A brain machine interface framework for exploring proactive control of smart environments

Brain machine interfaces (BMIs) can substantially improve the quality of life of elderly or disabled people. However, performing complex action sequences with a BMI system is onerous because it requires issuing commands sequentially. Fundamentally different from this, we have designed a BMI system that reads out mental planning activity and issues commands in a proactive manner. To demonstrate this, we recorded brain activity from freely-moving monkeys performing an instructed task and decoded it with an energy-efficient, small and mobile field-programmable gate array hardware decoder triggering real-time action execution on smart devices. Core of this is an adaptive decoding algorithm that can compensate for the day-by-day neuronal signal fluctuations with minimal re-calibration effort. We show that open-loop planning-ahead control is possible using signals from primary and pre-motor areas leading to significant time-gain in the execution of action sequences. This novel approach provides, thus, a stepping stone towards improved and more humane control of different smart environments with mobile brain machine interfaces.

Integrated Modular Neural Control for Versatile Locomotion and Object Transportation of a Dung Beetle-Like Robot

Dung beetles can effectively transport dung pallets of various sizes in any direction across uneven terrain. While this impressive ability can inspire new locomotion and object transportation solutions in multilegged (insect-like) robots, to date, most existing robots use their legs primarily to perform locomotion. Only a few robots can use their legs to achieve both locomotion and object transportation, although they are limited to specific object types/sizes (10%-65% of leg length) on flat terrain. Accordingly, we proposed a novel integrated neural control approach that, like dung beetles, pushes state-of-the-art insect-like robots beyond their current limits toward versatile locomotion and object transportation with different object types/sizes and terrains (flat and uneven). The control method is synthesized based on modular neural mechanisms, integrating central pattern generator (CPG)-based control, adaptive local leg control, descending modulation control, and object manipulation control. We also introduced an object transportation strategy combining walking and periodic hind leg lifting for soft object transportation. We validated our method on a dung beetle-like robot. Our results show that the robot can perform versatile locomotion and use its legs to transport hard and soft objects of various sizes (60%-70% of leg length) and weights (approximately 3%-115% of robot weight) on flat and uneven terrains. The study also suggests possible neural control mechanisms underlying the dung beetle Scarabaeus galenus' versatile locomotion and small dung pallet transportation.

The effect of surface topography on the ball-rolling ability of Kheper lamarcki (Scarabaeidae)

The most effective way to avoid intense inter- and intra-specific competition at the dung source, and to increase the distance to the other competitors, is to follow a single straight bearing. While ball-rolling dung beetles manage to roll their dung balls along nearly perfect straight paths when traversing flat terrain, the paths that they take when traversing more complex (natural) terrain are not well understood. In this study, we investigate the effect of complex surface topographies on the ball-rolling ability of Kheper lamarcki. Our results reveal that ball-rolling trajectories are strongly influenced by the characteristic scale of the surface structure. Surfaces with an increasing similarity between the average distance of elevations and the ball radius cause progressively more difficulties during ball transportation. The most important factor causing difficulties in ball transportation appears to be the slope of the substrate. Our results show that, on surfaces with a slope of 7.5 deg, more than 60% of the dung beetles lose control of their ball. Although dung beetles still successfully roll their dung ball against the slope on such inclinations, their ability to roll the dung ball sideways diminishes. However, dung beetles do not seem to adapt their path on inclines such that they roll their ball in the direction against the slope. We conclude that dung beetles strive for a straight trajectory away from the dung pile, and that their actual path is the result of adaptations to particular surface topographies.

Leg-body coordination strategies for obstacle avoidance and narrow space navigation of multi-segmented, legged robots

Introduction

Millipedes can avoid obstacle while navigating complex environments with their multi-segmented body. Biological evidence indicates that when the millipede navigates around an obstacle, it first bends the anterior segments of its corresponding anterior segment of its body, and then gradually propagates this body bending mechanism from anterior to posterior segments. Simultaneously, the stride length between pairs of legs inside the bending curve decreases to coordinate the leg motions with the bending mechanism of the body segments. In robotics, coordination between multiple legs and body segments during turning for navigating in complex environments, e.g., narrow spaces, has not been fully realized in multi-segmented, multi-legged robots with more than six legs.

Method

To generate the efficient obstacle avoidance turning behavior in a multi-segmented, multi-legged (millipede-like) robot, this study explored three possible strategies of leg and body coordination during turning: including the local leg and body coordination at the segment level in a manner similar to millipedes, global leg amplitude change in response to different turning directions (like insects), and the phase reversal of legs inside of turning curve during obstacle avoidance (typical engineering approach).

Results

Using sensory inputs obtained from the antennae located at the robot head and recurrent neural control, different turning strategies were generated, with gradual body bending propagation from the anterior to posterior body segments.

Discussion

We discovered differences in the performance of each turning strategy, which could guide the future control development of multi-segmented, legged robots.

