Connecting Artificial Brains to Robots in a Comprehensive Simulation Framework: The Neurorobotics Platform

Memristive Circuit Implementation of Caenorhabditis Elegans Mechanism for Neuromorphic Computing

To overcome the energy efficiency bottleneck of the von Neumann architecture and scaling limit of silicon transistors, an emerging but promising solution is neuromorphic computing, a new computing paradigm inspired by how biological neural networks handle the massive amount of information in a parallel and efficient way. Recently, there is a surge of interest in the nematode worm Caenorhabditis elegans (C. elegans), an ideal model organism to probe the mechanisms of biological neural networks. In this article, we propose a neuron model for C. elegans with leaky integrate-and-fire (LIF) dynamics and adjustable integration time. We utilize these neurons to build the C. elegans neural network according to their neural physiology, which comprises: 1) sensory modules; 2) interneuron modules; and 3) motoneuron modules. Leveraging these block designs, we develop a serpentine robot system, which mimics the locomotion behavior of C. elegans upon external stimulus. Moreover, experimental results of C. elegans neurons presented in this article reveals the robustness (1% error w.r.t. 10% random noise) and flexibility of our design in term of parameter setting. The work paves the way for future intelligent systems by mimicking the C. elegans neural system.

Application of Event Cameras and Neuromorphic Computing to VSLAM: A Survey

Simultaneous Localization and Mapping (SLAM) is a crucial function for most autonomous systems, allowing them to both navigate through and create maps of unfamiliar surroundings. Traditional Visual SLAM, also commonly known as VSLAM, relies on frame-based cameras and structured processing pipelines, which face challenges in dynamic or low-light environments. However, recent advancements in event camera technology and neuromorphic processing offer promising opportunities to overcome these limitations. Event cameras inspired by biological vision systems capture the scenes asynchronously, consuming minimal power but with higher temporal resolution. Neuromorphic processors, which are designed to mimic the parallel processing capabilities of the human brain, offer efficient computation for real-time data processing of event-based data streams. This paper provides a comprehensive overview of recent research efforts in integrating event cameras and neuromorphic processors into VSLAM systems. It discusses the principles behind event cameras and neuromorphic processors, highlighting their advantages over traditional sensing and processing methods. Furthermore, an in-depth survey was conducted on state-of-the-art approaches in event-based SLAM, including feature extraction, motion estimation, and map reconstruction techniques. Additionally, the integration of event cameras with neuromorphic processors, focusing on their synergistic benefits in terms of energy efficiency, robustness, and real-time performance, was explored. The paper also discusses the challenges and open research questions in this emerging field, such as sensor calibration, data fusion, and algorithmic development. Finally, the potential applications and future directions for event-based SLAM systems are outlined, ranging from robotics and autonomous vehicles to augmented reality.

Closing the loop: High-speed robotics with accelerated neuromorphic hardware

The BrainScaleS-2 system is an established analog neuromorphic platform with versatile applications in the diverse fields of computational neuroscience and spike-based machine learning. In this work, we extend the system with a configurable realtime event interface that enables a tight coupling of its distinct analog network core to external sensors and actuators. The 1,000-fold acceleration of the emulated nerve cells allows us to target high-speed robotic applications that require precise timing on a microsecond scale. As a showcase, we present a closed-loop setup for commuting brushless DC motors: we utilize PyTorch to train a spiking neural network emulated on the analog substrate to control an electric motor from a sensory event stream. The presented system enables research in the area of event-driven controllers for high-speed robotics, including self-supervised and biologically inspired online learning for such applications.

Toward coordinated planning and hierarchical optimization control for highly redundant mobile manipulator

This paper represents a constraint planning and optimization control scheme for a highly redundant mobile manipulator considering a complex indoor environment. Compared with the traditional optimization solution of a redundant manipulator, infinity norm and slack variable are additionally introduced and leveraged by the optimization algorithm. The former takes into account the joint limits effectively by considering individual joint velocities and the latter relaxes the equality constraint by decreasing the infeasible solution area. By using derived kinematic equations, the tracking control problem is expressed as an optimization problem and converted into a new quadratic programming (QP) problem. To address the optimization problem, the two-timescale recurrent neural networks optimization scheme is proposed and tested with a 9 DOFs nonholonomic mobile-based manipulator. Additionally, the BI2RRT∗ path-planning algorithm incorporates path planning in the complex environment where different obstacles are positioned. To test and evaluate the proposed optimization scheme, both predefined and generated paths are tested in the Neurorobotics Platform (NRP) 2which is open access and open source integrative simulation framework powered by Gazebo and developed by our team.

Dynamic event-based optical identification and communication

Optical identification is often done with spatial or temporal visual pattern recognition and localization. Temporal pattern recognition, depending on the technology, involves a trade-off between communication frequency, range, and accurate tracking. We propose a solution with light-emitting beacons that improves this trade-off by exploiting fast event-based cameras and, for tracking, sparse neuromorphic optical flow computed with spiking neurons. The system is embedded in a simulated drone and evaluated in an asset monitoring use case. It is robust to relative movements and enables simultaneous communication with, and tracking of, multiple moving beacons. Finally, in a hardware lab prototype, we demonstrate for the first time beacon tracking performed simultaneously with state-of-the-art frequency communication in the kHz range.

Multiscale co-simulation design pattern for neuroscience applications

Integration of information across heterogeneous sources creates added scientific value. Interoperability of data, tools and models is, however, difficult to accomplish across spatial and temporal scales. Here we introduce the toolbox Parallel Co-Simulation, which enables the interoperation of simulators operating at different scales. We provide a software science co-design pattern and illustrate its functioning along a neuroscience example, in which individual regions of interest are simulated on the cellular level allowing us to study detailed mechanisms, while the remaining network is efficiently simulated on the population level. A workflow is illustrated for the use case of The Virtual Brain and NEST, in which the CA1 region of the cellular-level hippocampus of the mouse is embedded into a full brain network involving micro and macro electrode recordings. This new tool allows integrating knowledge across scales in the same simulation framework and validating them against multiscale experiments, thereby largely widening the explanatory power of computational models.

