Humans possess a remarkable ability to react to unpredictable perturbations through immediate mechanical responses, which harness the visco-elastic properties of muscles to maintain balance. Inspired by this behavior, we propose a novel design of a robotic leg utilizing fibre jamming. The research highlights the potential of these structures for enhancing legged locomotion and adaptability in unpredictable environments.

In human–robot teams, human situational awareness is the operator’s conscious knowledge of the team’s states, actions, plans and their environment. Appropriate human situational awareness is critical to successful human–robot collaboration. In human–robot teaming, it is often assumed that the best and required level of situational awareness is knowing everything at all times. This view is problematic, because what a human needs to know for optimal team performance varies given the dynamic environmental conditions, task context, and roles and capabilities of team members. We explore this topic by interviewing 16 participants with active and repeated experience in diverse human–robot teaming applications. Based on analysis of these interviews, we derive a framework explaining the dynamic nature of required situational awareness in human–robot teaming. In addition, we identify a range of factors affecting the dynamic nature of required and actual levels of situational awareness (i.e., dynamic situational awareness), types of situational awareness inefficiencies resulting from gaps between actual and required situational awareness, and their main consequences. We also reveal various strategies, initiated by humans and robots, that assist in maintaining the required situational awareness. Our findings inform the implementation of accurate estimates of dynamic situational awareness and the design of user-adaptive human–robot interfaces. Therefore, this work contributes to the future design of more collaborative and effective human–robot teams.

Human operators in human-robot teams are commonly perceived to be critical for mission success. To explore the direct and perceived impact of operator input on task success and team performance, 16 real-world missions (10 h) were conducted based on the DARPA Subterranean Challenge. Missions involved deploying a heterogeneous team of robots to locate and identify artefacts such as climbing rope, drills and a mannequin representing a human survivor. Two conditions were evaluated: human operators that could control the robot team with state-of-the-art autonomy (Human-Robot Team) compared to autonomous missions without human operator input (Robot-Autonomy). Human interventions included creating waypoints to prioritise high-yield areas, and to navigate through error-prone spaces. Human-Robot Teams were often in directed autonomy mode (70% of mission time), found more items ( \(+\) 10.52%), traversed more distance ( \(+\) 12.71%), covered more unique ground ( \(+\) 10.56%), and longer time between safety-related events (34%). In routine conditions, both condition scores were comparable for artefacts, distance and coverage. Human-Robot Teams were faster at finding the first artefact but slower to respond to information from the robot team. Overall, operators contribute to mission-based outcomes, help to overcome environmental situations that can impede progress, and can assist robots to recover faster from difficult events.

In evolutionary robotics, Multi-Level Evolution (MLE) has been demonstrated for effective robot designs using a bottom-up approach, first evolving which materials to use for modular components and then how these components are connected into a functional robot design. This paper evaluates MLE robotic design, as an evolutionary design method on various task (robot ambulation) environments in comparison to human designed robots (pre-designed robot controller-morphology couplings). Results indicate that the MLE method evolves robots that are effective across increasingly difficult (locomotion) task environments, out-performing pre-designed robots, and thus provide further support for the efficacy of MLE as an evolutionary robotic design method. Furthermore, results indicate the MLE method enables the evolution of suitable robotic designs for various environments, where such designs would be non-intuitive and unlikely in conventional robotic design.

Modelling complex deformation for soft robotics provides a guideline to understand their behaviour, leading to safe interaction with the environment. However, building a surrogate model with high accuracy and fast inference speed can be challenging for soft robotics due to the nonlinearity from complex geometry, large deformation, material nonlinearity etc. The reality gap from surrogate models also prevents their further deployment in the soft robotics domain.In this study, we proposed a physics-informed Neural Networks (PINNs) named PINN-Ray to model complex deformation for a Fin Ray soft robotic gripper, which embeds the minimum potential energy principle from elastic mechanics and additional high-fidelity experimental data into the loss function of neural network for training. This method is significant in terms of its generalisation to complex geometry and robust to data scarcity as compared to other data-driven neural networks. Furthermore, it has been extensively evaluated to model the deformation of the Fin Ray finger under external actuation. PINN-Ray demonstrates improved accuracy as compared with Finite element modelling (FEM) after applying the data assimilation scheme to treat the sim-to-real gap. Additionally, we introduced our automated framework to design, fabricate soft robotic fingers, and characterise their deformation by visual tracking, which provides a guideline for the fast prototype of soft robotics.

