A novel multi-agent evolutionary robotics (ER) based framework, inspired by competitive evolutionary environments in nature, is demonstrated for training Spiking Neural Networks (SNN). The weights of a population of SNNs along with morphological parameters of bots they control in the ER environment are treated as phenotypes. Rules of the framework select certain bots and their SNNs for reproduction and others for elimination based on their efficacy in capturing food in a competitive environment. While the bots and their SNNs are given no explicit reward to survive or reproduce via any loss function, these drives emerge implicitly as they evolve to hunt food and survive within these rules. Their efficiency in capturing food as a function of generations exhibit the evolutionary signature of punctuated equilibria. Two evolutionary inheritance algorithms on the phenotypes, Mutation and Crossover with Mutation, are demonstrated. Performances of these algorithms are compared using ensembles of 100 experiments for each algorithm. We find that Crossover with Mutation promotes 40% faster learning in the SNN than mere Mutation with a statistically significant margin.
Sony Computer Science Laboratories, Inc.（索尼计算机科学研究所）；Earth-Life Science Institute, Tokyo Institute of Technology（东京工业大学地球生命研究所）；The University of Tokyo（东京大学）
Complex environments provide structured yet variable sensory inputs. To best exploit information from these environments, organisms must evolve the ability to anticipate consequences of unknown stimuli, and act on these predictions. We propose an evolutionary path for neural networks, leading an organism from reactive behavior to simple proactive behavior and from simple proactive behavior to induction-based behavior. Through in-vitro and in-silico experiments, we define the conditions necessary in a network with spike-timing dependent plasticity for the organism to go from reactive to proacti…
Brain-inspired Evolutionary Architectures for Spiking Neural Networks
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences（中国科学院脑科学与智能技术卓越创新中心）
ESL-SNNs: An Evolutionary Structure Learning Strategy for Spiking Neural Networks
The College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；School of Artificial Intelligence, Dalian University of Technology（大连理工大学人工智能学院）；School of Computing, University of Leeds（利兹大学计算学院）；Research Institute of Intelligent Computing, Zhejiang Lab（之江实验室智能计算研究院）
Multi-scale Evolutionary Neural Architecture Search for Deep Spiking Neural Networks
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences（中国科学院脑科学与智能技术卓越创新中心）
The increasing rise in machine learning and deep learning applications is requiring ever more computational resources to successfully meet the growing demands of an always-connected, automated world. Neuromorphic technologies based on Spiking Neural Network algorithms hold the promise to implement advanced artificial intelligence using a fraction of the computations and power requirements by modeling the functioning, and spiking, of the human brain. With the proliferation of tools and platforms aiding data scientists and machine learning engineers to develop the latest innovations in artificia…
Universidad de Sevilla（塞维利亚大学）；Universidad de Cádiz（加的斯大学）
Initially, robots were developed with the aim of making our life easier, carrying out repetitive or dangerous tasks for humans. Although they were able to perform these tasks, the latest generation of robots are being designed to take a step further, by performing more complex tasks that have been carried out by smart animals or humans up to date. To this end, inspiration needs to be taken from biological examples. For instance, insects are able to optimally solve complex environment navigation problems, and many researchers have started to mimic how these insects behave. Recent interest in ne…
Robotic vision introduces requirements for real-time processing of fast-varying, noisy information in a continuously changing environment. In a real-world environment, convenient assumptions, such as static camera systems and deep learning algorithms devouring high volumes of ideally slightly-varying data are hard to survive. Leveraging on recent studies on the neural connectome associated with eye movements, we designed a neuromorphic oculomotor controller and placed it at the heart of our in-house biomimetic robotic head prototype. The controller is unique in the sense that (1) all data are …
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 altere…
Institute for Advanced Simulation (IAS-6), Theoretical Neuroscience（高等模拟研究所（IAS-6），理论神经科学）；Institute of Neuroscience and Medicine (INM-6), Computational and Systems Neuroscience（神经科学与医学研究所（INM-6），计算与系统神经科学）；JARA BRAIN Institute I（JARA BRAIN 研究所 I）；Jülich Research Center（于利希研究中心）；JARA Jülich（JARA 于利希）；PDC Center for High Performance Computing KTH Stockholm（KTH 斯德哥尔摩高性能计算中心）；Faculty of Biology Albert-Ludwig University of Freiburg（弗赖堡阿尔伯特-路德维希大学生物学院）；Bernstein Center Freiburg Albert-Ludwig University of Freiburg（弗赖堡阿尔伯特-路德维希大学伯恩斯坦中心）