Finding the gap: neuromorphic motion-vision in dense environments

Animals have evolved mechanisms to travel safely and efficiently within different habitats. On a journey in dense terrains animals avoid collisions and cross narrow passages while controlling an overall course. Multiple hypotheses target how animals solve challenges faced during such travel. Here we show that a single mechanism enables safe and efficient travel. We developed a robot inspired by insects. It has remarkable capabilities to travel in dense terrain, avoiding collisions, crossing gaps and selecting safe passages. These capabilities are accomplished by a neuromorphic network steering the robot toward regions of low apparent motion. Our system leverages knowledge about vision processing and obstacle avoidance in insects. Our results demonstrate how insects might safely travel through diverse habitats. We anticipate our system to be a working hypothesis to study insects' travels in dense terrains. Furthermore, it illustrates that we can design novel hardware systems by understanding the underlying mechanisms driving behaviour.

Neurorobotic reinforcement learning for domains with parametrical uncertainty

Neuromorphic hardware paired with brain-inspired learning strategies have enormous potential for robot control. Explicitly, these advantages include low energy consumption, low latency, and adaptability. Therefore, developing and improving learning strategies, algorithms, and neuromorphic hardware integration in simulation is a key to moving the state-of-the-art forward. In this study, we used the neurorobotics platform (NRP) simulation framework to implement spiking reinforcement learning control for a robotic arm. We implemented a force-torque feedback-based classic object insertion task ("peg-in-hole") and controlled the robot for the first time with neuromorphic hardware in the loop. We therefore provide a solution for training the system in uncertain environmental domains by using randomized simulation parameters. This leads to policies that are robust to real-world parameter variations in the target domain, filling the sim-to-real gap.To the best of our knowledge, it is the first neuromorphic implementation of the peg-in-hole task in simulation with the neuromorphic Loihi chip in the loop, and with scripted accelerated interactive training in the Neurorobotics Platform, including randomized domains.

A perspective on large-scale simulation as an enabler for novel biorobotics applications

Our understanding of the complex mechanisms that power biological intelligence has been greatly enhanced through the explosive growth of large-scale neuroscience and robotics simulation tools that are used by the research community to perform previously infeasible experiments, such as the simulation of the neocortex's circuitry. Nevertheless, simulation falls far from being directly applicable to biorobots due to the large discrepancy between the simulated and the real world. A possible solution for this problem is the further enhancement of existing simulation tools for robotics, AI and neuroscience with multi-physics capabilities. Previously infeasible or difficult to simulate scenarios, such as robots swimming on the water surface, interacting with soft materials, walking on granular materials etc., would be rendered possible within a multi-physics simulation environment designed for robotics. In combination with multi-physics simulation, large-scale simulation tools that integrate multiple simulation modules in a closed-loop manner help address fundamental questions around the organization of neural circuits and the interplay between the brain, body and environment. We analyze existing designs for large-scale simulation running on cloud and HPC infrastructure as well as their shortcomings. Based on this analysis we propose a next-gen modular architecture design based on multi-physics engines, that we believe would greatly benefit biorobotics and AI.

Tutorial: using NEURON for neuromechanical simulations

The dynamical properties of the brain and the dynamics of the body strongly influence one another. Their interaction generates complex adaptive behavior. While a wide variety of simulation tools exist for neural dynamics or biomechanics separately, there are few options for integrated brain-body modeling. Here, we provide a tutorial to demonstrate how the widely-used NEURON simulation platform can support integrated neuromechanical modeling. As a first step toward incorporating biomechanics into a NEURON simulation, we provide a framework for integrating inputs from a "periphery" and outputs to that periphery. In other words, "body" dynamics are driven in part by "brain" variables, such as voltages or firing rates, and "brain" dynamics are influenced by "body" variables through sensory feedback. To couple the "brain" and "body" components, we use NEURON's pointer construct to share information between "brain" and "body" modules. This approach allows separate specification of brain and body dynamics and code reuse. Though simple in concept, the use of pointers can be challenging due to a complicated syntax and several different programming options. In this paper, we present five different computational models, with increasing levels of complexity, to demonstrate the concepts of code modularity using pointers and the integration of neural and biomechanical modeling within NEURON. The models include: (1) a neuromuscular model of calcium dynamics and muscle force, (2) a neuromechanical, closed-loop model of a half-center oscillator coupled to a rudimentary motor system, (3) a closed-loop model of neural control for respiration, (4) a pedagogical model of a non-smooth "brain/body" system, and (5) a closed-loop model of feeding behavior in the sea hare Aplysia californica that incorporates biologically-motivated non-smooth dynamics. This tutorial illustrates how NEURON can be integrated with a broad range of neuromechanical models.

Code available at

https://github.com/fietkiewicz/PointerBuilder.

The neuromechanics of animal locomotion: From biology to robotics and back

Robotics and neuroscience are sister disciplines that both aim to understand how agile, efficient, and robust locomotion can be achieved in autonomous agents. Robotics has already benefitted from neuromechanical principles discovered by investigating animals. These include the use of high-level commands to control low-level central pattern generator-like controllers, which, in turn, are informed by sensory feedback. Reciprocally, neuroscience has benefited from tools and intuitions in robotics to reveal how embodiment, physical interactions with the environment, and sensory feedback help sculpt animal behavior. We illustrate and discuss exemplar studies of this dialog between robotics and neuroscience. We also reveal how the increasing biorealism of simulations and robots is driving these two disciplines together, forging an integrative science of autonomous behavioral control with many exciting future opportunities.

Collaborating neuroscience online: The case of the Human Brain Project forum

This paper analyzes user interactions on the public-access online forum of the Human Brain Project (HBP), a major European Union-funded neuroscience research initiative, to understand the utility of the Forum for collaborative problem solving. We construct novel data using discussion forum posts and detailed user profiles on the HBP Forum. We find that HBP Forum utilization is comparable to that of a leading general-interest coding platform, and that online usage metrics quickly recovered after an initial Covid-19-related dip. Regression results show that user interactions on the Forum are more active for questions on programming and in HBP core areas. Further, Cox proportional hazard analyses show that such problems are solved faster. Forum posts with users from different countries tend to be discussed more actively but solved slower. Higher shares of administrator support tend to solve problems faster. There are no clear patterns regarding gender and seniority. Our results suggest that building novel collaborative forums can support researchers working on complex topics in challenging times.

