Evolving robot morphology and control systems

Lead Research Organisation: University of York
Department Name: Electronics


This research focuses on a disruptive robotic technology where robots are created, reproduce and evolve. The long-term vision is a technology enabling the evolution of entire autonomous robotic ecosystems that live and work for long periods in challenging and dynamic environments without the need for direct human oversight. This will require radically new autonomous systems, where robots are conceived and born, rather than designed and manufactured. Such robots have the potential impact to fundamentally change the concept of machines, showcasing a new breed that can change their form and behaviour, not in error but on purpose.

Aim: Combining advances in 3D-printing with a novel evolutionary architecture will enables evolution to produce physical robots, customised to specific environments.

Objectives: Develop a real (physical) environment, which enables the co-evolution and construction of hardware and software, including electronics, firmware and bodies.

The research methodology will be focused on robot morphologies that can be evolved from a set of pre-defined components, and define a representation and operators that enables the parameters and the number of each component to be evolved, and their relative positioning to the body; the controller will be specified by evolved neural network. The research will evaluate a state-of-the-art generative encoding, which has been shown to lead to more complex morphological and locomotion patterns and compare approaches in terms of their ability to produce viable physical robots in an efficient manner. Processes will be iterated as required based on success of translation to viable physical robots.

The generic work undertaken in this project fits squarely with the EPSRC's Robotics and Autonomous Systems Strategy, additionally having significant future impact potential within Autonomous Manufacturing.


10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/N509802/1 30/09/2016 30/03/2022
2107051 Studentship EP/N509802/1 30/09/2018 29/09/2021 Robert Woolley