Hybrid learning mechanisms under a neural control network for various walking speed generation of a quadruped robot

Legged robots that can instantly change motor patterns at different walking speeds are useful and can accomplish various tasks efficiently. However, state-of-the-art control methods either are difficult to develop or require long training times. In this study, we present a comprehensible neural control framework to integrate probability-based black-box optimization (PIBB) and supervised learning for robot motor pattern generation at various walking speeds. The control framework structure is based on a combination of a central pattern generator (CPG), a radial basis function (RBF) -based premotor network and a hypernetwork, resulting in a so-called neural CPG-RBF-hyper control network. First, the CPG-driven RBF network, acting as a complex motor pattern generator, was trained to learn policies (multiple motor patterns) for different speeds using PIBB. We also introduce an incremental learning strategy to avoid local optima. Second, the hypernetwork, which acts as a task/behavior to control parameter mapping, was trained using supervised learning. It creates a mapping between the internal CPG frequency (reflecting the walking speed) and motor behavior. This map represents the prior knowledge of the robot, which contains the optimal motor joint patterns at various CPG frequencies. Finally, when a user-defined robot walking frequency or speed is provided, the hypernetwork generates the corresponding policy for the CPG-RBF network. The result is a versatile locomotion controller which enables a quadruped robot to perform stable and robust walking at different speeds without sensory feedback. The policy of the controller was trained in the simulation (less than 1 h) and capable of transferring to a real robot. The generalization ability of the controller was demonstrated by testing the CPG frequencies that were not encountered during training.

Adaptive Modular Neural Control for Online Gait Synchronization and Adaptation of an Assistive Lower-Limb Exoskeleton

Gait synchronization has attracted significant attention in research on assistive lower-limb exoskeletons because it can circumvent conflicting movements and improve the assistance performance. This study proposes an adaptive modular neural control (AMNC) for online gait synchronization and the adaptation of a lower-limb exoskeleton. The AMNC comprises several distributed and interpretable neural modules that interact with each other to effectively exploit neural dynamics and adopt feedback signals to quickly reduce the tracking error, thereby smoothly synchronizing the exoskeleton movement with the user's movement on the fly. Taking state-of-the-art control as the benchmark, the proposed AMNC provides further improvements in the locomotion phase, frequency, and shape adaptation. Accordingly, under the physical interaction between the user and the exoskeleton, the control can reduce the optimized tracking error and unseen interaction torque by up to 80% and 30%, respectively. Accordingly, this study contributes to the advancement of exoskeleton and wearable robotics research in gait assistance for the next generation of personalized healthcare.

Robust and reusable self-organized locomotion of legged robots under adaptive physical and neural communications

Introduction

Animals such as cattle can achieve versatile and elegant behaviors through automatic sensorimotor coordination. Their self-organized movements convey an impression of adaptability, robustness, and motor memory. However, the adaptive mechanisms underlying such natural abilities of these animals have not been completely realized in artificial legged systems.

Methods

Hence, we propose adaptive neural control that can mimic these abilities through adaptive physical and neural communications. The control algorithm consists of distributed local central pattern generator (CPG)-based neural circuits for generating basic leg movements, an adaptive sensory feedback mechanism for generating self-organized phase relationships among the local CPG circuits, and an adaptive neural coupling mechanism for transferring and storing the formed phase relationships (a gait pattern) into the neural structure. The adaptive neural control was evaluated in experiments using a quadruped robot.

Results

The adaptive neural control enabled the robot to 1) rapidly and automatically form its gait (i.e., self-organized locomotion) within a few seconds, 2) memorize the gait for later recovery, and 3) robustly walk, even when a sensory feedback malfunction occurs. It also enabled maneuverability, with the robot being able to change its walking speed and direction. Moreover, implementing adaptive physical and neural communications provided an opportunity for understanding the mechanism of motor memory formation.

Discussion

Overall, this study demonstrates that the integration of the two forms of communications through adaptive neural control is a powerful way to achieve robust and reusable self-organized locomotion in legged robots.

A virtuous cycle between invertebrate and robotics research: perspective on a decade of Living Machines research

Many invertebrates are ideal model systems on which to base robot design principles due to their success in solving seemingly complex tasks across domains while possessing smaller nervous systems than vertebrates. Three areas are particularly relevant for robot designers: Research on flying and crawling invertebrates has inspired new materials and geometries from which robot bodies (their morphologies) can be constructed, enabling a new generation of softer, smaller, and lighter robots. Research on walking insects has informed the design of new systems for controlling robot bodies (their motion control) and adapting their motion to their environment without costly computational methods. And research combining wet and computational neuroscience with robotic validation methods has revealed the structure and function of core circuits in the insect brain responsible for the navigation and swarming capabilities (their mental faculties) displayed by foraging insects. The last decade has seen significant progress in the application of principles extracted from invertebrates, as well as the application of biomimetic robots to model and better understand how animals function. This Perspectives paper on the past 10 years of the Living Machines conference outlines some of the most exciting recent advances in each of these fields before outlining lessons gleaned and the outlook for the next decade of invertebrate robotic research.