In order to properly assess the function and computational properties of simulated neural systems, it is necessary to account for the nature of the stimuli that drive the system. However, providing stimuli that are rich and yet both reproducible and amenable to experimental manipulations is technically challenging, and even more so if a closed-loop scenario is required. In this work, we present a novel approach to solve this problem, connecting robotics and neural network simulators. We implement a middleware solution that bridges the Robotic Operating System (ROS) to the Multi-Simulator Coord…
Inspired by the natural nervous system, synaptic plasticity rules are applied to train spiking neural networks with local information, making them suitable for online learning on neuromorphic hardware. However, when such rules are implemented to learn different new tasks, they usually require a significant amount of work on task-dependent fine-tuning. This paper aims to make this process easier by employing an evolutionary algorithm that evolves suitable synaptic plasticity rules for the task at hand. More specifically, we provide a set of various local signals, a set of mathematical operators…
Evolving Efficient Genetic Encoding for Deep Spiking Neural Networks
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Center for Long-term Artificial Intelligence（长期人工智能中心）；Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology, Chinese Academy of Sciences（中国科学院脑认知与脑智能技术重点实验室）
Technische Universität München（慕尼黑工业大学）；Alfred Kärcher SE Co. & KG（阿尔弗雷德·卡赫股份有限公司）
Legged locomotion is a challenging task in the field of robotics but a rather simple one in nature. This motivates the use of biological methodologies as solutions to this problem. Central pattern generators are neural networks that are thought to be responsible for locomotion in humans and some animal species. As for robotics, many attempts were made to reproduce such systems and use them for a similar goal. One interesting design model is based on spiking neural networks. This model is the main focus of this work, as its contribution is not limited to engineering but also applicable to neuro…
Spiking Neural Networks (SNN) are third-generation Artificial Neural Networks (ANN) which are close to the biological neural system. In recent years SNN has become popular in the area of robotics and embedded applications, therefore, it has become imperative to explore its real-time and energy-efficient implementations. SNNs are more powerful than their predecessors because they encode temporal information and use biologically plausible plasticity rules. In this paper, a simpler and computationally efficient SNN model using FPGA architecture is described. The proposed model is validated on a X…
Building spiking neural networks (SNNs) based on biological synaptic plasticities holds a promising potential for accomplishing fast and energy-efficient computing, which is beneficial to mobile robotic applications. However, the implementations of SNNs in robotic fields are limited due to the lack of practical training methods. In this paper, we therefore introduce both indirect and direct end-to-end training methods of SNNs for a lane-keeping vehicle. First, we adopt a policy learned using the \textcolor{black}{Deep Q-Learning} (DQN) algorithm and then subsequently transfer it to an SNN usin…
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 al…
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 more than 1 …
Navy Center for Applied Research in Artificial Intelligence（海军人工智能应用研究中心）；Naval Research Laboratory（海军研究实验室）
Robotic hardware designs are becoming more complex as the variety and number of on-board sensors increase and as greater computational power is provided in ever-smaller packages on-board robots. These advances in hardware, however, do not automatically translate into better software for controlling complex robots. Evolutionary techniques hold the potential to solve many difficult problems in robotics which defy simple conventional approaches, but present many challenges as well. Numerous disciplines including artificial life, cognitive science and neural networks, rule-based systems, behavior-…
Neuromorphic hardware has several promising advantages compared to von Neumann architectures and is highly interesting for robot control. However, despite the high speed and energy efficiency of neuromorphic computing, algorithms utilizing this hardware in control scenarios are still rare. One problem is the transition from fast spiking activity on the hardware, which acts on a timescale of a few milliseconds, to a control-relevant timescale on the order of hundreds of milliseconds. Another problem is the execution of complex trajectories, which requires spiking activity to contain sufficient …
