David Howard

Prabhat Kumar, Chandra Prakash, Josh Pinskier et al.

This paper presents a systematic topology optimization framework for designing a soft pneumatic gripper (SPG), explicitly considering the design-dependent nature of the actuating load. The load is modeled using Darcy's law with an added drainage term. A 2D soft arm unit is optimized by formulating it as a compliant mechanism design problem using the robust formulation. The problem is posed as a min-max optimization, where the output deformations of blueprint and eroded designs are considered. A volume constraint is imposed on the blueprint part, while a strain-energy constraint is enforced on the eroded part. The MMA is employed to solve the optimization problem and obtain the optimized soft unit. Finite element analysis with the Ogden material model confirms that the optimized 2D unit outperforms a conventional rectangular design under pneumatic loading. The optimized 2D unit is extruded to obtain a 3D module, and ten such units are assembled to create a soft arm. Deformation profiles of the optimized arm are analysed under different pressure loads. Four arms are 3D-printed and integrated with a supporting structure to realize the proposed SPG. The gripping performance of the SPG is demonstrated on objects with different weights, sizes, stiffness, and shapes.

Yue Xie, Xing Wang, Fumiya Iida et al.

Computational design can excite the full potential of soft robotics that has the drawbacks of being highly nonlinear from material, structure, and contact. Up to date, enthusiastic research interests have been demonstrated for individual soft fingers, but the frame design space (how each soft finger is assembled) remains largely unexplored. Computationally design remains challenging for the finger-based soft gripper to grip across multiple geometrical-distinct object types successfully. Including the design space for the gripper frame can bring huge difficulties for conventional optimisation algorithms and fitness calculation methods due to the exponential growth of high-dimensional design space. This work proposes an automated computational design optimisation framework that generates gripper diversity to individually grasp geometrically distinct object types based on a quality-diversity approach. This work first discusses a significantly large design space (28 design parameters) for a finger-based soft gripper, including the rarely-explored design space of finger arrangement that is converted to various configurations to arrange individual soft fingers. Then, a contact-based Finite Element Modelling (FEM) is proposed in SOFA to output high-fidelity grasping data for fitness evaluation and feature measurements. Finally, diverse gripper designs are obtained from the framework while considering features such as the volume and workspace of grippers. This work bridges the gap of computationally exploring the vast design space of finger-based soft grippers while grasping large geometrically distinct object types with a simple control scheme.

Yao Yao, David Howard, Perla Maiolino

Task-driven design of soft robots requires models that are physically accurate and computationally efficient, while remaining transferable across actuator designs and task scenarios. However, existing modeling approaches typically face a fundamental trade-off between physical fidelity and computational efficiency, which limits model reuse across design and task variations and constrains scalable task-driven optimization. This paper presents a unified reduced-order finite element method (FEM)-based surrogate modeling pipeline for generalized task-driven soft robot design. High-fidelity FEM simulations characterize actuator behavior at the modular level, from which compact surrogate joint models are constructed for evaluation within a pseudo-rigid body model (PRBM). A meta-model maps actuator design parameters to surrogate representations, enabling rapid instantiation across a parameterized actuator family. The resulting models are embedded into a PRBM-based simulation environment, supporting task-level simulation and optimization under realistic physical constraints. The proposed pipeline is validated through sim-to-real transfer across multiple actuator types, including bellow-type pneumatic actuators and a tendon-driven soft finger, as well as two task-driven design studies: soft gripper co-design via Reinforcement Learning (RL) and 3D actuator shape matching via evolutionary optimization. The results demonstrate high accuracy, efficiency, and reliable reuse, providing a scalable foundation for autonomous task-driven soft robot design.