Soft robotics has emerged as the standard solution for grasping deformable objects, and has proven invaluable for mobile robotic exploration in extreme environments. However, despite this growth, there are no widely adopted computational design tools that produce quality, manufacturable designs. To advance beyond the diminishing returns of heuristic bio-inspiration, the field needs efficient tools to explore the complex, non-linear design spaces present in soft robotics, and find novel high-performing designs. In this work, we investigate a hierarchical design optimization methodology which combines the strengths of topology optimization and quality diversity optimization to generate diverse and high-performance soft robots by evolving the design domain. The method embeds variably sized void regions within the design domain and evolves their size and position, to facilitating a richer exploration of the design space and find a diverse set of high-performing soft robots. We demonstrate its efficacy on both benchmark topology optimization problems and soft robotic design problems, and show the method enhances grasp performance when applied to soft grippers. Our method provides a new framework to design parts in complex design domains, both soft and rigid.

Topology optimization is a powerful design tool in structural engineering and other engineering problems. The design domain is discretized into elements, and a finite element method model is iteratively solved to find the element that maximizes the structure's performance. Although gradient-based solvers have been used to solve topology optimization problems, they may be susceptible to suboptimal solutions or difficulty obtaining feasible solutions, particularly in non-convex optimization problems. The presence of non-convexities can hinder convergence, leading to challenges in achieving the global optimum. With this in mind, we discuss in this article the application of the quality diversity approach to topological optimization problems. Quality diversity (QD) algorithms have shown promise in the research field of optimization and have many applications in engineering design, robotics, and games. MAP-Elites is a popular QD algorithm used in robotics. In soft robotics, the MAP-Elites algorithm has been used to optimize the shape and control of soft robots, leading to the discovery of new and efficient motion strategies. This article introduces an approach based on MAP-Elites to provide diverse designs for structural optimization problems. Three fundamental topology optimization problems are used for experimental testing, and the results demonstrate the ability of the proposed algorithm to generate diverse, high-performance designs for those problems. Furthermore, the proposed algorithm can be a valuable engineering design tool capable of creating novel and efficient designs.

Humans possess a remarkable ability to react to unpredictable perturbations through immediate mechanical responses, which harness the visco-elastic properties of muscles to maintain balance. Inspired by this behavior, we propose a novel design of a robotic leg utilizing fibre jammed structures as passive compliant mechanisms to achieve variable joint stiffness and damping. We developed multimaterial fibre jammed tendons with tunable mechanical properties, which can be 3-D printed in one-go without need for assembly. Through extensive numerical simulations and experimentation, we demonstrate the usefulness of these tendons for shock absorbance and maintaining joint stability. We investigate how they could be used effectively in a multijoint robotic leg by evaluating the relative contribution of each tendon to the overall stiffness of the leg. Further, we showcase the potential of these jammed structures for legged locomotion, highlighting how morphological properties of the tendons can be used to enhance stability in robotic legs.

