Skip to main content

Research Repository

Advanced Search

All Outputs (189)

Improving Novelty Search with a Surrogate Model and Accuracy Objectives to Build High-Performing Ensembles of Classifiers (2025)
Journal Article
Cardoso, R. P., Hart, E., & Pitt, J. V. (2025). Improving Novelty Search with a Surrogate Model and Accuracy Objectives to Build High-Performing Ensembles of Classifiers. SN Computer Science, 6(6), Article 631. https://doi.org/10.1007/s42979-025-04056-4

Neuroevolution combined with Novelty Search to promote behavioural diversity is capable of constructing high-performing ensembles for classification. However, using gradient descent to train evolved architectures during the search can be computationa... Read More about Improving Novelty Search with a Surrogate Model and Accuracy Objectives to Build High-Performing Ensembles of Classifiers.

Opportunities and challenges for monitoring terrestrial biodiversity in the robotics age (2025)
Journal Article
Pringle, S., Dallimer, M., Goddard, M. A., Le Goff, L. K., Hart, E., Langdale, S. J., Fisher, J. C., Abad, S.-A., Ancrenaz, M., Angeoletto, F., Auat Cheein, F., Austen, G. E., Bailey, J. J., Baldock, K. C. R., Banin, L. F., Banks-Leite, C., Barau, A. S., Bashyal, R., Bates, A. J., Bicknell, J. E., …Davies, Z. G. (2025). Opportunities and challenges for monitoring terrestrial biodiversity in the robotics age. Nature Ecology & Evolution, 9(6), 1031-1042. https://doi.org/10.1038/s41559-025-02704-9

With biodiversity loss escalating globally, a step change is needed in our capacity to accurately monitor species populations across ecosystems. Robotic and autonomous systems (RAS) offer technological solutions that may substantially advance terrest... Read More about Opportunities and challenges for monitoring terrestrial biodiversity in the robotics age.

XAI for Algorithm Configuration and Selection (2025)
Book Chapter
Thomson, S. L., Hart, E., & Renau, Q. (2025). XAI for Algorithm Configuration and Selection. In N. van Stein, & A. V. Kononova (Eds.), Explainable AI for Evolutionary Computation. Springer. https://doi.org/10.1007/978-981-96-2540-6_6

In this chapter, we consider, formalise, and demonstrate the ways in which XAI can assist or inform algorithm selection and configuration. Reviewing the literature, we notice and taxonomise a much broader and more diverse notion of XAI than is typica... Read More about XAI for Algorithm Configuration and Selection.

Beyond the Hype: Benchmarking LLM-Evolved Heuristics for Bin Packing (2025)
Presentation / Conference Contribution
Sim, K., Hart, E., & Renau, Q. (2025, April). Beyond the Hype: Benchmarking LLM-Evolved Heuristics for Bin Packing. Presented at EvoSTAR 2025, Trieste, Italy

Coupling Large Language Models (LLMs) with Evolutionary Algorithms has recently shown significant promise as a technique to design new heuristics that outperform existing methods, particularly in the field of combinatorial optimisation. An escalating... Read More about Beyond the Hype: Benchmarking LLM-Evolved Heuristics for Bin Packing.

Algorithm Selection with Probing Trajectories: Benchmarking the Choice of Classifier Model (2025)
Presentation / Conference Contribution
Renau, Q., & Hart, E. (2025, April). Algorithm Selection with Probing Trajectories: Benchmarking the Choice of Classifier Model. Presented at EvoSTAR 2025, Trieste, Italy

Recent approaches to training algorithm selectors in the black-box optimisation domain have advocated for the use of training data that is 'algorithm-centric' in order to encapsulate information about how an algorithm performs on an instance, rather... Read More about Algorithm Selection with Probing Trajectories: Benchmarking the Choice of Classifier Model.

Stalling in Space: Attractor Analysis for any Algorithm (2025)
Presentation / Conference Contribution
Thomson, S. L., Renau, Q., Vermetten, D., Hart, E., van Stein, N., & Kononova, A. V. (2025, April). Stalling in Space: Attractor Analysis for any Algorithm. Paper presented at EvoStar 2025, Trieste, Italy

Network-based representations of fitness landscapes have grown in popularity in the past decade; this is probably because of growing interest in explainability for optimisation algorithms. Local optima networks (LONs) have been especially dominant in... Read More about Stalling in Space: Attractor Analysis for any Algorithm.

