Robot-assisted dressing is a popular but challenging topic in the field of robotic manipulation, offering significant potential to improve the quality of life for individuals with mobility limitations. Currently, the majority of research on robot-assisted dressing focuses on how to put on loose-fitting clothing, with little attention paid to tight garments. For the former, since the armscye is larger, a single robotic arm can usually complete the dressing task successfully. However, for the latter, dressing with a single robotic arm often fails due to the narrower armscye and the property of diminishing rigidity in the armscye, which eventually causes the armscye to get stuck. This paper proposes a bimanual dressing strategy suitable for dressing tight-fitting clothing. To facilitate the encoding of dressing trajectories that adapt to different human arm postures, a spherical coordinate system for dressing is established. We uses the azimuthal angle of the spherical coordinate system as a task-relevant feature for bimanual manipulation. Based on this new coordinate, we employ Gaussian Mixture Model (GMM) and Gaussian Mixture Regression (GMR) for imitation learning of bimanual dressing trajectories, generating dressing strategies that adapt to different human arm postures. The effectiveness of the proposed method is validated through various experiments.

For a long time engineering design has relied on human engineers manually crafting and refining designs using their expertise and experience. In Bio-inspired Evolutionary Development (EvoDevo), generative algorithms are employed to investigate a broader design space that may go beyond what human engineers have considered. Previous literature has demonstrated the use of quality and diversity (QD) algorithms in evolutionary approaches to drive the process to better quality solutions. This paper provides a study to understand the effects of using QD algorithms in EvoDevo processes for engineering design. This paper also analyses the impact of using different behavioural characterisations (BC) in the performance of the quality of the solutions found. The results demonstrate that quality and diversity algorithms can find better solutions than other EAs for engineering design problems. It was also found that the characterisation of the BC is important to get the best results.

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 behaviors 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 paper developed a decentralized multi-state Q-Learning algorithm for joint slot and power level selection in NOMA-ALOHA systems, which models the problem as a Markov Decision Process (MDP) and evaluates the quality of each action by a Q-Table. In a distributed manner, the proposed algorithm aims to find the best action strategy for each user who takes into account both the random collision with other users and the SINR threshold. In particular, novel reward function and state definition are proposed to achieve better exploration and leverage history observations, respectively. Simulation results indicate that the proposed algorithm can improve the average number of users with desired ASR compared to a number of benchmarks.

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.

Jointly optimising both the body and brain of a robot is known to be a challenging task, especially when attempting to evolve designs in simulation that will subsequently be built in the real world. To address this, it is increasingly common to combine evolution with a learning algorithm that can either improve the inherited controllers of new offspring to fine tune them to the new body design or learn them from scratch. In this paper an approach is proposed in which a robot is specified indirectly by two compositional pattern producing networks (CPPN) encoded in a single genome, one which encodes the brain and the other the body. The body part of the genome is evolved using an evolutionary algorithm (EA), with an individual learning algorithm (also an EA) applied to the inherited controller to improve it. The goal of this paper is to determine how to utilise the results of learning process most effectively to improve task performance of the robot. Specifically, three variants are investigated: (1) evolution of the body+controller only; (2) a learning algorithm is applied to the inherited controller with the learned fitness assigned to the genome; (3) learning is applied and the genome is updated with the learned controller, as well as being assigned the learned fitness. Experiments are performed in three different scenarios chosen to favour different bodies and locomotion patterns. It is shown that better performance can be obtained using learning but only if the learned controller is inherited by the offspring.

In order to improve the classification accuracy, state-of-the-art CNNs usually involve large and complex convolutional layers. However, for certain applications, e.g. Internet of Things (IoT), where such CNNs are to be implemented on resource-constrained platforms, the CNN architectures have to be small and efficient. To deal with this problem, reducing the resource consumption in convolutional layers has become one of the most significant efforts when designing CNNs. In this work, a multi-objective optimisation approach is proposed to trade-off between the amount of computation and network accuracy by using Multi-Objective Evolutionary Algorithms (MOEAs). The size and number of convolution kernels used are proportional to computational resource consumption of CNNs. Therefore, this paper considers reducing the computational resource consumption by reducing the size of kernels in convolutional layers. In addition to kernel size unconventional kernel shapes are investigated and results show these clearly improve performance over using traditionally square convolution kernels alone. The main contributions of this paper are therefore a methodology to significantly reduce computational cost of CNNs, based on unconventional kernel shapes, and provide different trade-offs for specific use cases. The experimental results further demonstrate that the proposed method achieves large improvements in resource consumption with no significant reduction in network performance. Compared with the benchmark CNN, the best trade-off architecture shows a reduction in multiplications of up to 4.06X and with slight increase in classification accuracy on CIFAR-10 dataset.

Fabrication issues throttle VLSI designs with pessimistic design constraints and speed-grade device binning necessary to avoid failure of devices. We propose that a on chip monitoring system (a Nervous System) can reduce this margin by automatically sensing and reacting to failures and environmental changes at runtime. We demonstrate that pessimistic margins in the FPGA tools allow our test circuit to be overclocked by twice the maximum design tool frequency and run at 50 °C above its maximum operating temperature without error. The Configurable Intelligence Array is introduced as a low-overhead intelligence platform and used for a prototype neural circuit that can close the loop between a timing-fault detector and a programmable Phase Locked Loop (PLL) oscillator.

In nature, the exploration of a design space is achieved by evolution. However, using artificial evolution to evolve physical shapes has been challenging because both the mapping from the genotype to phenotype and the means of measuring the resulting shape to estimate fitness are not straightforward. This contribution brings together recent advances in generative design with novelty search, an evolutionary method that replaces the fitness function with reward based purely on novelty. Bringing these techniques together yields a new methodology for exploring the power of shape descriptors. Novelty search with and without an archive is used to explore the range of shapes that are reachable from a hand-designed genotype, and compared with random walk mutations. Results indicate that the novelty search technique without an archive evolves a wider range of shapes than when an archive is used, but both are better than random walk.

