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.
SUMMARY: In this research, a Stewart parallel platform with rotary actuators is simulated and a prototype is tested under different operative conditions. The purpose is to make the robot robust against inertia variations considering the fact that different payloads of unknown size may be transported. Due to the complexity issued by expressing the equations of motion with independent variables, the governing equations are derived by Lagrange's method using Lagrange multipliers for imposing the kinematic constraints imposed on this parallel robot. Eliminating Lagrange multipliers by projecting the equations onto the orthogonal complement of the space of constraints, the equations of motion are transformed to a reduced form suitable for the purpose of controller design. The control approach considered here is based on a neuro-fuzzy interference method. As a first step, each revolute arm link are individually trained under different loadings and diverse maneuvers. It is purposed that once employed together, the links will have learned how to collaborate with each others for performing a common task. Training data are divided to several clusters by using a subtractive clustering algorithm. For every cluster, a fuzzy rule is derived so that the output follows the desired trajectory. In the last stage, these rules are employed by utilizing back propagation algorithms and the effectiveness of the neuro-fuzzy system becomes approved by performing multiple maneuvers and its robustness is checked under various inertia loads. The controller has ultimately been implemented on a prototype of the Stewart mechanism in order to analyze the reliability and feasibility of the method.