A neural coordination strategy for attachment and detachment of a climbing robot inspired by gecko locomotion

Climbing behavior is a superior motion skill that animals have evolved to obtain a more beneficial position in complex natural environments. Compared to animals, current bionic climbing robots are less agile, stable, and energy-efficient. Further, they locomote at a low speed and have poor adaptation to the substrate. One of the key elements that can improve their locomotion efficiency is the active and flexible feet or toes observed in climbing animals. Inspired by the active attachment-detachment behavior of geckos, a hybrid pneumatic-electric-driven climbing robot with active attachment-detachment bionic flexible feet (toes) was developed. Although the introduction of bionic flexible toes can effectively improve the robot's adaptability to the environment, it also poses control challenges, specifically, the realization of attachment-detachment behavior by the mechanics of the feet, the realization of hybrid drive control with different response characteristics, and the interlimb collaboration and limb-foot coordination with a hysteresis effect. Through the analysis of geckos' limbs and foot kinematic behavior during climbing, rhythmic attachment-detachment strategies and coordination behavior between toes and limbs at different inclines were identified. To enable the robot to achieve similar foot attachment-detachment behavior for climbing ability enhancement, we propose a modular neural control framework comprising a central pattern generator module, a post-processing central pattern generation module, a hysteresis delay line module, and an actuator signal conditioning module. Among them, the hysteresis adaptation module helps the bionic flexible toes to achieve variable phase relationships with the motorized joint, thus enabling proper limb-to-foot coordination and interlimb collaboration. The experiments demonstrated that the robot with neural control achieved proper coordination, resulting in a foot with a 285% larger adhesion area than that of a conventional algorithm. In addition, in the plane/arc climbing scenario, the robot with coordination behavior increased by as much as 150%, compared to the incoordinated one owing to its higher adhesion reliability.

No Need for Landmarks: An Embodied Neural Controller for Robust Insect-Like Navigation Behaviors

Bayesian filters have been considered to help refine and develop theoretical views on spatial cell functions for self-localization. However, extending a Bayesian filter to reproduce insect-like navigation behaviors (e.g., home searching) remains an open and challenging problem. To address this problem, we propose an embodied neural controller for self-localization, foraging, backward homing (BH), and home searching of an advanced mobility sensor (AMOS)-driven insect-like robot. The controller, comprising a navigation module for the Bayesian self-localization and goal-directed control of AMOS and a locomotion module for coordinating the 18 joints of AMOS, leads to its robust insect-like navigation behaviors. As a result, the proposed controller enables AMOS to perform robust foraging, BH, and home searching against various levels of sensory noise, compared to conventional controllers. Its implementation relies only on self-localization and heading perception, rather than global positioning and landmark guidance. Interestingly, the proposed controller makes AMOS achieve spiral searching patterns comparable to those performed by real insects. We also demonstrated the performance of the controller for real-time indoor and outdoor navigation in a real insect-like robot without any landmark and cognitive map.

Frictional Anisotropic Locomotion and Adaptive Neural Control for a Soft Crawling Robot

Crawling animals with bendable soft bodies use the friction anisotropy of their asymmetric body structures to traverse various substrates efficiently. Although the effect of friction anisotropy has been investigated and applied to robot locomotion, the dynamic interactions between soft body bending at different frequencies (low and high), soft asymmetric surface structures at various aspect ratios (low, medium, and high), and different substrates (rough and smooth) have not been studied comprehensively. To address this lack, we developed a simple soft robot model with a bioinspired asymmetric structure (sawtooth) facing the ground. The robot uses only a single source of pressure for its pneumatic actuation. The frequency, teeth aspect ratio, and substrate parameters and the corresponding dynamic interactions were systematically investigated and analyzed. The study findings indicate that the anterior and posterior parts of the structure deform differently during the interaction, generating different frictional forces. In addition, these parts switched their roles dynamically from push to pull and vice versa in various states, resulting in the robot's emergent locomotion. Finally, autonomous adaptive crawling behavior of the robot was demonstrated using sensor-driven neural control with a miniature laser sensor installed in the anterior part of the robot. The robot successfully adapted its actuation frequency to reduce body bending and crawl through a narrow space, such as a tunnel. The study serves as a stepping stone for developing simple soft crawling robots capable of navigating cluttered and confined spaces autonomously.

The Roles and Comparison of Rigid and Soft Tails in Gecko-Inspired Climbing Robots: A Mini-Review

Geckos use millions of dry bristles on their toes to adhere to and rapidly run up walls and across ceilings. This has inspired the successful development of dry adhesive materials and their application to climbing robots. The tails of geckos also help realize adaptive and robust climbing behavior. Existing climbing robots with gecko-inspired tails have demonstrated improved locomotion performance. However, few studies have focused on the role of a robot’s gecko-inspired tail when climbing a sloped surface and its effects on the overall locomotion performance. Thus, this paper reviews and analyzes the roles of the tails of geckos and robots in terms of their climbing performances and compares the advantages and disadvantages of robots’ tails made of rigid and soft materials. This review could assist roboticists decide whether a tail is required for their robots and which materials and motion types to use for the tail in order to fulfill their desired functions and even allow the robots to adapt to different environments and tasks.

Generic Mechanism for Waveform Regulation and Synchronization of Oscillators: An Application for Robot Behavior Diversity Generation

While nonlinear oscillators have been widely used for central pattern generators to produce basic rhythmic signals for robot locomotion control, methods to shape and regulate the signal waveform without changing the characteristics of the oscillators have not been fully investigated, especially during the network synchronization process. To illustrate the principle and process of waveform regulation of nonlinear oscillators in detail and ensure that the influence can be controlled, we present a method for waveform regulation and synchronization and analyze the relationship of different factors (e.g., initial conditions, network parameters, phase, and waveform regulation factors) in synchronization deviation. Then, the method is indicated to be effective in other commonly used nonlinear oscillators and neural oscillators. As an example application, a three-layer behavioral control architecture for a legged robot is constructed based on the proposed method. Modules for the body behavior, leg coordination, and single-leg adjustment are established to realize diverse robot behaviors. The effectiveness of the method is validated by a series of experiments. The results prove that the method performs well in terms of signal control accuracy, behavior pattern diversity, and smooth motion transition.