A human supervisor’s Situational Awareness (SA) is a critical aspect for successful Human-Robot Teaming (HRT). SA has been estimated using different techniques; however, many of those are associated with various biases, including recall and overgeneralisation biases. A key SA metric is latency, the delay between the time the robotic system requires supervisor assistance and the time the supervisor identifies that need in HRT experiments. Eye movements are increasingly used to assess SA across a range of domains, enabling objective and continuous SA assessment. However, to date, only a small number of features have been evaluated for estimating different types of SA latencies. In this paper, we investigated how two types of SA latencies (perceptual and comprehending) correlate with eye movement data collected during a remote field experiment, where a human supervisor directed a team of robots in a smart farming context. We identified 39 instances of SA latencies (13 perceptual and 26 comprehending). These instances were used to identify how a human supervisor’s SA is affected by task context, and to evaluate correlations between five eye movement features and SA latencies. Two eye movement features related to fixation duration and saccade duration demonstrated very strong correlations ($r \approx - 0.8$ and $r \approx 0.85$). Our findings can be extended to estimate the real-time likelihood of the human experiencing SA latency.

Curriculum learning allows complex tasks to be mastered via incremental progression over 'stepping stone' goals towards a final desired behaviour. Typical implementations learn locomotion policies for challenging environments through gradual complexification of a terrain mesh generated through a parameterised noise function. To date, researchers have predominantly generated terrains from a limited range of noise functions, and the effect of the generator on the learning process is underrepresented in the literature. We compare popular noise-based terrain generators to two indirect encodings, CPPN and GAN. To allow direct comparison between both direct and indirect representations, we assess the impact of a range of representation-agnostic MAP-Elites feature descriptors that compute metrics directly from the generated terrain meshes. Next, performance and coverage are assessed when training a humanoid robot in a physics simulator using the PPO algorithm. Results describe key differences between the generators that inform their use in curriculum learning, and present a range of useful feature descriptors for uptake by the community.

We study the effects of injecting human-generated designs into the initial population of an evolutionary robotics experiment, where subsequent population of robots are optimised via a Genetic Algorithm and MAP-Elites. First, human participants interact via a graphical front-end to explore a directly-parameterised legged robot design space and attempt to produce robots via a combination of intuition and trial-and-error that perform well in a range of environments. Environments are generated whose corresponding high-performance robot designs range from intuitive to complex and hard to grasp. Once the human designs have been collected, their impact on the evolutionary process is assessed by replacing a varying number of designs in the initial population with human designs and subsequently running the evolutionary algorithm. Our results suggest that a balance of random and hand-designed initial solutions provides the best performance for the problems considered, and that human designs are most valuable when the problem is intuitive. The influence of human design in an evolutionary algorithm is a highly understudied area, and the insights in this paper may be valuable to the area of AI-based design more generally.

Fibre jamming is a new and understudied soft robotic mechanism that has previously found success in stiffness-tunable arms and fingers. However, to date researchers have not fully taken advantage of the freedom offered by contemporary fabrication techniques including multi-material 3D printing in the creation of fibre jamming structures. In this research, we present a novel, modular, multi-material, 3D printed, fibre jamming tendon unit for use in a stiffness-tunable compliant robotic ankle, or Jammkle. Its multimaterial printed design offers unparalleled design freedom, enabling application specific tendon design. We develop analytical and finite element models of the tendon unit, showing good agreement with experimental data and numerically explore the design space. Finally, we demonstrate a practical application by integrating multiple tendon units into a robotic ankle and perform extensive testing and characterisation. We show that the Jammkle outperforms comparative leg structures in terms of compliance, damping, and slip prevention.

Perception and interpretation of the terrain is essential for robot navigation, particularly in off-road areas, where terrain characteristics can be highly variable. When planning a path, features such as the terrain gradient and roughness should be considered, and they can jointly represent the traversability cost of the terrain. Despite this range of contributing factors, most cost maps are currently binary in nature, solely indicating traversible versus non-traversible areas. This work presents a joint local and global planning methodology for building continuous cost maps using LIDAR, based on a novel traversability representation of the environment. We investigate two approaches. The first, a statistical approach, computes terrain cost directly from the point cloud. The second, a learning-based approach, predicts an IMU response solely from geometric point cloud data using a 2D-Convolutional-LSTM neural network. This allows us to estimate the cost of a patch without directly driving over it, based on a data set that maps IMU signals to point cloud patches. Based on the terrain analysis, two continuous cost maps are generated to jointly select the optimal path considering distance and traversability cost for local navigation. We present a real-time terrain analysis strategy applicable for local planning, and furthermore demonstrate the straightforward application of the same approach in batch mode for global planning. Off-road autonomous driving experiments in a large and hybrid site illustrate the applicability of the method. We have made the code available online for users to test the method.

