Old robots, new life: AI-powered cobots advance Industry 5.0 goals

The traditional industrial robot is undergoing a major transformation. As manufacturers seek to meet new demands for sustainability, flexibility, and human–machine collaboration, the concept of retrofitting existing robots into collaborative systems, known as “cobots”, is gaining momentum. Rather than replacing aging robotic infrastructure, a new study proposes turning legacy machines into safe, intelligent collaborators.

The peer-reviewed article, “Transforming Robots into Cobots: A Sustainable Approach to Industrial Automation,” published in Electronics presents a modular framework for converting conventional industrial robots into cobots through artificial intelligence, advanced sensors, and circular economy principles. Developed by researchers from the University of Costa Rica and the University of Alicante, the study outlines a comprehensive theoretical model focused on perception, safety, adaptability, and environmental impact mitigation.

What makes retrofitting industrial robots into cobots feasible?

The study identifies a layered modular architecture that facilitates the step-by-step enhancement of legacy robots. This includes a perceptual layer equipped with vision and sensor fusion technologies for real-time human detection and environmental awareness, safety control mechanisms that adhere to ISO/TS 15066 standards, and a cognitive layer capable of adaptive learning through machine learning and probabilistic reasoning.

The approach is grounded in sustainability and lifecycle optimization. It proposes upgrading robots instead of replacing them, which reduces e-waste, conserves resources, and extends the value of previous investments. For instance, articulated robots with modular joints and SCARA robots with standard control systems are flagged as optimal candidates for conversion due to their mechanical robustness and adaptability.

Critically, the system supports plug-and-play interoperability with hardware from different vendors, allowing for rapid deployment and minimal operational disruption. It also features a human–machine interaction layer with multimodal input systems, including gesture control, touchscreen interfaces, and even AR/VR tools for immersive control and feedback.

What are the safety, technical, and regulatory hurdles?

Despite the promise, the study acknowledges that retrofitting traditional robots into cobots is not without challenges. A key concern is meeting safety and compliance requirements. The framework emphasizes the necessity of incorporating certified safety PLCs, real-time monitoring, and fail-safe protocols to adhere to international regulations like ISO/TS 15066 and ISO 10218.

Moreover, many traditional robots operate on proprietary systems that are not readily compatible with open-source platforms like ROS. The framework addresses this by introducing middleware abstraction layers that can unify disparate systems while enabling real-time safety enforcement.

Another challenge is adapting the physical design. Traditional robots often feature sharp edges and fast movements not suitable for close human interaction. The study suggests modular protective shells, sensor-laden end-effectors, and adaptive brackets to create ergonomically safe configurations.

Additionally, retrofitting demands a strategic evaluation of feasibility, including cost-benefit analysis compared to purchasing new cobots. The researchers offer a six-step benchmarking process to assess economic viability, safety performance, operator learning curves, and system flexibility, aiming to guide decision-makers in industrial settings.

How does the framework support Industry 5.0 and sustainability?

The proposed framework is deeply aligned with the principles of Industry 5.0, which emphasizes human-centric, sustainable, and resilient production systems. By advocating the reuse of functional but outdated robots, the study embraces the circular economy. It proposes remanufacturing, recycling, and lifecycle assessments to reduce the environmental footprint of industrial automation.

Technologies like low-power actuators, energy-efficient control algorithms, and modular construction are identified as enablers of sustainable engineering. The integration of AI further enhances this potential by enabling context-aware learning and adaptive task execution, reducing waste and boosting efficiency.

The study also encourages future research to explore digital twins, cloud-based analytics, and federated AI systems for predictive maintenance and cross-facility coordination. These enhancements can help retrofitted cobots integrate into modern cyber–physical systems and Industrial Internet of Things (IIoT) environments.

Finally, scalability is addressed. The framework aims to democratize access to collaborative robotics for small and medium-sized enterprises (SMEs), which often cannot afford high-end cobots. By offering retrofitting toolkits and simulation environments, the model lowers the entry barrier for digital transformation across industrial ecosystems.