Dynamic role-adaptive collaborative robots for sustainable smart manufacturing: an AI-driven approach

Purpose The study aims to address critical challenges in collaborative robotics, focusing on dynamic role adaptation, efficient task planning and sustainability. The primary goal is to develop a framework that enhances cobots’ ability to adapt to changing tasks, collaborate effectively with human operators and contribute to sustainable manufacturing practices. Design/methodology/approach An innovative framework leveraging artificial intelligence (AI) and advanced machine learning techniques was developed to enable dynamic role adaptation in cobots. The framework was validated through experimental evaluations conducted in a simulated industrial environment using Gazebo. Performance metrics, including task efficiency, energy consumption and material waste, were analyzed to assess the framework’s effectiveness. Findings The experimental results demonstrated that the proposed framework improved task efficiency by 25%, reduced energy consumption by 20% and achieved significant reductions in material waste. These outcomes highlight the framework’s potential to optimize manufacturing operations while promoting sustainability. Originality/value This research introduces a novel AI-driven approach to collaborative robotics, integrating dynamic adaptability and sustainability metrics into cobot operations. By addressing the dual objectives of productivity and environmental impact, the framework advances the state-of-the-art in intelligent manufacturing systems and offers practical solutions to pressing industrial challenges.