Large-scale distributed computing architectures such as, e.g. systems on chip or many-core devices, offer ad-vantages over monolithic or centralised single-core systems in terms of speed, power/thermal performance and fault tolerance. However, these are not implicit properties of such systems and runtime management at software or hardware level is required to unlock these features. Biological systems naturally present such properties and are also adaptive and scalable. To consider how these can be similarly achieved in hardware may be beneficial. We present Social Insect behaviours as a suitable model for enabling autonomous runtime management (RTM) in many-core architectures. The emergent properties sought to establish are self-organisation of task mapping and system-level fault tolerance. For example, large social insect colonies accomplish a wide range of tasks to build and maintain the colony. Many thousands of individuals, each possessing relatively little intelligence, contribute without any centralised control. Hence, it would seem that social insects have evolved a scalable approach to task allocation, load balancing and robustness that can be applied to large many-core computing systems. Based on this, a self-optimising and adaptive, yet fundamentally scalable, design approach for many-core systems based on the emergent behaviours of social-insect colonies are developed. Experiments capture decision-making processes of each colony member to exhibit such high-level behaviours and embed these decision engines within the routers of the many-core system.

It is now known that astrocytes modulate the activity at the tripartite synapses where indirect signaling via the retrograde messengers, endocannabinoids, leads to a localized self-repairing capability. In this paper, a self-repairing spiking astrocyte neural network (SANN) is proposed to demonstrate a distributed self-repairing capability at the network level. The SANN uses a novel learning rule that combines the spike-timing-dependent plasticity (STDP) and Bienenstock, Cooper, and Munro (BCM) learning rules (hereafter referred to as the BSTDP rule). In this learning rule, the synaptic weight potentiation is not only driven by the temporal difference between the presynaptic and postsynaptic neuron firing times but also by the postsynaptic neuron activity. We will show in this paper that the BSTDP modulates the height of the plasticity window to establish an input-output mapping (in the learning phase) and also maintains this mapping (via self-repair) if synaptic pathways become dysfunctional. It is the functional dependence of postsynaptic neuron firing activity on the height of the plasticity window that underpins how the proposed SANN self-repairs on the fly. The SANN also uses the coupling between the tripartite synapses and γ -GABAergic interneurons. This interaction gives rise to a presynaptic neuron frequency filtering capability that serves to route information, represented as spike trains, to different neurons in the subsequent layers of the SANN. The proposed SANN follows a feedforward architecture with multiple interneuron pathways and astrocytes modulate synaptic activity at the hidden and output neuronal layers. The self-repairing capability will be demonstrated in a robotic obstacle avoidance application, and the simulation results will show that the SANN can maintain learned maneuvers at synaptic fault densities of up to 80% regardless of the fault locations.

Spiking Astrocyte-neuron Networks (SANNs) model the adaptive/repair feature of the human brain. They integrate astrocyte cells with spiking neurons to facilitate a distributed and fine-grained self-repair capability at the synapse level. SANNs are more complex with the addition of astrocyte cells and require longer simulation times, as they are dynamic over much longer time-scales than traditional neural networks. Therefore, dedicated FPGA accelerators offer reductions in simulation times. To support the acceleration of SANNs, the capability of fault injection to synapses and monitoring significant levels of neuron and astrocyte data for off-chip transmission to PC-based analysis, are required. This paper presents an FPGA-based monitoring platform (FMP) for injecting faults and capturing and analyzing data acquired from the SANN FPGA accelerator, Astrobyte. The FMP uses custom logic and a NIOS II based system to control fault injection and data monitoring on the FPGA. Results show accurate accelerated simulations of fault injection scenarios using FMP with speedups up to 65 times greater compared with equivalent Matlab implementations.

This paper describes a novel multi-reconfigurable architecture, which allows variability-aware design, rapid prototyping and post-fabrication optimisation of digital systems. This is achieved by exploiting reconfiguration at both the digital function level and the transistor level. A runtime variability map of the architecture, created using ring oscillators, is presented.

Intrinsic device variability has become a significant problem in deep sub-micron technology nodes. The stochastic variations in device performance, which are a result of structural irregularities at the atomic scale, can impact both the yield and reliability of a circuit design. In this paper we describe a novel multi-reconfigurable FPGA architecture, the programmable analogue and digital array (PAnDA), which can tackle this problem by allowing post-fabrication reconfiguration of the effective transistor gate widths in a circuit. We demonstrate the advantages of this architecture by creating a frequency variability map of the array using ring oscillators in order to ascertain the location of any frequency outliers. We then show that it is possible, using an evolutionary algorithm, to select alternative transistor configurations which minimise the difference in frequency between one of these outliers and the chips median frequency of operation. Such methods can be used to increase system performance and reliability by presenting an array with more uniform performance characteristics.

We present a novel methodology that addresses the problem of faults in synapses of a spiking neural network using astrocyte regulation, inspired by recovery processes in the brain. Since Field Programmable Gate Arrays (FPGAs) are widely used for neural network applications, we aim to achieve fault tolerance in an astrocyte-neuron unit implemented on an FPGA. A fault is considered as a reduction in transmission probability of a synapse, leading to reduced spiking activity. Our novel repair mechanism exploits Dynamic Partial Reconfiguration (DPR) of the FPGA Clock Management Tiles (CMTs) to increase the clock frequency of neurons with reduced synaptic input, which restores the firing rate to pre-fault levels. The system maintains effective functional behavior with a loss of up to 90% of the original synaptic inputs to a neuron. Our repair mechanism has minimal hardware footprints with the repair unit which consumes only 0.8215% of the complete design and therefore supports scalable implementations. Additionally, the impact on power consumption of the design is also minimal (1.371W). The work opens up a novel way to utilize the capabilities of modern hardware to mimic homeostatic self-repair behavior achieving fault recovery.

