Human–Robot Collaborative Assembly Line Balancing Problem Considering Uncertain Task Time

In the field of assembly lines, human–robot collaborative assembly lines have become a production mode for many manufacturing enterprises. However, robots consume energy and generate carbon emissions during the production process. With the intensification of global warming, low-carbon and energy-saving development has emerged as the mainstream trend. This study aims to address the human–robot collaborative assembly line balancing problem with the number of stations and carbon emissions as the primary and secondary objective, respectively. In addition to the traditional ALBP constraints, this study also considers the uncertainty of task production time. A chance-constrained model is formulated based on the uncertainty theory. An improved reinforcement learning algorithm — the two-stage [Formula: see text]-learning algorithm is proposed. Furthermore, five crossover and three mutation actions are put forward. Finally, numerical experiments were conducted to validate the effectiveness of the algorithm. The managerial insights from the results as well as the limitations of the study are also highlighted.