(Post)Doctoral Project: Rational selection of exploration strategies for robotic manipulation in partially observable, real-world environments

Principal Investigators

Description of the research project

How do people, when faced with a cognitive or behavioral task, select strategies that allow them to solve the task in a manner that matches their available resources? To address this question, the project will investigate how organisms infer the anticipated accuracy and costs associated with candidate strategies and how, when choosing from among the toolbox of available strategies, the consideration of the implementation costs is attuned to the resources that are available to the organism. These questions will be investigated both for strategies for decision making under risk and for exploration strategies, and both with human and robot participants.

Project Leads: Oliver Brock, Thorsten Pachur

Description of the (post)doctoral project

Robots (just like biological agents) operating in partially unknown environments must be able to acquire information about the world from their own interactions. In this project, we will investigate strategies for exploration of unknown environments for knowledge acquisition and problem solving. We will also investigate how a robot should choose between strategies based on characteristics of the task and the environment. The strategies themselves and the meta-strategy to switch between them must appropriately balance cost against task success, given uncertain knowledge about the environment. The project will employ state-of-the-art machine learning, such as particular differentiable programming, to represent and learn strategies and meta-strategies. The successful candidate will work together with cognitive scientists and psychologists as well as behavioral ecologists to exploit insights from humans and animals solving similar tasks. At the same time, experimental results from robots will be used to inform human and animal experiments in the other disciplines.

Application procedure

Applications should include: motivation letter, curriculum vitae, transcripts of records (for both BSc and MSc + doctoral degree if applicaple), copies of degree certificates (BSc, MSc), abstracts of Bachelor-, Master-thesis, e.g. doctoral thesis, list of publications and one selected manuscript (if applicable), two names of qualified persons who are willing to provide references, and any documents candidates feel may help us assess their competence.

To ensure equal opportunities between women and men, applications by women with the required qualifications are explicitly desired. Qualified individuals with disabilities will be favored. Applications are also expressly welcomed from suitably qualified persons seeking to be entered as “gender diverse” in the public register. The TU Berlin values the diversity of its members and is committed to the goals of equal opportunities.

Please send copies only. Original documents will not be returned.

Prerequisites

  • MS degree in computer science or similar field
  • Research experience in robotics and machine learning required
  • Research experience in computer vision and/or control desired
  • Basic knowledge in cognitive science and psychology is a plus
  • Interest in interdisciplinary research in the context of the Cluster of Excellence “Science of Intelligence”
  • Excellent software engineering and programming skills in C++
  • Excellent English writing and communication skills

Contact

For accessing the legally binding version of this job advertisement, please visit https://stellenticket.de/72236/?lang=en

User registration

You don't have permission to register

Reset Password