The growing impact of the network on the overall power consumption of many-core systems introduces a need for mechanisms that reduce the power required for data communication without significantly impacting performance. This paper proposes a low-overhead mechanism for frequency control of individual channels in a Network-on-Chip system. The proposed mechanism is low-overhead, distributed and easy to tune for varying traffic, which are crucial aspects in a many-core context. This is primarily achieved by the asymmetry of the controller, which defines different responses for increases and decreases in performance requirements, allowing a channel to operate at the minimum required frequency without adversely affecting stability, necessary for subsequent voltage scaling.

A novel hierarchical fault-tolerance methodology for reconfigurable devices is presented. A bespoke multi-reconfigurable FPGA architecture, the programmable analogue and digital array (PAnDA), is introduced allowing fine-grained reconfiguration beyond any other FPGA architecture currently in existence. Fault blind circuit repair strategies, which require no specific information of the nature or location of faults, are developed, exploiting architectural features of PAnDA. Two fault recovery techniques, stochastic and deterministic strategies, are proposed and results of each, as well as a comparison of the two, are presented. Both approaches are based on creating algorithms performing fine-grained hierarchical partial reconfiguration on faulty circuits in order to repair them. While the stochastic approach provides insights into feasibility of the method, the deterministic approach aims to generate optimal repair strategies for generic faults induced into a specific circuit. It is shown that both techniques successfully repair the benchmark circuits used after random faults are induced in random circuit locations, and the deterministic strategies are shown to operate efficiently and effectively after optimisation for a specific use case. The methods are shown to be generally applicable to any circuit on PAnDA, and to be straightforwardly customisable for any FPGA fabric providing some regularity and symmetry in its structure.

This paper describes the artificial epigenetic network, a recurrent connectionist architecture that is able to dynamically modify its topology in order to automatically decompose and solve dynamical problems. The approach is motivated by the behavior of gene regulatory networks, particularly the epigenetic process of chromatin remodeling that leads to topological change and which underlies the differentiation of cells within complex biological organisms. We expected this approach to be useful in situations where there is a need to switch between different dynamical behaviors, and do so in a sensitive and robust manner in the absence of a priori information about problem structure. This hypothesis was tested using a series of dynamical control tasks, each requiring solutions that could express different dynamical behaviors at different stages within the task. In each case, the addition of topological self-modification was shown to improve the performance and robustness of controllers. We believe this is due to the ability of topological changes to stabilize attractors, promoting stability within a dynamical regime while allowing rapid switching between different regimes. Post hoc analysis of the controllers also demonstrated how the partitioning of the networks could provide new insights into problem structure.

Large social insect colonies require a wide range of important tasks to be undertaken to build and maintain the colony. Fortunately, in most nests there are many thousands of workers available to offer their assistance to ensure the expansion and survival of the colony. However, there is a crucial equilibrium between the number of workers performing each task that must not only be maintained but must also continuously adapt to sudden changes in environment and colony need. What is most fascinating is that social insects can sustain this balance without any centralised control and with colony members that have relatively little intelligence when considered on their own. Due to this simplicity and evident scalability it would seem that social insects have evolved an interesting scalable approach to task allocation that could be applied to very large many-core systems. To investigate this we have explored biological models of task allocation in ant colonies and applied this to a 36-core Network on Chip. This paper not only shows that effective decentralised task allocation is achieved, but also that such a scheme can adapt to faults and alter its behaviour to meet soft real-time constraints. Therefore, it is established that social insect inspired intelligence models offer a suitable metaphor and development direction for tackling the challenges introduced by dark silicon and in-field faults in a decentralised and adaptive fashion.

A self-repairing robot utilising a spiking astrocyte-neuron network is presented in this paper. It uses the output spike frequency of neurons to control the motor speed and robot activation. A software model of the astrocyte-neuron network previously demonstrated self-detection of faults and its self-repairing capability. In this paper the application demonstrator of mobile robotics is employed to evaluate the fault-tolerant capabilities of the astrocyte-neuron network when implemented in a hardware-based robotic car system. Results demonstrated that when 20% or less synapses associated with a neuron are faulty, the robot car can maintain system performance and complete the task of forward motion correctly. If 80% synapses are faulty, the system performance shows a marginal degradation, however this degradation is much smaller than that of conventional fault-tolerant techniques under the same levels of faults. This is the first time that astrocyte cells merged within spiking neurons demonstrates a self-repairing capabilities in the hardware system for a real application.

In this paper, we propose a novel technique based on multiobjective genetic algorithms (MOGA) to solve the circuit clustering problem in field-programmable gate array (FPGA) computer aided design (CAD) flow. As the circuit clustering result is subsequently used by the circuit place-and-route process at the post-synthesis stage, the clustering quality significantly affects the routing cost and the utilisation of FPGA. Among clustering metrics, reducing the global interconnects (global nets) between configurable logic blocks (CLBs) can be viewed as the most efficient precondition to improve the clustering quality. Since the circuit has many connection properties, it is difficult to identify the proper component combinations for sub-circuits that optimise interconnect, and it is even more complicated when CLBs pose constraints. In our technique, we break the circuit clustering task into two phases. We firstly apply the MOGA to identify the best component combinations to FPGA CLBs while respecting constraints, and a second MOGA takes clustering results from the first phase and performs further optimisation. Our proposed method is tested using the MCNC-20 benchmark. The results show that the proposed technique produces better results than state-of-art algorithms in reducing global nets. The overall improvement is up to 4.33% and 14.24% in reducing the cluster number and the global net number compared to the FPGA circuit packer, iRAC, which is considered to be the best clustering method to reduce global nets.

Implementing Dynamic Voltage and Frequency Scaling (DVFS) is a non-trivial task on FPGAs and requires knowledge about the feasible voltage and frequency (VF) ranges as a first step. The VF feasible ranges depend not only on the size of the critical path in the design but also on the inter- and intra-die variability on the FPGA die. Moreover, the variations in the configuration of the FPGA highly affect feasible VF ranges. Therefore, it is crucial to characterise feasibility by studying the relationship between feasible VF regions and these sources of variability in FPGAs. In this paper we employ a self-checking multiplier which uses residue codes and DVFS implemented on the programmable logic component of a Xilinx Zynq ZC702 device as an error-detection circuit to study these feasible regions. Results show that, as expected, feasible VF ranges vary with FPGA configuration. More interestingly, significant variation of the feasible VF regions is found for different dies. These results highlight the necessity of dynamic self-testing as a part of an adaptive DVFS implementation on FPGAs. Employing the techniques presented in this work enables the implementation of efficient adaptive on-line DVFS on programmable logic while ensuring reliability.