Keyhole surgery requires highly dexterous snake-like robotic arms capable of bending around anatomical obstacles to access clinical targets that diverge from the direct port-of-access. Design optimization for these robots under patient-specific anatomical constraints is still lacking, particularly concerning the critical metric of dexterity. In this article, we propose an end-to-end design and production workflow for patient-specific surgical manipulators, assessing dexterity using orientability constrained by task space obstacles. In our work, parametric evolutionary optimization maximizes dexterity in patient-specific task spaces for challenging knee arthroscopy operations. We implement our framework in the design of SnakeRaven—a 3-D printed tool to be attached to the RAVEN II surgical robot in a phantom study for knee arthroscopy. The solution achieved more than three times the dexterity of a state-of-the-art rigid instrument and more than twice the dexterity of a volume-based approach for the same task. We further assemble and validate this design by teleoperating the robot to reach the desired clinical targets in a phantom. We also investigate the changes in the design morphology to changes in the task objectives and found an advantage in task specialization. We also observe guidelines for achieving a dexterous design produced by our algorithms.

Jamming Grippers are a novel class of soft robotic actuators that can robustly grasp and manipulate objects of arbitrary shape. They are formed by placing a granular material within a flexible skin connected to a vacuum pump and function by pressing the un-jammed gripper against a target object and evacuating the air to transition the material to a jammed (solid) state, gripping the target object. However, due to the complex interactions between grain morphology and target object shape, much uncertainty still remains regarding optimal constituent grain shapes for specific gripping applications. We address this challenge by utilising a modern Evolutionary Algorithm, NSGA-III, combined with a Discrete Element Method soft robot model to perform a multi-objective optimisation of grain morphology for use in jamming grippers for a range of target object sizes. Our approach optimises the microscopic properties of the system to elicit bespoke functional granular material performance driven by the complex relationship between the individual particle morphologies and the related emergent behaviour of the bulk state. Results establish the important contribution of grain morphology to gripper performance and the critical role of local surface curvature and the length scale governed by the relative sizes of the grains and target object.

A long short-term memory neural network is used to provide a system model that captures the temporal-dynamics of a holonomic, fully-actuated aquatic surface vehicle. As is true in many fields, new developments in robotics often are made in simulation first before being applied to real systems. To simulate an aquatic or aerial robot, a dynamic system model of the robot is required. The more representative the dynamic model is of the real robot, the smaller the simulation-to-reality gap becomes. The performance of the neural network is compared against a classical parametric model, where coefficients of the parametric model were identified using the same data that was used to train the neural network. The results show that the neural network consistently outperforms the classical parametric model and significantly reduces the error between real velocities and estimated velocities. The neural network also demonstrated the ability to capture complex hydrodynamic effects that were not captured in the parametric model. In addition to the performance improvements, the neural network method can be easily adapted to similarly actuated aquatic vehicles by simply retraining, whereas the classical approach would require manual selection of new equation terms. The neural network model that was created has been used in a vehicle simulation and is presently being used as a research tool.

