Autonomous Robotics: Action, Perception, and Cognition
This course will be combine presence and online features ("hybrid").
There will be elements of the "inverted classrooom" in which short videos will be made available that students should watch BEFORE the lecture hour. During the lecture hour, an in-depth presentation and discussion of the material will be done. The lectures and exercises will take place in the classroom, but can also be followed in real time through a Zoom channel.
In the exercise sessions, solutions of the corrected exercises will be discussed. The exercise session can also be used to ask general questions.
The course uses e-learning features provided through the present webpages. This course is NOT managed through moodle! To take the course, you must registerm, therefore, through this webpage: Go to "e-learning", select this course, and follow the instructions there. You will need an email address of the Ruhr-University or the Technical University Dortmund for registration. If you are an exchange student without such an email address or come from another university within the Ruhr-Alliance, contact us by email as instructed there. When registering, please fill in your degree program (for example, "MSC Angewandte Informatik", not just "Master of Science"). This is important information for us to manage exams and credit points.
Autonomous robotics is an interdisciplinary research field in which embodied systems equipped with their own sensors and with actuators generate behavior that is not completely pre-programmed. Autonomous robotics thus entails perception, movement generation, as well as core elements of cognition such as making decisions, planning, and integrating multiple constraints. The main focus of the course are solutions to autonomous movement generation that are inspired by analogies with how nervous systems generate movement.
This course touches on various approaches to this interdisciplinary problem. In the first half of the course focusses on movement generation for autonomous vehicles. The main emphasis will dynamical systems methods (attractor dynamics) for that problem, reviewing related approaches as well. The second half of the course will study motion in robot arms, including motion planning, timing, and control. Analogies with human movement will be exploited to illustrate ideas and problems, including the degree of freedom problem, coordination, and relex control of muscles.
Lecturers
Prof. Dr. Gregor SchönerLecturer |
(+49) 234-32-27965 gregor.schoener@ini.rub.de NB 3/31 |
Lukas BildheimTeaching Assistant (primary contact) |
(+49) 234-32-27971 lukas.bildheim@ini.rub.de NB 02/76 |
Details
- Course type
- Lectures
- Credits
- 6 CP
- Term
- Summer Term 2024
- E-Learning
- e-learning course available
Dates
- Lecture
-
Takes place
every week on Thursday from 14:15 to 16:00 in room NB 3/57.
First appointment is on 11.04.2024
Last appointment is on 18.07.2024 - Exercise
-
Takes place
every week on Thursday from 16:15 to 17:00 in room NB 3/57.
First appointment is on 11.04.2024
Last appointment is on 18.07.2024
Requirements
The emphasis of the course is on learning concepts, practicing interdisciplinary scholarship including reading and writing at a scientific and technical level. Mathematical concepts are used throughout, so understanding these concepts is important. Mathematical skills are not critical to mastering the material, but helpful. The mathematics is mostly from the qualitative theory of dynamical systems, attractors and their instabilities. Short tutorials on some of these concepts will be provided.
Further reading
Readings will be posted on this web page. Also have a look at the web page of the Dynamic Field Theory community that is interested in related problems and solutions. There you find more exercises, reading material, slides and lecture videos that have some overlap with the lecture.
Teaching Units
Introduction
Lecture slides | Organizational issues |
Lecture slides | Introduction to the course |
Video | Introduction |
Document | Background reading: Relation behavioral dynamics / neural dynamics |
Dynamical Systems Tutorial
Attractor dynamics approach
Lecture slides | Attractor dynamics approach to vehicle movement generation (symbolic) |
Video | Attractor dynamics approach to vehicle movement generation (symbolic) |
Exercises | Exercise 2: Attractor dynamics for obstacle avoidance |
Document |
Reading for Exercise 2
Also provides background for the entire attractor dynamics approach. The second part of the paper is about dynamic neural field that form the core of the winter semester course on neural dynamics, so not immediately relevant here. |
Exercises | Exercise 3: Attractor dynamics for human locomotion |
Document | Reading for exercise 3 |
Lecture slides | Attractor dynamics approach to vehicle movement generation (sub-symbolic) |
Video | Attractor dynamics approach to vehicle movement generation: Sub-symbolic |
Exercises | Essay exercise 4: attractor dynamics approach to vehicle movement generation |
Document | Reading for essay exercise 4 |
Survey motion planning
Lecture slides | Survey over approaches to vehicle motion planning |
Video | Survey over approaches to vehicle motion planning |
Exercises | Exercise 5 Potential field approach |
Navigation
Lecture slides | Navigation |
Video |
Navigation
This is a video from earlier years, that is close to the lecture give, but differs is some details. Unfortunately, recording didn't work this week... |
Robotic manipulators
Lecture slides | Robotic manipulators: basic concepts |
Exercises | Exercise 6: robot arm kinematics |
Video | Robotic manipulators: basic concepts (summary) |
Lecture slides | Timing and coordination |
Video | Timing and coordination |
Document | Background reading for timing and coordination |
Lecture slides | Motor control: kinetics and control of robot arms |
Video | Motor control: kinetics and control of robot arms |
Human motor control
Lecture slides | Human motor control, lecture by Dr. Lei Zhang |
Video | Human motor control, lecture by Dr. Lei Zhang |
Documents
Document | Rules for credit |
Document | Note on the use of ChatGPT |
The Institut für Neuroinformatik (INI) is a central research unit of the Ruhr-Universität Bochum. We aim to understand the fundamental principles through which organisms generate behavior and cognition while linked to their environments through sensory systems and while acting in those environments through effector systems. Inspired by our insights into such natural cognitive systems, we seek new solutions to problems of information processing in artificial cognitive systems. We draw from a variety of disciplines that include experimental approaches from psychology and neurophysiology as well as theoretical approaches from physics, mathematics, electrical engineering and applied computer science, in particular machine learning, artificial intelligence, and computer vision.
Universitätsstr. 150, Building NB, Room 3/32
D-44801 Bochum, Germany
Tel: (+49) 234 32-28967
Fax: (+49) 234 32-14210