Lab Cognitive Robotics (MA-INF 4304)

Prof. Dr. Sven Behnke, Max Schwarz

Block course at the end of the semester: 4.9. - 22.9.

First organizational meeting: 21st July 2017, 12:30, room I.42, Friedrich-Ebert-Allee 144

Cognitive robotics is an active research area at the border between artificial intelligence and robotics. 
It investigates and tries to implement in technical systems mental functions, which are associated with intelligence.
This covers the perception of the environment, action planning, and learning. In this lab course, the students will implement algorithms for the control of our cognitive robots. 

In this semester, students will be able to work with the following robotic platforms:

• 

  Amazon Robotics Challenge 2017: Our team NimbRo participates in the Amazon Robotics Challenge, which requires robotic systems to automate stowing and picking tasks in warehouses. During the lab, students can work on selected tasks in the perception pipeline (from sensor measurements to object segmentation and pose estimation) or the action generation side.

• 

  Mario: Our ground robot Mario (along with our flying robots) won the MBZIRC Challenge. Specifically, this robot is very fast (up to 4m/s), which makes specialized planning methods necessary. Students can develop new planning algorithms in simulation and test them on the real platform.

• 

  Baxter: Baxter is a versatile two-armed manipulation robot. Students may work on grasp planners and trajectory optimization for two-armed manipulation.

Own proposals/ideas are encouraged!

Prerequisites

• Good programming skills in C/C++ or some other object-oriented programming language.
• Knowledge in robotics, artificial intelligence, or machine learning is helpful.

• The students will work in small groups.
• The lab is a good preparation for writing a Master thesis in the Autonomous Intelligent Systems group.
• Selected participants will have the opportunity to join our robotics team as student researchers.

Literature

David Droeschel, Matthias Nieuwenhuisen, Marius Beul, Dirk Holz, Jörg Stückler, and Sven Behnke:
Multi-Layered Mapping and Navigation for Autonomous Micro Aerial Vehicles
Journal of Field Robotics, 33(4):451-475, Wiley, 2016.

Max Schwarz, Marius Beul, David Droeschel, Sebastian Schüller, Arul Selvam Periyasamy, Christian Lenz, Michael Schreiber, and Sven Behnke:
Supervised Autonomy for Exploration and Mobile Manipulation in Rough Terrain with a Centaur-like Robot
Accepted for Frontiers in Robotics and AI, section Humanoid Robotics, to appear 2016.

Max Schwarz, Tobias Rodehutskors, David Droeschel, Marius Beul, Michael Schreiber, Nikita Araslanov, Ivan Ivanov, Christian Lenz, Jan Razlaw, Sebastian Schüller, David Schwarz, Angeliki Topalidou-Kyniazopoulou, and Sven Behnke:
NimbRo Rescue: Solving Disaster-Response Tasks through Mobile Manipulation Robot Momaro