Prof Andy Tyrrell FREng

The Univeristy of York team will be taking part in the UK Robotics LiveStream on Wednesday 21st June at 4pm, you can watch the demonstrastion LIVE here – https://www.youtube.com/live/Wf29_bbNlko?feature=share

Published as an IEEE Access Research Article, January 2023

Genetic algorithms (GAs) have been used to evolve optimal/sub-optimal solutions of many problems. When using GAs for evolving solutions, often fitness evaluation is the most computationally expensive, and this discourages researchers from applying GAs for computationally challenging problems. This paper presents an approach for generating offspring based on a local fitness landscape exploration to increase the speed of the search for optimal/sub-optimal solutions and to evolve better fitness solutions. The proposed algorithm, “Fitness Landscape Exploration based Genetic Algorithm” (FLEX-GA) can be applied to single and multi-objective optimization problems. Experiments were conducted on several single and multi-objective benchmark problems with and without constraints. The performance of the FLEX-based algorithm on single-objective problems is compared with a canonical GA and other algorithms. For multi-objective benchmark problems, the comparison is made with NSGA-II, and other multi-objective optimization algorithms. Lastly, Pareto solutions are evolved on eight real-world multi-objective optimization problems, and a comparative performance is presented with NSGA-II. Experimental results show that using FLEX on most of the single and multi-objective problems, the speed of the search improves up to 50% and the quality of solutions also improves. These results provide sufficient evidence of the applicability of fitness landscape approximation-based algorithms for solving real-world optimization problems.

This paper was presented by Professor Andy Tyrrell on behalf of our Alumni, Rahul Dubey at the July 2024 IEEE sponsored World Congress on Computational Intelligence from June 30 – July 5, in Yokohama, Japan Conference

In recent years, the evolutionary developmental (Evo-Devo) concept has gained traction in the field of engineering design. This paper presents a new biologically inspired approach rooted in Evo-Devo principles to iteratively develop car chassis designs based on a specified design brief. The proposed method draws inspiration from biological cell growth and differentiation behaviours to generate intricate engineering designs. Employing evolutionary algorithms, the paper aims to evolve gene regulatory
networks that govern the growth of a minimal viable design. The primary goal is to achieve an optimal design capable of withstanding sudden crash impacts within safety limits. Comprehensive simulation results demonstrate that the proposed approach, using genetic algorithms, evolves gene regulatory networks that generate a spectrum of viable designs. Furthermore, the best evolved solution exhibits generalizability and adaptability across different simulation parameters.

This presentation was given by Professor Andy Tyrrell on behalf of our Alumni, Rahul Dubey at the July 2024 IEEE sponsored World Congress on Computational Intelligence from June 30 – July 5, in Yokohama, Japan Conference

Simon Hickinbotham, a Research Fellow from the RIED team at the University of York, presented this Late Breaking Abstract and Poster at the International Society for Artificial Life 22-26 July 2024 Conference in Copenhagen.

Published in the Artificial Life Journal

Abstract: Engineering design optimization poses a significant challenge, usually requiring human expertise to discover superior solutions. Although various search techniques have been employed to generate diverse designs, their effectiveness is often limited by problem-specific parameter tuning, making them less generalizable and scalable. This article introduces a framework inspired by
evolutionary and developmental (evo-devo) concepts, aiming to automate the evolution of structural engineering designs. In biological systems, evo-devo governs the growth of single-cell organisms into multicellular organisms through the use of gene regulatory networks (GRNs). GRNs are inherently complex and highly nonlinear, and this article explores the use of neural networks and genetic programming as artificial representations of GRNs to emulate such behaviors. To evolve a wide range of Pareto fronts for artificial GRNs, this article introduces a new technique, a real value–encoded neuroevolutionary method termed real-encoded NEAT (RNEAT). The performance of RNEAT is compared with that of two well-known evolutionary search techniques across different 2-D and 3-D problems. The experimental results demonstrate two key findings. First, the proposed framework effectively generates a population of GRNs that can produce diverse structures for both 2-D and 3-D problems. Second, the proposed RNEAT algorithm outperforms its competitors on more than 50% of the problems examined. These results validate the proof of concept underlying the proposed evo-devo-based engineering design evolution.

This paper was presented by Imelda Friel at the MadeAI Conference in Porto, Portugal in July 2024.

