module specification

The "AI for Robotics" module offers students a thorough exploration of implementing AI within the robotics domain. Covering essential algorithms like Simultaneous Localization and Mapping (SLAM), Automatic Navigation (AutoNav), computer vision, etc., students gain hands-on experience in algorithmic implementation through practical workshops. The students will also be introduced to real-world applications spanning industrial automation, autonomous vehicles, and medical robotics, analysing case studies to understand AI's transformative impact and learn about robotic perception and cognition tasks in this process. Working methodologies of equipment such as LIDAR, odometry sensors, stereo cameras etc., will also be taught to the students such that they are able to select the appropriate hardware for their application. Moreover, students will navigate the legal and ethical landscapes surrounding robotics, including health and safety regulations, intellectual property rights, and ethical considerations. Through a blend of formal lectures, hands-on workshops, and interactive discussions, this module equips students with the skills to effectively integrate AI into robotics solutions while fostering a critical awareness of societal implications. One of the aims of this module is to also ensure that the students are well equipped for the module “AI with ROS” which they will be undertaking in the upcoming semester.

CT4002 Electronic Systems CS4001 Programming

Mathematical concepts essential for AI algorithms: probability theory, matrix algebra, optimization methods, linear algebra and graph theory.

AI in Robotics Part 1- SLAM (Simultaneous Localization and Mapping): EKF (Extended Kalman Filter) SLAM, FastSLAM, GraphSLAM algorithms.

SLAM oriented concepts: Loop closure detection and map optimization.

AI in Robotics Part 2- AutoNAV (Autonomous Navigation) and Path Planning: A* algorithm, Dijkstra’s algorithm, RRT (Rapidly exploring Random Tree) algorithms.

AI in Robotics Part 3- Cognitive Robotics: Cognitive architecture for robotics systems, decision making and planning in robotics.

Understanding the Hardware involved: In-depth knowledge of hardware components such as LIDAR, odometry sensors, stereo cameras etc. including the understanding of selection criteria, calibration techniques and integration challenges associated such equipment.

AI in Robotics Part 4- Robot perception, Computer Vision and Sensor Fusion: Modelling of an environment for the robot based on the understanding of the robot’s perception, feature extraction and sensor fusion. Also, computer vision algorithms such as SSD for detecting an object.

Program design, maintenance and safe disposal of end-of-life products. Laboratory skills and safety, LSEP: legal, social, ethical and professional issues in context of artificial intelligence and robotics.

Students will cultivate a comprehensive understanding and hands-on investigative skills through weekly lectures, tutorials, and supervised workshops tailored to the AI for Robotics module. These sessions will employ examples and case studies to elucidate fundamental principles pertinent to robotics applications. Specifically designed workshops will provide students with invaluable problem-solving skills. They will be given different real-life scenarios and will be asked to develop solutions for the same.

A range of blended learning approaches and cutting-edge technologies, including the University's Virtual Learning Environment (VLE), simulation tools, and state-of-the-art laboratory equipment, will be integrated to facilitate and enrich student learning experiences. These tools will serve to deliver course content, foster active engagement,administer formative and summative assessments, and provide timely feedback, thereby enhancing student involvement and overall learning outcomes.

Students will be encouraged to maintain reflective commentaries on their learning activities, documenting their tasks in their practical portfolios. Both individual and group work will be encouraged and expected as students collaborate to devise and implement innovative solutions to workshop exercises and coursework assignments, fostering collaborative problem-solving skills essential in the field of AI-driven robotics.

On successful completion of this module students should be able to:

LO1. Build a comprehensive understanding of robot perception, cognition tasks, and core algorithms like SLAM, AutoNav, and computer vision, covering both theoretical foundations and practical applications.

LO2. Develop proficiency in essential mathematical techniques for AI in robotics—probability, matrix algebra, optimization, linear algebra, and graph theory—enabling effective application and optimization of AI algorithms in robotic contexts.

LO3. Explore diverse real-world applications of AI techniques in robotics, spanning industrial automation, autonomous vehicles, and medical robotics, fostering an understanding of the breadth and depth of AI's impact in various domains.

LO4. Gain a thorough understanding of the legal and regulatory framework for robotics and AI, covering safety, IP, liability, and ethical considerations, including equality, diversity, inclusion, societal impact, and industry standards.

LO5. Develop adaptive problem-solving skills in AI-driven robotics through scenario-based case studies, enabling students to apply flexible strategies and refine their approach to complex challenges via reflection and peer discussion.

Core Text:

Anis Koubaa, (2021) Robot Operating System (ROS), The Complete Reference (Volume 6), Springer Cham, ISBN:978-3-030-75471-6

Ahmad Taher Azar, Anis Koubaa., (2023) Artificial Intelligence for Robotics and Autonomous Systems Applications, Springer Cham, ISBN: 978-3-031-28714-5

Other Text:

Rabindra Nath Shaw, Ankush Ghosh, Valentina Emilia Balas, Monica Bianchini., (2021) Artificial Intelligence for Future Generation Robotics, Elsevier, ISBN: 978-0-323-85498-6

Robin R. Murphy., (2019) Introduction to AI Robotics, Second Edition, The MIT Press, ISBN: 9780262038485

Miller R., Miller M., (2017) Robots and Robotics: Principles, Systems, and Industrial Applications, McGraw-Hill Education, ISBN-13: 978-1259859786

Vaish, D. (2018) Python Robotics Projects: Build smart and collaborative robots using Python, Packt Publishing, ISBN-13: 978-1788832922

Journals:

A. R. Khairuddin, M. S. Talib and H. Haron, "Review on simultaneous localization and mapping (SLAM)," 2015 IEEE International Conference on Control System, Computing and Engineering (ICCSCE), Penang, Malaysia, 2015, pp. 85-90, doi: 10.1109/ICCSCE.2015.7482163.

Chao Duan, Steffen Junginger, Jiahao Huang, Kairong Jin, Kerstin Thurow, Deep Learning for Visual SLAM in Transportation Robotics: A review, Transportation Safety and Environment, Volume 1, Issue 3, 12 December 2019, Pages 177–184, https://doi.org/10.1093/tse/tdz019

X. Ding, J. Guo, Z. Ren and P. Deng, "State-of-the-Art in Perception Technologies for Collaborative Robots," in IEEE Sensors Journal, vol. 22, no. 18, pp. 17635-17645, 15 Sept.15, 2022, doi: 10.1109/JSEN.2021.3064588.

Lindsay J. Robertson (2019), Engineering-Based Design Methodology for Embedding Ethics in Autonomous Robots, Proceedings of the IEEE, DOI: 10.1109/JPROC.2018.2889678

Websites

University Library website- https://student.londonmet.ac.uk/library/

Electronic Databases:

IEEE Xplore / IET Digital Library (IEL) - https://ieeexplore.ieee.org/Xplore/home.jsp

Springer Nature - https://www.springernature.com/gp/products/books

Wiley Online Library - https://0-www-onlinelibrary-wiley-com.emu.londonmet.ac.uk/