Continuous Online Adaptation of Bioinspired Adaptive Neuroendocrine Control for Autonomous Walking Robots

Walking animals can continuously adapt their locomotion to deal with unpredictable changing environments. They can also take proactive steps to avoid colliding with an obstacle. In this study, we aim to realize such features for autonomous walking robots so that they can efficiently traverse complex terrains. To achieve this, we propose novel bioinspired adaptive neuroendocrine control. In contrast to conventional locomotion control methods, this approach does not require robot and environmental models, exteroceptive feedback, or multiple learning trials. It integrates three main modular neural mechanisms, relying only on proprioceptive feedback and short-term memory, namely: 1) neural central pattern generator (CPG)-based control; 2) an artificial hormone network (AHN); and 3) unsupervised input correlation-based learning (ICO). The neural CPG-based control creates insect-like gaits, while the AHN can continuously adapt robot joint movement individually with respect to the terrain during the stance phase using only the torque feedback. In parallel, the ICO generates short-term memory for proactive obstacle negotiation during the swing phase, allowing the posterior legs to step over the obstacle before hitting it. The control approach is evaluated on a bioinspired hexapod robot walking on complex unpredictable terrains (e.g., gravel, grass, and extreme random stepfield). The results show that the robot can successfully perform energy-efficient autonomous locomotion and online continuous adaptation with proactivity to overcome such terrains. Since our adaptive neural control approach does not require a robot model, it is general and can be applied to other bioinspired walking robots to achieve a similar adaptive, autonomous, and versatile function.

Neural Control and Online Learning for Speed Adaptation of Unmanned Aerial Vehicles

Unmanned aerial vehicles (UAVs) are involved in critical tasks such as inspection and exploration. Thus, they have to perform several intelligent functions. Various control approaches have been proposed to implement these functions. Most classical UAV control approaches, such as model predictive control, require a dynamic model to determine the optimal control parameters. Other control approaches use machine learning techniques that require multiple learning trials to obtain the proper control parameters. All these approaches are computationally expensive. Our goal is to develop an efficient control system for UAVs that does not require a dynamic model and allows them to learn control parameters online with only a few trials and inexpensive computations. To achieve this, we developed a neural control method with fast online learning. Neural control is based on a three-neuron network, whereas the online learning algorithm is derived from a neural correlation-based learning principle with predictive and reflexive sensory information. This neural control technique is used here for the speed adaptation of the UAV. The control technique relies on a simple input signal from a compact optical distance measurement sensor that can be converted into predictive and reflexive sensory information for the learning algorithm. Such speed adaptation is a fundamental function that can be used as part of other complex control functions, such as obstacle avoidance. The proposed technique was implemented on a real UAV system. Consequently, the UAV can quickly learn within 3–4 trials to proactively adapt its flying speed to brake at a safe distance from the obstacle or target in the horizontal and vertical planes. This speed adaptation is also robust against wind perturbation. We also demonstrated a combination of speed adaptation and obstacle avoidance for UAV navigations, which is an important intelligent function toward inspection and exploration.

A gecko-inspired robot with CPG-based neural control for locomotion and body height adaptation

Today's gecko-inspired robots have shown the ability of omnidirectional climbing on slopes with a low centre of mass. However, such an ability cannot efficiently cope with bumpy terrains or terrains with obstacles. In this study, we developed a gecko-inspired robot (Nyxbot) with an adaptable body height to overcome this limitation. Based on an analysis of the skeletal system and kinematics of real geckos, the adhesive mechanism and leg structure design of the robot were designed to endow it with adhesion and adjustable body height capabilities. Neural control with exteroceptive sensory feedback is utilised to realise body height adaptability while climbing on a slope. The locomotion performance and body adaptability of the robot were tested by conducting slope climbing and obstacle crossing experiments. The gecko robot can climb a 30° slope with spontaneous obstacle crossing (maximum obstacle height of 38% of the body height) and can climb even steeper slopes (up to 60°) without an obstacle or bump. Using 3D force measuring platforms for ground reaction force analysis of geckos and the robot, we show that the motions of the developed robot driven by neural control and the motions of geckos are dynamically comparable. To this end, this study provides a basis for developing climbing robots with adaptive bump/obstacle crossing on slopes towards more agile and versatile gecko-like locomotion.

Network Architecture Producing Swing to Stance Transitions in an Insect Walking System

The walking system of the stick insect is one of the most thoroughly described invertebrate systems. We know a lot about the role of sensory input in the control of stepping of a single leg. However, the neuronal organization and connectivity of the central neural networks underlying the rhythmic activation and coordination of leg muscles still remain elusive. It is assumed that these networks can couple in the absence of phasic sensory input due to the observation of spontaneous recurrent patterns (SRPs) of coordinated motor activity equivalent to fictive stepping-phase transitions. Here we sought to quantify the phase of motor activity within SRPs in the isolated and interconnected meso- and meta-thoracic ganglia. We show that SRPs occur not only in the meso-, but also in the metathoracic ganglia of the stick insect, discovering a qualitative difference between them. We construct a network based on neurophysiological data capable of reproducing the measured SRP phases to investigate this difference. By comparing network output to the biological measurements we confirm the plausibility of the architecture and provide a hypothesis to account for these qualitative differences. The neural architecture we present couples individual central pattern generators to reproduce the fictive stepping-phase transitions observed in deafferented stick insect preparations after pharmacological activation, providing insights into the neural architecture underlying coordinated locomotion.

