• RUB
  • INI
  • Courses
  • Autonomous Robotics: Action, Perception, and Cognition

Autonomous Robotics: Action, Perception, and Cognition

Neural computation is concerned with the discovery of new solutions to technical problems of information processing. These solutions are sought based on analogies with nervous systems and the behaviour of organisms.

This course focuses on three exemplary problems to illustrate this approach:
(a) Artificial action (autonomous robotics);
(b) Artificial perception (robot vision);
(c) Artificial cognition (simplest cognitive capabilities of autonomous robots such as decision making, scene representation, working memory, sequence generation, behavioral organization).

The main method is nonlinear dynamical systems applied to neural networks, leading to Dynamic Field Theory and neural dynamics.

Lecturers

Details

Course type
Lectures
Credits
6 CP
Term
Summer Term 2018

Dates

Lecture
Takes place every week on Thursday from 14:15 to 16:00 in room NB 3/57.
First appointment is on 12.04.2018
Last appointment is on 19.07.2018
Exercise
Takes place every week on Thursday from 16:15 to 17:00 in room NB 3/57.
First appointment is on 19.04.2018
Last appointment is on 19.07.2018

Exercises

Usually, we upload an exercise sheet after each lecture. This sheet has to be handed in before the lecture of the following week (alternatively, you can hand it in via email to Jean-Stephane Jokeit), which gives you a week to work on the solutions.

After collecting your solutions, we take a week to correct them and then discuss them in the exercise session following the lecture.

Exercises are corrected, and exercise sessions lead by Jean-Stephane Jokeit.

Further reading

In case you are interested in additional material that goes beyond the scope of the course, have a look at the web page of our community.  It contains more exercises, reading materials, slides and talks that have some overlap with the lecture.

Documents

Document Rules for credit and grade
Lecture slides Organizational issues
Lecture slides Introductory lecture
Document Background review paper
Lecture slides Attractor dynamics approach to vehicle motion planning
Lecture slides Dynamical systems tutorial
Document Link to textbook on dynamical systems

Ed Scheinerman has made his excellent and very readable undergraduate textbook on dynamical systems available online for free at:

      https://github.com/scheinerman/InvitationToDynamicalSystems

This textbook covers both continuous time dynamical systems as used in this course and discrete time dynamical systems (iterative maps). You can ignore the latter. 
Exercises Exercise sheet 1
Document Reading for exercise 1
Lecture slides Attractor dynamics for vehicle motion: sub-symbolic approach
Exercises Exercise 2
Document Reading for exercise 2 (and the lecture about the sub-symbolic attractor dynamics approach)

This is a useful resource for exam preparation. 
Lecture slides Lecture on pedestrian navigation aligned with the attractor dynamics approach
Lecture slides Lecture on the second order attractor dynamics approach to vehicle motion
Exercises Exercise 3: Essay
Document Reading for Exercise 3 Fajen et al

The short presentation of the attractor dynamics approach on pages 3 and 4 is useful for exam preparation. 
Document Secondary reading for Exercise 3 Arkin
Lecture slides Timing and Coordination
Exercises Exercise 4: Timing
Document Paper to support lecture on Timing and Coordination and exercise 4

Sections 2.2 and 3.2 are useful for exam preparation. 
Document Matlab code for bonus question of excise 4
Document Matlab auxiliary code
Lecture slides Dynamic Movement Primitives
Lecture slides Degree of Freedom Problem I
Lecture slides Degree of Freedom Problem II
Document Background reading to the Uncontrolled Manifold

Read primarily the Introduction
Lecture slides Motor Control and Neural Muscle Models
Document Background reading to Muscle Models

Only the first 8 pages or so are relevant. 
Lecture slides Summary of lecture course with concepts relevant to oral exams
Lecture slides Integrated neural architecture for generating targeted movements of the hand

Here is a link to the full presentation which also contains a pointer/link to the code, that you can download and try out: link
Document Final list of dates of oral exams

About the INI

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.

Contact

Universitätsstr. 150, Building NB, Room 3/32
D-44801 Bochum, Germany

Tel: (+49) 234 32-28967
Fax: (+49) 234 32-14210

sekretariat@ini.rub.de
www.ini.rub.de