home


Publications

Teaching

Software


Machine Learning & Robotics Lab


Computer Science Department


Robotics Course, WS 13/14, U Stuttgart

See my general teaching page for previous versions of this lecture.
picture
Robotics is an ultimate test of our progress in Artificial Intelligence, Machine Learning and Control Theory research. However, while these research fields consider general but idealized problem formulations, robotics has to deal with the specifics our concrete 3-dimensional physical world and eventually integrate methods and hardware in autonomous systems. Therefore robotics is more than an application of the above fields and requires specific knowledge of how to generate montion, physically interact with the environment and perceive it.


The lecture will give an introduction to robotics in four chapters:

Scope
Kinematics & Dynamics
goal: orchestrate joint movements for desired movement in task spaces
(Kinematic map, Jacobian, optimality principle of inverse kinematics, singularities, configuration/operational/null space, multiple simultaneous tasks, special task variables, trajectory interpolation, motion profiles; 1D point mass, damping \& oscillation, PID, general dynamic systems, Newton-Euler, joint space control, reference trajectory following, optimal operational space control)
Planning and optimization
goal: planning around obstacles, optimizing trajectories
(Path finding vs.\ trajectory optimization, local vs.\ global, Dijkstra, Probabilistic Roadmaps, Rapidly Exploring Random Trees, differential constraints, metrics; trajectory optimization, general cost function, task variables, transition costs, gradient methods, 2nd order methods, Dynamic Programming)
Control Theory
theory on designing optimal controllers
(Topics in control theory, optimal control, HJB equation, infinite horizon case, Linear-Quadratic optimal control, Riccati equations (differential, algebraic, discrete-time), controllability, stability, eigenvalue analysis, Lyapunov function)
Mobile robots
goal: localize and map yourself; walk
(State estimation, Bayes filter, odometry, particle filter, Kalman filter, Bayes smoothing, SLAM, joint Bayes filter, EKF SLAM, particle SLAM, graph-based SLAM)
Prerequisites
As a prerequisite, student should have basic knowledge of linear algebra, probability theory and optimization.
Organization
  • This is the central website of the lecture. Link to slides, exercise sheets, announcements, etc will all be posted here.
  • See the 01-introduction slides for further information.
Schedule, slides & exercises
date topics slides exercises
(due on 'date'+1)
15.10. Introduction & Organization 01-introduction read this
22.10. Kinematics 02-kinematics e01-geometry
29.10. Kinematics (cont.) e02-kinematics
5.11. Path Planning 03-pathPlanning e03-pegInAHole
12.11. Path Optimization
Dynamics 		04-pathOptimization
05-dynamics 		e04-pathFinding
19.11. Dynamics 05-dynamics e05-dynamics
26.11. Mobile Robotics 07-mobileRobotics
06-probabilities 		e06-dynamics
3.12. Mobile Robotics (cont.) 07-mobileRobotics e07-particleFilter
10.12. Control Theory 08-controlTheory e08-kalmanSLAM
10.12. Practical: The `racer' 09-racer e09-cartPole
7.1. Practical: The `racer' (cont.) e10-racer
e10-riccati
14.1. Control Theory (cont.) 08-controlTheory e11-SysId
../data/01-imu.dat
../data/02-imu.dat
../data/01-times.dat
../data/02-times.dat
racer.h
racer.cpp
21.1. Reinforcement Learning in Robotics 10-RL e12-stability
28.1. cancelled in favor of exercise work (exercises take place) e13-policySearch
CMA.tgz
4.2. Summary and Exam Preparation 13-Robotics-script
I will give a summary over everything you learned, and answer questions about the exam.		 cancelled Instead, please have a look on the full script (see '13-Robotics-script') and prepare questions for the lecture, if you have any
resources
online lectures: books: history: state-of-the-art (major conferences):