Jessica Gumowski, Krishna Manaswi Digumarti, David Howard

Organisms in nature, such as Cephalopods and Pachyderms, exploit stiffness modulation to achieve amazing dexterity in the control of their appendages. In this paper, we explore the phenomenon of layer jamming, which is a popular stiffness modulation mechanism that provides an equivalent capability for soft robots. More specifically, we focus on mechanical layer jamming, which we realise through two-layer multi material structure with tooth-like protrusions. We identify key design parameters for mechanical layer jamming systems, including the ability to modulate stiffness, and perform a variety of comprehensive tests placing the specimens under bending and torsional loads to understand the influence of our selected design parameters (mainly tooth geometry) on the performance of the jammed structures. We note the ability of these structures to produce a peak change in stiffness of 5 times in bending and 3.2 times in torsion. We also measure the force required to separate the two jammed layers, an often ignored parameter in the study of jamming-induced stiffness change. This study aims to shed light on the principled design of mechanical layer jammed systems and guide researchers in the selection of appropriate designs for their specific application domains.

Hashini Senaratne, Richard Attfield, Samith Widhanapathirana et al.

Maintaining situational awareness (SA) is critical in human-robot teams. Yet, under high workload and dynamic conditions, operators often experience SA gaps. Automated detection of SA gaps could provide timely assistance for operators. However, conventional SA measures either disrupt task flow or cannot capture real-time fluctuations, limiting their operational utility. To the best of our knowledge, no publicly available dataset currently supports the systematic evaluation of online human SA assessment in human-robot teaming. To advance the development of online SA assessment tools, we introduce HRI-SA, a multimodal dataset from 30 participants in a realistic search-and-rescue human-robot teaming context, incorporating eye movements, pupil diameter, biosignals, user interactions, and robot data. The experimental protocol included predefined events requiring timely operator assistance, with ground truth SA latency of two types (perceptual and comprehension) systematically obtained by measuring the time between assistance need onset and resolution. We illustrate the utility of this dataset by evaluating standard machine learning models for detecting perceptual SA latencies using generic eye-tracking features and contextual features. Results show that eye-tracking features alone effectively classified perceptual SA latency (recall=88.91%, F1=67.63%) using leave-one-group-out cross-validation, with performance improved through contextual data fusion (recall=91.51%, F1=80.38%). This paper contributes the first public dataset supporting the systematic evaluation of SA throughout a human-robot teaming mission, while also demonstrating the potential of generic eye-tracking features for continuous perceptual SA latency detection in remote human-robot teaming.

Humphrey Munn, Brendan Tidd, Peter Böhm et al.

Reinforcement Learning (RL) robot controllers usually aggregate many task objectives into one scalar reward. While large-scale proximal policy optimisation (PPO) has enabled impressive results such as robust robot locomotion in the real world, many tasks still require careful reward tuning and are brittle to local optima. Tuning cost and sub-optimality grow with the number of objectives, limiting scalability. Modelling reward vectors and their trade-offs can address these issues; however, multi-objective methods remain underused in RL for robotics because of computational cost and optimisation difficulty. In this work, we investigate the conflict between gradient contributions for each objective that emerge from scalarising the task objectives. In particular, we explicitly address the conflict between task-based rewards and terms that regularise the policy towards realistic behaviour. We propose GCR-PPO, a modification to actor-critic optimisation that decomposes the actor update into objective-wise gradients using a multi-headed critic and resolves conflicts based on the objective priority. Our methodology, GCR-PPO, is evaluated on the well-known IsaacLab manipulation and locomotion benchmarks and additional multi-objective modifications on two related tasks. We show superior scalability compared to parallel PPO (p = 0.04), without significant computational overhead. We also show higher performance with more conflicting tasks. GCR-PPO improves on large-scale PPO with an average improvement of 9.5%, with high-conflict tasks observing a greater improvement. The code is available at https://github.com/humphreymunn/GCR-PPO.

Humphrey Munn, Brendan Tidd, Peter Bohm et al.

