Casper Schou

Human-robot interface for instructing industrial tasks using kinesthetic teaching

Today, the manufacturing industries increasingly demand more flexible and agile production systems. This demand is also reflected onto the field of robotics, as the majority of robots in the industry today are bolted to the ground and dedicated to a specific task. An Autonomous Industrial Mobile Manipulator (AIMM) offers a higher level of hardware flexibility, but in order to benefit from this flexibility the demand for new approaches to operating and programming new tasks is inevitable. Research within this topic has proposed a task-level-programming, where robot programming is generalized into a selection of skills. This paper presents a human-robot interface based on task-level-programming and kinesthetic teaching, which was assessed by nine people of varying robotics experience. In evaluation of the tests several improvements to the HRI are proposed, while the underlying concept is found to simplify programming of industrial task and thus making this available to the production floor operator.

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...

Developing Modular Manufacturing Architectures - An Industrial Case Report

The manufacturing industry needs flexibility and changeability to accommodate the increasing market dynamics and the related need for product change, variety, and customisation. Achieving such manufacturing responsiveness is the focus of Modular Manufacturing Systems (MMS). MMS have become central in research, but yet are short numbered in industry. This paper presents a case report on MMS platform development at a large Danish manufacturing company. The approach taken is based on related theory of modular product development and hence, modular architectures. The platform is developed following a six-step method and the paper provides thorough descriptions and illustrative examples of each step.

Transfer of contact skills to new environmental conditions

Robots operating in contact with the environment should typically take into account the knowledge of both position/orientation trajectories as well as the accompanying force/torque profiles for successful execution. Pure position control is not appropriate because even small errors in the desired trajectory can cause significant forces at the contact points. In this paper we present a method that computes an appropriate control policy for a given condition of a contact task, with the peg-in-hole (PiH) assembly tasks as example use-cases. Our method is based on statistical generalization of successfully recorded executions at different values of the external condition. The major novelty of the method is that it provides not only generalized position and orientation trajectories, but a complete skill, consisting of desired position/orientation trajectories and the accompanying force/torque profiles. To improve the execution of the skill after generalization, we combine the proposed approach with an adaptation method to refine the newly generated movement. The versatility of the proposed approach was shown by applying it to firstly, two different types of robot arms: a humanoid 7-axis Kuka LWR-4 arm and a 6-axis industrial Universal robot UR5 arm and secondly, two different peg-in-hole problems: insertion of a square peg and insertion of a round peg.

A Plug and Produce Framework for Industrial Collaborative Robots

Collaborative robots are today ever more interesting in response to the increasing need for agile manufacturing equipment. Contrary to traditional industrial robots, collaborative robots are intended for working in dynamic environments alongside the production staff. To cope with the dynamic environment and workflow, new configuration and control methods are needed compared to those of traditional industrial robots. The new methods should enable shop floor operators to reconfigure the robot. This article presents a plug and produce framework for industrial collaborative robots. The article focuses on the control framework enabling quick and easy exchange of hardware modules as an approach to achieving plug and produce. To solve this, an agent-based system is proposed building on top of the robot operating system. The framework enables robot operating system packages to be adapted into agents and thus supports the software sharing of the robot operating system community. A clear separation of the hardware agents and the higher level task control is achieved through standardization of the functional interface, a standardization maintaining the possibility of specialized function features. A feasibility study demonstrates the validity of the framework through a series of reconfigurations performed on a modular collaborative robot.

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.

Fast Setup and Adaptation of Industrial Assembly Tasks with Force-Based Exception Strategies

In this paper we present a method for fast setup and adaptation of desired movement for industrial assembly tasks. Our method is based on adaption of desired movements acquired by Programming by Demonstration (PbD) and fast setup methods such as the Skill Based System (SBS) that are capable to quickly learn sequential skills to perform assembly. The major novelty of the proposed method is the integration of fast setup methods with force based adaptation skills and exception strategies for fast and efficient task execution. To improve the execution of the skill, the learned movements are online adapted according to forces and torques arising during the execution, effectively eliminating the environmental uncertainties. Results show that this approach can be arbitrarily applied to different robotics platforms. We performed tests on the 7-axis Kuka LWR-4 and on the 6- axis UR-5 Universal robot.

Optimizing tracking performance of XY repositioning system with ILC

Controlling complex mechanical systems is often a difficult task, requiring a skilled developer with experience in control engineering. In practice however, the theoretical difficulties of designing a good controller is only a first step as the implementation itself on the various pieces of equipment is also often challenging. This paper investigates if iterative learning control (ILC) can be used as an alternative to tuning existing controllers for improving system performance. This is evaluated by a case study on a high speed XY-positioning system used for laser cutting. An ILC algorithm is implemented by using a server client structure from Matlab. After tuning the parameters an implementation is found which is able to increase the tracking accuracy significantly for cutting speeds up to \(0.5\;{\text{m}}/{\text{s}}\). This is done only by implementing code on the master control unit and thus without changing subsystem controllers.