Andreas Geiger has been awarded the KIT Doctoral Award
In his PhD thesis, Andreas Geiger has developed algorithms for 3D scene perception in autonomous vehicles which can help to improve traffic safety, reduce traffic jams and enable car rides for elderly or visually impaired people. His approach combines visual recognition using stereo cameras with probabilistic models which are able to determine the location and orientation of roads, lanes and other traffic participants.
Intelligent Systems Research: Spanning the Length Scale
Stuttgart / Tübingen. Five years of basic research is secured: The physicist Dr. Laura Na Liu and the computer scientist Dr. Ludovic Righetti, both from the Max Planck Institute for Intelligent Systems, receive an ERC Starting Grant of 1,5 Million Euro, respectively. Prof. Jan Peters, head of the robot learning group at the institute (while mainly active as full professor at the TU Darmstadt) will invest part of his ERC starting grant into his research group at the institute. The researchers have won against 3.273 applicants - only 10 per cent of the submitted project appraisals receive the requested award, granted by the European Research Council (ERC).
The robot "Athena" carries new impulses for robotics research in its luggage
Travelling from Los Angeles to Frankfurt onboard of Lufthansa flight LH 457, the passenger arrived on December 16, at 11.05 a.m. with no signs of jet lag: this was no ordinary holidaymaker, after all, but the first humanoid robot to take up a seat on a commercial flight. And despite causing quite a stir when boarding the plane in Los Angeles, Athena, dressed in a T-shirt and fetching red shoes, received no special treatment: like most of us, she flew economy class. During the nine-hour flight, the robotic creation was accompanied by scientists from the Max Planck Institute for Intelligent Systems. Athena made her way from Los Angeles to Tübingen in order to acquire many new skills: standing, balancing, walking - and various other meaningful activities, which she can use to assist people in daily life.
Researchers at the Max Planck Institute for Intelligent Systems unveil new technology for motion and shape capture
The new technology (MoSh) will help animators jump the “Uncanny Valley” by turning a few moving dots into detailed body shapes that jiggle and deform like real humans. Researchers at the Max Planck Institute for Intelligent Systems in Tübingen, presented their Motion and Shape Capture (MoSh) study, which appeared in the journal ACM Transactions on Graphics, at SIGGRAPH Asia in Shenzhen on December 6, 2014. Devised by a team of researchers under the direction of Michael J. Black, Director of the Perceiving Systems department, MoSh is a method that allows animators to record the three-dimensional (3D) motion and shape of a real human and digitally “retarget” it to a new body shape. With MoSh, realistic virtual humans can populate games, the Internet, and virtual reality, while reducing animation costs for the special effects industry.
Our work on realizing a microscallop and nanopropellers that can move through biological tissue is in the news. Our group appears on TV, radio, in newspapers, and on multiple news sites. (December 2014).
PhD student will present his work on probabilistic solvers for differential equations
Michael Schober' paper on probabilistic solvers for ordinary differential equations has been selected for a full oral presentation at the flagship conference of machine learning.
KIT-Zentrum für Mobilitätssysteme zeichnet Doktorarbeit von Andreas Geiger aus
Für ein autonomes Fahrzeug bedeutet eine innerstädtische Kreuzung mit mehreren Verkehrsteilnehmern eine große Herausforderung. Wie komplexe Verkehrssituationen mithilfe von Videosequenzen besser verstanden werden können, hat Dr. Andreas Geiger in seiner Doktorarbeit gezeigt. Dafür hat er am 27. November 2014 vom KIT-Zentrum für Mobilitätssysteme den Ernst-Schoemperlen-Preis verliehen bekommen.
In machine learning, we use data to automatically find dependences in the world, with the goal of predicting future observations. Most machine learning methods build on statistics, but one can also try to go beyond this, assaying causal structures underlying statistical dependences. The hope is that this also allows prediction in certain situations where systems change, for instance by interventions.
Research group leader Samuel Sánchez elected as “Innovator of the year 2014”
Tiny self-propelled motors which speed through the water and clean up pollutions along the way or small robots which can swim effortlessly through blood to one day transport medication to a certain part of the body – this sounds like taken from a science fiction movie script. However, Samuel Sánchez is already hard at work in his lab at the Max Planck Institute for Intelligent Systems in Stuttgart to make these visions come true. For his innovative research, the 34 years old chemist has now been named as Spain’s top innovators under 35 by the Spanish edition of the journal MIT Technology Review.