Into the Black Box: Mining Variable Importance with XAI (2025)
Presentation / Conference Contribution
Hunter, K., Thomson, S. L., & Hart, E. (2025, April). Into the Black Box: Mining Variable Importance with XAI. Presented at Evostar 2025, Trieste, Italy

Recent works have shown that the idea of mining search spaces to train machine learning models can facilitate increasing understanding of variable importance in optimisation problems. However , so far, the problems studied have typically either been... Read More about Into the Black Box: Mining Variable Importance with XAI.

Bots on the Ground vs Boots on the Ground: The Future of Robots in Terrestrial Ecological Surveying (2025)
Journal Article
White, P., Le Goff, L., Emery, L., Abrahams, C., Findlay, M., Cook, J., Macleod, K., Deacon, L., Reason, P., Stanhope, K., Wale, M., Hart, E., & Diele, K. (2025). Bots on the Ground vs Boots on the Ground: The Future of Robots in Terrestrial Ecological Surveying. In Practice (CIEEM), 27, 47-52

At the 2023 CIEEM Modernising Ecology conference, a robot greeted the attendees as they arrived. Was it a glimpse into the future? As with other technologies, robots have the potential to revolutionise ecological surveying, yet this comes with both o... Read More about Bots on the Ground vs Boots on the Ground: The Future of Robots in Terrestrial Ecological Surveying.

An Evaluation of Domain-agnostic Representations to Enable Multi-task Learning in Combinatorial Optimisation (2025)
Presentation / Conference Contribution
Stone, C., Renau, Q., Miguel, I., & Hart, E. (2024, June). An Evaluation of Domain-agnostic Representations to Enable Multi-task Learning in Combinatorial Optimisation. Presented at 18th Learning and Intelligent Optimization Conference, Ischia, Italy

We address the question of multi-task algorithm selection in combinatorial optimisation domains. This is motivated by a desire to simplify the algorithm-selection pipeline by developing a more general classifier that does not require specialised info... Read More about An Evaluation of Domain-agnostic Representations to Enable Multi-task Learning in Combinatorial Optimisation.

Towards a Unified Framework for Software-Hardware Integration in Evolutionary Robotics (2024)
Journal Article
Buchanan, E., Le Goff, L. K., Hale, M. F., Hart, E., Eiben, A. E., De Carlo, M., Angus, M., Woolley, R., Timmis, J., Winfield, A. F., & Tyrrell, A. M. (2024). Towards a Unified Framework for Software-Hardware Integration in Evolutionary Robotics. Robotics, 13(11), Article 157. https://doi.org/10.3390/robotics13110157

The discrepancy between simulated and hardware experiments, the reality gap, is a challenge in evolutionary robotics. While strategies have been proposed to address this gap in fixed-body robots, they are not viable when dealing with populations and... Read More about Towards a Unified Framework for Software-Hardware Integration in Evolutionary Robotics.

An Open Intent Discovery Evaluation Framework (2024)
Presentation / Conference Contribution
Anderson, G., Hart, E., Gkatzia, D., & Beaver, I. (2024, September). An Open Intent Discovery Evaluation Framework. Presented at SIGDIAL 2024, Kyoto, Japan

In the development of dialog systems the discovery of the set of target intents to identify is a crucial first step that is often overlooked. Most intent detection works assume that a labelled dataset already exists, however creating these datasets i... Read More about An Open Intent Discovery Evaluation Framework.

Automated Human-Readable Label Generation in Open Intent Discovery (2024)
Presentation / Conference Contribution
Anderson, G., Hart, E., Gkatzia, D., & Beaver, I. (2024, September). Automated Human-Readable Label Generation in Open Intent Discovery. Presented at Interspeech 2024, Kos, Greece

The correct determination of user intent is key in dialog systems. However, an intent classifier often requires a large, labelled training dataset to identify a set of known intents. The creation of such a dataset is a complex and time-consuming task... Read More about Automated Human-Readable Label Generation in Open Intent Discovery.

Evaluating the Robustness of Deep-Learning Algorithm-Selection Models by Evolving Adversarial Instances (2024)
Presentation / Conference Contribution
Hart, E., Renau, Q., Sim, K., & Alissa, M. (2024, September). Evaluating the Robustness of Deep-Learning Algorithm-Selection Models by Evolving Adversarial Instances. Presented at 18th International Conference on Parallel Problem Solving From Nature PPSN 2024, Hagenburg, Austria

Deep neural networks (DNN) are increasingly being used to perform algorithm-selection in combinatorial optimisation domains, particularly as they accommodate input representations which avoid designing and calculating features. Mounting evidence fro... Read More about Evaluating the Robustness of Deep-Learning Algorithm-Selection Models by Evolving Adversarial Instances.