Telerobotic systems combined with miniaturised snake-like or elephant-trunk robotic arms can improve the ergonomics and accessibility in minimally invasive surgical tasks such as knee arthroscopy. Such systems, however, are usually designed in a specific and integral approach, making it expensive to adapt to various procedures or patient anatomies. 3D printed instruments with a detachable design can bring the benefits of patient-specific customisation, affordability, and adaptability to new clinical scenarios. However, the integration of such snake-like instruments to standard telerobotic systems can be challenging in terms of design and control. In this study, a teleoperation system is developed to control and steer the pose of SnakeRaven: a 3D printed, customisable snake-like end-effector attached to the RAVEN II platform for the application of fibre-optic knee arthroscopy. Algorithms for the parametric inverse kinematics and mapping between the RAVEN II joint space to the coupled tendon-driven rolling joints are developed. The controller is tested and validated on the physical prototype interfacing with the RAVEN II platform in a teleoperation experiment. A video demonstrating the main results of this paper can be found via https://youtu.be/ApJjR853kIQ

Robots operating in the real world will experience a range of different environments and tasks. It is essential for the robot to have the ability to adapt to its surroundings to work efficiently in changing conditions. Evolutionary robotics aims to solve this by optimizing both the control and body (morphology) of a robot, allowing adaptation to internal, as well as external factors. Most work in this field has been done in physics simulators, which are relatively simple and not able to replicate the richness of interactions found in the real world. Solutions that rely on the complex interplay among control, body, and environment are therefore rarely found. In this article, we rely solely on real-world evaluations and apply evolutionary search to yield combinations of morphology and control for our mechanically self-reconfiguring quadruped robot. We evolve solutions on two distinct physical surfaces and analyze the results in terms of both control and morphology. We then transition to two previously unseen surfaces to demonstrate the generality of our method. We find that the evolutionary search finds high-performing and diverse morphology-controller configurations by adapting both control and body to the different properties of the physical environments. We additionally find that morphology and control vary with statistical significance between the environments. Moreover, we observe that our method allows for morphology and control parameters to transfer to previously unseen terrains, demonstrating the generality of our approach.

A critical issue in evolutionary robotics is the transfer of controllers learned in simulation to reality. This is especially the case for small Unmanned Aerial Vehicles (UAVs), as the platforms are highly dynamic and susceptible to breakage. Previous approaches often require simulation models with a high level of accuracy, otherwise significant errors may arise when the well-designed controller is being deployed onto the targeted platform. Here we try to overcome the transfer problem from a different perspective, by designing a spiking neurocontroller which uses synaptic plasticity to cross the reality gap via online adaptation. Through a set of experiments we show that the evolved plastic spiking controller can maintain its functionality by self-adapting to model changes that take place after evolutionary training, and consequently exhibit better performance than its non-plastic counterpart.

The Lobula giant movement detector (LGMD) is an identified neuron of the locust that detects looming objects and triggers the insect's escape responses. Understanding the neural principles and network structure that leads to these fast and robust responses can facilitate the design of efficient obstacle avoidance strategies for robotic applications. Here, we present a neuromorphic spiking neural network model of the LGMD driven by the output of a neuromorphic dynamic vision sensor (DVS), which incorporates spiking frequency adaptation and synaptic plasticity mechanisms, and which can be mapped onto existing neuromorphic processor chips. However, as the model has a wide range of parameters and the mixed-signal analog-digital circuits used to implement the model are affected by variability and noise, it is necessary to optimize the parameters to produce robust and reliable responses. Here, we propose to use differential evolution (DE) and Bayesian optimization (BO) techniques to optimize the parameter space and investigate the use of self-adaptive DE (SADE) to ameliorate the difficulties of finding appropriate input parameters for the DE technique. We quantify the performance of the methods proposed with a comprehensive comparison of different optimizers applied to the model and demonstrate the validity of the approach proposed using recordings made from a DVS sensor mounted on an unmanned aerial vehicle (UAV).

We compare two representations used to define the morphology of legs for a hexapod robot, which are subsequently 3D printed. A leg morphology occupies a set of voxels in a voxel grid. One method, a direct representation, uses a collection of Bezier splines. The second, an indirect method, utilises CPPN-NEAT. In our first experiment, we investigate two strategies to post-process the CPPN output and ensure leg length constraints are met. The first uses an adaptive threshold on the output neuron, the second, previously reported in the literature, scales the largest generated artefact to our desired length. In our second experiment, we build on our past work that evolves the tibia of a hexapod to provide environment-specific performance benefits. We compare the performance of our direct and indirect legs across three distinct environments, represented in a high-fidelity simulator. Results are significant and support our hypothesis that the indirect representation allows for further exploration of the design space leading to improved fitness.

