Lecture Humanoid Robotics (MAINF 4215)
Humanoid robots are currently an active research platform. Since they have a humanlike body plan they can act in environments designed for humans. Humanoid robots are able to, e.g., climb stairs, walk through cluttered environments, manipulate objects, and open doors.
This lecture covers techniques for humanoid robots such as perception, navigation, motion planning, grasping, and human motion analysis.
Organization
 Lecturer: Prof. Dr. Maren Bennewitz
 Coorganizer: Stefan Oßwald
 Tutorials: AbdElMoniem Bayoumi
 Lectures: Thursdays 08:30–10:00 (s.t.), LBH room III.03a
 Tutorials: Tuesdays 08:30–10:00 (s.t.), LBH room III.03a
Exam (second round)
The second round of oral exams will take place on October 5 in LBH room I.44.
Exam
The oral exams will take place on August 26 and 29 and on September 1 in LBH room I.44.
Slides
No.  Topic  Date  Slides 

0  Introduction  April 19  [PDF] 
1  Linear Algebra  April 21  [PDF] 
2  Least squares and odometry calibration  April 28  [PDF] 
3  Projective geometry and homogeneous coordinates  May 10  [PDF] 
4  Camera parameters  May 10  [PDF] 
5  Wholebody self calibration  May 24  [PDF] 
6  3D world representations  May 24, June 2  [PDF] 
7  Monte Carlo localization  June 9, June 16  [PDF] 
8  Path planning and walking  June 16, June 23  [PDF] 
9  Statistical testing  June 30  [PDF] 
10  Wholebody motion planning  July 7, July 14  [PDF] 
11  Bagofwords models and appearancebased mapping  July 14  [PDF] 
Assignments
No.  Topic  Date published  Submission deadline  

1  GIT, linear algebra  April 21  April 28  [PDF] 
2  Odometry calibration  April 28  May 6  [PDF] 
3  Projective geometry  May 12  May 24  [PDF] 
4  Forward kinematics, octrees, kd trees  May 25  June 2  [PDF] 
5  Signed distance function, ICP  June 2  June 9  [PDF] 
6  Particle filter  June 9  June 16  [PDF] 
7  Path planning and footstep planning with A*  June 16  June 23  [PDF] 
8  Anytime Repairing A* (ARA*)  June 23  June 30  [PDF] 
9  Statistical testing  June 30  July 7  [PDF] 
10  Inverse kinematics, RRT  July 7  July 14  [PDF] 
11  Reachability maps  July 14  July 21  [PDF] 
Literature for further reading
Topic  Literature  Links 

robotics in general  Probabilistic Robotics. S. Thrun, W. Burgard, and D. Fox. Cambridge, Mass.: MIT Press, 2006. ISBN: 9780262201629. 
[ULB] [www] 
least squares  Any textbook on numeric analysis or optimization. Follow the links for a list of books available in the University Library.  [ULB English] [ULB German] 
projective geometry 
Multiple View Geometry in Computer Vision. Chapters 23: Projective Geometry and Transformations of 2D/3D. 
[ULB], fulltext available 
Photogrammetry I. Chapter 14: Homogeneous Coordinates. 

camera calibration  Multiple View Geometry in Computer Vision. Chapter 6: Camera Models. R. Hartley and A. Zisserman. Cambridge: Cambridge University Press, 2004, ISBN: 9780521540513 
[ULB], fulltext available 
Photogrammetry I. Chapter 15: Camera Extrinsics and Intrinsics. C. Stachniss. Lecture material, University of Bonn, 2016. 
[slides] [lecture recording]  
humanoid calibration  WholeBody SelfCalibration via GraphOptimization and Automatic Configuration Selection. D. Maier and M. Bennewitz. Proceedings of the IEEE International Conference on Robotics & Automation (ICRA), 2015. 
[PDF] 
CameraBased Humanoid Robot Navigation. Chapter 2: WholeBody SelfCalibration. 

3D world models  MultiLevel Surface Maps for Outdoor Terrain Mapping and Loop Closing. R. Triebel, P. Pfaff, and W. Burgard. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2006. 
[PDF] 
OctoMap: An Efficient Probabilistic 3D Mapping Framework Based on Octrees. 

RealTime Camera Tracking and 3D Reconstruction Using Signed Distance Functions. E. Bylow, J. Sturm, C. Kerl, F. Kahl, and D. Cremers. Proceedings of Robotics: Science and Systems (RSS), 2013. 
[PDF]  
Continuous Humanoid Locomotion over Uneven Terrain using Stereo Fusion. M. F. Fallon, P. Marion, R. Deits, T. Whelan, M. Antone, J. McDonald, and R. Tedrake. Proceedings of the IEEERAS International Conference on Humanoid Robotics (HUMANOIDS), 2015. 
[PDF]  
ICP  A method for registration of 3D shapes. P.J. Besl and N.D. McKay. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992. 
[PDF] 
Efficient Variants of the ICP Algorithm. S. Rusinkiewicz and M. Levoy. Proceedings of the International Conference on 3D Digital Imaging and Modeling, 2001. 
[PDF]  
Linear LeastSquares Optimization for PointtoPlane ICP Surface Registration. K.L. Low. Technical Report, University of North Carolina, 2004. 
[PDF]  
CameraBased Humanoid Robot Navigation. Chapter 5: 3D Footstep Planning Among Clutter. Daniel Maier. PhD thesis, University of Freiburg, 2015. 
[PDF]  
6D localization for humanoid robots 
Humanoid Robot Navigation in Complex Indoor Environments. Chapter 3: Monte Carlo Localization for Humanoid Robots. 
[PDF] 
path planning 
Anytime SearchBased Footstep Planning with Suboptimality Bounds. 
[PDF] 
ARA*: Anytime A* with provable bounds on suboptimality. 
[PDF]  
Introduction to Humanoid Robotics. Chapter 3: ZMP and Dynamics. 
[ULB]  
Searchbased planning library (SBPL). Searchbased Planning Lab, Carnegie Mellon University, Pittsburgh. Opensource library and ROS package. 
[www] [ROS]  
Footstep planning implementation based on SBPL. J. Garimort and A. Hornung, Humanoid Robots Lab, University of Freiburg. Opensource ROS package. 
[ROS]  
ZeroMoment Point (ZMP) 
Introduction to Humanoid Robotics. Chapter 3: ZMP and Dynamics. 
[ULB] 
inverse kinematics 
Introduction to Inverse Kinematics with Jacobian Transpose, Pseudoinverse and Damped Least methods. 
[PDF] 
Rapidlyexploring Random Trees (RRT) 
RRTConnect: An Efficient Approach to SingleQuery Path Planning. 
[PDF] 
wholebody motion planning 
WholeBody Motion Planning for Manipulation of Articulated Objects. 
[PDF] 
Inverse Reachability Maps (IRM)

Stance Selection for Humanoid Grasping Tasks by Inverse Reachability Maps. 
[PDF] 
Robot Placement based on Reachability Inversion. 
[PDF]  
statistical testing 
Empirical Methods for Artificial Intelligence. Chapter 4: Hypothesis Testing and Estimation. 
[ULB] 