The modeling and simulation of semiconductor devices is a difficult and computationally intensive task. However the expense of fabrication and testing means that accurate modeling and simulation are crucial to the continued progress of the industry. To create these models and then perform the simulations requires parameters from accurate physical models to be obtained and then more abstract models created that can perform more complex circuit simulations. Device models (motifs) are created as a mitigation technique for improvement the circuit performance and as technology advances to help with the effects of transistor variability. In order to explore the characteristics of new device motifs on circuit designs, obtaining accurate and reliable device models becomes the first problem for designers. In this paper a Two Step Evolution Strategy (2SES) is proposed for device parameter model extraction. The proposed 2SES approach automatically extracts a set of parameters with respect to a specified device model. Compared with conventional mathematical extraction approach, 2SES is an efficient and accurate method to solve the parameter extraction problem and simultaneously addresses the fact of the mathematical extraction having the complexity of Multi-objective optimization. Compared with single step ES extract result, it is shown that the two-step ES extraction process continues improving generations by adjusting the optimisation parameters. Finally, an application of a new device motif on circuit design is given at end of the paper and compared against a standard device.

Biological organisms exist within environments in which complex nonlinear dynamics are ubiquitous. They are coupled to these environments via their own complex dynamical networks of enzyme-mediated reactions, known as biochemical networks. These networks, in turn, control the growth and behavior of an organism within its environment. In this paper, we consider computational models whose structure and function are motivated by the organization of biochemical networks. We refer to these as artificial biochemical networks and show how they can evolve to control trajectories within three behaviorally diverse complex dynamical systems: 1) the Lorenz system; 2) Chirikov's standard map; and 3) legged robot locomotion. More generally, we consider the notion of evolving dynamical systems to control dynamical systems, and discuss the advantages and disadvantages of using higher order coupling and configurable dynamical modules (in the form of discrete maps) within artificial biochemical networks (ABNs). We find both approaches to be advantageous in certain situations, though we note that the relative tradeoffs between different models of ABN strongly depend on the type of dynamical systems being controlled.

Parkinson's disease is a debilitating neurological condition that affects approximately 1 in 500 people and often leads to severe disability. To improve clinical care, better assessment tools are needed that increase the accuracy of differential diagnosis and disease monitoring. In this paper, we report how we have used evolutionary algorithms to induce classifiers capable of recognizing the movement characteristics of Parkinson's disease patients. These diagnostically relevant patterns of movement are known to occur over multiple time scales. To capture this, we used two different classifier architectures: sliding-window genetic programming classifiers, which model over-represented local patterns that occur within time series data, and artificial biochemical networks, computational dynamical systems that respond to dynamical patterns occurring over longer time scales. Classifiers were trained and validated using movement recordings of 49 patients and 41 age-matched controls collected during a recent clinical study. By combining classifiers with diverse behaviors, we were able to construct classifier ensembles with diagnostic accuracies in the region of 95%, comparable to the accuracies achieved by expert clinicians. Further analysis indicated a number of features of diagnostic relevance, including the differential effect of handedness and the over-representation of certain patterns of acceleration.

This paper explores the potential for transistor level fault tolerance on a new Programmable Analogue and Digital Array (PAnDA) architecture1. In particular, this architecture features Combinatorial Configurable Analogue Blocks (CCABs) that can implement a number of combinatorial functions similar to FPGAs. In addition, PAnDA allows one to reconfigure features of the underlying analogue layer. In PAnDA-EINS, the functions that the CCAB can implement are predefined through the use of a routing block. This paper is a study of whether removing this routing block and allowing direct control of the transistors provides benefits for fault tolerance. Experiments are conducted in two stages. In the first stage, a logic function is evolved on a CCAB and then optimised using a GA. A fault is then injected into the substrate, breaking the logic function. The second stage of the experiment consists of evolving the logic function again on the faulty substrate. The results of these experiments show that the removal of the routing block from the CCAB is beneficial for fault tolerance.

A novel bio-inspired architecture comprising three layers is introduced for a six-legged robot in order to generate adaptive rhythmic locomotion patterns using environmental information. Taking inspiration from the intracellular signalling processes that decode environmental information, and considering the emergent behaviours that arise from the interaction of multiple signalling pathways, we develop a decentralised robot controller composed of a collection of artificial signalling networks. Crosstalk, a biological signalling mechanism, is used to couple such networks favouring their interaction. We also apply nonlinear oscillators to model gait generators, which induce symmetric and rhythmical locomotion movements. The trajectories are modulated by a coupled artificial signalling network, which yields adaptive and stable robotic locomotive patterns. Gait trajectories are converted into joint angles by means of inverse kinematics. The architecture is implemented in a simulated version of the real robot T-Hex. Our results demonstrate the ability of the architecture to generate adaptive and periodic gaits.

Field programmable gate arrays (FPGAs) are widely used in applications where online reconfigurable signal processing is required. Speed and function density of FPGAs are increasing as transistor sizes shrink to the nanoscale. As these transistors reduce in size intrinsic variability becomes more of a problem and to reliably create electronic designs according to specification time consuming statistical simulations become necessary; and even with accurate models and statistical simulation, the fabrication yield will decrease as every physical instance of a design behaves differently. This paper describes an adaptive, evolvable architecture that allows for correction and optimization of circuits directly in hardware using bioinspired techniques. Similar to FPGAs, the programmable analog and digital array (PAnDA) architecture introduced provides a digital configuration layer for circuit design. Accessing additional configuration options of the underlying analog layer enables continuous adjustment of circuit characteristics at runtime, which enables dynamic optimization of the mapped design's performance. Moreover, the yield of devices can be improved postfabrication via reconfiguration of the analog layer, which can overcome faults induced due to variability and process defects. Since optimization goals are generic, i.e., not restricted to reducing stochastic variability, power consumption or increasing speed, the same mechanisms can also enhance the device's fault tolerant abilities in the case of component degradation and failures during its lifetime or when exposed to hazardous environments.