Electromagnetic Feet With Soft Toes for Adaptive, Versatile, and Stable Locomotion of an Inchworm-Inspired Pipe Crawling Robot

Feet play an important role in the adaptive, versatile, and stable locomotion of legged creatures. Accordingly, several robotic research studies have used biological feet as the inspiration for the design of robot feet in traversing complex terrains. However, so far, no robot feet can allow legged robots to adaptively, versatilely, and robustly crawl on various curved metal pipes, including flat surfaces for pipe inspection. To address this issue, we propose here a novel hybrid rigid-soft robot-foot design inspired by the leg morphology of an inchworm. The foot consists of a rigid section with an electromagnet and a soft toe covering for enhanced adhesion to a metal pipe. Finite element analysis , performed under different loading conditions, reveals that due to its compliance, the soft toe can undergo recoverable deformation with adaptability to various curved metal pipes and plain metal surfaces. We have successfully implemented electromagnetic feet with soft toes (EROFT) on an inchworm-inspired pipe crawling robot for adaptive, versatile, and stable locomotion. Foot-to-surface adaptability is provided by the inherent elasticity of the soft toe, making the robot a versatile and stable metal pipe crawler. Experiments show that the robot crawling success rate reaches 100% on large diameter metal pipes. The proposed hybrid rigid-soft feet (i.e., electromagnetic feet with soft toes) can solve the problem of continuous surface adaptation for the robot in a stable and efficient manner, irrespective of the surface curvature, without the need to manually change the robot feet for specific surfaces. To this end, the foot development enables the robot to meet a set of deployment requirements on large oil and gas pipelines for potential use in inspecting various faults and leakages.

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.

Locomotion Control With Frequency and Motor Pattern Adaptations

Existing adaptive locomotion control mechanisms for legged robots are usually aimed at one specific type of adaptation and rarely combined with others. Adaptive mechanisms thus stay at a conceptual level without their coupling effect with other mechanisms being investigated. However, we hypothesize that the combination of adaptation mechanisms can be exploited for enhanced and more efficient locomotion control as in biological systems. Therefore, in this work, we present a central pattern generator (CPG) based locomotion controller integrating both a frequency and motor pattern adaptation mechanisms. We use the state-of-the-art Dual Integral Learner for frequency adaptation, which can automatically and quickly adapt the CPG frequency, enabling the entire motor pattern or output signal of the CPG to be followed at a proper high frequency with low tracking error. Consequently, the legged robot can move with high energy efficiency and perform the generated locomotion with high precision. The versatile state-of-the-art CPG-RBF network is used as a motor pattern adaptation mechanism. Using this network, the motor patterns or joint trajectories can be adapted to fit the robot's morphology and perform sensorimotor integration enabling online motor pattern adaptation based on sensory feedback. The results show that the two adaptation mechanisms can be combined for adaptive locomotion control of a hexapod robot in a complex environment. Using the CPG-RBF network for motor pattern adaptation, the hexapod learned basic straight forward walking, steering, and step climbing. In general, the frequency and motor pattern mechanisms complement each other well and their combination can be seen as an essential step toward further studies on adaptive locomotion control.

Insect-Inspired Robots: Bridging Biological and Artificial Systems

This review article aims to address common research questions in hexapod robotics. How can we build intelligent autonomous hexapod robots that can exploit their biomechanics, morphology, and computational systems, to achieve autonomy, adaptability, and energy efficiency comparable to small living creatures, such as insects? Are insects good models for building such intelligent hexapod robots because they are the only animals with six legs? This review article is divided into three main sections to address these questions, as well as to assist roboticists in identifying relevant and future directions in the field of hexapod robotics over the next decade. After an introduction in section (1), the sections will respectively cover the following three key areas: (2) biomechanics focused on the design of smart legs; (3) locomotion control; and (4) high-level cognition control. These interconnected and interdependent areas are all crucial to improving the level of performance of hexapod robotics in terms of energy efficiency, terrain adaptability, autonomy, and operational range. We will also discuss how the next generation of bioroboticists will be able to transfer knowledge from biology to robotics and vice versa.

Mini Review: Comparison of Bio-Inspired Adhesive Feet of Climbing Robots on Smooth Vertical Surfaces

Developing climbing robots for smooth vertical surfaces (e.g., glass) is one of the most challenging problems in robotics. Here, the adequate functioning of an adhesive foot is an essential factor for successful locomotion performance. Among the various technologies (such as dry adhesion, wet adhesion, magnetic adhesion, and pneumatic adhesion), bio-inspired dry adhesion has been actively studied and successfully applied to climbing robots. Thus, this review focuses on the characteristics of two different types of foot microstructures, namely spatula-shaped and mushroom-shaped, capable of generating such adhesion. These are the most used types of foot microstructures in climbing robots for smooth vertical surfaces. Moreover, this review shows that the spatula-shaped feet are particularly suitable for massive and one-directional climbing robots, whereas mushroom-shaped feet are primarily suitable for light and all-directional climbing robots. Consequently, this study can guide roboticists in selecting the right adhesive foot to achieve the best climbing ability for future robot developments.