Reproducing a decision-making network in a virtual visual discrimination task

We reproduced a decision-making network model using the neural simulator software neural simulation tool (NEST), and we embedded the spiking neural network in a virtual robotic agent performing a simulated behavioral task. The present work builds upon the concept of replicability in neuroscience, preserving most of the computational properties in the initial model although employing a different software tool. The proposed implementation successfully obtains equivalent results from the original study, reproducing the salient features of the neural processes underlying a binary decision. Furthermore, the resulting network is able to control a robot performing an in silico visual discrimination task, the implementation of which is openly available on the EBRAINS infrastructure through the neuro robotics platform (NRP).

The quest for multiscale brain modeling

Addressing the multiscale organization of the brain, which is fundamental to the dynamic repertoire of the organ, remains challenging. In principle, it should be possible to model neurons and synapses in detail and then connect them into large neuronal assemblies to explain the relationship between microscopic phenomena, large-scale brain functions, and behavior. It is more difficult to infer neuronal functions from ensemble measurements such as those currently obtained with brain activity recordings. In this article we consider theories and strategies for combining bottom-up models, generated from principles of neuronal biophysics, with top-down models based on ensemble representations of network activity and on functional principles. These integrative approaches are hoped to provide effective multiscale simulations in virtual brains and neurorobots, and pave the way to future applications in medicine and information technologies.

Bayesian Integration in a Spiking Neural System for Sensorimotor Control

The brain continuously estimates the state of body and environment, with specific regions that are thought to act as Bayesian estimator, optimally integrating noisy and delayed sensory feedback with sensory predictions generated by the cerebellum. In control theory, Bayesian estimators are usually implemented using high-level representations. In this work, we designed a new spike-based computational model of a Bayesian estimator. The state estimator receives spiking activity from two neural populations encoding the sensory feedback and the cerebellar prediction, and it continuously computes the spike variability within each population as a reliability index of the signal these populations encode. The state estimator output encodes the current state estimate. We simulated a reaching task at different stages of cerebellar learning. The activity of the sensory feedback neurons encoded a noisy version of the trajectory after actual movement, with an almost constant intrapopulation spiking variability. Conversely, the activity of the cerebellar output neurons depended on the phase of the learning process. Before learning, they fired at their baseline not encoding any relevant information, and the variability was set to be higher than that of the sensory feedback (more reliable, albeit delayed). When learning was complete, their activity encoded the trajectory before the actual execution, providing an accurate sensory prediction; in this case, the variability was set to be lower than that of the sensory feedback. The state estimator model optimally integrated the neural activities of the afferent populations, so that the output state estimate was primarily driven by sensory feedback in prelearning and by the cerebellar prediction in postlearning. It was able to deal even with more complex scenarios, for example, by shifting the dominant source during the movement execution if information availability suddenly changed. The proposed tool will be a critical block within integrated spiking, brain-inspired control systems for simulations of sensorimotor tasks.

Brain-Inspired Spiking Neural Network Controller for a Neurorobotic Whisker System

It is common for animals to use self-generated movements to actively sense the surrounding environment. For instance, rodents rhythmically move their whiskers to explore the space close to their body. The mouse whisker system has become a standard model for studying active sensing and sensorimotor integration through feedback loops. In this work, we developed a bioinspired spiking neural network model of the sensorimotor peripheral whisker system, modeling trigeminal ganglion, trigeminal nuclei, facial nuclei, and central pattern generator neuronal populations. This network was embedded in a virtual mouse robot, exploiting the Human Brain Project's Neurorobotics Platform, a simulation platform offering a virtual environment to develop and test robots driven by brain-inspired controllers. Eventually, the peripheral whisker system was adequately connected to an adaptive cerebellar network controller. The whole system was able to drive active whisking with learning capability, matching neural correlates of behavior experimentally recorded in mice.

A Spiking Neural Network Model of Rodent Head Direction Calibrated With Landmark Free Learning

Maintaining a stable estimate of head direction requires both self-motion (idiothetic) information and environmental (allothetic) anchoring. In unfamiliar or dark environments idiothetic drive can maintain a rough estimate of heading but is subject to inaccuracy, visual information is required to stabilize the head direction estimate. When learning to associate visual scenes with head angle, animals do not have access to the 'ground truth' of their head direction, and must use egocentrically derived imprecise head direction estimates. We use both discriminative and generative methods of visual processing to learn these associations without extracting explicit landmarks from a natural visual scene, finding all are sufficiently capable at providing a corrective signal. Further, we present a spiking continuous attractor model of head direction (SNN), which when driven by idiothetic input is subject to drift. We show that head direction predictions made by the chosen model-free visual learning algorithms can correct for drift, even when trained on a small training set of estimated head angles self-generated by the SNN. We validate this model against experimental work by reproducing cue rotation experiments which demonstrate visual control of the head direction signal.

The Neurorobotics Platform Robot Designer: Modeling Morphologies for Embodied Learning Experiments

The more we investigate the principles of motion learning in biological systems, the more we reveal the central role that body morphology plays in motion execution. Not only does anatomy define the kinematics and therefore the complexity of possible movements, but it now becomes clear that part of the computation required for motion control is offloaded to body dynamics (a phenomenon referred to as “Morphological Computation.”) Consequentially, a proper design of body morphology is essential to carry out meaningful simulations on motor control of robotic and musculoskeletal systems. The design should not be fixed for simulation experiments beforehand, but is a central research aspect in every motion learning experiment that requires continuous adaptation during the experimental phase. We herein introduce a plugin for the 3D modeling suite Blender that enables researchers to design morphologies for simulation experiments in, particularly but not restricted to, the Neurorobotics Platform. We include design capabilities for both musculoskeletal bodies, as well as robotic systems in the Robot Designer. Thereby, we hope to not only foster understanding of biological motions and enabling better robot designs, but enabling true Neurorobotic experiments that may consist of biomimetic models such as tendon-driven robot as a mix of both or a transition between both biology and technology. This plugin helps researchers design and parameterize models with a Graphical User Interface and thus simplifies and speeds up the overall design process.