Granular materials, such as sands, soils, grains and powders, are ubiquitous in both natural and artificial systems. They are core to many industrial systems from mining and food production to pharmaceuticals and construction. Granular media display unique properties, including their ability to flow like a liquid at low densities and jam in to a solid state at high densities. Granular materials are used functionally in a number of industrial systems, where for example their insulating, energy absorption, filtration or vibration damping properties are variously exploited. A recent emerging industrial application is to utilise the jamming transition of granular matter (transition from a sold to a liquid) to create functional jammed systems such as universal grippers or soft robotic devices with potential broad impact across many industrial sectors. However, controlling the microscopic properties of such systems to elicit bespoke functional granular systems remains challenging due to the complex relationship between the individual particle morphologies and the related emergent behaviour of the bulk state. Here, we investigate the use of evolution to explore the functional landscapes of granular systems. We employ a superellipsoid representation of the particle shape which allows us to smoothly transition between a large variety of particle aspect ratios and angularities, and investigate the use of multi-component systems alongside homogenous granular arrangements. Results show the ability to successfully characterise a sample design space, and represents an important step towards the creation of bespoke jammed systems with a range of practical applications across broad swathes of industry.

We quantify the accuracy of various simulators compared to a real world robotic reaching and interaction task. Simulators are used in robotics to design solutions for real world hardware without the need for physical access. The `reality gap' prevents solutions developed or learnt in simulation from performing well, or at all, when transferred to real-world hardware. Making use of a Kinova robotic manipulator and a motion capture system, we record a ground truth enabling comparisons with various simulators, and present quantitative data for various manipulation-oriented robotic tasks. We show the relative strengths and weaknesses of numerous contemporary simulators, highlighting areas of significant discrepancy, and assisting researchers in the field in their selection of appropriate simulators for their use cases.

This research considers the task of evolving the physical structure of a robot to enhance its performance in various environments, which is a significant problem in the field of Evolutionary Robotics. Inspired by the fields of evolutionary art and sculpture, we evolve only targeted parts of a robot, which simplifies the optimisation problem compared to traditional approaches that must simultaneously evolve both (actuated) body and brain. Exploration fidelity is emphasised in areas of the robot most likely to benefit from shape optimisation, whilst exploiting existing robot structure and control. Our approach uses a Genetic Algorithm to optimise collections of Bezier splines that together define the shape of a legged robot's tibia, and leg performance is evaluated in parallel in a high-fidelity simulator. The leg is represented in the simulator as 3D-printable file, and as such can be readily instantiated in reality. Provisional experiments in three distinct environments show the evolution of environment-specific leg structures that are both high-performing and notably different to those evolved in the other environments. This proof-of-concept represents an important step towards the environment-dependent optimisation of performance-critical components for a range of ubiquitous, standard, and already-capable robots that can carry out a wide variety of tasks.

Self-adaptive parameters are increasingly used in the field of Evolutionary Robotics, as they allow key evolutionary rates to vary autonomously in a context-sensitive manner throughout the optimisation process. A significant limitation to self-adaptive mutation is that rates can be set unfavourably which hinders convergence. Rate restarts are typically employed to remedy this, but thus far have only been applied in Evolutionary Robotics for mutation-only algorithms. This paper focuses on the level at which evolutionary rate restarts are applied in population-based algorithms with >1 evolutionary operator. After testing on a real hexacopter hovering task, we conclude that individual-level restarting results in higher fitness solutions without fitness stagnation, and population restarts provide a more stable rate evolution. Without restarts, experiments can become stuck in suboptimal controller/rate combinations which can be difficult to escape from.