Deploying learned control policies on humanoid robots is challenging: policies that appear robust in simulation can execute confidently in out-of-distribution (OOD) states after Sim-to-Real transfer, leading to silent failures that risk hardware damage. Although anomaly detection can mitigate these failures, prior methods are often incompatible with high-rate control, poorly calibrated at the extremely low false-positive rates required for practical deployment, or operate as black boxes that provide a binary stop signal without explaining why the robot drifted from nominal behavior. We present RAPT, a lightweight, self-supervised deployment-time monitor for 50Hz humanoid control. RAPT learns a probabilistic spatio-temporal manifold of nominal execution from simulation and evaluates execution-time predictive deviation as a calibrated, per-dimension signal. This yields (i) reliable online OOD detection under strict false-positive constraints and (ii) a continuous, interpretable measure of Sim-to-Real mismatch that can be tracked over time to quantify how far deployment has drifted from training. Beyond detection, we introduce an automated post-hoc root-cause analysis pipeline that combines gradient-based temporal saliency derived from RAPT's reconstruction objective with LLM-based reasoning conditioned on saliency and joint kinematics to produce semantic failure diagnoses in a zero-shot setting. We evaluate RAPT on a Unitree G1 humanoid across four complex tasks in simulation and on physical hardware. In large-scale simulation, RAPT improves True Positive Rate (TPR) by 37% over the strongest baseline at a fixed episode-level false positive rate of 0.5%. On real-world deployments, RAPT achieves a 12.5% TPR improvement and provides actionable interpretability, reaching 75% root-cause classification accuracy across 16 real-world failures using only proprioceptive data.

Rafael Oliveira, Dino Sejdinovic, David Howard et al.

The process of calibrating computer models of natural phenomena is essential for applications in the physical sciences, where plenty of domain knowledge can be embedded into simulations and then calibrated against real observations. Current machine learning approaches, however, mostly rely on rerunning simulations over a fixed set of designs available in the observed data, potentially neglecting informative correlations across the design space and requiring a large amount of simulations. Instead, we consider the calibration process from the perspective of Bayesian adaptive experimental design and propose a data-efficient algorithm to run maximally informative simulations within a batch-sequential process. At each round, the algorithm jointly estimates the parameters of the posterior distribution and optimal designs by maximising a variational lower bound of the expected information gain. The simulator is modelled as a sample from a Gaussian process, which allows us to correlate simulations and observed data with the unknown calibration parameters. We show the benefits of our method when compared to related approaches across synthetic and real-data problems.

David Howard, Jack O'Connor, Jordan Letchford et al.

The application of granular jamming in soft robotics is a recent and promising new technology offer exciting possibilities for creating higher performance robotic devices. Granular jamming is achieved via the application of a vacuum pressure inside a membrane containing particulate matter, and is particularly interesting from a design perspective, as a myriad of design parameters can potentially be exploited to induce a diverse variety of useful behaviours. To date, the effect of variables such as grain shape and size, as well as membrane material, have been studied as a means of inducing bespoke gripping performance, however the other main contributing factor, membrane morphology, has not been studied due to its particular complexities in both accurate modelling and fabrication. This research presents the first study that optimises membrane morphology for granular jamming grippers, combining multi-material 3D printing and an evolutionary algorithm to search through a varied morphology design space in materio. Entire generations are printed in a single run and gripper retention force is tested and used as a fitness measure. Our approach is relatively scalable, circumvents the need for modelling, and guarantees the real-world performance of the grippers considered. Results show that membrane morphology is a key determinant of gripper performance. Common high performance designs are seen to optimise all three of the main identified mechanisms by which granular grippers generate grip force, are significantly different from a standard gripper morphology, and generalise well across a range of test objects.

Raghav Mishra, Tyson Philips, Gary W. Delaney et al.

Granular jamming is a popular soft robotics technology that has seen recent widespread applications including industrial gripping, surgical robotics and haptics. However, to date the field has not fully exploited the fundamental science of the jamming phase transition, which has been rigorously studied in the field of statistical and condensed matter physics. This work introduces vibration as a means to improve the properties of granular jamming grippers through vibratory fluidisation and the exploitation of resonant modes within the granular material. We show that vibration in soft jamming grippers can improve holding strength, reduce the downwards force needed for the gripping action, and lead to a simplified setup where the second air pump, generally used for unjamming, could be removed. In a series of studies, we show that frequency and amplitude of the waveforms are key determinants to performance, and that jamming performance is also dependent on temporal properties of the induced waveform. We hope to encourage further study in transitioning fundamental jamming mechanisms into a soft robotics context to improve performance and increase diversity of applications for granular jamming grippers.

