Lecturers

 

Dr. Pedro U. Lima


Instituto de Sistemas e Robotica,

IST Lisboa, Portugal


pal@isr.ist.utl.pt

http://www.isr.ist.utl.pt/~pal


 

TITLE

Mobile Manipulation in Robot Competitions


ABSTRACT

In this lecture I will overview some of the current challenges in mobile manipulation, and how those are faced by teams participating in robot competitions such as RoCKIn@Home, RoCKIn@Work (and their RoboCup counterparts), as well as in other competitions such as DARPA Grand Challenge and the recently announced Mohamed Bin Zayed International Robotics Challenge (MBZIRC).

 

Dr. Fernando Gómez


Department of Systems Engineering and Automation,

Universidad de Huelva, Spain


fernando.gomez@diesia.uhu.es

http://www.uhu.es/fernando.gomez/

 

TITLE

Fundamentals of robot motion planning


ABSTRACT

The aim of this lecture is to present the basis of the motion planning techniques in robotic system. This topic have attracted the attention of the robotic community along the last decades, resulting in a set of methodologies that are applied in different areas of the robotic field. The talk will attempt to address this wide subject with a multi-disciplinary approach,focusing on describing the theoretical basis of robot motion, and paying special attention to explain the fundamentals through real applications.

 

Dr. Marc Carreras


Underwater Robotics Research Centre (CIRS)

Universitat de Girona, Spain


marc.carreras@udg.edu

http://eia.udg.es/~marcc

 

TITLE

Marine robotic platform for the euRathlon competition


ABSTRACT

This talk will relate the experience of the University of Girona in developing and programming an Autonomous Underwater Vehicle (AUV) for participating in robotics competitions, such as the euRathlon competition. The talk will describe the Sparus II AUV, an open hardware and software platform conceived to simplify the operation of the vehicle in the marine environment. The vehicle allows and easy integration of new equipment in the payload area. The hovering capability of the vehicle allows an extended manoeuvrability, in comparison with classical AUVs, which is also required to achieve most of the competition tasks. The University of Girona participated in the euRathlon competition with its own vehicle and developed also 3 more units for teams competing without AUV. The talk will describe the tasks that were proposed by the competition, how they were attempted and the obtained results. In September 2015, the 4 Sparus II AUVs will compete again in the final euRathlon competition, in which land and air robots will also cooperate to test the intelligence and autonomy of all of them in realistic mock emergency-response scenarios inspired by the 2011 Fukushima accident. The talk will conclude by giving details and preliminary results of this final contest.


 

Dr. Markus Vincze


Vienna University of Technology, Automation and Control Institute,

Austria


vincze@acin.tuwien.ac.at

http://www.acin.tuwien.ac.at/index.php?id=231&L=1

 

TITLE

Grasping Objects from a Pile


ABSTRACT

When moving to real-world scenarios grasping methods will need to move from single-standing objects to clutter and piles of objects. We propose a method for grasping unknown objects given a point cloud from a single depth camera. We introduce a shape-based method - Symmetry Height Accumulated Features (SHAF) - that reduces the scene description complexity such that the use of machine learning techniques becomes feasible. We describe the basic Height Accumulated Features and the Symmetry Features and discuss the gain from Symmetry Features for grasp classification. In robotic experiments of grasping single objects, we test 10 novel objects in 150 trials and show significant improvement over a state-of-the-art method, achieving a success rate of 92%. We also improve over competitive methods for the task of clearing a table with 5 to 10 objects and overall 90 trials. Furthermore we show that our approach is easily adaptable for different manipulators by running our experiments on different platform.



 

Dr. J.M. Martinez Montiel



Robotics Perception
and Real Time,
Universidad de Zaragoza,

Spain


josemari@unizar.es

http://webdiis.unizar.es/~josemari/









 

TITLE

Visual Mapping for Rigid and Non-Rigid Scenes


ABSTRACT

The speaker presents diverse results recently developed in the Robotics Perception and Real Time group at Universidad de Zaragoza. The focus of the research has been to push the limits of the visual mapping techniques considering different research venues:

1.- ORBSLAM, keyframe based SLAM where the map points correspond to image points described by their ORB signature. ORB are combined with a Bag of Words recognition algorithm, resulting in an efficient relocation and loop closure detection method. It is worth noting that the very same features are used for mapping and for recognition resulting in a system with unprecedented performance.

2.- A variational formulation for real-time dense 3D mapping from a RGB monocular sequence that incorporates Manhattan and piecewise-planar constraints in indoor and outdoor man-made scenes. It is shown that the addition of a third energy term modelling Manhattan and piecewise-planar structures greatly improves the accuracy of the dense visual maps, particularly for low-textured man-made environments where the data term can be ambiguous.

3.- A Monocular visual SLAM algorithm tailored to deal with medical image sequences in order to provide an up-to-scale 3D map of the observed cavity and the endoscope trajectory at frame rate. The algorithm is validated human in-vivo sequences corresponding to fifteen laparoscopic hernioplasties where accurate ground-truth distances are available, showing the feasibility of SLAM in medical endoscopic sequences.

4.-Visual SLAM is cross fertilized Navier’s equations to model elastic solid deformations, the scene is coded as a Finite Element Method (FEM) elastic thin-plate solid, the resulting sequential methods has proven to recover accurately the scene and camera geometry.


 

Dr. Kostas Alexis

Autonome Systeme,

ETH Zürich


konstantinos.alexis@mavt.ethz.ch

http://www.kostas-alexis.com/


 

TITLE

Path–Planning and Control for Aerial Robotic Infrastructure Inspection and Maintenance


ABSTRACT

Aerial robots can play a major role in infrastructure inspection and maintenance operations. Relying on novel contributions in the fields of flight control, manipulator design and control, perception and path planning, aerial robots will soon be able to execute an autonomous high–fidelity 3D reconstruction task, detect potential risks and hazards and subsequently attempt maintenance work via means of aerial manipulation. This talk will try to cover the fields of inspection path planning for known as well as unknown environments, control for inspection through contact as well as the emerging field of agile manipulation using Micro Aerial Vehicles. Finally, results from the ongoing work of the AEROWORKS Horizon 2020 (http://www.aeroworks2020.eu/) project will be discussed.



PRACTICAL SESSIONS
 

Dr. Guillaume Walck

Neuroinformatik group at the CITEC of University of Bielefeld, Germany


gwalck@techfak.uni-bielefeld.de

https://ni.www.techfak.uni-bielefeld.de/people/gwalck


 

TITLE

Hand Motion Planning with MoveIt!



ABSTRACT

A practical session (3h Lab session) will permit to do hand motion planning from start (understanding a hand model, creating inverse kinematics, creating hand semantic model for planning) to end (useful hand motions with the fingers).    

 

Dr. Raúl Marín

Interactive and Robotic Systems Lab (IRS-Lab), Jaume I University,

Castellón, Spain


rmarin@uji.es

http://www.irs.uji.es/users/rmarin


 

TITLE

Control & Navigation of a real robotic platform



ABSTRACT

A practical session (3h Lab session). Control & Navigation by using a real robotic platform (based on ROS/ARDUINO/ANDROID)