Worker-Aware Robotic Motion Planner in Construction for Improved Psychological Well-Being during Worker-Robot Interaction

Abstract

Collaborative robots have recently shown the potential to assist workers in performing dexterous and physically demanding construction tasks. However, due to unparalleled diligence, a lack of social intelligence, and a lack of functional perception, a collaborative robot poses problems for the mental and emotional states of workers when interacting with them. These effects can lead to mental health problems, such as depression and anxiety. To ensure the mental well-being of workers during human-robot collaboration (HRC), this study proposes a psychologically stimulated motion planner built into collaborative robots. This capacity to adapt will be based on the robots’ recognition of workers’ mental states. Through it, first, the cognitive load of workers will be decoded from their brainwave signals via the Multilayer Perceptron Classifier. Second, the decoded results will activate a robotic control mechanism to achieve human-friendly interaction. To examine the safety and feasibility of the robot motion planner, an HRC materials-delivery experiment was designed using a 3D robotic-simulation environment (i.e., Gazebo). The planner allowed robots to assess subjects’ cognitive load with an 86.4% accuracy. Once subjects experienced an undesirable cognitive load, the motion planner adjusted the movements of the robots to deliver materials at a safer distance and more comfortable speed. The findings demonstrate the potential of establishing the psych physiologically based HRC solution, opening new avenues to implementing collaborative robots at construction sites.