A robot localization proposal for the RobotAtFactory 4.0: A novel robotics competition within the Industry 4.0 concept

Abstract

Robotic competitions are an excellent way to promote innovative solutions for the current industries’ challenges and entrepreneurial spirit, acquire technical and transversal skills through active teaching, and promote this area to the public. In other words, since robotics is a multidisciplinary field, its competitions address several knowledge topics, especially in the STEM (Science, Technology, Engineering, and Mathematics) category, that are shared among the students and researchers, driving further technology and science. A new competition encompassed in the Portuguese Robotics Open was created according to the Industry 4.0 concept in the production chain. In this competition, RobotAtFactory 4.0, a shop floor, is used to mimic a fully automated industrial logistics warehouse and the challenges it brings. Autonomous Mobile Robots (AMRs) must be used to operate without supervision and perform the tasks that the warehouse requests. There are different types of boxes which dictate their partial and definitive destinations. In this reasoning, AMRs should identify each and transport them to their destinations. This paper describes an approach to the indoor localization system for the competition based on the Extended Kalman Filter (EKF) and ArUco markers. Different innovation methods for the obtained observations were tested and compared in the EKF. A real robot was designed and assembled to act as a test bed for the localization system’s validation. Thus, the approach was validated in the real scenario using a factory floor with the official specifications provided by the competition organization.

A Machine Learning Approach to Robot Localization Using Fiducial Markers in RobotAtFactory 4.0 Competition

“…This indicates that, in general, the ML approaches have similar results to the analytical approach. It is important to highlight that only the ArUco present on the floor was used, as in [ 4 ]. It is also important to note that the results are not intended to reflect the final prediction, but serve as an input for a sensor fusion filter, which will improve the quality of the prediction.…”

“…The use of fiducial markers in a Simultaneous Localization and Mapping (SLAM) problem with other localization techniques (e.g., Monte Carlo) was also explored [ 22 ]. As previously mentioned, in the RobotAtFactory 4.0 competition, an analytical approach using fiducial markers has been proposed by [ 4 ].…”

“…Figure 9 displays the detected markers alongside their reference frames, and their corresponding pose arrays are shown in Table 1 . More details about the ArUco identification can be seen in [ 4 ].…”

“…This model will be used to compare with the analytical approach using dataset D (built with the random route through the field). It is important to highlight that, in this part, only ArUcos on the floor are used (this limitation is used to ensure the possibility of comparison with the approach used by [ 4 ]).…”

“…One of the current approaches to solve the localization problem at the RobotAtFactory 4.0 competition is using the stored data of the ArUcos pose and the relative position of the ArUcos with the camera reference frame, using geometry, to estimate the robot pose [ 4 ]. Each identified ArUco has an estimated pose, and, with some filters (such as Kalman and Mahalanobis filters), it is possible to aggregate these poses and generate a good estimate of the robot pose.…”