Biological genomes have evolved over a period of millions of years and comprise thousands of genes, even for the simplest organisms. However, in nature, only 1-2% of the genes play an active role in creating and maintaining the organism, while the majority are evolutionary fossils. This raises the question of whether a considerably larger number of (partly redundant) genes are required in order to effectively build a functional developmental system, of which, in the final system only a fraction is required for the latter to function. This paper investigates different approaches to creating artificial developmental systems (ADSs) based on variable length gene regulatory networks (GRNs). The GRNs are optimized using an evolutionary algorithm (EA). A comparison is made between the different variable length representations and fixed length representations. It is shown that variable length GRNs can achieve both reducing computational effort during optimization and increasing speed and compactness of the resulting ADS, despite the higher complexity of the encoding required. The results may also improve the understanding of how to effectively model GRN based developmental systems. Taking results of all experiments into account makes it possible to create an overall ranking of the different patterns used as a testbench in terms of their complexity. This ranking may aid to compare related work against. In addition, this allows a detailed assessment of the ADS used and enables the identification of missing mechanisms.

Living organisms are complex systems, and yet they possess extremely high degrees of reliability. Since failures are local, their repair will often be taken on the local (cell) level. Engineers have long sought systems that could offer similar reliability and have relatively recently started trying to integrate ideas inspired by nature into the modern silicon technology of today. While bio-inspired proposals inspired by multicellular systems demonstrated feasibility, the resulting systems were often unduly complex. We are proposing a radically new methodology inspired by the characteristics, morphology, and behavior of simpler prokaryotic bacteria and bacterial communities. The hypothesis we use is that such simple unicellular organisms could help to build simpler cost effective systems, but with improved reliability than hitherto achieved by other methods. The result is a cellular array-based fault-tolerant electronic system with online self-test and self-repair capability. These ideas are simulated, tested, and verified through the successful construction of demonstrators: a proportional, integral, and differential and a robot controller. This paper discusses the underlying biological principles that guide our research and the bio-inspired model that we have derived. It also gives a detailed circuit and system description of the architecture and its run-time self-diagnostic and self-repair capability.

This paper describes the application of the receptor density algorithm, an artificial immune system, as used to detect chemicals from data provided by various spectrometers. The system creates chemical signatures which are matched to a library of known chemicals, allowing the positive identification of hazardous substances. The performance of the system is tested against a publicly available mass-spectrometry dataset, against which it has previously been demonstrated as an effective anomaly detection algorithm. An autonomous chemical-detection device is then discussed, in which the algorithm is running on hardware embedded in a Pioneer robot carrying a portable chemical agent monitor.

In this paper we have investigated the efficacy of applying multi-objective optimisation to Cartesian genetic programming (CGP) when used for evolution of cell-array configurations. A cell-array is a proposed type of custom FPGA, where digital circuits can be formed from interconnected configurable cells; thus, the CGP nodes are more complex than in its standard implementation. We have described modifications to a previously described optimisation algorithm that has led to significant improvements in performance; circuits close to a hand designed equivalent have been found, in terms of the optimised objectives. Additionally we have investigated the effect of circuit decomposition techniques on evolutionary performance. We found that using a hybrid of input and output decomposition techniques substantial reductions in evolution time were observed. Further, while the number of circuit inputs is the key factor for functional evolution time, the number of circuit outputs is the key factor for optimisation time.

This paper details an extension to an architecture for robust bidirectional hetero-associative recall. Our proposed Protein Processor Associative Memory (PPAM) is fundamentally different from the traditional processing methods which use arithmetic operations and consequently Arithmetic and Logic Units (ALUs). In this paper, we improve on our initial work addressing concerns surrounding hardware implementation. We present the improved computational architecture, coupled with a corresponding hardware architecture for implementation. Results of applying the hardware implementation on a small dataset are included, along with reports from synthesis tools about hardware utilisation.

Swarm systems consist of a number of relatively simple agents that interact with each other to afford a complex behaviour. Such swarm systems are inherently parallel but as yet little work has focussed on the development of specific hardware platforms that might take advantage of such parallelism. This paper proposes a hardware platform for the implementation of swarm system simulations, using a case study of Reynolds' boids. Our platform provides a flexible decentralised intelligent bus communication architecture designed to provide effective communication between agents on a hardware platform.

Multicellular organisms in biology possess invaluable characteristics, which artificial systems in engineering lack, such as adaptivity and robustness. Modeling biologically inspired multicellular developmental systems in evolutionary computation have been considered for a number of years, and there exist many developmental simulations that capture multicellular characteristics of biological organisms. However, the relative importance of many mechanisms in such models is still poorly understood. This paper undertakes a detailed investigation of the importance of many mechanisms and parameters on the organizational behavior of a gene regulatory network based artificial developmental system via classical pattern matching experiments. The work leads to an improved understanding of artificial multicellular development, which will assist in its utilization in the application of evolutionary computation. It may also provide a better understanding of mechanisms of biological development.

The five papers in this special issue focus on evolving developmental systems.

This paper presents a lightweight, immune-inspired system for the diagnosis of faults. We adapt the dendritic cell algorithm, to develop the Diagnostic Dendritic Cell Algorithm (D-DCA) to afford on-line diagnosis of stuck-at-fault conditions. Our work shows that the D-DCA is capable of successfully diagnosing simple faults within an acceptable time frame, with an acceptable accuracy.

The evolvable hardware field has been an area of research interest since the early 1990s. However, the number of significant accomplishments has noticeably diminished in recent years. In this paper we discuss several reasons why this is so. We then introduce a new model called metamorphic systems that builds upon evolvable hardware principles placing more emphasis on adapting system behavior rather than evolving desired system behavior. Our metamorphic system approach is better suited to non-electronic systems. Two example metamorphic systems are presented.