Research Center for Brain-inspired Intelligence, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所类脑智能研究中心）；School of Future Technology, University of Chinese Academy of Sciences（中国科学院大学未来技术学院）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）；Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences（中国科学院脑科学与智能技术卓越创新中心）
Brain inspired spiking neural networks (SNNs) have been successfully applied to many pattern recognition domains. The SNNs based deep structure have achieved considerable results in perceptual tasks, such as image classification, target detection. However, the application of deep SNNs in reinforcement learning (RL) tasks is still a problem to be explored. Although there have been previous studies on the combination of SNNs and RL, most of them focus on robotic control problems with shallow networks or using ANN-SNN conversion method to implement spiking deep Q Network (SDQN). In this work, we …
A robotic swarm that is required to operate for long periods in a potentially unknown environment can use both evolution and individual learning methods in order to adapt. However, the role played by the environment in influencing the effectiveness of each type of learning is not well understood. In this paper, we address this question by analysing the performance of a swarm in a range of simulated, dynamic environments where a distributed evolutionary algorithm for evolving a controller is augmented with a number of different individual learning mechanisms. The learning mechanisms themselves …
Neuromorphic architectures achieve low-power operation by using many simple spiking neurons in lieu of traditional hardware. Here, we develop methods for precise linear computations in spiking neural networks and use these methods to map the evolution of a linear dynamical system (LDS) onto an existing neuromorphic chip: IBM's TrueNorth. We analytically characterize, and numerically validate, the discrepancy between the spiking LDS state sequence and that of its non-spiking counterpart. These analytical results shed light on the multiway tradeoff between time, space, energy, and accuracy in ne…
Centre for Theoretical Neuroscience（理论神经科学中心）；University of Waterloo（滑铁卢大学）
We train spiking deep networks using leaky integrate-and-fire (LIF) neurons, and achieve state-of-the-art results for spiking networks on the CIFAR-10 and MNIST datasets. This demonstrates that biologically-plausible spiking LIF neurons can be integrated into deep networks can perform as well as other spiking models (e.g. integrate-and-fire). We achieved this result by softening the LIF response function, such that its derivative remains bounded, and by training the network with noise to provide robustness against the variability introduced by spikes. Our method is general and could be applied…
In Evolutionary Robotics a population of solutions is evolved to optimize robots that solve a given task. However, in traditional Evolutionary Algorithms, the population of solutions tends to converge to local optima when the problem is complex or the search space is large, a problem known as premature convergence. Quality Diversity algorithms try to overcome premature convergence by introducing additional measures that reward solutions for being different while not necessarily performing better. In this paper we compare a single objective Evolutionary Algorithm with two diversity promoting se…
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 s…
Studying and understanding the computational primitives of our neural system requires for a diverse and complementary set of techniques. In this work, we use the Neuro-robotic Platform (NRP)to evaluate the vestibulo ocular cerebellar adaptatIon (Vestibulo-ocular reflex, VOR)mediated by two STDP mechanisms located at the cerebellar molecular layer and the vestibular nuclei respectively. This simulation study adopts an experimental setup (rotatory VOR)widely used by neuroscientists to better understand the contribution of certain specific cerebellar properties (i.e. distributed STDP, neural prop…
Université de Lorraine（洛林大学）；INRIA Nancy Grand-Est（法国国家数字科学与技术研究所南锡大东部大区中心）
In this paper, we study the impact of selection methods in the context of on-line on-board distributed evolutionary algorithms. We propose a variant of the mEDEA algorithm in which we add a selection operator, and we apply it in a taskdriven scenario. We evaluate four selection methods that induce different intensity of selection pressure in a multi-robot navigation with obstacle avoidance task and a collective foraging task. Experiments show that a small intensity of selection pressure is sufficient to rapidly obtain good performances on the tasks at hand. We introduce different measures to c…
