Implementing a (tree-based) decoding for robot generation

In the Autonomous Robotic Evolution project robots for different types of challenging environments are autonomously designed and fabricated with the Robot Fabricator. Robots with different shapes and numbers of components can be decoded with the current implementation. However, one of the limitations of the current decoding method is that it is difficult to create small changes in the final robot when decoding. This research programme will consider new robot decoding methods and compare results with the previous decoding methods. It is important to highlight that the new decoding has to consider the manufacturability constraints, as the programme is ultimately focused on real robots. One of the outcomes of this research is to validate the hypothesis that morphology decoding has an influence on evolution and the reality gap.

How to apply:

Applicants should apply via the University’s online application system . Please read the application guidance first so that you understand the various steps in the application process.

Funding:

This is a self-funded project and you will need to have sufficient funds in place (eg from scholarships, personal funds and/or other sources) to cover the tuition fees and living expenses for the duration of the research degree programme. Please check the School of Physics, Engineering and Technology website for details about funding opportunities at York.