Linking Brain Structure, Activity, and Cognitive Function through Computation

Understanding the human brain is a "Grand Challenge" for 21st century research. Computational approaches enable large and complex datasets to be addressed efficiently, supported by artificial neural networks, modeling and simulation. Dynamic generative multiscale models, which enable the investigation of causation across scales and are guided by principles and theories of brain function, are instrumental for linking brain structure and function. An example of a resource enabling such an integrated approach to neuroscientific discovery is the BigBrain, which spatially anchors tissue models and data across different scales and ensures that multiscale models are supported by the data, making the bridge to both basic neuroscience and medicine. Research at the intersection of neuroscience, computing and robotics has the potential to advance neuro-inspired technologies by taking advantage of a growing body of insights into perception, plasticity and learning. To render data, tools and methods, theories, basic principles and concepts interoperable, the Human Brain Project (HBP) has launched EBRAINS, a digital neuroscience research infrastructure, which brings together a transdisciplinary community of researchers united by the quest to understand the brain, with fascinating insights and perspectives for societal benefits.

Computational Neuroscience Approach to Psychiatry: A Review on Theory-driven Approaches

Translating progress in neuroscience into clinical benefits for patients with psychiatric disorders is challenging because it involves the brain as the most complex organ and its interaction with a complex environment and condition. Dealing with such complexity requires powerful techniques. Computational neuroscience approach to psychiatry integrates multiple levels and types of simulation, analysis and computation according to the different types of computational models to enhance comprehending, prediction and treatment of psychiatric disorder. This approach comprises two approaches: theory-driven and data-driven. In this review, we focus on recent advances in theory-driven approaches that mathematically and mechanistically examine the relationships between disorder-related changes and behavior at different level of brain organization. We discuss recent progresses in computational neuroscience models that relate to psychiatry and show how principles of neural computational modeling can be employed to explain psychopathology.

Embodied neuromorphic intelligence

The design of robots that interact autonomously with the environment and exhibit complex behaviours is an open challenge that can benefit from understanding what makes living beings fit to act in the world. Neuromorphic engineering studies neural computational principles to develop technologies that can provide a computing substrate for building compact and low-power processing systems. We discuss why endowing robots with neuromorphic technologies - from perception to motor control - represents a promising approach for the creation of robots which can seamlessly integrate in society. We present initial attempts in this direction, highlight open challenges, and propose actions required to overcome current limitations.

Neuromorphic Engineering Needs Closed-Loop Benchmarks

Neuromorphic engineering aims to build (autonomous) systems by mimicking biological systems. It is motivated by the observation that biological organisms—from algae to primates—excel in sensing their environment, reacting promptly to their perils and opportunities. Furthermore, they do so more resiliently than our most advanced machines, at a fraction of the power consumption. It follows that the performance of neuromorphic systems should be evaluated in terms of real-time operation, power consumption, and resiliency to real-world perturbations and noise using task-relevant evaluation metrics. Yet, following in the footsteps of conventional machine learning, most neuromorphic benchmarks rely on recorded datasets that foster sensing accuracy as the primary measure for performance. Sensing accuracy is but an arbitrary proxy for the actual system's goal—taking a good decision in a timely manner. Moreover, static datasets hinder our ability to study and compare closed-loop sensing and control strategies that are central to survival for biological organisms. This article makes the case for a renewed focus on closed-loop benchmarks involving real-world tasks. Such benchmarks will be crucial in developing and progressing neuromorphic Intelligence. The shift towards dynamic real-world benchmarking tasks should usher in richer, more resilient, and robust artificially intelligent systems in the future.

Deep learning for biosignal control: insights from basic to real-time methods with recommendations

Biosignal control is an interaction modality that allows users to interact with electronic devices by decoding the biological signals emanating from the movements or thoughts of the user. This manner of interaction with devices can enhance the sense of agency for users and enable persons suffering from a paralyzing condition to interact with everyday devices that would otherwise be challenging for them to use. It can also improve control of prosthetic devices and exoskeletons by making the interaction feel more natural and intuitive. However, with the current state of the art, several issues still need to be addressed to reliably decode user intent from biosignals and provide an improved user experience over other interaction modalities. One solution is to leverage advances in Deep Learning (DL) methods to provide more reliable decoding at the expense of added computational complexity. This scoping review introduces the basic concepts of DL and assists readers in deploying DL methods to a real-time control system that should operate under real-world conditions. The scope of this review covers any electronic device, but with an emphasis on robotic devices, as this is the most active area of research in biosignal control. We review the literature pertaining to the implementation and evaluation of control systems that incorporate DL to identify the main gaps and issues in the field, and formulate suggestions on how to mitigate them. Additionally, we formulate guidelines on the best approach to designing, implementing and evaluating research prototypes that use DL in their biosignal control systems.

Reaching and Grasping Movements in Parkinson's Disease: A Review

Parkinson's disease (PD) is known to affect the brain motor circuits involving the basal ganglia (BG) and to induce, among other signs, general slowness and paucity of movements. In upper limb movements, PD patients show a systematic prolongation of movement duration while maintaining a sufficient level of endpoint accuracy. PD appears to cause impairments not only in movement execution, but also in movement initiation and planning, as revealed by abnormal preparatory activity of motor-related brain areas. Grasping movement is affected as well, particularly in the coordination of the hand aperture with the transport phase. In the last fifty years, numerous behavioral studies attempted to clarify the mechanisms underlying these anomalies, speculating on the plausible role that the BG-thalamo-cortical circuitry may play in normal and pathological motor control. Still, many questions remain open, especially concerning the management of the speed-accuracy tradeoff and the online feedback control. In this review, we summarize the literature results on reaching and grasping in parkinsonian patients. We analyze the relevant hypotheses on the origins of dysfunction, by focusing on the motor control aspects involved in the different movement phases and the corresponding role played by the BG. We conclude with an insight into the innovative stimulation techniques and computational models recently proposed, which might be helpful in further clarifying the mechanisms through which PD affects reaching and grasping movements.