The evolution of Artificial Intelligence has passed through many phases over the years, going from rigorous mathematical grounding to more intuitive bio-inspired approaches. Despite the abundance of AI algorithms and machine learning techniques, the state of the art still fails to capture the rich analytical properties of biological beings or their robustness. Most parallel hardware architectures tend to combine Von Neumann style processors to make a multi-processor environment and computation is based on Arithmetic and Logic Units (ALU). This paper introduces an alternate architecture that is inspired from the biological world, and is fundamentally different from traditional processing which uses arithmetic operations. The architecture proposed here is targeted towards robust artificial intelligence applications.

In nature, modules pervade organisms at all levels and construct complex and scalable organisms. Modularity is fundamental for achieving large and complex systems. In engineering design, as required systems become larger, the complex and modularity of the design becomes more important. Inspired by nature, this paper introduces a bottom-up construction method to construct digital circuits using gene regulation in a cellular system. It uses modular design to achieve scalable combinatorial systems.

A novel approach to image compression using a gene regulatory network (GRN) based artificial developmental system (ADS) is introduced. The proposed algorithm exploits the fact that a series of complex organisms (≡ developmental states) can be represented via a GRN description and the indices of the developmental steps in which they occur. Organisms are interpreted as tiles of an image at each developmental step which results in the (re-)construction of an image during the developmental process. It is shown that GRNs are suitable for image compression and achieve higher compression rates than JPEG when optimised for a particular image. It is also shown that the same GRN has the potential to encode multiple images, each represented by a different series of numbers of developmental steps.

This paper describes an approach to optimise transistor dimensions within a standard cell library. The goal is to extract high-speed and low-power circuits which are more tolerant to the random fluctuations that will be prevalent in future technology nodes. Using statistically enhanced SPICE models based on 3D-atomistic simulations, a genetic algorithm optimises the device widths within a circuit using a multi-objective fitness function. The results show the impact of threshold voltage variation can be reduced by optimising transistor widths, and suggest a similar method could be extended to the optimisation of larger circuits.

Many researchers have encountered the problem that the evolution of electronic circuits becomes exponentially more difficult when problems with an increasing number of outputs are tackled. Although this is an issue in both intrinsic and extrinsic evolution experiments, overcoming this problem is particularly challenging in the case of evolvable hardware, where logic and routing resources are constrained according to the given architecture. Consequently, the success of experiments also depends on how the inputs and outputs are interfaced to the evolvable hardware. Various approaches have been made to solve the multiple output problem: partitioning the task with respect to the input or output space, incremental evolution of sub-tasks or resource allocation. However, in most cases, the proposed methods can only be applied in the case of extrinsic evolution. In this paper, we have accordingly, focused on scaling problem of increasing numbers of outputs when logic circuits are intrinsically evolved. We raise a number of questions: how big is the performance drop when increasing the number of outputs? Can the resources of evolvable hardware be structured in a suitable way to overcome the complexity imposed by multiple outputs, without including knowledge about the problem domain? Can available resources in hardware still be efficiently used when pre-structured? In order to answer these questions, different structural implementations are investigated. We have looked at these issues in solving three problems: 4-bit parity, 2-bit adder and 2-bit multiplier.

The immune system is a key component in the maintenance of host homeostasis. Key actors in this process are cells known as dendritic cells (DCs). An artificial immune system based on DCs (known as the Dendritic Cell Algorithm: DCA) is well established in the literature and has been applied in a number of applications. Work in this paper is concerned with the development of an integrated homeostatic system for small, autonomous robotic systems, implemented on a resource limited micro-controller. As a first step, we have modified the DCA to operate in both simulated robotic units, and a resource constrained micro-controller that can operate in an on-line manner. Errors can be introduced into the robotic unit during operation, and these can be detected and then circumvented by the modified DCA.

A model for intrinsic artificial development is introduced in this paper. The proposed model features a novel mechanism where growth emerges, rather than being triggered by a single action. Different types of cell signalling ensure that breaking symmetries is rather the norm than an exception, and gene activity is regulated on two layers: first, by the proteins that are produced by the gene regulatory network (GRN). Second, through structural feedback by second messenger molecules, which are not directly produced through gene expression, but are produced by sensor proteins, which take the cell's structure into account. The latter feedback mechanism is a novel approach, intended to enable adaptivity and environment coupling in real-world applications. The model is implemented in hardware, and is designed to run autonomously in resource limited embedded systems. Initial experiments are carried out to measure long-term stability, dynamics, adaptivity and scalability of the new approach. Furthermore the ability of the GRN to produce patterns of different symmetries is examined.

As the size of CMOS devices is approaching the atomic level, the increasing intrinsic device variability is leading to higher failure rates in conventional CMOS designs. This paper introduces a design tool capable of evolving CMOS topologies using a modified form of Cartesian genetic programming and a multi-objective strategy. The effect of intrinsic variability within the design is then analysed using statistically enhanced SPICE models based on 3D-atomistic simulations. The goal is to produce industry-feasible topology designs which are more tolerant to the random fluctuations that will be prevalent in future technology nodes. The results show evolved XOR and XNOR CMOS topologies and compare the impact of threshold voltage variation on the evolved designs with those from a standard cell library.

Real working agents normally operate in dynamic changing environments. These changes could either affect the efficiency of the agents' performance or even damage the functionality of the agent. Robustness is the key requirement to solve this problem. Inspired by nature, this paper demonstrates two mechanisms that contribute to individual's robustness in changing environments: evolution and degeneracy. Through evolution in damaging environment, evolved agents have to cope with changes in the environment and acquire robustness. Through degeneracy, individuals can maintain their fitness even when some damaged parts are involved in system function.