The SMOOTH-Robot: A Modular, Interactive Service Robot

The SMOOTH-robot is a mobile robot that-due to its modularity-combines a relatively low price with the possibility to be used for a large variety of tasks in a wide range of domains. In this article, we demonstrate the potential of the SMOOTH-robot through three use cases, two of which were performed in elderly care homes. The robot is designed so that it can either make itself ready or be quickly changed by staff to perform different tasks. We carefully considered important design parameters such as the appearance, intended and unintended interactions with users, and the technical complexity, in order to achieve high acceptability and a sufficient degree of utilization of the robot. Three demonstrated use cases indicate that such a robot could contribute to an improved work environment, having the potential to free resources of care staff which could be allocated to actual care-giving tasks. Moreover, the SMOOTH-robot can be used in many other domains, as we will also exemplify in this article.

The SMOOTH-Robot: A Modular, Interactive Service Robot

The SMOOTH-robot is a mobile robot that-due to its modularity-combines a relatively low price with the possibility to be used for a large variety of tasks in a wide range of domains. In this article, we demonstrate the potential of the SMOOTH-robot through three use cases, two of which were performed in elderly care homes. The robot is designed so that it can either make itself ready or be quickly changed by staff to perform different tasks. We carefully considered important design parameters such as the appearance, intended and unintended interactions with users, and the technical complexity, in order to achieve high acceptability and a sufficient degree of utilization of the robot. Three demonstrated use cases indicate that such a robot could contribute to an improved work environment, having the potential to free resources of care staff which could be allocated to actual care-giving tasks. Moreover, the SMOOTH-robot can be used in many other domains, as we will also exemplify in this article.

Echo State Networks for Estimating Exteroceptive Conditions From Proprioceptive States in Quadruped Robots

We propose a methodology based on reservoir computing for mapping local proprioceptive information acquired at the level of the leg joints of a simulated quadruped robot into exteroceptive and global information, including both the ground reaction forces at the level of the different legs and information about the type of terrain traversed by the robot. Both dynamic estimation and terrain classification can be achieved concurrently with the same reservoir computing structure, which serves as a soft sensor device. Simulation results are presented together with preliminary experiments on a real quadruped robot. They demonstrate the suitability of the proposed approach for various terrains and sensory system fault conditions. The strategy, which belongs to the class of data-driven models, is independent of the robotic mechanical design and can easily be generalized to different robotic structures.

Corrigendum: Small-Sized Reconfigurable Quadruped Robot With Multiple Sensory Feedback for Studying Adaptive and Versatile Behaviors

[This corrects the article DOI: 10.3389/fnbot.2020.00014.].

Generic Neural Locomotion Control Framework for Legged Robots

In this article, we present a generic locomotion control framework for legged robots and a strategy for control policy optimization. The framework is based on neural control and black-box optimization. The neural control combines a central pattern generator (CPG) and a radial basis function (RBF) network to create a CPG-RBF network. The control network acts as a neural basis to produce arbitrary rhythmic trajectories for the joints of robots. The main features of the CPG-RBF network are: 1) it is generic since it can be applied to legged robots with different morphologies; 2) it has few control parameters, resulting in fast learning; 3) it is scalable, both in terms of policy/trajectory complexity and the number of legs that can be controlled using similar trajectories; 4) it does not rely heavily on sensory feedback to generate locomotion and is thus less prone to sensory faults; and 5) once trained, it is simple, minimal, and intuitive to use and analyze. These features will lead to an easy-to-use framework with fast convergence and the ability to encode complex locomotion control policies. In this work, we show that the framework can successfully be applied to three different simulated legged robots with varying morphologies and, even broken joints, to learn locomotion control policies. We also show that after learning, the control policies can also be successfully transferred to a real-world robot without any modifications. We, furthermore, show the scalability of the framework by implementing it as a central controller for all legs of a robot and as a decentralized controller for individual legs and leg pairs. By investigating the correlation between robot morphology and encoding type, we are able to present a strategy for control policy optimization. Finally, we show how sensory feedback can be integrated into the CPG-RBF network to enable online adaptation.

Online sensorimotor learning and adaptation for inverse dynamics control

We propose a micro-data (< 10 trials) sensorimotor learning and adaptation (SEED) model for human-like arm inverse dynamics control. The SEED model consists of a feedforward Gaussian motor primitive (GATE) neural network and an adaptive feedback impedance (AIM) mechanism. Sensorimotor weights over trials are learned in the GATE network, while the AIM mechanism is used to online tune impedance gains in a trial. The model was validated by periodic and non-periodic tracking tasks on a two-joint robot arm. As a result, the proposed model enables the arm to stably learn the tasks within 10 trials, compared to thousands of trials required by state-of-art deep learning. This model facilitates the exploration of unknown arm dynamics, in which the elbow joint requires much less active control compared to the shoulder. This control goes below 3% of the overall effort. This finding complies with a proximal-distal control gradient in human arm control. Taken together, the proposed SEED model paves a way for implementing data-efficient sensorimotor learning and adaptation of human-like arm movement.