James Brett, Katrina Lo Surdo, Lauren Hanson et al.

Fibre jamming is a relatively new and understudied soft robotic mechanism that has previously found success when used in stiffness-tuneable 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-tuneable compliant robotic ankle, or Jammkle. We describe the design and fabrication of the Jammkle and highlight its advantages compared to examples from modern literature. We develop a multiphysics model of the tendon unit, showing good agreement with experimental data. 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.

Jack Collins, Ross Brown, Jürgen Leitner et al.

We propose a novel iterative approach for crossing the reality gap that utilises live robot rollouts and differentiable physics. Our method, RealityGrad, demonstrates for the first time, an efficient sim2real transfer in combination with a real2sim model optimisation for closing the reality gap. Differentiable physics has become an alluring alternative to classical rigid-body simulation due to the current culmination of automatic differentiation libraries, compute and non-linear optimisation libraries. Our method builds on this progress and employs differentiable physics for efficient trajectory optimisation. We demonstrate RealitGrad on a dynamic control task for a serial link robot manipulator and present results that show its efficiency and ability to quickly improve not just the robot's performance in real world tasks but also enhance the simulation model for future tasks. One iteration of RealityGrad takes less than 22 minutes on a desktop computer while reducing the error by 2/3, making it efficient compared to other sim2real methods in both compute and time. Our methodology and application of differentiable physics establishes a promising approach for crossing the reality gap and has great potential for scaling to complex environments.

David Howard, Jack O'Connor, James Brett et al.

Granular jamming is a popular soft actuation mechanism that provides high stiffness variability with minimum volume variation. Jamming is particularly interesting from a design perspective, as a myriad of design parameters can potentially be exploited to induce a diverse variety of useful behaviours. To date, grain shape has been largely ignored. Here, we focus on the use of 3D printing to expose design variables related to grain shape and size. Grains are represented by parameterised superquadrics (superellipsoids); four diverse shapes are investigated along with three size variations. Grains are 3D printed at high resolution and performance is assessed in experimental pull-off testing on a variety of benchmark test objects. We show that grain shape and size are key determinants in granular gripping performance. Moreover, there is no universally-optimal grain shape for gripping. Optical imaging assesses the accuracy of printed shapes compared to their ideal models. Results suggest that optimisation of grain shape is a key enabler for high-performance, bespoke, actuation behaviour and can be exploited to expand the range and performance of granular grippers across a range of diverse usage scenarios.

Ahmadreza Ahmadi, Tønnes Nygaard, Navinda Kottege et al.

Legged robots are popular candidates for missions in challenging terrains due to the wide variety of locomotion strategies they can employ. Terrain classification is a key enabling technology for autonomous legged robots, as it allows the robot to harness their innate flexibility to adapt their behaviour to the demands of their operating environment. In this paper, we show how highly capable machine learning techniques, namely gated recurrent neural networks, allow our target legged robot to correctly classify the terrain it traverses in both supervised and semi-supervised fashions. Tests on a benchmark data set shows that our time-domain classifiers are well capable of dealing with raw and variable-length data with small amount of labels and perform to a level far exceeding the frequency-domain classifiers. The classification results on our own extended data set opens up a range of high-performance behaviours that are specific to those environments. Furthermore, we show how raw unlabelled data is used to improve significantly the classification results in a semi-supervised model.

Shelvin Chand, David Howard

Multi-level evolution is a bottom-up robotic design paradigm which decomposes the design problem into layered sub-tasks that involve concurrent search for appropriate materials, component geometry and overall morphology. Each of the three layers operate with the goal of building a library of diverse candidate solutions which will be used either as building blocks for the layer above or provided to the decision maker for final use. In this paper we provide a theoretical discussion on the concepts and technologies that could potentially be used as building blocks for this framework.

