An intelligent robotic framework for automated assembly

Abstract

Recent applications of robots for industrial automation have shown significant improvement in manufacturing processes in terms of reducing labor participation, enhancing flexibility, efficiency and quality of the products. However, most applications are limited to point-to-point and noninteractive operations in which the availability of a highly structured setup is a prerequisite. This prompts the vast emergency of researches on intelligent robotics that are aimed to improve the adaptability, flexibility and dexterity so as to enhance the intelligence of industrial robots. This paper investigates the designs of intelligent robotic systems and discusses the proposed criteria required to achieve an intelligent robotic system. A proposed conceptual framework for robotic assembly is then presented that contains two main parts, namely, a robotic state recognizer and a control strategy generator. In addition to these two components, the integration of compliant motion control into the framework will be described. An example of using the proposed framework to develop a robotic assembly system is given.

A framework to support Robotic process automation

“…This Delphi study aims to get the expert panel's consensus on the criteria that should be used to evaluate business processes to automate. (Ratia, Myllärniemi, and Helander, 2018;Santos, Pereira, and Vasconcelos, 2019;Riedl and Beetz, 2019) Data structure of inputs (Santos, Pereira, and Vasconcelos, 2019;Riedl and Beetz, 2019;Wellmann, et al, 2020;Rhouati, et al,2021;Wewerka and Reichert, 2020;Siderska, 2020;Syed, et al, 2020;Lau et al, 2000;Griffiths and Pretorius, 2021;Viehhauser and Doerr, 2021;Marciniak and Stanisławski, 2021;) Rule-based process (Santos et al, 2019;Riedl and Beetz, 2019;Hofmann et al, 2020;Wellmann et al,, 2020;Rhouati, 2021;Enriquez, 2020;Wewerka and Reichert, 2020;Wewerka and Reichert, 2020;Ivančić et al, (Rhouati et al, 2021;Wewerka and Reichert, 2020;Syed et al, 2020), (Lau et al, 2000;Choi, 2021;) Human Error (Lau et al, 2000) Complexity (Wewerka, and Reichert, 2020;Syed et al, 2020;Lacity, Willcocks and Craig, 2015) In this Delphi study, the surveys can be divided into two types. The first one used in the first round of the survey was compounded by open questions to retrieve order criteria not present on the initial criteria list obtained from the SLR in Section 2.…”

Adaptive Modeling of Robotic Assembly Using Augmented Petri Nets

“…They model the assembly process as contact states and their relations, plan a sequence of contact states [2], change contact states to reach a goal state through identifying and controlling contact states, and accordingly generate the robot motions [1] [11] [12].…”