Schwerpunkt: AI

Robotics is a complex field that emerged at the intersection of multiple disciplines such as physics, mathematics and computer science. New advances in hardware and software design and progress in artificial intelligence enable robotics research to pursue higher goals and achieve increased autonomy in various environments. For instance, robots can operate in disaster zones for search and rescue operations, can be employed in rehabilitation and healthcare, space and underwater exploration, etc. Given the complexity of such scenarios, it is essential to develop robust robotic systems with a high degree of autonomy, able to assist humans in difficult and tedious tasks.

This course aims to provide the fundamentals of modern robot control approaches that enable robotic agents to operate in the environment autonomously. The course introduces a basic understanding of autonomous robots, along with tools and methods to control various types of mobile robotic platforms and manipulators. Firstly, the course presents the types of sensors and actuators employed in autonomous robotic platforms. Secondly, it offers a formal understanding of the robot geometry, its kinematic and dynamic models. Finally, the course provides methods and approaches to control the robotic system from a deliberative and reactive point of view. Students will put this knowledge into practice during tutorials and exercise sheets using Python implementation and robot simulations.

Contents

• Introduction to Robotics and AI: long term robot autonomy, artificial intelligence, deliberative vs. reactive control, robotic applications.
• Sensing and Actuation Modalities: types of sensors and actuators, sensor fusion, actuator control.
• Robot Geometry and Transformations: robot transformations in the 3D space, exponential and logarithmic maps, forward and inverse geometric models.
• Kinematics: definition of twists and wrenches for rigid bodies, geometric Jacobian formulation, forward and inverse kinematics.
• Dynamics: an introduction to Lagrangian and Newtonian mechanics, robot dynamics formulation, recursive Newton-Euler algorithm.
• Localization: direct and probabilistic methods for robot localization, odometry, global localization, particle filter.
• Path Planning: path vs. trajectory generation, graph-based methods for path planning (e.g. Djikstra, A\*).
• Kinodynamic Planning: transcribing a dynamic planning problem into trajectory optimization, direct and indirect methods, costs and constraints.
• Reinforcement Learning-based Control: mathematical foundations, discrete vs continuous methods, reinforcement learning for closed-loop robot control.
• Dynamic Control: PD gravity compensation control, computed torque control, admittance vs impedance control.
• Optimal Control: energy-shaping control, LQR and time-varying LQR control.

Learning Outcomes

At the end of the course, the student is expected to be able to:

• Define robot autonomy and list its key aspects.
• Describe the sensor and actuator modalities used in robotics, and explain their relevance for robot control.
• Implement and understand the low-level actuator control methods.
• Compute the 3D world coordinate transformations for rigid bodies.
• Apply the robot forward and inverse geometric model.
• Describe a robotic system based on its kinematic and dynamic properties.
• Use probabilistic methods for robot localization.
• Generate an optimal path for a mobile robot or manipulator using graph search methods.
• Plan a path taking into account the robot kinodynamic properties.
• Use reinforcement learning methods to control simple robotic systems.
• Apply dynamical and optimal control methods on robotic systems such that they are robust against disturbances.
• Assess the strengths and limitations of different control methods presented in the course.
• Identify open challenges in robotics research and current trends in state-of-the-art.
• Communicate confidently using the terminology in the field of robotics.
• Cooperate and work in teams in order to solve tasks.

Examination

a) Submission of 6 worksheets in groups of 4 students and group interview for final grade (Übungsaufgaben und Fachgespräch).
b) Individual oral exam without worksheet submission (mündliche Prüfung).

References

• Mechanics of Robotic Manipulation, Mathew T. Masen, MIT press, 2001.
• Algebra and Geometry, Alan F. Beardon, Cambridge University Press, 2005.
• Modelling and Control of Robot Manipulators, Lorenzo Sciavicco, Bruno Siciliano, Springer, 2000.
• Probabilistic Robotics (Intelligent Robotics and Autonomous Agents), Sebastian Thrun, Wolfram Burgard, and Dieter Fox, MIT Press, 2005.
• Introduction to Autonomous Mobile Robots, Siegwart R., Nourbakhsh I., Scaramuzza D., MIT press, 2011.
• Automated Planning: Theory and Practice, Malik Ghallab, Dana Nau, Paolo Traverso, Elsevier, 2004.
• Behaviour-based robotics, R. C. Arkin, MIT press, 1998.
• Modern Robotics: Mechanics, Planning, and Control, Kevin M. Lynch and Frank C. Park, Cambridge University Press, 2017.