Tonnes F. Nygaard, David Howard, Kyrre Glette

Evolutionary algorithms offer great promise for the automatic design of robot bodies, tailoring them to specific environments or tasks. Most research is done on simplified models or virtual robots in physics simulators, which do not capture the natural noise and richness of the real world. Very few of these virtual robots are built as physical robots, and the few that are will rarely be further improved in the actual environment they operate in, limiting the effectiveness of the automatic design process. We utilize our shape-shifting quadruped robot, which allows us to optimize the design in its real-world environment. The robot is able to change the length of its legs during operation, and is robust enough for complex experiments and tasks. We have co-evolved control and morphology in several different scenarios, and have seen that the algorithm is able to exploit the dynamic morphology solely through real-world experiments.

David Howard, Thomas Lowe, Wade Geles

We combine MAP-Elites and highly parallelisable simulation to explore the design space of a class of large legged robots, which stand at around 2m tall and whose design and construction is not well-studied. The simulation is modified to account for factors such as motor torque and weight, and presents a reasonable fidelity search space. A novel robot encoding allows for bio-inspired features such as legs scaling along the length of the body. The impact of three possible control generation schemes are assessed in the context of body-brain co-evolution, showing that even constrained problems benefit strongly from coupling-promoting mechanisms. A two stage process in implemented. In the first stage, a library of possible robots is generated, treating user requirements as constraints. In the second stage, the most promising robot niches are analysed and a suite of human-understandable design rules generated related to the values of their feature variables. These rules, together with the library, are then ready to be used by a (human) robot designer as a Design Assist tool.

Tønnes F. Nygaard, Charles P. Martin, David Howard et al.

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 between control, body, and environment are therefore rarely found. In this paper, 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.

Jack Collins, Ross Brown, Jurgen Leitner et al.

The large demand for simulated data has made the reality gap a problem on the forefront of robotics. We propose a method to traverse the gap by tuning available simulation parameters. Through the optimisation of physics engine parameters, we show that we are able to narrow the gap between simulated solutions and a real world dataset, and thus allow more ready transfer of leaned behaviours between the two. We subsequently gain understanding as to the importance of specific simulator parameters, which is of broad interest to the robotic machine learning community. We find that even optimised for different tasks that different physics engine perform better in certain scenarios and that friction and maximum actuator velocity are tightly bounded parameters that greatly impact the transference of simulated solutions.

Huanneng Qiu, Matthew Garratt, David Howard et al.

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.

Jack Collins, Jessie McVicar, David Wedlock et al.

We present a benchmark to facilitate simulated manipulation; an attempt to overcome the obstacles of physical benchmarks through the distribution of a real world, ground truth dataset. Users are given various simulated manipulation tasks with assigned protocols having the objective of replicating the real world results of a recorded dataset. The benchmark comprises of a range of metrics used to characterise the successes of submitted environments whilst providing insight into their deficiencies. We apply our benchmark to two simulation environments, PyBullet and V-Rep, and publish the results. All materials required to benchmark an environment, including protocols and the dataset, can be found at the benchmarks' website https://research.csiro.au/robotics/manipulation-benchmark/.

Llewyn Salt, David Howard, Giacomo Indiveri et al.

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 lead 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 analogue-digital circuits used to implement the model are affected by variability and noise, it is necessary to optimise the parameters to produce robust and reliable responses. Here we propose to use Differential Evolution (DE) and Bayesian Optimisation (BO) techniques to optimise the parameter space and investigate the use of Self-Adaptive Differential Evolution (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 optimisers applied to the model, and demonstrate the validity of the approach proposed using recordings made from a DVS sensor mounted on a UAV.

Huanneng Qiu, Matthew Garratt, David Howard et al.

