Rasmus Skovgaard Andersen

Intuitive task programming of stud welding robots for ship construction

Ship construction is a major industry worldwide, and many tasks have been automated. One task that is still solely carried out manually is welding of studs. This paper presents a semi-autonomous approach to robotic stud the welding with focus on the HRI (Human-Robot Interaction). The welding itself is carried out autonomously by an autonomous industrial mobile manipulator (AIMM). An intuitive interface is proposed for the AIMM to ensure safe and correct operation. The interface allows non-expert operators to program, verify, and reprogram the robots task on the manufacturing site. Task specific information is projected directly into object space as augmented reality using a projector mounted on the robot end-effector. Specifically, stud positions are shown on the ship wall before welding is initiated, and positions can be added, deleted, and moved using an IMU as pointing device. The contribution of this paper is an intuitive interface for on-site programming of stud welding robots; implemented in a skill-based task programming architecture. The system is designed and implemented, and proof-of-concept tests are presented.

Integration of Mobile Manipulators in an Industrial Production

Purpose – The purpose of this study has been to evaluate the technology of autonomous mobile manipulation in a real world industrial manufacturing environment. The objective has been to obtain experience in the integration with existing equipment and determine key challenges in maturing the technology to a level of readiness suitable for industry. Despite much research within the topic of industrial mobile manipulation, the technology has not yet found its way to the industry. To mature the technology to a level of readiness suitable for industry real-world experience is crucial. This paper reports from such a real-world industrial experiment with two mobile manipulators. Design/methodology/approach – In the experiment, autonomous industrial mobile manipulators are integrated into the actual manufacturing environment of the pump manufacturer Grundfos. The two robots together solve the task of producing rotors; a task constituted by several sub-tasks ranging from logistics to complex assembly. With a total...

Interactive Assembly Guide Using Augmented Reality

This paper presents an Augmented Reality system for aiding a pump assembling process at Grundfos, one of the leading pump producers. Stable pose estimation of the pump is required in order to augment the graphics correctly. This is achieved by matching image edges with synthesized edges from CAD models. To ensure a system which operates at interactive-time the CAD models are pruned off-line and a two-step matching strategy is introduced. On-line the visual edges of the current synthesized model are extracted and compared with the image edges using chamfer matching together with a truncated L2 norm. A dynamic visualization of the augmented graphics provides the user with guidance. Usability tests show that the accuracy of the system is sufficient for assembling the pump.

Projecting robot intentions into human environments

Trained human co-workers can often easily predict each others intentions based on prior experience. When collaborating with a robot coworker, however, intentions are hard or impossible to infer. This difficulty of mental introspection makes human-robot collaboration challenging and can lead to dangerous misunderstandings. In this paper, we present a novel, object-aware projection technique that allows robots to visualize task information and intentions on physical objects in the environment. The approach uses modern object tracking methods in order to display information at specific spatial locations taking into account the pose and shape of surrounding objects. As a result, a human co-worker can be informed in a timely manner about the safety of the workspace, the site of next robot manipulation tasks, and next subtasks to perform. A preliminary usability study compares the approach to collaboration approaches based on monitors and printed text. The study indicates that, on average, the user effectiveness and satisfaction is higher with the projection based approach.

Task space HRI for cooperative mobile robots in fit-out operations inside ship superstructures

In the rising area of close human-robot collaboration in industrial scenarios, the human operator must be able to easily understand the intent of and data from the robot. Shipbuilding environments exhibit unique features, which make deployment of mobile robots both challenging, relevant, and interesting. One task that is still solely carried out manually today due to its complexity and high need for mobility is the fit-out operation stud welding. This paper presents the latest state-of-the-art developments in human-robot interaction (HRI) for robotic stud welding in large semi-structured manufacturing spaces. The welding itself is carried out autonomously by an autonomous industrial mobile manipulator (AIMM). A novel HRI is proposed, which employs projection mapping and an IMU device to enable intuitive and natural interaction with the robot. Task specific information is projected directly into task space as augmented reality using a projector mounted on the robot end-effector. The IMU device enables non-expert operators to program, verify, and reprogram the robots task on-site in a ship superstructure. The usability of the system is tested in an extensive user test. It is concluded that non-experts after a short introduction are able to both modify a previous task and instruct and a new task using on average 1:01 and 1:16 minutes. Finally, the HRI has been implemented on a prototype robot and tested in an actual shipyard facility. The precision of the system, including operator inaccuracy, was evaluated to have a standard deviation of 3.6mm.