Corrigendum: [A Comparative Study of Adaptive Interlimb Coordination Mechanisms for Self-Organized Robot Locomotion]

[This corrects the article DOI: 10.3389/frobt.2021.638684.].

A Comparative Study of Adaptive Interlimb Coordination Mechanisms for Self-Organized Robot Locomotion

Walking animals demonstrate impressive self-organized locomotion and adaptation to body property changes by skillfully manipulating their complicated and redundant musculoskeletal systems. Adaptive interlimb coordination plays a crucial role in this achievement. It has been identified that interlimb coordination is generated through dynamical interactions between the neural system, musculoskeletal system, and environment. Based on this principle, two classical interlimb coordination mechanisms (continuous phase modulation and phase resetting) have been proposed independently. These mechanisms use decoupled central pattern generators (CPGs) with sensory feedback, such as ground reaction forces (GRFs), to generate robot locomotion autonomously without predefining it (i.e., self-organized locomotion). A comparative study was conducted on the two mechanisms under decoupled CPG-based control implemented on a quadruped robot in simulation. Their characteristics were compared by observing their CPG phase convergence processes at different control parameter values. Additionally, the mechanisms were investigated when the robot faced various unexpected situations, such as noisy feedback, leg motor damage, and carrying a load. The comparative study reveals that the phase modulation and resetting mechanisms demonstrate satisfactory performance when they are subjected to symmetric and asymmetric GRF distributions, respectively. This work also suggests a strategy for the appropriate selection of adaptive interlimb coordination mechanisms under different conditions and for the optimal setting of their control parameter values to enhance their control performance.

Integrating Non-spiking Interneurons in Spiking Neural Networks

Researchers working with neural networks have historically focused on either non-spiking neurons tractable for running on computers or more biologically plausible spiking neurons typically requiring special hardware. However, in nature homogeneous networks of neurons do not exist. Instead, spiking and non-spiking neurons cooperate, each bringing a different set of advantages. A well-researched biological example of such a mixed network is a sensorimotor pathway, responsible for mapping sensory inputs to behavioral changes. This type of pathway is also well-researched in robotics where it is applied to achieve closed-loop operation of legged robots by adapting amplitude, frequency, and phase of the motor output. In this paper we investigate how spiking and non-spiking neurons can be combined to create a sensorimotor neuron pathway capable of shaping network output based on analog input. We propose sub-threshold operation of an existing spiking neuron model to create a non-spiking neuron able to interpret analog information and communicate with spiking neurons. The validity of this methodology is confirmed through a simulation of a closed-loop amplitude regulating network inspired by the internal feedback loops found in insects for posturing. Additionally, we show that non-spiking neurons can effectively manipulate post-synaptic spiking neurons in an event-based architecture. The ability to work with mixed networks provides an opportunity for researchers to investigate new network architectures for adaptive controllers, potentially improving locomotion strategies of legged robots.

General Distributed Neural Control and Sensory Adaptation for Self-Organized Locomotion and Fast Adaptation to Damage of Walking Robots

Walking animals such as invertebrates can effectively perform self-organized and robust locomotion. They can also quickly adapt their gait to deal with injury or damage. Such a complex achievement is mainly performed via coordination between the legs, commonly known as interlimb coordination. Several components underlying the interlimb coordination process (like distributed neural control circuits, local sensory feedback, and body-environment interactions during movement) have been recently identified and applied to the control systems of walking robots. However, while the sensory pathways of biological systems are plastic and can be continuously readjusted (referred to as sensory adaptation), those implemented on robots are typically static. They first need to be manually adjusted or optimized offline to obtain stable locomotion. In this study, we introduce a fast learning mechanism for online sensory adaptation. It can continuously adjust the strength of sensory pathways, thereby introducing flexible plasticity into the connections between sensory feedback and neural control circuits. We combine the sensory adaptation mechanism with distributed neural control circuits to acquire the adaptive and robust interlimb coordination of walking robots. This novel approach is also general and flexible. It can automatically adapt to different walking robots and allow them to perform stable self-organized locomotion as well as quickly deal with damage within a few walking steps. The adaptation of plasticity after damage or injury is considered here as lesion-induced plasticity. We validated our adaptive interlimb coordination approach with continuous online sensory adaptation on simulated 4-, 6-, 8-, and 20-legged robots. This study not only proposes an adaptive neural control system for artificial walking systems but also offers a possibility of invertebrate nervous systems with flexible plasticity for locomotion and adaptation to injury.

Flexible Spiking CPGs for Online Manipulation During Hexapod Walking

Neural signals for locomotion are influenced both by the neural network architecture and sensory inputs coordinating and adapting the gait to the environment. Adaptation relies on the ability to change amplitude, frequency, and phase of the signals within the sensorimotor loop in response to external stimuli. However, in order to experiment with closed-loop control, we first need a better understanding of the dynamics of the system and how adaptation works. Based on insights from biology, we developed a spiking neural network capable of continuously changing amplitude, frequency, and phase online. The resulting network is deployed on a hexapod robot in order to observe the walking behavior. The morphology and parameters of the network results in a tripod gait, demonstrating that a design without afferent feedback is sufficient to maintain a stable gait. This is comparable to results from biology showing that deafferented samples exhibit a tripod-like gait and adds to the evidence for a meaningful role of network topology in locomotion. Further, this work enables research into the role of sensory feedback and high-level control signals in the adaptation of gait types. A better understanding of the neural control of locomotion relates back to biology where it can provide evidence for theories that are currently not testable on live insects.