Evolutionary algorithms have previously shown promise in generating controllers for legged robots. Multiple evaluations across many evolutionary generations are typically required - simulators are frequently used to accommodate this. However, performance degradation is frequently observed when transferring controllers from simulation to reality due to inconsistencies between the two. In this paper we demonstrate a testbed that permits repeated, direct evolution of hexapod controllers as a closed-loop system. The testbed uses a two-stage evolutionary process. In stage 1, a multi-objective evolutionary algorithm spreads a population of controllers across a space of desirable criteria. The second stage allows for specific criteria to be selected for on a per-mission basis, with promising initial controller parameters taken from the first stage. As the optimisation occurs directly on the robot, performance is guaranteed. Furthermore, controllers can be made specific to irregularities in e.g., motor wear, and robot mass distribution, creating controllers that are sensitive to the hardware state of the individual robot.

We describe an experimental platform that uses differential evolution to automatically discover high-performance multirotor controllers. All control parameters are tuned simultaneously, no modeling is required, and, as the evolution occurs on a real multirotor, the controllers are guaranteed to work in reality. The platform is able to run back-to-back experiments for over a week without human intervention. Self-adaptive rates are shown improve solution fitness whilst (at least) maintaining convergence times. This platform is the first to allow for evolutionary robotics experimentation to occur safely and repeatedly on real multirotors. High-performance controllers are evolved despite noisy fitness evaluations, real-world sensory noise, low population sizes, and limited numbers of evolutionary generations.

We describe an experimental platform that uses an evolutionary algorithm to automatically tune the gains of a cascaded PID quadcopter controller. All parameters are tuned simultaneously, few platform assumptions are necessary, and no modeling is required. The platform is able to run back-to-back experiments for over 24 hours without human intervention. In a sample experiment, we apply the system to solve a hovering task - the behaviors generated by an initially-random population of gain vectors are evaluated and gradually improved, with the attainment of high fitness hover controllers reported within 12 hours.

Neuromorphic computing – brain-like computing in hardware – typically requires myriad complimentary metal oxide semiconductor spiking neurons interconnected by a dense mesh of nanoscale plastic synapses. Memristors are frequently cited as strong synapse candidates due to their statefulness and potential for low-power implementations. To date, plentiful research has focused on the bipolar memristor synapse, which is capable of incremental weight alterations and can provide adaptive self-organisation under a Hebbian learning scheme. In this paper, we consider the unipolar memristor synapse – a device capable of non-Hebbian switching between only two states (conductive and resistive) through application of a suitable input voltage – and discuss its suitability for neuromorphic systems. A self-adaptive evolutionary process is used to autonomously find highly fit network configurations. Experimentation on two robotics tasks shows that unipolar memristor networks evolve task-solving controllers faster than both bipolar memristor networks and networks containing constant non-plastic connections whilst performing at least comparably.

We investigate the automatic development of robust quadrotor neurocontrollers based on spiking neural networks. A self-adaptive evolutionary algorithm is used to generate highutility topology/weight combinations in the networks, and a simple synaptic plasticity mechanism provides some degree of in-trial adaptation. Incremental evolution gradually increases the severity of environmental conditions that the agent can successfully handle. Results compare the spiking networks to tuned Proportional/Integral/Derivative controllers and feedforward neural networks for waypointholding experiments in varied atmospheric conditions. It is shown that the spiking controllers are able to maintain a closer distance to the waypoint than the comparative controllers, and more effectively deal with more challenging environmental conditions.

Neuromorphic computing is a brainlike information processing paradigm that requires adaptive learning mechanisms. A spiking neuro-evolutionary system is used for this purpose; plastic resistive memories are implemented as synapses in spiking neural networks. The evolutionary design process exploits parameter self-adaptation and allows the topology and synaptic weights to be evolved for each network in an autonomous manner. Variable resistive memories are the focus of this research; each synapse has its own conductance profile which modifies the plastic behaviour of the device and may be altered during evolution. These variable resistive networks are evaluated on a noisy robotic dynamic-reward scenario against two static resistive memories and a system containing standard connections only. The results indicate that the extra behavioural degrees of freedom available to the networks incorporating variable resistive memories enable them to outperform the comparative synapse types.