Multimodal Representation Learning for Place Recognition Using Deep Hebbian Predictive Coding

Recognising familiar places is a competence required in many engineering applications that interact with the real world such as robot navigation. Combining information from different sensory sources promotes robustness and accuracy of place recognition. However, mismatch in data registration, dimensionality, and timing between modalities remain challenging problems in multisensory place recognition. Spurious data generated by sensor drop-out in multisensory environments is particularly problematic and often resolved through adhoc and brittle solutions. An effective approach to these problems is demonstrated by animals as they gracefully move through the world. Therefore, we take a neuro-ethological approach by adopting self-supervised representation learning based on a neuroscientific model of visual cortex known as predictive coding. We demonstrate how this parsimonious network algorithm which is trained using a local learning rule can be extended to combine visual and tactile sensory cues from a biomimetic robot as it naturally explores a visually aliased environment. The place recognition performance obtained using joint latent representations generated by the network is significantly better than contemporary representation learning techniques. Further, we see evidence of improved robustness at place recognition in face of unimodal sensor drop-out. The proposed multimodal deep predictive coding algorithm presented is also linearly extensible to accommodate more than two sensory modalities, thereby providing an intriguing example of the value of neuro-biologically plausible representation learning for multimodal navigation.

NeuroVis: Real-Time Neural Information Measurement and Visualization of Embodied Neural Systems

Understanding the real-time dynamical mechanisms of neural systems remains a significant issue, preventing the development of efficient neural technology and user trust. This is because the mechanisms, involving various neural spatial-temporal ingredients [i.e., neural structure (NS), neural dynamics (ND), neural plasticity (NP), and neural memory (NM)], are too complex to interpret and analyze altogether. While advanced tools have been developed using explainable artificial intelligence (XAI), node-link diagram, topography map, and other visualization techniques, they still fail to monitor and visualize all of these neural ingredients online. Accordingly, we propose here for the first time "NeuroVis," real-time neural spatial-temporal information measurement and visualization, as a method/tool to measure temporal neural activities and their propagation throughout the network. By using this neural information along with the connection strength and plasticity, NeuroVis can visualize the NS, ND, NM, and NP via i) spatial 2D position and connection, ii) temporal color gradient, iii) connection thickness, and iv) temporal luminous intensity and change of connection thickness, respectively. This study presents three use cases of NeuroVis to evaluate its performance: i) function approximation using a modular neural network with recurrent and feedforward topologies together with supervised learning, ii) robot locomotion control and learning using the same modular network with reinforcement learning, and iii) robot locomotion control and adaptation using another larger-scale adaptive modular neural network. The use cases demonstrate how NeuroVis tracks and analyzes all neural ingredients of various (embodied) neural systems in real-time under the robot operating system (ROS) framework. To this end, it will offer the opportunity to better understand embodied dynamic neural information processes, boost efficient neural technology development, and enhance user trust.

Bringing Together Robotics, Neuroscience, and Psychology: Lessons Learned From an Interdisciplinary Project

The diversified methodology and expertise of interdisciplinary research teams provide the opportunity to overcome the limited perspectives of individual disciplines. This is particularly true at the interface of Robotics, Neuroscience, and Psychology as the three fields have quite different perspectives and approaches to offer. Nonetheless, aligning backgrounds and interdisciplinary expectations can present challenges due to varied research cultures and practices. Overcoming these challenges stands at the beginning of each productive collaboration and thus is a mandatory step in cognitive neurorobotics. In this article, we share eight lessons that we learned from our ongoing interdisciplinary project on human-robot and robot-robot interaction in social settings. These lessons provide practical advice for scientists initiating interdisciplinary research endeavors. Our advice can help to avoid early problems and deal with differences between research fields, prepare for and anticipate challenges, align project expectations, and speed up research progress, thus promoting effective interdisciplinary research across Robotics, Neuroscience, and Psychology.

Neurorobotic Models of Neurological Disorders: A Mini Review

Modeling is widely used in biomedical research to gain insights into pathophysiology and treatment of neurological disorders but existing models, such as animal models and computational models, are limited in generalizability to humans and are restricted in the scope of possible experiments. Robotics offers a potential complementary modeling platform, with advantages such as embodiment and physical environmental interaction yet with easily monitored and adjustable parameters. In this review, we discuss the different types of models used in biomedical research and summarize the existing neurorobotics models of neurological disorders. We detail the pertinent findings of these robot models which would not have been possible through other modeling platforms. We also highlight the existing limitations in a wider uptake of robot models for neurological disorders and suggest future directions for the field.

Nengo and Low-Power AI Hardware for Robust, Embedded Neurorobotics

In this paper we demonstrate how the Nengo neural modeling and simulation libraries enable users to quickly develop robotic perception and action neural networks for simulation on neuromorphic hardware using tools they are already familiar with, such as Keras and Python. We identify four primary challenges in building robust, embedded neurorobotic systems, including: (1) developing infrastructure for interfacing with the environment and sensors; (2) processing task specific sensory signals; (3) generating robust, explainable control signals; and (4) compiling neural networks to run on target hardware. Nengo helps to address these challenges by: (1) providing the NengoInterfaces library, which defines a simple but powerful API for users to interact with simulations and hardware; (2) providing the NengoDL library, which lets users use the Keras and TensorFlow API to develop Nengo models; (3) implementing the Neural Engineering Framework, which provides white-box methods for implementing known functions and circuits; and (4) providing multiple backend libraries, such as NengoLoihi, that enable users to compile the same model to different hardware. We present two examples using Nengo to develop neural networks that run on CPUs and GPUs as well as Intel's neuromorphic chip, Loihi, to demonstrate two variations on this workflow. The first example is an implementation of an end-to-end spiking neural network in Nengo that controls a rover simulated in Mujoco. The network integrates a deep convolutional network that processes visual input from cameras mounted on the rover to track a target, and a control system implementing steering and drive functions in connection weights to guide the rover to the target. The second example uses Nengo as a smaller component in a system that has addressed some but not all of those challenges. Specifically it is used to augment a force-based operational space controller with neural adaptive control to improve performance during a reaching task using a real-world Kinova Jaco² robotic arm. The code and implementation details are provided, with the intent of enabling other researchers to build and run their own neurorobotic systems.

