Please select the desired project time frame:
- July 2026
- January 2026
- July 2025
- January 2025
- July 2024
- January 2024
- July 2023
- January 2023
- July 2022
- January 2022
- July 2021
- January 2021
- July 2020
- January 2020
- July 2019
- January 2019
- July 2018
- January 2018
- July 2017
- January 2017
- July 2016
- January 2016
- July 2015
- January 2015
- July 2014
- January 2014
- July 2013
- January 2013
- July 2012
- January 2012
- July 2011
- January 2011
- July 2010
- January 2010
- July 2009
- January 2009
- July 2008
- January 2008
- July 2007
- January 2007
- July 2006
- January 2006
- July 2005
- January 2005
- July 2004
- January 2004
- July 2003
- January 2003
- July 2002
- January 2002
- July 2001
- January 2001
Start of funding 01.07.2013
Real-Time Reactive Motion Planning for Human-Robot Interaction
Florian Walter
Technische Universität München
Computer Sciences 6 - Robotics & Embedded Systems
Prof. Dr. Oussama Khatib
Stanford University
Artificial Intelligence Laboratory
Motion planning is one of the most complex tasks in robot control. When computing the movements of a robot, it is not only required to take the mechanical parameters of the robot into account but also to pay attention to surrounding obstacles in order to avoid collisions. Thanks to new approaches like the Elastic Strip Framework developed by the research group of Prof. Oussama Khatib at Stanford University, these computations can be carried out in real-time and thus, the robot can also avoid moving obstacles. Especially in the field of human-robot interaction, one of the areas of research at the department of Prof. Alois Knoll at the Technical University of Munich, fast response to changes in the environment is important in order to ensure that humans do not get hurt by a collision with a robot. Findings from neurosciences suggest that another criterion might be of importance for motion planning in the context of human-robot interaction: The movements of a robot should be as natural and smooth as possible in order to appear sensible and predictable to humans. Thus, advanced mo-tion planners could play an important role in future scenarios for human-robot interaction. The main goal of the planned collaboration is to examine how the algorithms developed at Stanford University can be extended. The new methods will be evaluated on a KUKA lightweight robot.