Integrating Intelligence and Knowledge of Human Factors to Facilitate Collaboration in Manufacturing

Abstract

The implementation of automation has become a common occurrence in recent years, and automated robotic systems are actively used in many manufacturing processes. However, fully automated manufacturing systems are far less common, and human operators remain prevalent. The resulting scenario is one where human and robotic operators work in close proximity, and directly affect the behavior of one another. Conversely to their robotic counterparts, human beings do not share the same level of repeatability or accuracy, and as such can be a source of uncertainty in such processes. Concurrently, the emergence of intelligent manufacturing has presented opportunities for adaptability within robotic control. This work examines relevant human factors and develops a learning model to examine how to utilize this knowledge and provide appropriate adaptability to robotic elements, with the intention of improving collaborative interaction with human colleagues, and optimized performance. The work is supported by an example case-study, which explores the application of such a control system, and its performance in a real-world production scenario.

Designing human-robot collaboration (HRC) workspaces in industrial settings: A systematic literature review

“…To improve teamwork/ collaborative interaction, the human factors on task performance (e.g., type of task, fatigue, skill level, environment, etc.) must be taken into account [86].…”

“…In terms of a human worker that efficiently complete independent tasks in a shared physical workspace without explicitly communicating planned actions, studies are concluding that human productivity in a shared workspace is comparable to human productivity alone, as long the robot does not interfere directly with the human's physical motions or attention [85]. To improve teamwork/collaborative interaction with humans [86], use human factors on task performance, (such as type of task, fatigue, skill level, environment, emotional state, satiety and caffeine consumption) to provide appropriate adaptability of the human to the robotic elements. Still in the field of behavioural experiment [87], study concluded that the combination of goal inference and dynamic task planning significantly improves both objective and perceived performance of the human-robot team.…”

Study on Promoting Intelligent Manufacturing Path Choice of Manufacturing Enterprises Based on Coevolution Strategy

“…Li et al [10] considered that the intelligent manufacturing is a new driving force for the transformation and upgrading of manufacturing enterprises and proposed the "two-step" path of "smart manufacturing" and "energy conversion of manufacturing industry." Oliff et al [11] proposed the path for manufacturing enterprises with "human-computer interaction and two-way cooperation" to promote intelligent manufacturing. Bittencourt et al [12] emphasized the important role of the subjectivity of manufacturing enterprises and proposed three ways to realize intelligent manufacturing in manufacturing enterprises, namely, market type, network transportation type, and vertical chain type.…”