Course content

The course contains a selection of the following topics, with an emphasis on applications within robotics and intelligent systems:

• Industrial and collaborative robots.
• Mobile robots.
• Data structures and algorithms.
• C++ programming.
• Software development and development tools, design patterns, and best practices.
• Rigid-body motions (e.g., homogeneous transformation matrices, rotations, and exponential coordinates).
• Kinematics and modelling of kinematic chains.
• Optimization methods (e.g., root-finding and minimization using gradient descent and Newton-Raphson's method).
• Inverse kinematics.
• Trajectory generation and motion planning.
• Dynamics of open chains.
• Actuators and robot control.
• Artificial intelligence and intelligent systems (e.g., evolutionary algorithms, agent-based modelling, and path finding).
• Sensors for robot interaction and perception (e.g., machine vision or simultaneous localization and mapping (SLAM)).
• Data analysis and applied machine learning.
• Prototyping.
• Potentially other topics relevant to the project work.

More details about the curriculum will provided during the start of semester.

Learning outcome

Knowledge and skills

Within the context of robotics and intelligent systems, the candidate can use and/or explain:

• The difference between robotics, mechatronics and automation.
• Fundamental theory, methods, and components within automation and robotics, including common components, sensors, and actuators.
• Industrial control systems, microcontrollers (e.g., Arduino), microcomputers (e.g., Raspberry Pi or Jetson Nano) or programmable logic controls (PLCs) in robotic systems.
• Industrial and collaborative robots, robot programming, and robot architectures.
• Theory and methods within software engineering, data communication, IoT, machine vision, and cyber-physical systems for collecting, processing, storing, and sending data.
• Methods, principles and tools within software engineering (e.g., design patterns, integrated development environments (IDEs), testing, validation, diagnostics and debugging techniques).
• Software and programming for data analysis, machine learning, and machine vision.
• Methods, algorithms, and intelligent systems for automatic control of robots and automatic systems.
• Methods and tools (e.g., Fusion 360, Matlab or Python) for design, simulation, and virtual prototyping.
• Relevant electrical and mechanical tools used in labs.

Competence

With respect to robotics and intelligent systems, the candidate can:

• Identify and analyze complex problems and challenges.
• Explain and use methods or tools for developing sustainable solutions.
• Explain, evaluate and compare the methods and tools used in this course.
• Find, use and evaluate critically research and scientific papers within the field.
• Find, use and evaluate critically any relevant technical or innovation-based information within the field.
• Identify gaps or potentials in the field and develop proposals for innovation and research.
• Identify and explain societal challenges and potential solutions (including possible consequences and future outcomes).
• Reflect on norms, ethics and sustainability at an individual, societal, and global level, and their relevance.
• Work individually and goal-oriented, take initiative and interact well in a team, and show leadership in project and development work.
• Present and discuss the topics within this course to a relevant audience (e.g., their peers, scholars or business representatives).
• Develop and demonstrate the ability and willingness for lifelong learning.

Learning methods and activities

A constructivist approach for learning is endorsed, with focus on problem solving and practical application of theory. This course may use flipped-classroom and problem-based learning for a student-centered approach to learning. Learning activities generally include a mix of Q&A sessions (questions and answers), lectures, tutorials, compulsory assignments, compulsory quizzes, and practical lab/project work. The learning activities are adapted to the practical work (assignments or project) taking place at any time, and may touch upon the concept of "delayed instruction." The course aims to have synergies with the learning activities in the other courses that run in parallel (e.g., AIS4001 Cybernetics and Robotics (autumn semester) or AIS4002 Intelligent Machines (spring semester)).

Project work is carried out individually and within a team. There are primarily individual works in the first semester and group works in the second semester.

During the study year, there might be events such as excursions to relevant industry, seminars and conferences, and guest lectures and coursework provided from company representatives.

Compulsory assignments

• Compulsory learning activities

Specific conditions

Recommended previous knowledge

Prior experience in programming is highly recommended, for example:

• AIS1003 - Object-oriented programming for cyber-physical systems
• TDT4102 - Procedural and Object-Oriented Programming

All assignments and project work in this course rely heavily on C++ (and to a lesser extent Python). Without prior experience, be prepared for extra self-study on programming and C++ during this course.

Required previous knowledge

The course has no prerequisites. It is a requirement that students are either (a) enrolled in the study programme to which the course belongs, or (b) taking the course as an exchange student. Other exceptions may be made upon approval from the academic director of the study programme.

Course materials

An updated course overview, including curriculum, is presented at the start of the semester.