Your mission: Information gathering is a fundamental task in a wide range of applications such as environmental monitoring, or search and rescue missions. Such task can clearly benefit from multi-robot cooperation as it brings robustness and efficiency to the system. At DLR, we are working on developing a multi-robot information gathering algorithm that employs deep reinforcement learning to learn optimal robot actions. In particular, we employed a CPU-based deep reinforcement learning algorithm.
The goal of this master thesis is to extend our work on deep reinforcement learning and investigate GPU-based learning methods for multi-robot information gathering. In contrast to CPU-based algorithms, GPU-based methods are computationally more efficient and typically implementations are more robust against parameters variations. It is foreseen that a potential applicant will begin with an analysis of the state-of-the-art GPU-based deep reinforcement learning algorithms and select an appropriate hardware platform. Next, the studied schemes shall be tested with a multirobot system programmed to solve information gathering task using reinforcement learning. Apart from pure numerical studies, the latter will also involve the validation of the methods on real robotic hardware.
You look forward to a fulfilling job with an employer who appreciates your commitment and supports your personal and professional development.
Our unique infrastructure offers you a working environment in which you have unparalled scope to develop your creative ideas and accomplish your professional objectives. Disabled applicants with equivalent qualifications will be given preferential treatment.
Look forward to a fulfilling job with an employer who appreciates your commitment and supports your personal and professional development.
Our unique infrastructure offers you a working environment in which you have unparalled scope to develop your creative ideas and accomplish your professional objectives.
Our human resources policy places great value on a healthy family and work-life-balance as well as equal opportunities for persons of all genders (m/f/non-binary).
Individuals with disabilities will be given preferential consideration in the event their qualifications are equivalent to those of other candidates.
You can send this job advertisement via e-mail and complete your application on a personal computer or laptop.
We need your digital application documents (PDF). The document upload function is not supported by all mobile devices. Please complete your application on a PC/laptop.
Alberto Viseras Ruiz
Institute of Communications and Navigation
Phone: +49 8153 28-4143