Experimental and Computational Study on Motor Control and Recovery After Stroke: Toward a Constructive Loop Between Experimental and Virtual Embodied Neuroscience

Being able to replicate real experiments with computational simulations is a unique opportunity to refine and validate models with experimental data and redesign the experiments based on simulations. However, since it is technically demanding to model all components of an experiment, traditional approaches to modeling reduce the experimental setups as much as possible. In this study, our goal is to replicate all the relevant features of an experiment on motor control and motor rehabilitation after stroke. To this aim, we propose an approach that allows continuous integration of new experimental data into a computational modeling framework. First, results show that we could reproduce experimental object displacement with high accuracy via the simulated embodiment in the virtual world by feeding a spinal cord model with experimental registration of the cortical activity. Second, by using computational models of multiple granularities, our preliminary results show the possibility of simulating several features of the brain after stroke, from the local alteration in neuronal activity to long-range connectivity remodeling. Finally, strategies are proposed to merge the two pipelines. We further suggest that additional models could be integrated into the framework thanks to the versatility of the proposed approach, thus allowing many researchers to achieve continuously improved experimental design.

Neurorobotics Workshop for High School Students Promotes Competence and Confidence in Computational Neuroscience

Understanding the brain is a fascinating challenge, captivating the scientific community and the public alike. The lack of effective treatment for most brain disorders makes the training of the next generation of neuroscientists, engineers and physicians a key concern. Over the past decade there has been a growing effort to introduce neuroscience in primary and secondary schools, however, hands-on laboratories have been limited to anatomical or electrophysiological activities. Modern neuroscience research labs are increasingly using computational tools to model circuits of the brain to understand information processing. Here we introduce the use of neurorobots – robots controlled by computer models of biological brains – as an introduction to computational neuroscience in the classroom. Neurorobotics has enormous potential as an education technology because it combines multiple activities with clear educational benefits including neuroscience, active learning, and robotics. We describe a 1-week introductory neurorobot workshop that teaches high school students how to use neurorobots to investigate key concepts in neuroscience, including spiking neural networks, synaptic plasticity, and adaptive action selection. Our do-it-yourself (DIY) neurorobot uses wheels, a camera, a speaker, and a distance sensor to interact with its environment, and can be built from generic parts costing about $170 in under 4 h. Our Neurorobot App visualizes the neurorobot’s visual input and brain activity in real-time, and enables students to design new brains and deliver dopamine-like reward signals to reinforce chosen behaviors. We ran the neurorobot workshop at two high schools (n = 295 students total) and found significant improvement in students’ understanding of key neuroscience concepts and in students’ confidence in neuroscience, as assessed by a pre/post workshop survey. Here we provide DIY hardware assembly instructions, discuss our open-source Neurorobot App and demonstrate how to teach the Neurorobot Workshop. By doing this we hope to accelerate research in educational neurorobotics and promote the use of neurorobots to teach computational neuroscience in high school.

Embodied Synaptic Plasticity With Online Reinforcement Learning

The endeavor to understand the brain involves multiple collaborating research fields. Classically, synaptic plasticity rules derived by theoretical neuroscientists are evaluated in isolation on pattern classification tasks. This contrasts with the biological brain which purpose is to control a body in closed-loop. This paper contributes to bringing the fields of computational neuroscience and robotics closer together by integrating open-source software components from these two fields. The resulting framework allows to evaluate the validity of biologically-plausibe plasticity models in closed-loop robotics environments. We demonstrate this framework to evaluate Synaptic Plasticity with Online REinforcement learning (SPORE), a reward-learning rule based on synaptic sampling, on two visuomotor tasks: reaching and lane following. We show that SPORE is capable of learning to perform policies within the course of simulated hours for both tasks. Provisional parameter explorations indicate that the learning rate and the temperature driving the stochastic processes that govern synaptic learning dynamics need to be regulated for performance improvements to be retained. We conclude by discussing the recent deep reinforcement learning techniques which would be beneficial to increase the functionality of SPORE on visuomotor tasks.

Combining Evolutionary and Adaptive Control Strategies for Quadruped Robotic Locomotion

In traditional robotics, model-based controllers are usually needed in order to bring a robotic plant to the next desired state, but they present critical issues when the dimensionality of the control problem increases and disturbances from the external environment affect the system behavior, in particular during locomotion tasks. It is generally accepted that the motion control of quadruped animals is performed by neural circuits located in the spinal cord that act as a Central Pattern Generator and can generate appropriate locomotion patterns. This is thought to be the result of evolutionary processes that have optimized this network. On top of this, fine motor control is learned during the lifetime of the animal thanks to the plastic connections of the cerebellum that provide descending corrective inputs. This research aims at understanding and identifying the possible advantages of using learning during an evolution-inspired optimization for finding the best locomotion patterns in a robotic locomotion task. Accordingly, we propose a comparative study between two bio-inspired control architectures for quadruped legged robots where learning takes place either during the evolutionary search or only after that. The evolutionary process is carried out in a simulated environment, on a quadruped legged robot. To verify the possibility of overcoming the reality gap, the performance of both systems has been analyzed by changing the robot dynamics and its interaction with the external environment. Results show better performance metrics for the robotic agent whose locomotion method has been discovered by applying the adaptive module during the evolutionary exploration for the locomotion trajectories. Even when the motion dynamics and the interaction with the environment is altered, the locomotion patterns found on the learning robotic system are more stable, both in the joint and in the task space.

A Biomimetic Control Method Increases the Adaptability of a Humanoid Robot Acting in a Dynamic Environment

One of the big challenges in robotics is to endow agents with autonomous and adaptive capabilities. With this purpose, we embedded a cerebellum-based control system into a humanoid robot that becomes capable of handling dynamical external and internal complexity. The cerebellum is the area of the brain that coordinates and predicts the body movements throughout the body-environment interactions. Different biologically plausible cerebellar models are available in literature and have been employed for motor learning and control of simplified objects. We built the canonical cerebellar microcircuit by combining machine learning and computational neuroscience techniques. The control system is composed of the adaptive cerebellar module and a classic control method; their combination allows a fast adaptive learning and robust control of the robotic movements when external disturbances appear. The control structure is built offline, but the dynamic parameters are learned during an online-phase training. The aforementioned adaptive control system has been tested in the Neuro-robotics Platform with the virtual humanoid robot iCub. In the experiment, the robot iCub has to balance with the hand a table with a ball running on it. In contrast with previous attempts of solving this task, the proposed neural controller resulted able to quickly adapt when the internal and external conditions change. Our bio-inspired and flexible control architecture can be applied to different robotic configurations without an excessive tuning of the parameters or customization. The cerebellum-based control system is indeed able to deal with changing dynamics and interactions with the environment. Important insights regarding the relationship between the bio-inspired control system functioning and the complexity of the task to be performed are obtained.