This paper presents a spiking neuroevolutionary system which implements memristors as plastic connections, i.e., whose weights can vary during a trial. The evolutionary design process exploits parameter self-adaptation and variable topologies, allowing the number of neurons, connection weights, and interneural connectivity pattern to emerge. By comparing two phenomenological real-world memristor implementations with networks comprised of: 1) linear resistors, and 2) constant-valued connections, we demonstrate that this approach allows the evolution of networks of appropriate complexity to emerge whilst exploiting the memristive properties of the connections to reduce learning time. We extend this approach to allow for heterogeneous mixtures of memristors within the networks; our approach provides an in-depth analysis of network structure. Our networks are evaluated on simulated robotic navigation tasks; results demonstrate that memristive plasticity enables higher performance than constant-weighted connections in both static and dynamic reward scenarios, and that mixtures of memristive elements provide performance advantages when compared to homogeneous memristive networks.

This paper presents a spiking neuro-evolutionary system which implements memristors as neuromodulatory connections, i.e. whose weights can vary during a trial. The evolutionary design process exploits parameter self-adaptation and a constructionist approach, allowing the number of neurons, connection weights, and inter-neural connectivity pattern to be evolved for each network. Additionally, each memristor has its own conductance profile, which alters the neuromodulatory behaviour of the memristor and may be altered during the application of the GA. We demonstrate that this approach allows the evolutionary process to discover beneficial memristive behaviours at specific points in the networks. We evaluate our approach against two phenomenological real-world memristive implementations, a theoretical "linear memristor", and a system containing standard connections only. Performance is evaluated on a simulated robotic navigation task.

This paper presents a spiking neuro-evolutionary system which implements memristors as neuromodulatory connections, i.e. whose weights can vary during a trial. The evolutionary design process exploits parameter self-adaptation and a constructionist approach, allowing the number of neurons, connection weights, and inter-neural connectivity pattern to be evolved for each network. We demonstrate that this approach allows the evolution of networks of appropriate complexity to emerge whilst exploiting the memristive properties of the connections to reduce learning time. We evaluate two phenomenological real-world memristive implementations against a theoretical “linear memristor”, and a system containing standard connections only. Our networks are evaluated on a simulated robotic navigation task.

This paper presents a Learning Classifier System (LCS) where each traditional rule is represented by a spiking neural network, a type of network with dynamic internal state. The evolutionary design process exploits parameter self-adaptation and a constructionist approach, providing the system with a flexible knowledge representation. It is shown how this approach allows for the evolution of networks of appropriate complexity to emerge whilst solving a continuous maze environment. Additionally, we extend the system to allow for temporal state decomposition. We evaluate our spiking neural LCS against one that uses Multi Layer Perceptron rules.

This paper presents a Learning Classifier System (LCS) where each classifier condition is represented by a feed-forward multi-layered perceptron (MLP) network. Adaptive behavior is realized through the use of self-adaptive parameters and neural constructivism, providing the system with a flexible knowledge representation. The approach allows for the evolution of networks of appropriate complexity to solve a continuous maze environment, here using either discrete-valued actions, continuous-valued actions, or continuous-valued actions of continuous duration. In each case, it is shown that the neural LCS employed is capable of developing optimal solutions to the reinforcement learning task presented in this paper.

For artificial entities to achieve high degrees of autonomy they will need to display appropriate adaptability. In this sense adaptability includes representational flexibility guided by the environment at any given time. This paper presents the use of constructivism-inspired mechanisms within a neural learning classifier system which exploits parameter self-adaptation as an approach to realize such behaviour. The system uses a rule structure in which each is represented by an artificial neural network. It is shown that appropriate internal rule complexity emerges during learning at a rate controlled by the system. Further, the use of computed predictions is shown possible.