The design of a new biologically inspired artificial developmental system is described in this paper. In general, developmental systems converge slower and are more computationally expensive than direct evolution. However, the performance trends of development indicate that the full benefit of development will arise with larger and more complex problems that exhibit some sort of regularity in their structure: thus, the aim is to evolve larger electronic systems through the modularity allowed by development. The hope is that the proposed artificial developmental system will exhibit adaptivity and fault tolerance in the future. The cell signalling and the system of Gene Regulatory Networks present in biological organisms are modelled in our developmental system, and tailored for tackling real world problems on electronic hardware. For the first time, a Gene Regulatory Network system is successfully shown to develop the complete circuit structure of a desired digital circuit without the help of another mechanism or any problem specific structuring. Experiments are presented that show the modular behaviour of the developmental system, as well as its ability to solve non-modular circuit problems.

This work is part of a project that aims to develop and operate integrated evolvable hardware systems using unconstrained evolution. Experiments are carried out on an evolvable hardware platform featuring both combinatorial and registered logic as well as sequential feedback loops. In order to be able to accurately assess the transient output of the system and at the same time speed up evolution, new fitness evaluation methods are introduced. These bitwise and hierarchical fitness evaluation methods are adapted and further developed specifically for hardware implementation. It is shown that the newly developed approaches are particularly powerful in coping with two important issues: computational ambiguities, which generally occur when evaluating binary strings, and transient effects resulting from measuring hardware output. On two combinatorial problems it is shown that the new fitness functions improve the performance of evolution and allow stable solutions to be found more reliably. The experiments are carried out with a recently developed hardware platform called reconfigurable integrated system array (RISA).

Biology presents incomparable, but desirable, characteristics compared to engineered systems. Inspired by biological development, we have devised a multi-layered design architecture that attempts to capture many of the favorable characteristics of biological mechanisms for application to design problems. In this paper we have identified and implemented essential features of Genetic Regulatory Networks (GRNs) and cell signaling so that our system exhibits self-organization which is reminiscent of aspects of biological systems.

In previous work, we have shown how an evolutionary algorithm with a clustered population can be used to concurrently discover multiple regulatory motifs present within the promoter sequences of co-expressed genes. In this paper, we extend the algorithm by co-evolving a population of Boolean classification rules in parallel with the motif population. Results using synthetic data suggest that this approach allows poorly conserved motifs to be identified in promoter sequences an order of magnitude longer than using population clustering alone, whilst results using muscle-specific promoter data show the algorithm is able to evolve meaningful sequence classifiers in parallel with motifs-suggesting that co-evolution provides a suitable framework for composite motif discovery within eukaryotic sequences.

A nonlinear dynamical system that exhibits limit cycle behaviour is investigated through numerical simulations of cardiac cells. This system's self-organizing behaviour is characterized aiming at harnessing it in an artificial system. Results of circuit simulations for different configurations of an architecture based on simple electronic elements are shown, characterizing self-organization in an artificial electronic circuit

The hippocampus region may help in the design of a neuro-controller used for path navigation of a robot. The spatial representation of the hippocampus can help provide a spatial mapping of the environment. The representation used is the place cell/place field representation. Place cell represents a population of neurons and place fields provide the spatial mapping of the environment. A place cell fires if the agent is believed to be in the environment for which its respective place field is representing. The hippocampus-inspired neural network model is not only spatially motivated but is also directionally driven. This model will be fully implemented onto an FPGA device to provide autonomy.

This study uses models of pyramidal neurons in the hippocampus to design a hardware spiking neural network neuro-controller model for the purpose of navigation. The neural network model consists of individual neurons modeled using the two-dimensional bio-inspired Izhikevich algorithm. The network is connected according to the connectivity within the hippocampus region, as this region is one of the regions in the brain that is responsible for path navigation. The information processed by the model helps provide navigation and creates memories. The neural network model is intended to be implemented onto a field programmable gate array (FPGA) device. This eliminates the need of an operating system to run the network, thus achieving autonomy.

Evolvable hardware offers much for the future of complex systems design. Evolutionary techniques not only have the potential for larger solution space coverage, but when implemented on hardware, also allow system designs to adapt to changes in the environment, including failures in system components. This article reviews a number of novel techniques, all based in the field of bio-inspired systems, that provide varying degrees of dependability over and above standard designs. In particular, three different techniques are considered: using FPGAs and ideas from developmental biology to create designs that possess emergent fault-tolerant properties, using FPGAs and continuous evolution to circumvent faults as and when they occur, and, finally, we consider a novel ASIC designed and built with bio-inspired systems in mind.

This paper describes a novel evolutionary algorithm for regulatory motif discovery in DNA promoter sequences. The algorithm uses data clustering to logically distribute the evolving population across the search space. Mating then takes place within local regions of the population, promoting overall solution diversity and encouraging discovery of multiple solutions. Experiments using synthetic data sets have demonstrated the algorithm's capacity to find position frequency matrix models of known regulatory motifs in relatively long promoter sequences. These experiments have also shown the algorithm's ability to maintain diversity during search and discover multiple motifs within a single population. The utility of the algorithm for discovering motifs in real biological data is demonstrated by its ability to find meaningful motifs within muscle-specific regulatory sequences.

Fault tolerance is a crucial operational aspect of biological systems and the self-repair capabilities of complex organisms far exceeds that of even the most advanced electronic devices. While many of the processes used by nature to achieve fault tolerance cannot easily be applied to silicon-based systems, in this paper we show that mechanisms loosely inspired by the operation of multicellular organisms can be transported to electronic systems to provide self-repair capabilities. Features such as dynamic routing, reconfiguration, and on-chip reprogramming can be invaluable for the realization of adaptive hardware systems and for the design of highly complex systems based on the kind of unreliable components that are likely to be introduced in the not-too-distant future. In this paper, we describe the implementation of fault tolerant features that address error detection and recovery through dynamic routing, reconfiguration, and on-chip reprogramming in a novel application specific integrated circuit. We take inspiration from three biological models:phylogenesis, ontogenesis,andepigenesis(hence the POE in POEtic). As in nature, our approach is based on a set of separate and complementary techniques that exploit the novel mechanisms provided by our device in the particular context of fault tolerance.