Error-Based Learning Mechanism for Fast Online Adaptation in Robot Motor Control

Existing state-of-the-art frequency adaptation mechanisms of central pattern generators (CPGs) for robot locomotion control typically rely on correlation-based learning. They do not account for the tracking error that may occur between the actual system motion and CPG output, leading to the loss of precision, unwanted movement, inefficient energy locomotion, and in the worst cases, motor collapse. To overcome this problem, we developed online error-based learning for frequency adaptation of CPGs. The learning mechanism used for error reduction is a novel modification of the dual learner (DL) called dual integral learner (DIL). Being able to reduce tracking and steady-state errors, it can also perform fast and stable learning, adapting the CPG frequency to match the performance of robotic systems. Control parameters of the DIL are more straightforward for complex systems (like walking robots), compared to traditional correlation-based learning, since they correspond to error reduction. Due to its embedded memory, the DIL can relearn quickly and recover spontaneously from the previously learned parameters. All these features are not covered by the existing frequency adaptation mechanisms. We integrated the DIL into a neural CPG-based motor control system for use on different legged robots with various morphologies for evaluation. The results show that: 1) the DIL does not require precise adjustment of its parameters to fit specific robots; and 2) the DIL can automatically and quickly adapt the CPG frequency to the robots such that the entire trajectory of the CPG can be precisely followed with very low tracking and steady-state errors. Consequently, the robots can perform the desired movements with more energy-efficient locomotion compared to the state-of-the-art correlation-based learning mechanism called frequency adaptation through fast dynamical coupling (AFDC). In the future, the proposed error-based learning mechanism for fast online adaptation in robot motor control can be used as a basis for trajectory optimization, universal controllers, and other studies concerning the change of intrinsic or extrinsic parameters.

Small-Sized Reconfigurable Quadruped Robot With Multiple Sensory Feedback for Studying Adaptive and Versatile Behaviors

Self-organization of locomotion characterizes the feature of automatically spontaneous gait generation without preprogrammed limb movement coordination. To study this feature in quadruped locomotion, we propose here a new open-source, small-sized reconfigurable quadruped robot, called Lilibot, with multiple sensory feedback and its physical simulation. Lilibot was designed as a friendly quadrupedal platform with unique characteristics, including light weight, easy handling, modular components, and multiple real-time sensory feedback. Its modular components can be flexibly reconfigured to obtain features, such as different leg orientations for testing the effectiveness and generalization of self-organized locomotion control. Its multiple sensory feedback (i.e., joint angles, joint velocities, joint currents, joint voltages, and body inclination) can support vestibular reflexes and compliant control mechanisms for body posture stabilization and compliant behavior, respectively. To evaluate the performance of Lilibot, we implemented our developed adaptive neural controller on it. The experimental results demonstrated that Lilibot can autonomously and rapidly exhibit adaptive and versatile behaviors, including spontaneous self-organized locomotion (i.e., adaptive locomotion) under different leg orientations, body posture stabilization on a tiltable plane, and leg compliance for unexpected external load compensation. To this end, we successfully developed an open-source, friendly, small-sized, and lightweight quadruped robot with reconfigurable legs and multiple sensory feedback that can serve as a generic quadrupedal platform for research and education in the fields of locomotion, vestibular reflex-based, and compliant control.

Neural computational model GrowthEstimate: A model for studying living resources through digestive efficiency

The neural computational model GrowthEstimate is introduced with focusing on new perspectives for the practical estimation of weight specific growth rate (SGR, % day-1). It is developed using recurrent neural networks of reservoir computing type, for estimating SGR based on the known data of three key biological factors relating to growth. These factors are: (1) weight (g) for specifying the age of the growth stage; (2) digestive efficiency through the pyloric caecal activity ratio of trypsin to chymotrypsin (T/C ratio) for specifying genetic differences in food utilization and growth potential, basically resulting from food consumption under variations in food quality and environmental conditions; and (3) protein growth efficiency through the condition factor (CF, 100 × g cm-3), as higher dietary protein level affecting higher skeletal growth (length) and resulting in lower CF. The computational model was trained using four datasets of different salmonids with size variations. It was evaluated with 15% of each dataset, resulting in an acceptable range of SGR outputs. Additional tests with different species indicated similarity between the estimated SGR outputs and the real SGR values, and the same ranking of wild population growth. The developed model GrowthEstimate is exceptionally useful for the precise and comparable growth estimation of living resources at individual levels, especially in natural ecosystems where the studied individuals, environmental conditions, food availability and consumption rates cannot be controlled. It is a revelation and will help to minimize uncertainty in wild stock assessment process. This will improve our knowledge in nutritional ecology, through the biochemical effects of climate change and environmental impact on the growth performance quality of aquatic living resources in the wild, as well as in aquaculture. The original GrowthEstimate software is available at GitHub repository (https://github.com/RungruangsakTorrissenManoonpong/GrowthEstimate). All other relevant data are within the paper. It will be improved for generality for future use, and required co-operations of the biodata collections of different species from different climate zones. Therefore, a co-operation will be available.