, and human-centric industrial automation, with future research directed toward continual learning, explainable AI, federated robotic intelligence, edge AI, and trustworthy autonomous decision-making.
Narendra Karmarkar· International Journal of Int...· 0 citations
Robots are being deployed for an increasingly diverse set of purposes, from industrial manufacturing to delivery, inspection, and surgical assistance, and the systems entering these roles are markedly more capable than earlier generations, utilizing learned perception, language-based planning, and multi-sensor input. This increase in the number of deployments is reflected in industry forecasts that report rapid, sustained growth in industrial robot installations and in the worldwide operational stock [18]. As robots take on broader and more complex missions in human-centered environments, their quality assurance and physical safety become increasingly relevant. However, despite this growth and advancements, few existing works offer a comprehensive review of robotic test automation with its conventional, AI-powered, and agentic landscape and overall trends. This paper addresses this gap by summarizing, classifying, and visualizing conventional and AI-based robot testing. Extending this, a reading of the commercial landscape suggests that conventional and AI methods act as complements rather than substitutes. Lastly, this work portrays many problems, challenges, and needs to aid in future research.
Karthik Rengarajan, Siddharth Pokuri, J. Gao· International Conference on...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
