News

Bachelor and master students in Mechatronics are involved in project “DEEPCOBOT”. The projects are supervised by Prof. Jing Zhou and Assoc. Prof. Ilya Tyapin. The bachelor and master students have worked together with PhD students Emil and Jayant.

https://www.uia.no/en/research/priority-research-centres/top-research-centre-mechatronics-trcm/news/next-generation-artificial-intelligence-for-industrial-robots2

• Bachelor Thesis title: Human-Cobot Sequential Cooperation 

The objective of this bachelor project is to provide a solution to perform semi autonomous collaborative tasks, between a robot and a human. The project is focused on making a usable autonomous solution, that will find a sequence of actions that will lead to a desired goal. The tasks include solving different planning problems such as identifying objects, picking and placing objects, moving around in a known environment, and interacting with the environment to complete its goal. To achieve these tasks it was necessary to make new software for the robot to run. All programming was done within the ROS framework. By using ROS melodic, Linux Ubuntu 18.04 and Python programming language. The majority of all testing was in simulation using Gazebo, testing was done on the physical robot when simulation was satisfactory. 

Bachelor Thesis: Multi Robot Cell Operation using Robot Operating System

This project contains the work for a bachelor’s thesis at the University of Agder (UiA) in spring 2021. With cobots being the fastest growing segment of industrial automation, this thesis will investigate a multi robot cell operation. This cell consists of the Universal Robot 5 (UR5) and TIAGo. This project was carried out with the use of Robot Operating System (ROS) with the Melodic Morenia distribution along side Linux Ubuntu 18.04. The goal of this thesis is to make these cobots perform a pick and place operation in a fast and effective
manner. TIAGo will identify an object, pick it up, and navigate to the UR5. Then, UR5 will detect the object and store it. This task is performed both in simulation, as well as on a physical setup.

Master Thesis: Model-free object grasping with a learning-free approach
Student: Tom Erik Vange

The industry standards and capability are constantly advancing and pushing forward to increase data collection, efficiency, profit, and quality as well as decrease downtime, injuries, and hazards as much as possible. In recent years, robot systems have received more attention in the context of a large number of industrial applications, such as automotive manufacturing, additive manufacturing, assembly, quality inspection, and co-packing. The collaboration between multiple robots and human operators is considered to be the most prominent strategy in Industry 4.0 and future Industry 5.0, sharing the same space and collaborating on tasks according to their complementary capabilities. With the use of robots and their abilities could efficiency, profit, safety, and quality be further increased, potentially revolutionizing the industry and production.

This project has looked into the problem of grasping an unknown and previously unseen object with a learning-free approach. By implementing a model-free picking algorithm onto a robot arm with a gripper and robot vision could it be able to pick up a vast variety of objects. A virtual environment has been created with a robot arm and depth-camera during this project. The result from this project is a setup that is able to scan objects placed on a workbench and create a point cloud representation of these objects. The point cloud is since used to calculate the curvature of the objects, creating a foundation for further use in a learning-free setup for grasping previously unseen objects.

Title: Learning-based Control and Applications

Speaker: Professor Zhong-Ping Jiang (New York University, Fellow of IEEE & IFAC)

Time and Date: 15:00-16:00, 15^th June 2021 (Tuesday)

Seminar link:

https://uiano.zoom.us/j/63312474623?pwd=MHNvMVJrRFBUeTBaTjlDelN0dmQ1UT09

Abstract

This talk presents a new design paradigm, called “learning-based control”, that is fundamentally different from traditional model-based control and model-free machine learning. Learning-based control is aimed at learning real-time optimal controllers directly from input-output data, for stability and robustness of dynamical systems in uncertain environments. Novel tools and methods for data-driven control are proposed as an entanglement of techniques from reinforcement learning and control theory. The effectiveness of learning-based control design is demonstrated via its applications to network systems such as connected and autonomous vehicles and neural science problems such as computational principles of human movement.

Bio of the Speaker

Zhong-Ping JIANG received the M.Sc. degree in statistics from the University of Paris XI, France, in 1989, and the Ph.D. degree in automatic control and mathematics from the Ecole des Mines de Paris (now, called ParisTech-Mines), France, in 1993, under the direction of Prof. Laurent Praly.

Currently, he is a Professor of Electrical and Computer Engineering at the Tandon School of Engineering, New York University. His main research interests include stability theory, robust/adaptive/distributed nonlinear control, robust adaptive dynamic programming, reinforcement learning and their applications to information, mechanical and biological systems. In these fields, he has written six books and is author/co-author of over 500 peer-reviewed journal and conference papers.

Prof. Jiang is a recipient of the prestigious Queen Elizabeth II Fellowship Award from the Australian Research Council, CAREER Award from the U.S. National Science Foundation, JSPS Invitation Fellowship from the Japan Society for the Promotion of Science, Distinguished Overseas Chinese Scholar Award from the NSF of China, and several best paper awards. He has served as Deputy Editor-in-Chief, Senior Editor and Associate Editor for numerous journals. Prof. Jiang is a Fellow of the IEEE, a Fellow of the IFAC, a Fellow of the CAA and is among the Clarivate Analytics Highly Cited Researchers.

Our TIAGo robot has arrived! TIAGo from PAL Robotics combines perception, navigation, manipulation & Human-Robot Interaction skills. TIAGo robot will be used in the DeepCobot project, exploring the collaboration between TIAGo robot and the human and the cooperation between TIAGo robot and UR cobot.

The Mechatronics Centre and WISENET Centre at UiA have joined forces in a new multidisciplinary frontier research project that combines Robotics and Explainable Artificial Intelligence. They have received NOK 16 million from the Research Council of Norway to develop robots that can learn and cooperate both between themselves and with human operators in industrial environments. 

Continue reading “Next-generation Artificial Intelligence for Industrial robots”