Postdoctoral researcher, Project: 'Algorithmic models of group hunting and shepherding behaviour'
(salary grade E13 TV-L, under the reserve that funds are granted, starting no later than from 1.10.2021 / for 3 years / closing date for applications 20.11.2020, Ref SCIoI-C3-33b)
The Humboldt Universität zu Berlin invites applications for a Postdoc position for the Cluster of Excellence “Science of Intelligence”.
What are the principles of intelligence, shared by all forms of intelligence, no matter whether artificial or biological, whether robot, computer program, human, or animal? And how can we apply these principles to create intelligent technology?
Answering these questions – in an ethically responsible way – is the central scientific objective of the new Cluster of Excellence Science of Intelligence (www.scienceofintelligence.de), where researchers from a large number of analytic and synthetic disciplines – artificial intelligence, machine learning, control, robotics, computer vision, behavioural biology, psychology, educational science, neuroscience, and philosophy – join forces to create a multi-disciplinary research program across universities and research institutes in Berlin. Interdisciplinary research projects have been defined (https://www.scienceofintelligence.de/research/projects), which combine analytic and synthetic research and which address key aspects of individual, social, and collective intelligence.
Shepherding behaviour in predator-prey interactions
Postdoctoral project “Algorithmic models of group hunting and shepherding behaviour”
The objective of this project is to adapt and generate from scratch shepherding/hunting behaviours that are feasible with real robots interacting in teams. We will start from generic individual-based models, implementing the simplest biologically reasonable predator behaviour. This approach will provide first reference models (“Null models”) for the empirically observed behaviour. These models will be further developed through comparison with empirical observations, testing, as well as generating new biological hypotheses. We will use methods from optimization and machine learning to adapt parameters and a limited set of algorithmic behaviours to improve the algorithmic representation of the real-world biological behaviour. To facilitate the real-world implementation on a robotic platform, we will move beyond mathematical models by implementing and testing the corresponding algorithmic models in simple simulations with low computational load allowing for efficient use of machine learning and accounting for the hardware constraints of our platform (e.g. ARGoS, Webots etc). In particular, we will use the simulations to explore the three scenario classes for the real-world swarm experiments.
Throughout, the postdoctoral candidate is expected to closely collaborate with a second postdoc, who focuses on a study of predator-prey interactions during group hunting.
Applicants must hold a PhD in robotics, computer science, electrical engineering or similar and with a strong background in several of the following topics:
- Programming in C/C++, Python or similar
- Programming and experimenting with small mobile robots
- Machine learning or evolutionary computation
- Simulation of (self-organized) swarm/multi-agent systems
- Mathematical modelling of robot teams or animal groups/swarms
- Interdisciplinary background in biology
Excellent English skills are required. Previous experience with working in collaborative research activities including multidisciplinary teams is a plus.
Candidates should upload their application preferably via the portal www.scienceofintelligence.de/jobs in order to receive full consideration.
Applications should include: motivation letter, curriculum vitae, transcripts of records (for both BSc and MSc), copies of degree certificates (BSc, MSc, PhD), abstracts of Bachelor-, Master- and PhD-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.