Curated Model Development Using NEUROiD: A Web-Based NEUROmotor Integration and Design Platform

Decades of research on neuromotor circuits and systems has provided valuable information on neuronal control of movement. Computational models of several elements of the neuromotor system have been developed at various scales, from sub-cellular to system. While several small models abound, their structured integration is the key to building larger and more biologically realistic models which can predict the behavior of the system in different scenarios. This effort calls for integration of elements across neuroscience and musculoskeletal biomechanics. There is also a need for development of methods and tools for structured integration that yield larger in silico models demonstrating a set of desired system responses. We take a small step in this direction with the NEUROmotor integration and Design (NEUROiD) platform. NEUROiD helps integrate results from motor systems anatomy, physiology, and biomechanics into an integrated neuromotor system model. Simulation and visualization of the model across multiple scales is supported. Standard electrophysiological operations such as slicing, current injection, recording of membrane potential, and local field potential are part of NEUROiD. The platform allows traceability of model parameters to primary literature. We illustrate the power and utility of NEUROiD by building a simple ankle model and its controlling neural circuitry by curating a set of published components. NEUROiD allows researchers to utilize remote high-performance computers for simulation, while controlling the model using a web browser.

A Closed-Loop Toolchain for Neural Network Simulations of Learning Autonomous Agents

Neural network simulation is an important tool for generating and evaluating hypotheses on the structure, dynamics, and function of neural circuits. For scientific questions addressing organisms operating autonomously in their environments, in particular where learning is involved, it is crucial to be able to operate such simulations in a closed-loop fashion. In such a set-up, the neural agent continuously receives sensory stimuli from the environment and provides motor signals that manipulate the environment or move the agent within it. So far, most studies requiring such functionality have been conducted with custom simulation scripts and manually implemented tasks. This makes it difficult for other researchers to reproduce and build upon previous work and nearly impossible to compare the performance of different learning architectures. In this work, we present a novel approach to solve this problem, connecting benchmark tools from the field of machine learning and state-of-the-art neural network simulators from computational neuroscience. The resulting toolchain enables researchers in both fields to make use of well-tested high-performance simulation software supporting biologically plausible neuron, synapse and network models and allows them to evaluate and compare their approach on the basis of standardized environments with various levels of complexity. We demonstrate the functionality of the toolchain by implementing a neuronal actor-critic architecture for reinforcement learning in the NEST simulator and successfully training it on two different environments from the OpenAI Gym. We compare its performance to a previously suggested neural network model of reinforcement learning in the basal ganglia and a generic Q-learning algorithm.

Retina-Based Pipe-Like Object Tracking Implemented Through Spiking Neural Network on a Snake Robot

Vision based-target tracking ability is crucial to bio-inspired snake robots for exploring unknown environments. However, it is difficult for the traditional vision modules of snake robots to overcome the image blur resulting from periodic swings. A promising approach is to use a neuromorphic vision sensor (NVS), which mimics the biological retina to detect a target at a higher temporal frequency and in a wider dynamic range. In this study, an NVS and a spiking neural network (SNN) were performed on a snake robot for the first time to achieve pipe-like object tracking. An SNN based on Hough Transform was designed to detect a target with an asynchronous event stream fed by the NVS. Combining the state of snake motion analyzed by the joint position sensors, a tracking framework was proposed. The experimental results obtained from the simulator demonstrated the validity of our framework and the autonomous locomotion ability of our snake robot. Comparing the performances of the SNN model on CPUs and on GPUs, respectively, the SNN model showed the best performance on a GPU under a simplified and synchronous update rule while it possessed higher precision on a CPU in an asynchronous way.

Running Large-Scale Simulations on the Neurorobotics Platform to Understand Vision - The Case of Visual Crowding

Traditionally, human vision research has focused on specific paradigms and proposed models to explain very specific properties of visual perception. However, the complexity and scope of modern psychophysical paradigms undermine the success of this approach. For example, perception of an element strongly deteriorates when neighboring elements are presented in addition (visual crowding). As it was shown recently, the magnitude of deterioration depends not only on the directly neighboring elements but on almost all elements and their specific configuration. Hence, to fully explain human visual perception, one needs to take large parts of the visual field into account and combine all the aspects of vision that become relevant at such scale. These efforts require sophisticated and collaborative modeling. The Neurorobotics Platform (NRP) of the Human Brain Project offers a unique opportunity to connect models of all sorts of visual functions, even those developed by different research groups, into a coherently functioning system. Here, we describe how we used the NRP to connect and simulate a segmentation model, a retina model, and a saliency model to explain complex results about visual perception. The combination of models highlights the versatility of the NRP and provides novel explanations for inward-outward anisotropy in visual crowding.

Functional Source Separation for EEG-fMRI Fusion: Application to Steady-State Visual Evoked Potentials

Neurorobotics is one of the most ambitious fields in robotics, driving integration of interdisciplinary data and knowledge. One of the most productive areas of interdisciplinary research in this area has been the implementation of biologically-inspired mechanisms in the development of autonomous systems. Specifically, enabling such systems to display adaptive behavior such as learning from good and bad outcomes, has been achieved by quantifying and understanding the neural mechanisms of the brain networks mediating adaptive behaviors in humans and animals. For example, associative learning from aversive or dangerous outcomes is crucial for an autonomous system, to avoid dangerous situations in the future. A body of neuroscience research has suggested that the neurocomputations in the human brain during associative learning involve re-shaping of sensory responses. The nature of these adaptive changes in sensory processing during learning however are not yet well enough understood to be readily implemented into on-board algorithms for robotics application. Toward this overall goal, we record the simultaneous electroencephalogram (EEG) and functional magnetic resonance imaging (fMRI), characterizing one candidate mechanism, i.e., large-scale brain oscillations. The present report examines the use of Functional Source Separation (FSS) as an optimization step in EEG-fMRI fusion that harnesses timing information to constrain the solutions that satisfy physiological assumptions. We applied this approach to the voxel-wise correlation of steady-state visual evoked potential (ssVEP) amplitude and blood oxygen level-dependent imaging (BOLD), across both time series. The results showed the benefit of FSS for the extraction of robust ssVEP signals during simultaneous EEG-fMRI recordings. Applied to data from a 3-phase aversive conditioning paradigm, the correlation maps across the three phases (habituation, acquisition, extinction) show converging results, notably major overlapping areas in both primary and extended visual cortical regions, including calcarine sulcus, lingual cortex, and cuneus. In addition, during the acquisition phase when aversive learning occurs, we observed additional correlations between ssVEP and BOLD in the anterior cingulate cortex (ACC) as well as the precuneus and superior temporal gyrus.