The objective of the work reported in this paper was the development of an application that combined evolution and learning on a hardware platform. This was achieved on two different platforms: a COTS FPGA and a new device specifically designed for bio-inspired implementations, termed the POEtic chip. The learning process is based around a spiking neural network with Hebbian learning.

The dynamics of variable length representations in evolutionary computation have been shown to be complex and different from those seen in standard fixed length genetic algorithms. This paper explores a simple variable length genetic algorithm with multiple chromosomes and its underlying dynamics when used for the onemax problem. The changes in length of the chromosomes are especially observed and explanations for these fluctuations are sought.

This paper documents new extensions to the selection model in genetic programming, designed to be analogous to the more complex behaviour of selection in natural evolution. Specifically, a negative assortative mating scheme is presented in conjunction with a model of psychological evolution, allowing the mating strategy to change throughout the evolutionary process. Results show that self-adaptive mate selection accelerates evolution for several well known test problems.

This paper introduces an evolutionary algorithm which uses multiple chromosomes to evolve solutions to a symbolic regression problem. Inspiration for this algorithm is provided by the existence of multiple chromosomes in natural evolution, particularly in plants. A multi-chromosomal system usually requires a dominance system and subsequently dominance in nature and in previous artificial evolutionary systems has also been considered. An implementation of a multi-chromosomal system is presented with initial results which support the use of multi-chromosomal techniques in evolutionary algorithms.

A novel error detection mechanism is demonstrated for integration into a hardware fault tolerant system. Inspiration is taken from principles of immunology to create a hardware immune system that runs in real-time hardware and continuously monitors a finite state machine architecture for errors. The work is demonstrated through immunisation of the ISCAS'89 benchmark state machine data set.

This paper considers the ability of an evolved circuit to acquire fault tolerance by including fault conditions within the fitness measure of the evolutionary process. A simple oscillator circuit, implemented on a Xilinx FPGA, showed a 12 fold increase in fault-tolerance when compared to a control oscillator using realistic faults.

The functionality model is a new approach in enzyme genetic programming which enables the evolution of variable length solutions whilst preserving local context. This paper introduces the model and presents an analysis of crossover and the evolution of program size.

A novel approach to hardware fault tolerance is demonstrated that takes inspiration from the human immune system as a method of fault detection. The human immune system is a remarkable system of interacting cells and organs that protect the body from invasion and maintains reliable operation even in the presence of invading bacteria or viruses. This paper seeks to address the field of electronic hardware fault tolerance from an immunological perspective with the aim of showing how novel methods based upon the operation of the immune system can both complement and create new approaches to the development of fault detection mechanisms for reliable hardware systems. In particular, it is shown that by use of partial matching, as prevalent in biological systems, high fault coverage can be achieved with the added advantage of reducing memory requirements. The development of a generic finite-state-machine immunization procedure is discussed that allows any system that can be represented in such a manner to be "immunized" against the occurrence of faulty operation. This is demonstrated by the creation of an immunized decade counter that can detect the presence of faults in real time.

The work reported in the paper follows from the hypothesis that better performance in certain domains of artificial evolution can be achieved by adhering more closely to the features that make natural evolution effective within biological systems. An important issue in evolutionary computation is the choice of solution representation. Genetic programming, whilst borrowing from biology in the evolutionary axis of behaviour, remains firmly rooted in the artificial domain with its use of a parse tree representation. Following concerns that this approach does not encourage solution evolvability, the paper presents an alternative method modelled upon representations used by biology. Early results are encouraging, demonstrating that the method is competitive when applied to problems in the area of combinatorial circuit design.

Since the advent of computers, numerous approaches have been taken to create hardware systems that provide a high degree of reliability even in the presence of errors. This paper addresses the problem from a biological perspective using the human immune system as a source of inspiration. The immune system uses many ingenious methods to provide reliable operation in the body and so may suggest how similar methods can be used in the future design of reliable computer systems. The paper addresses this challenge through the implementation of an immunised finite state machine-based counter. The proposed methods demonstrate how through a process of self/non-self-differentiation, the hardware immune system creates a set of tolerance conditions to monitor the change in states of the hardware. Potential faults may then be flagged, assessed and the appropriate recovery action taken.

Limiting the extent of error propagation when faults occur and localizing the subsequent error recovery are common concerns in the design of fault tolerant parallel processing systems. Both activities are made easier if the designer associates fault tolerance mechanisms with the underlying atomic actions of the system. With this in mind, the paper has investigated two methods for the identification of atomic actions in parallel processing systems described using CSP. Explicit trace evaluation forms the basis of the first algorithm, which enables a designer to analyze interprocess communications and thereby locate atomic action boundaries in a hierarchical fashion. The second method takes CSP descriptions of the parallel processes and uses structural arguments to infer the atomic action boundaries. This method avoids the difficulties involved with producing full trace sets, but does incur the penalty of a more complex algorithm.>

The fine granularity and reconfigurable nature of field-programmable gate arrays (FPGA's) suggest that defect-tolerant methods can be readily applied to these devices in order to increase their maximum economic sizes, through increased yield. This paper identifies the inability to contain faults within single cells and the need for fast reconfiguration as the key obstacles to obtaining a significant increase in yield. Monte Carlo defect modeling of the photolithographic layers of VLSI FPGA's is used as a foundation for the yield modeling of various defect-tolerant architectures. Results suggest that a medium-grain architecture is the best solution, offering a substantial increase in size without significant side effects. This architecture is shown to produce greater gate densities than the alternative approach of realizing ultralarge scale FPGA's-multichip modules.>

The problems of error detection and recovery are examined in a number of concurrent processes expressed as a set of communicating sequential processes (CSP). A method is proposed which uses a Petri net model to formally identify both the state and the state reachability tree of a distributed system. These are used to define systematically the boundaries of a conversation, including the recovery and test lines which are essential parts of the fault-tolerant mechanism. The techniques are implemented using the OCCAM programming language, which is derived from CSP. The application of this method is shown by a control example.