Autonomous Robot Evolution (ARE): Cradle to Grave

Lead Research Organisation: University of York
Department Name: Electronics


Robotics is changing the landscape of innovation. But traditional design approaches are not suited to novel or unknown habitats and contexts, for instance: robot colonies for ore mining, exploring or developing other planets or asteroids, or robot swarms for monitoring extreme environments on Earth. New design methodologies are needed that support optimising robot behaviour under different conditions for different purposes. It is accepted that behaviour is determined by a combination of the body (morphology, hardware) and the mind (controller, software). Embodied AI and morphological computing have made major progress in engineering artificial agents (i.e., robots) by focusing on the links between morphology and intelligence of natural agents (i.e., animals). While such a holistic body-mind approach has been hailed for its merits, we still lack an actual pathway to achieve this.
While this goal is ambitious, it is achievable by introducing a unique methodology: a hybridisation of the physical evolutionary system with a virtual one. On the one hand, it is appreciated that an effective design methodology requires the use and testing of physical robots. This is because simulations are prone to hidden biases, errors and simplifications in the underlying models. Simulating populations of robots (rather than just simulating specific parts) leads to accumulated errors and a lack of physical plausibility: the evolved designs will not work in the real system. This is the notorious reality gap of evolutionary robotics. On the other hand, evolving everything in hardware is time and resource consuming. One of our major innovations is to run simulated evolution concurrently with the physical and hybridise them by cross-breeding, where a physical and a virtual robot can parent a child that may be born in the real world, in the virtual world or in both. The advantages of such a hybrid system are significant. Physical evolution is accelerated by the virtual component that can run faster to find good robot features with less time and resources; simulated evolution benefits from the influx of genes that are tested favourably in the real world. Furthermore, monitoring of and feedback from the physical system can improve the simulator, reducing the reality gap.

Planned Impact

Impact on science
This project will lead to new ideas behind the co-evolution of brains and bodies applied in the context of robotics. Researchers working in the field of robotics will be an obvious group that this research will be highly relevant to. Additionally, the novel evolutionary methods and techniques developed will be of interest to the general evolutionary computation community. New and interesting evolutionary results will be uncovered, through the use of challenging case studies to give insight into the complex interaction between controller and body shape, which will be of wider scientific interest.
Our system also offers a tool for biologists in that it represents a physical, rather than digital, model of evolution. Unlike digital models in simulation, a hardware-based model is guaranteed not to violate the laws of physics and can help test biological hypotheses. To this end, our demonstrator forms a prototype of a research instrument that can be used to carry out a wide range of investigations. Just as a cyclotron is a tool for nuclear physics, our system will be a tool for research into evolution and embodied intelligence.

Impact on technology and the economy
The Robotics Technology Market is expected to reach $82.7 billion by 2020 ( Robotics technology is used in a wide range of industries including healthcare, defense, aerospace, automotive and infrastructure, and allows consumers to automate processes, increase productivity, enhance quality and reduce human errors. In the UK, the government has identified robotics as one of the "8 Great Technologies" central to the future growth of the UK economy - this project is central to delivering this growth.
It will deliver a technology prototype demonstrator that enables the creation of intelligent machines while minimising the reality gap. This will have a large and lasting impact on robotics by initiating radically new robotic systems where robots are conceived and born, rather than designed and manufactured. This project is designed to provide the world's first demonstration of the co-evolution of brains and bodies of robots in real time and real space. This represents a significant technological advance that potentially opens up new approaches to design and manufacture, with significant potential to challenge and disrupt conventional approaches. Technology licensing and technology transfer will provide economic benefit to many of the industries listed. However, in particular, the project specifically targets nuclear decommissioning. The cost of the future clean up of nuclear plants across the UK was forecast in a government report in 2016 to be around £117 billion spread across the next 120 years. Therefore, providing new technologies to accomplish this has the potential to have significant economic impact. This project will result in significant potential for exploitation through technology licensing and technology transfer. This could result in UK leading companies and the economic impact that would flow. That in turn could lead to future economic benefit could flow from the potentially substantial cost savings to the taxpayer in improved methods for nuclear decommissioning.

Impact on society
Work resulting from this project will pave the way for reduced exposure of humans to hazardous environments, e.g. nuclear decommissioning. Evolved, specialist robots, will be well suited and adapted to these challenging environments, thus reducing the need to expose humans to either, long-term potential harm, or in some cases, using robots instead of humans. This will also lead to longer-term benefits to the environment, through effective decommissioning. Also, since this project will undoubtedly generate significant public and press interest (developed through outreach and public engagement), there will be a positive impact in showing how advanced robots can help people and the environment.


10 25 50
Description There is now an automated robot fabrication facility that allows evolved robot body plans to be automatically printed and organs attached to the body.
Exploitation Route The construction of an automated fabrication facility to manufacture evolved physical entities, in this case robots, could be made use of in various other field in the future.
Sectors Aerospace, Defence and Marine,Digital/Communication/Information Technologies (including Software),Education

Description There have been a number of "popular press" articles written about the project. Demonstrations have been given at York Festival of Ideas in 2019.
First Year Of Impact 2019
Sector Digital/Communication/Information Technologies (including Software),Electronics
Impact Types Societal

Description Distinguished Visiting Professor 
Organisation Fudan University
Country China 
Sector Academic/University 
PI Contribution New appointment for Prof Timmis to explore further applications of the technology in intelligent robotics.
Collaborator Contribution Initial discussions on case studies and possible research student supervision.
Impact None as yes.
Start Year 2021