A Brief History of Simulation Neuroscience

Our knowledge of the brain has evolved over millennia in philosophical, experimental and theoretical phases. We suggest that the next phase is simulation neuroscience. The main drivers of simulation neuroscience are big data generated at multiple levels of brain organization and the need to integrate these data to trace the causal chain of interactions within and across all these levels. Simulation neuroscience is currently the only methodology for systematically approaching the multiscale brain. In this review, we attempt to reconstruct the deep historical paths leading to simulation neuroscience, from the first observations of the nerve cell to modern efforts to digitally reconstruct and simulate the brain. Neuroscience began with the identification of the neuron as the fundamental unit of brain structure and function and has evolved towards understanding the role of each cell type in the brain, how brain cells are connected to each other, and how the seemingly infinite networks they form give rise to the vast diversity of brain functions. Neuronal mapping is evolving from subjective descriptions of cell types towards objective classes, subclasses and types. Connectivity mapping is evolving from loose topographic maps between brain regions towards dense anatomical and physiological maps of connections between individual genetically distinct neurons. Functional mapping is evolving from psychological and behavioral stereotypes towards a map of behaviors emerging from structural and functional connectomes. We show how industrialization of neuroscience and the resulting large disconnected datasets are generating demand for integrative neuroscience, how the scale of neuronal and connectivity maps is driving digital atlasing and digital reconstruction to piece together the multiple levels of brain organization, and how the complexity of the interactions between molecules, neurons, microcircuits and brain regions is driving brain simulation to understand the interactions in the multiscale brain.

Body Randomization Reduces the Sim-to-Real Gap for Compliant Quadruped Locomotion

Designing controllers for compliant, underactuated robots is challenging and usually requires a learning procedure. Learning robotic control in simulated environments can speed up the process whilst lowering risk of physical damage. Since perfect simulations are unfeasible, several techniques are used to improve transfer to the real world. Here, we investigate the impact of randomizing body parameters during learning of CPG controllers in simulation. The controllers are evaluated on our physical quadruped robot. We find that body randomization in simulation increases chances of finding gaits that function well on the real robot.

Combining Motor Primitives for Perception Driven Target Reaching With Spiking Neurons

Target reaching is one of the most important areas in robotics, object interaction, manipulation and grasping tasks require reaching specific targets. The authors avoid the complexity of calculating the inverse kinematics and doing motion planning, and instead use a combination of motor primitives. A bio-inspired architecture performs target reaching with a robot arm without planning. A spiking neural network represents motions in a hierarchy of motor primitives, and different correction primitives are combined using an error signal. In this article two experiments using a simulation of a robot arm are presented, one to extensively cover the working space by going to different points and returning to the start point, the other to test extreme targets and random points in sequence. Robotics applications—like target reaching—can provide benchmarking tasks and realistic scenarios for validation of neuroscience models, and also take advantage of the capabilities of spiking neural networks and the properties of neuromorphic hardware to run the models.

Exploring the role of striatal D1 and D2 medium spiny neurons in action selection using a virtual robotic framework

The basal ganglia have been hypothesized to be involved in action selection, i.e. resolving competition between simultaneously activated motor programs. It has been shown that the direct pathway facilitates action execution whereas the indirect pathway inhibits it. However, as the pathways are both active during an action, it remains unclear whether their role is co-operative or competitive. In order to investigate this issue, we developed a striatal model consisting of D1 and D2 medium spiny neurons (MSNs) and interfaced it to a simulated robot moving in an environment. We demonstrate that this model is able to reproduce key behavioral features of several experiments involving optogenetic manipulation of the striatum, such as freezing and ambulation. We then investigate the interaction of D1- and D2-MSNs. We find that their fundamental relationship is co-operative within a channel and competitive between channels; this turns out to be crucial for action selection. However, individual pairs of D1- and D2-MSNs may exhibit predominantly competition or co-operation depending on their distance, and D1- and D2-MSNs population activity can alternate between co-operation and competition modes during a stimulation. Additionally, our results show that D2-D2 connectivity between channels is necessary for effective resolution of competition; in its absence, a conflict of two motor programs typically results in neither being selected.

Neurorobotics-A Thriving Community and a Promising Pathway Toward Intelligent Cognitive Robots

Neurorobots are robots whose control has been modeled after some aspect of the brain. Since the brain is so closely coupled to the body and situated in the environment, Neurorobots can be a powerful tool for studying neural function in a holistic fashion. It may also be a means to develop autonomous systems that have some level of biological intelligence. The present article provides my perspective on this field, points out some of the landmark events, and discusses its future potential.

A Survey of Robotics Control Based on Learning-Inspired Spiking Neural Networks

Biological intelligence processes information using impulses or spikes, which makes those living creatures able to perceive and act in the real world exceptionally well and outperform state-of-the-art robots in almost every aspect of life. To make up the deficit, emerging hardware technologies and software knowledge in the fields of neuroscience, electronics, and computer science have made it possible to design biologically realistic robots controlled by spiking neural networks (SNNs), inspired by the mechanism of brains. However, a comprehensive review on controlling robots based on SNNs is still missing. In this paper, we survey the developments of the past decade in the field of spiking neural networks for control tasks, with particular focus on the fast emerging robotics-related applications. We first highlight the primary impetuses of SNN-based robotics tasks in terms of speed, energy efficiency, and computation capabilities. We then classify those SNN-based robotic applications according to different learning rules and explicate those learning rules with their corresponding robotic applications. We also briefly present some existing platforms that offer an interaction between SNNs and robotics simulations for exploration and exploitation. Finally, we conclude our survey with a forecast of future challenges and some associated potential research topics in terms of controlling robots based on SNNs.