Novelty search has shown to be a promising approach for the evolution of controllers for swarm robotics. In existing studies, however, the experimenter had to craft a domain dependent behaviour similarity measure to use novelty search in swarm robotics applications. The reliance on hand-crafted similarity measures places an additional burden to the experimenter and introduces a bias in the evolutionary process. In this paper, we propose and compare two task-independent, generic behaviour similarity measures: combined state count and sampled average state. The proposed measures use the values o…
Instituto de Telecomunicações（葡萄牙电信研究所）；Faculdade de Ciências da Universidade de Lisboa（里斯本大学理学院）；Instituto Universitário de Lisboa (ISCTE-IUL)（里斯本大学学院）
Evolutionary techniques driven by behavioural diversity, such as novelty search, have shown significant potential in evolutionary robotics. These techniques rely on priorly specified behaviour characterisations to estimate the similarity between individuals. Characterisations are typically defined in an ad hoc manner based on the experimenter's intuition and knowledge about the task. Alternatively, generic characterisations based on the sensor-effector values of the agents are used. In this paper, we propose a novel approach that allows for systematic derivation of behaviour characterisations …
Tuning Synaptic Connections instead of Weights by Genetic Algorithm in Spiking Policy Network
School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Institute of Automation, Chinese Academy of Sciences (CAS)（中国科学院自动化研究所）；Center for Excellence in Brain Science and Intelligence Technology, CAS（中国科学院脑科学与智能技术卓越创新中心）
Roborobo! is a multi-platform, highly portable, robot simulator for large-scale collective robotics experiments. Roborobo! is coded in C++, and follows the KISS guideline ("Keep it simple"). Therefore, its external dependency is solely limited to the widely available SDL library for fast 2D Graphics. Roborobo! is based on a Khepera/ePuck model. It is targeted for fast single and multi-robots simulation, and has already been used in more than a dozen published research mainly concerned with evolutionary swarm robotics, including environment-driven self-adaptation and distributed evolutionary op…
Web-based applications are highly accessible to users, providing rich, interactive content while eliminating the need to install software locally. However, evolutionary robotics (ER) has faced challenges in this domain as web-based technologies have not been amenable to 3D physics simulations. Traditionally, physics-based simulations require a local installation and a high degree of user knowledge to configure an environment, but the emergence of Javascript-based physics engines enables complex simulations to be executed in web browsers. These developments create opportunities for ER research …
University of the West of England（西英格兰大学）；Politecnico di Milano（米兰理工大学）
Learning Classifier Systems (LCS) are population-based reinforcement learners used in a wide variety of applications. This paper presents a LCS where each traditional rule is represented by a spiking neural network, a type of network with dynamic internal state. We employ a constructivist model of growth of both neurons and dendrites that realise flexible learning by evolving structures of sufficient complexity to solve a well-known problem involving continuous, real-valued inputs. Additionally, we extend the system to enable temporal state decomposition. By allowing our LCS to chain together …
The semi-automatic or automatic synthesis of robot controller software is both desirable and challenging. Synthesis of rather simple behaviors such as collision avoidance by applying artificial evolution has been shown multiple times. However, the difficulty of this synthesis increases heavily with increasing complexity of the task that should be performed by the robot. We try to tackle this problem of complexity with Artificial Homeostatic Hormone Systems (AHHS), which provide both intrinsic, homeostatic processes and (transient) intrinsic, variant behavior. By using AHHS the need for pre-def…
The Role of Morphological Variation in Evolutionary Robotics: Maximizing Performance and Robustness
Federal University of Santa Catarina (UFSC)（圣卡塔琳娜联邦大学）；Institute of Cognitive Sciences and Technologies (ISTC), National Research Council (CNR)（国家研究委员会认知科学与技术研究所）