Automatic parameter learning for easy instruction of industrial collaborative robots

The manufacturing industry faces challenges in meeting requirements of flexibility, product variability and small batch sizes. Automation of high mix, low volume productions requires faster (re)configuration of manufacturing equipment. These demands are to some extend accommodated by collaborative robots. Certain actions can still be hard or impossible to manually adjust due to inherent process uncertainties. This paper proposes a generic iteratively learning approach based on Bayesian Optimisation to efficiently search for the optimal set of process parameters. The approach takes into account the process uncertainties by iteratively making a statistical founded choice on the next parameter-set to examine only based on the prior binomial outcomes. Moreover, our function estimator uses Wilson Score to make proper estimates on the success probability and the associated uncertain measure of sparsely sampled regions. The function estimator also generalises the experiment outcomes to the neighbour region through kernel smoothing by integrating Kernel Density Estimation. Our approach is applied to a real industrial task with significant process uncertainties, where sufficiently robust process parameters cannot intuitively be chosen. Using our approach, a collaborative robot automatically finds a reliable solution.

A Conceptual Digital Assistance System Supporting Manual Changeovers in High-Variety Production

The advent of production strategies such as Mass Customization and Changeable Manufacturing requires that production systems be increasingly flexible towards diverse customer needs. Although humans remain the most flexible entity in modern production systems, the increasing complexity of these systems presents a challenge for the operators with regards to remaining efficient. Research related to Industry 4.0 has promoted the application of digital assistance systems, as a method of augmenting human operators to handle the complexity of these production systems better. However, no digital assistance system that supports human operators in performing manual changeover operations in complex production systems has been identified. This paper, therefore, presents a conceptual digital assistance system, which utilizes information about two consecutive production configurations, and processes this data through an algorithm, to determine which specific changeover operations are required to perform a changeover most efficiently. Potentials of implementing the proposed digital assistance system are briefly introduced, and topics for further research are outlined.

Fast calibration of industrial mobile robots to workstations using QR codes

Much research is directed at developing increasingly efficient and flexible production, and one important potential advancement is the robots known as Autonomous Industrial Mobile Manipulators (AIMMs). The idea behind AIMMs is to have robots that can move around and have the ability to perform a wide variety of tasks, while at the same time being fast and easy to configure and program. When an AIMM moves from one workstation to another, it is essential that it is able to calibrate its position with respect to that new station. In this paper, a new and fast calibration method based on QR codes is proposed. With this QR calibration, it is possible to calibrate an AIMM to a workstation in 3D in less than 1 second, which is significantly faster than existing methods. The accuracy of the calibration is ±4 mm. The method is modular in the sense that it directly supports integration and calibration of a new camera. The calibration have been implemented on Aalborg Universitys AIMM, Little Helper [8, 9], and tested both in a laboratory and in a real-life industrial environment at the Danish pump manufacturer Grundfos A/S.

Proceedings of the 44th International Symposium on Robotics ISR 2013

Much research is directed at developing increasingly efficient and flexible production, and one important potential advancement is the robots known as Autonomous Industrial Mobile Manipulators (AIMMs). The idea behind AIMMs is to have robots that can move around and have the ability to perform a wide variety of tasks, while at the same time being fast and easy to configure and program. When an AIMM moves from one workstation to another, it is essential that it is able to calibrate its position with respect to that new station. In this paper, a new and fast calibration method based on QR codes is proposed. With this QR calibration, it is possible to calibrate an AIMM to a workstation in 3D in less than 1 second, which is significantly faster than existing methods. The accuracy of the calibration is ±4 mm. The method is modular in the sense that it directly supports integration and calibration of a new camera. The calibration have been implemented on Aalborg Universitys AIMM, Little Helper [8, 9], and tested both in a laboratory and in a real-life industrial environment at the Danish pump manufacturer Grundfos A/S.