From medical decision support systems to automatic language translation, from sorting and prioritizing news on social networks to autonomous cars: Machine learning is woven into the fabric of daily life. Applying machine learning, data science aims to extract knowledge or insights from data.

The class will provide an introduction to data science and applied machine learning. For this, the programming language Python will be used (and taught). You will learn about the difference between supervised and unsupervised machine learning, and four machine learning tasks:
• Classification (e.g. k-NN, Decision Trees, Support Vector Machines)
• Regression (Linear Regression, Logistic Regression)
• Clustering (k-means)
• Dimensionality Reduction (PCA, t-SNE)
We will explore natural language processing for text mining and computer vision. Exploratory data analysis and evaluation, as an integral part of data science, will also be taught.

This class is taught remotely. Every week, the lecturer will upload new material to this website. To succeed in this course, you have to watch the videos, do the exercises and applications, and work on your own project. Remember that these videos are not full-fledged lectures, they are a starting point for your own learning. Use material like the coursebook to learn more about the topics as we progress in the course.

This is an online course, not a lecture that was filmed and put online. The course format was adapted to suit both the needs of the medium and the material.

We will meet regularly, but most of the input will be provided as videos. This allows you to rewatch videos, watch them at different speeds, and discuss the videos with each other.

A large number of problems arising in practical scenarios like communication, transportation, planning, logistics etc. can be formulated as discrete linear optimization problems. This course briefly introduces the theory of such problems. We develop a toolkit to model real-world problems as (discrete) linear programs. We also explore several ways to find integer solutions such as cutting planes, branch & bound, and column generation.

Throughout the course, we learn these skills by modeling and solving, for example, scheduling, packing, matching, routing, and network-design problems. We focus on translating practical examples into mixed-integer linear programs. We learn how to use solvers (such as CPLEX and Gurobi) and tailor the solution process to certain properties of the problem.

This course consists of two phases:

• One week Mon-Fri (full day) of lectures and practical labs during Sep 26–30, 2022.
• An individual project period: One project has to be modeled, implemented, and solved individually or in a group of at most two students. The topic will be either developed with or provided by the lecturers. The project including the implementation has to be presented before the beginning of the winter semester.

There are no prerequisites except some basic programming skills to participate.

Important: please register for this course by September 1, 2022 by Email to Felix Hommelsheim (fhommels@uni-bremen.de)

Zu Beginn jedes Semesters findet eine Infoveranstaltung statt, wo die Scheinkriterien für Versuchspersonen erläutert werden. Außerdem werden (aufbauend auf den Inhalten von WA1) Forschungsmethoden von Studien mit Versuchspersonen vermittelt.
Im weiteren Verlauf des Studiums sollen Studierende 15 Versuchspersonenstunden absolvieren (d.h. an mehreren Studien teilnehmen). Jede Studienteilnahme wird mit Versuchspersonenstunden vergütet, die in ECTS anerkannt werden können. Die Versuchspersonenstunden können über mehre Semester gesammelt werden.
Die Teilnahme an den Studien soll in einer schriftlichen Ausarbeitung dokumentiert und reflektiert werden.



At the beginning of each semester, an information session is held where the certificate criteria for subjects are explained. In addition, research methods of studies with test subjects are taught (building on the contents of WA1).

Later in the program, students are expected to complete 15 subject hours (i.e., participate in different studies). Each study participation is compensated with subject hours, which can be recognized in ECTS. The subject hours may be accumulated over multiple semesters.

Participation in the studies should be documented and reflected upon in a written paper at the end.
The selection of participants is made manually after registration.

Users who wish to register for this event will receive more detailed information and can then still decide against participation.

Profil: SQ, KIKR.
Schwerpunkt: IMA-SQ, AI, VMC
weitere Studiengänge: M-M-Alg-Num, M-T

Schwerpunkt: SQ

Profil: KIKR
Schwerpunkt: IMAP-AI, IMA-VMC

Profil: SQ.
Schwerpunkt: DMI, SQ
Die Veranstaltung ist inhaltlich identisch mit "Entwurf von Informationssystemen" (keine Doppelanerkennung möglich).