Spiking Neural Networks are powerful computational modelling tools that have attracted much interest because of the bioinspired modelling of synaptic interactions between neurons. Most of the research employing spiking neurons has been non-behavioural and discontinuous. Comparatively, this paper presents a recurrent spiking controller that is capable of solving nonlinear control problems in continuous domains using a popular topology evolution algorithm as the learning mechanism. We propose two mechanisms necessary to the decoding of continuous signals from discrete spike transmission: (i) a background current component to maintain frequency sufficiency for spike rate decoding, and (ii) a general network structure that derives strength from topology evolution. We demonstrate that the proposed spiking controller can learn significantly faster to discover functional solutions than sigmoidal neural networks in solving a classic nonlinear control problem.

Jack Collins, Ben Cottier, David Howard

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.

David Howard, Agoston E. Eiben, Danielle Frances Kennedy et al.

Natural lifeforms specialise to their environmental niches across many levels; from low-level features such as DNA and proteins, through to higher-level artefacts including eyes, limbs, and overarching body plans. We propose Multi-Level Evolution (MLE), a bottom-up automatic process that designs robots across multiple levels and niches them to tasks and environmental conditions. MLE concurrently explores constituent molecular and material 'building blocks', as well as their possible assemblies into specialised morphological and sensorimotor configurations. MLE provides a route to fully harness a recent explosion in available candidate materials and ongoing advances in rapid manufacturing processes. We outline a feasible MLE architecture that realises this vision, highlight the main roadblocks and how they may be overcome, and show robotic applications to which MLE is particularly suited. By forming a research agenda to stimulate discussion between researchers in related fields, we hope to inspire the pursuit of multi-level robotic design all the way from material to machine.

Jack Collins, David Howard, Jürgen Leitner

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 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. All code and parameter listings are publicly available from: https://bitbucket.csiro.au/scm/~col549/quantifying-the-reality-gap-in-robotic-manipulation-tasks.git .

Jack Collins, Wade Geles, David Howard et al.

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.

Llewyn Salt, David Howard, Giacomo Indiveri et al.

The Lobula Giant Movement Detector (LGMD) is a an identified neuron of the locust that detects looming objects and triggers its escape responses. Understanding the neural principles and networks that lead to these fast and robust responses can lead to the design of efficient facilitate obstacle avoidance strategies in 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 has been optimised to produce robust and reliable responses in the face of the constraints and variability of its mixed signal analogue-digital circuits. As this LGMD model has many parameters, we use the Differential Evolution (DE) algorithm to optimise its parameter space. We also investigate the use of Self-Adaptive Differential Evolution (SADE) which has been shown to ameliorate the difficulties of finding appropriate input parameters for DE. We explore the use of two biological mechanisms: synaptic plasticity and membrane adaptivity in the LGMD. We apply DE and SADE to find parameters best suited for an obstacle avoidance system on an unmanned aerial vehicle (UAV), and show how it outperforms state-of-the-art Bayesian optimisation used for comparison.

David Howard, Larry Bull, Ben De Lacy Costello

Neuromorphic computing --- brainlike computing in hardware --- typically requires myriad CMOS spiking neurons interconnected by a dense mesh of nanoscale plastic synapses. Memristors are frequently citepd 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 a two robotics tasks shows that unipolar memristor networks evolve task-solving controllers faster than both bipolar memristor networks and networks containing constant nonplastic connections whilst performing at least comparably.

David Howard, Larry Bull, Pier-Luca Lanzi

Learning Classifier Systems (LCS) are population-based reinforcement learners that were originally designed to model various cognitive phenomena. This paper presents an explicitly cognitive LCS by using spiking neural networks as classifiers, providing each classifier with a measure of temporal dynamism. We employ a constructivist model of growth of both neurons and synaptic connections, which permits a Genetic Algorithm (GA) to automatically evolve sufficiently-complex neural structures. The spiking classifiers are coupled with a temporally-sensitive reinforcement learning algorithm, which allows the system to perform temporal state decomposition by appropriately rewarding "macro-actions," created by chaining together multiple atomic actions. The combination of temporal reinforcement learning and neural information processing is shown to outperform benchmark neural classifier systems, and successfully solve a robotic navigation task.