Integrated (Embedded) Intelligent Systems
Module IN2063
This module handbook serves to describe contents, learning outcome, methods and examination type as well as linking to current dates for courses and module examination in the respective sections.
Basic Information
IN2063 is a semester module in German or English language at Bachelor’s level and Master’s level which is offered in summer semester.
This module description is valid to WS 2017/8.
| Total workload | Contact hours | Credits (ECTS) |
|---|---|---|
| 150 h | 60 h | 5 CP |
Content, Learning Outcome and Preconditions
Content
The course teaches state-of-the-art techniques for the implementation of physically embedded intelligent systems, that is computer systems that are equipped with sensors and effectors. Such computer systems become increasingly important in areas such as pervasive and ubiquitous computing, intelligent working and living environments, semi automated supply chains, service robots, space probes, planetary rovers, driver assistant systems, ...
The course covers the following topics:
- sensors, effectors, and the physical infrastructure of intelligent embedded systems, in particular smart sensors, sensor networks, computer systems in everyday objects, ...
- computational models for controlling embedded intelligent systems: dynamical system model, rational agent model, technical cognitive systems;
- principles of probabilistic state estimation: Bayes filter, Kalman filter, particle filter, multi hypotheses tracking, learning sensor and action models, Hidden Markov models, expectation maximization;
- applications of probabilistic state estimation: self localization, acquisition of environment models, object tracking;
- acquisition of motion and action models and interpretation of intensional activities;
- programming methods for intelligent embedded systems: concurrent reactive control, behavior-based programming, plan-based robot control,grid-based programming techniques.
The course covers the following topics:
- sensors, effectors, and the physical infrastructure of intelligent embedded systems, in particular smart sensors, sensor networks, computer systems in everyday objects, ...
- computational models for controlling embedded intelligent systems: dynamical system model, rational agent model, technical cognitive systems;
- principles of probabilistic state estimation: Bayes filter, Kalman filter, particle filter, multi hypotheses tracking, learning sensor and action models, Hidden Markov models, expectation maximization;
- applications of probabilistic state estimation: self localization, acquisition of environment models, object tracking;
- acquisition of motion and action models and interpretation of intensional activities;
- programming methods for intelligent embedded systems: concurrent reactive control, behavior-based programming, plan-based robot control,grid-based programming techniques.
Learning Outcome
The participants attain basic knowledge about the design and the realization of perception and control mechanisms in intelligent embedded systems, i.e. computer systems that have sensors and actuators. This knowledge enables them to design perception components as well as planning and control mechanisms for realistic application domains, and it enables them to algorithmically solve the associated problems. The problem areas include the selection of the hardware infrastructure, computational models for control, techniques on probabilistic state estimation, the acquisition of motion and action models, plan-based control, and programming methods.
Preconditions
IN2062 Techniques in Artificial Intelligence, basic courses in informatics
Courses, Learning and Teaching Methods and Literature
Learning and Teaching Methods
Lecture, exercise course, problems for individual study
Media
Slides, assignment sheets
Literature
Sebastian Thrun, Wolfram Burgard, and Dieter Fox: Probabilistic Robotics (Intelligent Robotics and Autonomous Agents), The MIT Press
Roland Siegwart, Illah R. Nourbakhsh: Introduction to Autonomous Mobile Robots (Intelligent Robotics and Autonomous Agents), The MIT Press
Roland Siegwart, Illah R. Nourbakhsh: Introduction to Autonomous Mobile Robots (Intelligent Robotics and Autonomous Agents), The MIT Press