Reasoning for robust autonomous navigation
Website Cognitive Robotics Department, TU Delft
Control architectures for mobile robots involve multiple algorithms for localization, collision avoidance and navigation, that need to be properly chosen and configured for each application and environment. However, autonomous robots that have to perform multiple tasks in different environments (empty corridors, rooms with people, etc.) need to flexibly and dynamically adapt their algorithms. This is a research challenge to deploy autonomous robots in which multiple industries are interested: logistics, agri-food, inspection and maintenance, etc.
The project will develop self-adaptation and reconfiguration mechanisms  for the control of autonomous mobile robots, based on symbolic reasoning about the properties and parameters of localization, planning and motion control algorithms. Advanced knowledge-based and symbolic reasoning methods will be used, such as the KnowRob  CRAM [3,4] frameworks.
The concrete objectives of the project are:
- Design a self-adaptation mechanism for the navigation architecture of a mobile robot, using the CRAM
- Create a ROS package for the implementation of the self-adaptive navigation architecture to be reused in different mobile platforms and applications.
- Analyze the performance of the self-adaptive navigation architecture on a mobile robot performing multiple navigation tasks.
. C. Hernandez, J. Bermejo-Alonso, and R. Sanz. A self-adaptation framework based on functional knowledge for augmented autonomy in robots. Integrated Computer-Aided Engineering, 25(2):157–172, 2018.
. M. Beetz, D. Beßler, A. Haidu, M. Pomarlan, A. Kaan Bozcuoglu, and G. Bartels. KnowRob 2.0 — A 2nd Generation Knowledge Processing Framework for Cognition-Enabled Robotic Agents. pages 512–519, 05 2018
. M. Beetz, L. Mosenlechner, and M. Tenorth. CRAM — A Cognitive Robot Abstract Machine for everyday manipulation in human environments. In 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems, pages 1012–1017, Oct 2010.
If you are interested in the project, please contact Dr. Carlos Hernandez by email at email@example.com, including:
- Short motivation letter stating:
- Why are you interested? What would you like to achieve/contribute (theoretical, applied)?
- Intended starting date, and what courses will you have left by then.
- Relevant experience (courses, tech. projects, internships, etc.), and skills (programming, C++, Python, ROS, Etc.)
- A short CV (½ – 1 page)
- BSc & MSc transcripts
- BSc thesis (PDF)
To apply for this job email your details to firstname.lastname@example.org