The promise of intelligent robot systems is that they can accomplish more tasks, more efficiently than a single-purpose industrial robotic solution. Intelligent robots act competently because they can plan, sequence and enact the actions that are appropriate in the context in which they find themselves. In order to achieve this capability, intelligent robots use Artificial Intelligence (AI) Search Methods. These are general-purpose algorithms for solving combinatorial problems, in other words, they constitute a robot's "reasoning engine". This course introduces students to the most important types of AI search methods. These are then instantiated in three industrially-relevant application contexts, namely, resource scheduling, motion planning, and multi-robot coordination.

ROS (Robot Operating System) is a common set of tools used in academia to do research within autonomous systems. It shortly provides a middleware for handling communication, as well as interfacing sensors and actuators, visualization, simulation and datalogging and infrastructure where it is easy to share your own methods and algorithms. The latter has allowed a large set of different of state-of-the-art research approaches to be readily available for downloading. Due to its popularity it is also getting more widespread in the industrial community, especially in R&D. This course will give you hands-on experience how to utilize these tools and apply them to a problem of your choice.

Answer Set Programming (ASP) is a declarative programming paradigm designed within the field of Artificial Intelligence (AI), and used to solve complex search-problems. The declarative nature of ASP allows one to encode a problem by means of logic. In this way, unlike in imperative programming approaches, there is no need to design an algorithm as a solution for the given problem. In this sense, ASP is comparable with SAT-based encoding or constraint satisfaction problems. However, due to its stable-model semantics, ASP provides a richer representation language useful to handle uncertain situations more effectively for real world scenarios. The advantages of declarative programming together with non-monotonic nature of ASP in handling uncertainties have recently made ASP more attractive both for academia and industry. This course focuses on formalizing and solving various search problems in planning, scheduling and system configuration in ASP.

Producing good machine learning models using the algorithms discussed in Introduction to Machine Learning – Part I typically depends on proper usage and preprocessing of the data, as well as the ability to interpret and act on the results generated by the method. Thereto, you will learn in this course more about the practical side of applying the machine learning techniques to actual problems including feature extraction methods, to figure out which part of the data is relevant to your problem, the bias-variance dilemma, to figure out if you have enough data for your model, ensemble learning, for combining more than one machine learning technique, and other experience-based practical recommendations. Armed with this knowledge, you will have to solve a classification problem in competition with the rest of the class, getting a hands-on experience in using Machine Learning.

By taking part in this course you will learn about the role of visualization in industrial applications with a specific focus on Industry 4.0. You will learn how to evaluate and develop production systems and processes that integrate visualization technologies, such as digital twins, virtual and augmented reality and are supported by artificial intelligence.

During the course, you will explore a variety of optimization problems related to production systems. You will gain hands-on experience on modern methods for practically simulating and optimizing production systems. You will collaborate in groups towards applying the gained knowledge on your own production cases through state-of-the-art optimization software. At the end of the course, you will be equipped with the theoretical knowledge and practical experience to implement optimization techniques on real-world production systems.

The course covers digitalisation and automation technologies and their application in smart factories. Technologies covered include simulation and deployment, digital twin, connectivity as an enabler for e.g. predictive maintenance, manufacturing execution systems and robotics.

Would you like to know what Industry 4.0 is about? Then this course is for you! In the course, we look at enabling technologies of Industry 4.0 from a human and industrial perspective. The course covers many topics and you will learn the basic terminology related to Industry 4.0 as well as insight and understanding of the Fourth Industrial Revolution and how it is set to affect industry and individuals.

You will acquire knowledge about planning and implementing industrialization activities for achieving a faster time-to-market and time-to-volume with higher quality. During the course you will work on one of your company’s industrialization challenges as a “project case” and analyse ways to tackle them in an efficient way.

Reinforcement Learning (RL) is a type of machine learning technique that enables an agent to learn in an interactive environment by trial and error using feedback from its own actions and experiences. The course is part of the education initiative Smarter at Örebro University. This is course requires completion of course Reinforcement Learning part 1.  Read more

This course, Digitally-enabled production, is offered in a collaboration between Mälardalens högskola (MDH), Högskolan Väst (HV) and Linnéuniversitetet (LNU). The course aims to support and facilitate our partner manufacturing companies to become competitive in digitally-enabled production. During the course, we address the potential prerequisites and capabilities required for implementing industry 4.0 in the context of an overall production system. More specifically, we increase the competence base of companies in three areas—internal logistics systems, virtual factory, and sensor and signal processing—which can holistically interconnect the key components for the successful implementation of industry 4.0. This course consists of three interconnected course modules at an advanced level and it is offered between September and November 2020: Internal Logistics in Industry 4.0, 2.5 credits, MDH, https://www.mdh.se/en/malardalen-university/education/course-syllabus?id=29594 Virtual Factory and Robot Cell Simulation, 2.5 credits, HV, https://admin.hv.se/samverka-med-oss/kompetensutveckling/teknik/kompetensutveckling-inom-produktionsteknik/virtual-factory-and-robot-cell-simulation/ Data Acquisition and Monitoring, 2.5 credits, LNU, https://kursplan.lnu.se/kursplaner/kursplan-4MT017-1.pdf More information about the course is available on the below link: https://www.mdh.se/en/malardalen-university/education/further-training/smart-production/digitally-enabled-production-7.5-hp Apply to the course in the below link:  https://www.mdh.se/en/malardalen-university/education/further-training/smart-production/digitally-enabled-production-7.5-hp/application-form-digitally-enabeled-production-7.5-hp

The aim of this course is to give students insight about certification and about what it means to certify/self-assess safety- critical systems with focus on software system and to create a safety case, including a multi-concern perspective when needed and reuse opportunities, when appropriate.

The emergence of artificial intelligence has created a new opportunity to apply machine learning (ML) in industry 4.0. In this era of the Internet of Things and Big data, processing of a large amount of data would not be possible without ML. Thus, ML made industrial production smarter than ever before.  So, learn the course “Machine learning for Industry 4.0” to bring in new business models in your company and boost productivity using ML.  The course provides knowledge about basics of ML and data, describes ML algorithms and tools and also explains the concept of Industry 4.0 and digitalization in industry 4.0.   The individual processes can be better understood and optimized with the help of the knowledge from the course. Also, it could have an important contribution in analysing the industrial data set, improving results, and making  decision and/or predictions for failure, demand, sales, and production. This course is a collaboration between Högskolan Väst, Linnéuniversitetet and Mälardalens Högskola. It consist of three course modules: Introduction to Machine Learning (MDH – 2 credits, Basic level), Industry Digitalization – Industry 4.0 (HV – 2,5 credits, Advanced level), Applied Machine Learning (LNU – 3 credits, Advanced level). Students who pass all three courses will receive a diploma from Learning for Professionals.