This paper examines the application of a novel Evolutionary-Development (Evo-Devo)
system that integrates AI tools within the conceptual design process to produce populations of
innovative design options. The aim is to allow the behaviours of designs to be learned and then
exploited later in the design process. Here a design concept (referred to as an organism) is
constructed from cells, which have an evolving NN architecture controlling each
cells’parameterisation. The following work demonstrates the application of the Evo-Devo
process on a volume-to-point heat transfer problem, returning design concepts with a network
of heat channels that direct heat built up in the plate to a point at ambient temperature

This presentation was given by Dr Edgar Buchanan Berumen, a member of our RIED Team from the University of York, to the IEEE sponsored World Congress on Computational Intelligence, from June 30 – July 5, in Yokohama, Japan.

Other RIED team members including Simon Hickinbotham, Rahul Dubey, Imelda Field, Andrew Colligan, Mark Price and Andy Tyrrell contributed to the paper.

We are delighted to share that Colin Roitt, a RIED PhD Student at the University of York, recently presented a paper and poster at the 13th International Conference on Artificial Intelligence in Music, Sound, Art and Design (EvoMUSART). This was part of “evostar”, the leading European event on Bio-Inspired Computation that took part in Aberystwyth, Wales, UK 3-5 April

Colin’s paper entitled “Enough is Enough: Learning to Stop in Generative Systems” proposed that while Gene regulatory networks (GRNs) have been used to drive artificial generative systems these systems must begin and then stop generation, or growth, akin to their biological counterpart. A Long Short-Term Memory style network was implemented as a GRN for an Evo-Devo generative system and was tested on one simple (single point target) and two more complex problems (structured and unstructured point clouds). The novel LSTMGRN performed well in simple tasks to optimise stopping conditions, but struggled to manage more complex environments. This early work in self-regulating growth will allow for further research in more complex systems to allow the removal of hyperparameters and allowing the evolutionary system to stop dynamically and prevent organisms overshooting the optimal.

Here are links to the paper

https://link.springer.com/chapter/10.1007/978-3-031-56992-0_22

https://doi.org/10.1007/978-3-031-56992-0_22

Well done Colin !

This paper was presented at the 2023 IEEE Symposium Series on Computational Intelligence (SSCI), Mexico City, Mexico in December 2023.

Engineering design has traditionally involved human engineers manually creating and iterating on designs based on their expertise and knowledge. In Bio-inspired Evolutionary Development (EvoDevo), generative algorithms are used to explore a much larger design space that may not have ever been considered by human engineers. However, for complex systems, the designer is often required to start the EvoDevo process with an initial design (seed) which the development process will optimise. The question is: will a good starting seed yield a good set of design solutions for the given problem? This paper considers this question and suggests that sub-optimal seeds can provide, up to certain limits, better design solutions than relatively more optimal seeds. In addition, this paper highlights the importance of designing the appropriate seed for the appropriate problem. In this paper, the problem analysed is the structural performance of a Warren Truss (bridge-like structure) under a single load. The main conclusion of this paper is that up to a limit sub optimal seeds provide in general better sets of solutions than more optimal seeds. After this limit, the performance of sub-optimal seed starts to degrade as parts of the phenotype landscape become inaccessible.

This paper was presented at the 2023 IEEE Symposium Series on Computational Intelligence (SSCI in Mexico City, Mexico from 5-8 December 2023.

Evolutionary approaches to engineering design involve generating populations of candidate solutions that compete via a selection process iteratively, to improve measures of performance over many generations. Although the attractive properties of biological evolutionary systems have motivated researchers to investigate emulating them for engineering design, there has been an emphasis on using encodings of the technical artefacts themselves, rather than encoding a complete bio-inspired system which is capable of producing such artefacts. It is the latter approach which is the subject of this contribution: how might a bio-inspired system be designed that self-organises the process of engineering design and manufacture?

Supporting presentation to the Evolving Design Modifiers paper

Evolutionary Developmental biology (EvoDevo) is a process of directed growth whose mechanisms could be used in an evolutionary algorithm for engineering applications. Engineering design can be thought of as a search through a high-dimensional design space for a small number of solutions that are optimal by various metrics. Configuring this search within an EvoDevo algorithm may allow developmental processes to provide a facility to give more immediate, localised feedback to the system as it grows into its final optimal configuration (form). This approach would augment current design practices. The main components needed to run EvoDevo for engineering design are set out in this paper, and these are developed into an algorithm for initial investigations, resulting in evolved neural network-based structural design modifying operators that optimise the structure of a planar truss in an iterative, decentralized manner against multiple objectives. Preliminary results are presented which show that the two levels feedback at the Evo and Devo stages drive the system to ultimately produce feasible solutions.