An approach to robotics called layered evolution and merging features from the subsumption architecture into evolutionary robotics is presented, and its advantages are discussed. This approach is used to construct a layered controller for a simulated robot that learns which light source to approach in an environment with obstacles. The evolvability and performance of layered evolution on this task is compared to (standard) monolithic evolution, incremental and modularised evolution. To corroborate the hypothesis that a layered controller performs at least as well as an integrated one, the evol…
This article 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 inter-neural connectivity pattern to emerge. By comparing two phenomenological real-world memristor implementations with networks comprised of (i) linear resistors (ii) constant-valued connections, we demonstrate that this approach allows the evolution of networks of appropriate complexity to emerg…
Neuromorphic computing is a new paradigm for design of both the computing hardware and algorithms inspired by biological neural networks. The event-based nature and the inherent parallelism make neuromorphic computing a promising paradigm for building efficient neural network based architectures for control of fast and agile robots. In this paper, we present a spiking neural network architecture that uses sensory feedback to control rotational velocity of a robotic vehicle. When the velocity reaches the target value, the mapping from the target velocity of the vehicle to the correct motor comm…
Okinawa Institute of Science and Technology（冲绳科学技术大学院大学）
Evolution and development operate at different timescales; generations for the one, a lifetime for the other. These two processes, the basis of much of life on earth, interact in many non-trivial ways, but their temporal hierarchy -- evolution overarching development -- is observed for most multicellular lifeforms. When designing robots however, this tenet lifts: it becomes -- however natural -- a design choice. We propose to inverse this temporal hierarchy and design a developmental process happening at the phylogenetic timescale. Over a classic evolutionary search aimed at finding good gaits…
Elucidating principles that underlie computation in neural networks is currently a major research topic of interest in neuroscience. Transfer Entropy (TE) is increasingly used as a tool to bridge the gap between network structure, function, and behavior in fMRI studies. Computational models allow us to bridge the gap even further by directly associating individual neuron activity with behavior. However, most computational models that have analyzed embodied behaviors have employed non-spiking neurons. On the other hand, computational models that employ spiking neural networks tend to be restric…
Biological sensing and processing is asynchronous and sparse, leading to low-latency and energy-efficient perception and action. In robotics, neuromorphic hardware for event-based vision and spiking neural networks promises to exhibit similar characteristics. However, robotic implementations have been limited to basic tasks with low-dimensional sensory inputs and motor actions due to the restricted network size in current embedded neuromorphic processors and the difficulties of training spiking neural networks. Here, we present the first fully neuromorphic vision-to-control pipeline for contro…
The University of New South Wales Canberra（新南威尔士大学堪培拉分校）；CSIRO（联邦科学与工业研究组织）
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 t…
The adaptive changes in synaptic efficacy that occur between spiking neurons have been demonstrated to play a critical role in learning for biological neural networks. Despite this source of inspiration, many learning focused applications using Spiking Neural Networks (SNNs) retain static synaptic connections, preventing additional learning after the initial training period. Here, we introduce a framework for simultaneously learning the underlying fixed-weights and the rules governing the dynamics of synaptic plasticity and neuromodulated synaptic plasticity in SNNs through gradient descent. W…
Institute of Neuroinformatics, University of Zurich and ETH Zurich（苏黎世大学与苏黎世联邦理工学院神经信息学研究所）；KTH Royal Institute of Technology（瑞典皇家理工学院）；University of Hertfordshire（赫特福德大学）；Western Sydney University（西悉尼大学）
Vibration patterns yield valuable information about the health state of a running machine, which is commonly exploited in predictive maintenance tasks for large industrial systems. However, the overhead, in terms of size, complexity and power budget, required by classical methods to exploit this information is often prohibitive for smaller-scale applications such as autonomous cars, drones or robotics. Here we propose a neuromorphic approach to perform vibration analysis using spiking neural networks that can be applied to a wide range of scenarios. We present a spike-based end-to-end pipeline…