Profil: KIKR.
Schwerpunkt: IMA-AI, VMC

Profil: KIKR, DMI.
Schwerpunkt: DMI, VMC, AI

Profil: DMI
Schwerpunkt: IMA-DMI, IMA-VMC

Profil: DMI
Schwerpunkt: IMK-DMI, IMA-VMC

Profil: SQ
Schwerpunkt: SQ
Die Veranstaltung findet online statt.

The development of solving techniques for linear programming tasks are a huge contribution of Mathematics to the solution of practical optimization problems. This course is an introduction both into the theory and the application of linear and integer optimization. We will cover the theoretical background as well as algorithmic ideas and practical applications. Main topics that we will cover in the course are the Simplex Method, Ellipsoid Method, Interior Point Method, Cutting Planes, Branch & Bound, LP Duality, and Polyhedral Theory.

Schwerpunkt: AI, DMI

Profil: KIKR
Schwerpunkt: AI

Profil: SQ, KIKR, DMI.
Schwerpunkt: SQ, AI, DMI, VMC
Some prior expertise in C will be helpful. The lecture will be held in German or English, depending on demand.
https://cgvr.cs.uni-bremen.de/teaching/

Profil: SQ
Schwerpunkt: SQ

Profil: SQ
Schwerpunkt: SQ

Schwerpunkt: SQ

Schwerpunkt: AI, DMI
This aim of this course is to create an understanding of the major aspects of sports applications. The course is split into two parts: the first half has a classic lecture/tutorial style, whereas the second half will focus on the creation of individual sports applications.

The lectures will explain the necessary fundamentals, such as sensor technology, user feedback, and the conduction of empirical studies, along with a number of inspiring examples.

In the project part, own prototypes for sports applications are developed in small groups. The exact application as well as the technical implementation approach can be chosen freely. The final graded outcome of the course will be a small sports application about which a presentation has to be held and a documentation in a scientific paper style has to be written.

The course will be held in English.

Schwerpunkt: AI, DMI

Profil: DMI.
Schwerpunkt: DMI, VMC

Profil: DMI
Schwerpunkt: DMI

Die Veranstaltung richtet sich an Studenten der Informatik und Digitalen Medien. In Gruppenarbeit sollen die Studierenden semesterbegleitend ein App-Projekt umsetzen. In der Vorlesung werden alle relevanten Informationen der modernen Softwareentwicklung, mit Fokus auf die mobile App-Entwickung, vermittelt. Dazu gehören Themen wie mobiles Testing, Scrum, UX Design, Evaluation & Nutzertests, Design Patterns und Cross-Plattform-Entwicklung. Das Ziel dabei ist die Vermittlung von praxisrelevantem Wissen aus dem Alltag eines erfolgreichen Unternehmens.

Profil: KIKR

Profil: KIKR, DMI.
Die Veranstaltung findet in Englischer Sprache statt.

60 Lehrveranstaltungen in Deutsch und Englisch für Bachelor- und Masterstudentinnen aller Fächer. Als General Studies sowie teilweise als Fachstudium im Sommersemester 2022 sowie im Wintersemester 2022/23 anerkannt. Alle Einzelangaben, Zeiten und Anmeldungen jederzeit nur über die Website https://www.informatica-feminale.de.
60 courses in German and English for women Bachelor and Master students from all fields of study. Courses are part of General Studies, some are accepted in Informatics; in the summer semester 2022 as well as in winter semester 2022/23. Further information, schedules and registration only on the website https://www.informatica-feminale.de.

Veranstaltung für Doktoranten, jeden 1. Montag im Monat von 14-16h in Raum 5300.

60 Lehrveranstaltungen in Deutsch und Englisch für Bachelor- und Masterstudentinnen aller Fächer. Als General Studies sowie teilweise als Fachstudium im Sommersemester 2022 sowie im Wintersemester 2022/23 anerkannt. Alle Einzelangaben, Zeiten und Anmeldungen jederzeit nur über die Website https://www.informatica-feminale.de.
60 courses in German and English for women Bachelor and Master students from all fields of study. Courses are part of General Studies, some are accepted in Informatics; in the summer semester 2022 as well as in winter semester 2022/23. Further information, schedules and registration only on the website https://www.informatica-feminale.de.