Identifying Easy Instances to Improve Efficiency of ML Pipelines for Algorithm-Selection (2024)
Presentation / Conference Contribution
Renau, Q., & Hart, E. (2024, September). Identifying Easy Instances to Improve Efficiency of ML Pipelines for Algorithm-Selection. Presented at 18th International Conference, PPSN 2024, Hagenberg, Austria

Algorithm-selection (AS) methods are essential in order to obtain the best performance from a portfolio of solvers over large sets of instances. However, many AS methods rely on an analysis phase, e.g. where features are computed by sampling solution... Read More about Identifying Easy Instances to Improve Efficiency of ML Pipelines for Algorithm-Selection.

Improving Efficiency of Evolving Robot Designs via Self-Adaptive Learning Cycles and an Asynchronous Architecture (2024)
Presentation / Conference Contribution
Le Goff, L., & Hart, E. (2024, July). Improving Efficiency of Evolving Robot Designs via Self-Adaptive Learning Cycles and an Asynchronous Architecture. Presented at GECCO 2024 Embodied and Evolved Artificial Intelligence Workshop, Melbourne, Australia

Algorithmic frameworks for the joint optimisation of a robot's design and controller often utilise a learning loop nested within an evolutionary algorithm to refine the controller associated with a newly generated robot design. Intuitively, it is rea... Read More about Improving Efficiency of Evolving Robot Designs via Self-Adaptive Learning Cycles and an Asynchronous Architecture.

Learning Descriptors for Novelty-Search Based Instance Generation via Meta-evolution (2024)
Presentation / Conference Contribution
Marrero, A., Segredo, E., León, C., & Hart, E. (2024, July). Learning Descriptors for Novelty-Search Based Instance Generation via Meta-evolution. Presented at GECCO '24: Genetic and Evolutionary Computation Conference, Melbourne, Australia

The ability to generate example instances from a domain is important in order to benchmark algorithms and to generate data that covers an instance-space in order to train machine-learning models for algorithm selection. Quality-Diversity (QD) algorit... Read More about Learning Descriptors for Novelty-Search Based Instance Generation via Meta-evolution.

Understanding fitness landscapes in morpho-evolution via local optima networks (2024)
Presentation / Conference Contribution
Thomson, S. L., Le Goff, L., Hart, E., & Buchanan, E. (2024, July). Understanding fitness landscapes in morpho-evolution via local optima networks. Presented at Genetic and Evolutionary Computation Conference (GECCO 2024), Melbourne, Australia

Morpho-Evolution (ME) refers to the simultaneous optimisation of a robot's design and controller to maximise performance given a task and environment. Many genetic encodings have been proposed which are capable of representing design and control. Pre... Read More about Understanding fitness landscapes in morpho-evolution via local optima networks.

Ealain: A Camera Simulation Tool to Generate Instances for Multiple Classes of Optimisation Problem (2024)
Presentation / Conference Contribution
Renau, Q., Dreo, J., & Hart, E. (2024, July). Ealain: A Camera Simulation Tool to Generate Instances for Multiple Classes of Optimisation Problem. Presented at GECCO '24: Genetic and Evolutionary Computation Conference, Melbourne, Australia

Artificial benchmark datasets are common in both numerical and discrete optimisation domains. Existing benchmarks cover a broad range of classes of optimisation, but as a general rule have limited value due to their poor resemblance to real-world pro... Read More about Ealain: A Camera Simulation Tool to Generate Instances for Multiple Classes of Optimisation Problem.

Improving Algorithm-Selectors and Performance-Predictors via Learning Discriminating Training Samples (2024)
Presentation / Conference Contribution
Renau, Q., & Hart, E. (2024, July). Improving Algorithm-Selectors and Performance-Predictors via Learning Discriminating Training Samples. Presented at GECCO 2024, Melbourne, Australia

The choice of input-data used to train algorithm-selection models is recognised as being a critical part of the model success. Recently, feature-free methods for algorithm-selection that use short trajec-tories obtained from running a solver as input... Read More about Improving Algorithm-Selectors and Performance-Predictors via Learning Discriminating Training Samples.