Abstract
Digital-enabled manufacturing systems require a high level of automation for fast and low-cost production but should also present flexibility and adaptiveness to varying and dynamic conditions in their environment, including the presence of human beings; however, this presence of workers in the shared workspace with robots decreases the productivity, as the robot is not aware about the human position and intention, which leads to concerns about human safety. This issue is addressed in this work by designing a reliable safety monitoring system for collaborative robots (cobots). The main idea here is to significantly enhance safety using a combination of recognition of human actions using visual perception and at the same time interpreting physical human–robot contact by tactile perception. Two datasets containing contact and vision data are collected by using different volunteers. The action recognition system classifies human actions using the skeleton representation of the latter when entering the shared workspace and the contact detection system distinguishes between intentional and incidental interactions if physical contact between human and cobot takes place. Two different deep learning networks are used for human action recognition and contact detection, which in combination, are expected to lead to the enhancement of human safety and an increase in the level of cobot perception about human intentions. The results show a promising path for future AI-driven solutions in safe and productive human–robot collaboration (HRC) in industrial automation.
Highlights
As the manufacturing industry evolves from rigid conventional procedures of production to a much more flexible and intelligent way of automation within the frame of the Industry 4.0 paradigm, human–robot collaboration (HRC) has gained rising attention [1,2]
Depending on whether the contact is intentional or incidental, the cobot should provide an adequate response, which in every case, ensures the safety of the human operator. At this step, identifying the cobot link where the collision occurred is important information for anticipating proper robot reaction, which needs to be considered in contact perception [61]. With this background and considering the fact that contact propertiespatterns of incidental and intentional states are different according to the contacted link, we aim to use supervised learning, convolutional neural network, to have a model-free contact detection
The efficiency of safety and productivity of cobots in HRC can be improved if cobots are able to recognize complex human actions and can differentiate between multitude contact types
Summary
As the manufacturing industry evolves from rigid conventional procedures of production to a much more flexible and intelligent way of automation within the frame of the Industry 4.0 paradigm, human–robot collaboration (HRC) has gained rising attention [1,2]. The robot becomes a companion or so-called collaborative robot (cobot) for flexible task accomplishment rather than a preprogrammed slave for repetitive, rigid automation. It is expected that cobots actively assist operators in performing complex tasks, with highest priority on human safety in cases humans and cobots need to physically cooperate and/or share their workspace [3]. This is problematic because the current settings of cobots do not provide an adequate perception of human presence in the shared workspace. There are some safety monitoring systems [4,5,6,7], Sensors 2020, 20, 6347; doi:10.3390/s20216347 www.mdpi.com/journal/sensors
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
