Guided sampling of high-dimensional configuration spaces

Add to your list(s) Download to your calendar using vCal

• Vojtech Vonasek, Czech Technical University Prague
• Friday 11 December 2020, 10:00-11:00
• https://bham-ac-uk.zoom.us/j/81307795008?pwd=ZUFXZjVsK0VxcE9XeU1CTnA3cE5zQT09.

If you have a question about this talk, please contact Martin Rudorfer.

Path planning finds many applications in robotics, computer-aided design, computer games, and in the distant field of computational biochemistry. Many planning problems can be formulated as a search in a configuration space. Practical problems usually lead to high-dimensional spaces that can be searched using sampling-based approaches like Rapidly Exploring Random Tree (RRT) or Probabilistic Roadmaps (PRM). The talk will give an overview of recent achievements in the area of sampling-based planning with the focus to guided-based sampling. In the guided sampling, the space is searched using a hint that can be defined using workspace knowledge, designed by a user or even discovered automatically. Basic guiding techniques for robots with few DOF (Degrees of Freedom) will be described with their extensions for motion planning of many-DOF robots like modular robots. The performance of the proposed methods will be demonstrated in scenarios with simulated as well as real robots. Finally, I will show an application of sampling-based planning in the area of computational biochemistry.

Vojtech Vonasek is a post-doc researcher at the Department of Cybernetics, Faculty of Electrical Engineering at Czech Technical University (FEE-CTU) in Prague. He received his Ph.D. in artificial intelligence from FEE -CTU in 2016. He spent one year in the Intelligent Process Automation and Robotics group (IPR) at Karlsruhe Institute of Technology (KIT), Germany. He was a post-doc researcher at the Industrial Automation Technology Group of Technische Universität Berlin, Germany within German Academic Exchange Service (DAAD) post-doc programme in 2017. His research interests include path and motion planning for various robotic systems, automatic learning of locomotion gaits of modular robots and application of motion planning techniques in computational biochemistry.

This talk is part of the IRLab Seminars: Robotics, Computer Vision & AI series.

This talk is included in these lists:

• IRLab Seminars: Robotics, Computer Vision & AI
• https://bham-ac-uk.zoom.us/j/81307795008?pwd=ZUFXZjVsK0VxcE9XeU1CTnA3cE5zQT09

Note that ex-directory lists are not shown.