Animals exhibit remarkable adaptability in sensing their environments, employing strategies that optimize information gathering. For instance, silk moths adjust their wingflapping frequency to detect pheromones, while dogs modify their sniffing behavior by altering sniff height and frequency based on proximity to an odor source. Despite the potential to enhance odor detection for olfactory navigation by drawing inspiration from these natural mechanisms, many existing approaches focus on computationally intensive methods like multi-sensory integration or rely on multiple robots for odor localization, rather than leveraging embodied sensing. In this study, we propose an embodied adaptive sensing strategy that enhances odor detection by implementing an active odor sensor on a legged robot and applying a bio-inspired adaptive robot height control system for dynamically adapting the robot's height based on real-time gas concentration feedback. The control system employs a simple artificial hormone mechanism to regulate the robot height by processing gas concentration derivatives, mimicking biological adaptability. By utilizing the interaction between the active odor sensor, adaptive control system, and the legged body, this approach allows the robot to optimize its height online to capture the maximum gas concentration, thereby reducing the need for complex algorithms and high computational resources. As a result, it offers a more efficient solution for odor-driven tasks, with potential applications in real-world environments.

Lizards are capable of climbing stably on various terrains. Their tails are key to this ability. The lizard uses its flexible tail with graded stiffness as a fifth limb and climbing aid. The tail also enables soft landings, preventing injury from falls. Inspired by this, tails have been incorporated into many climbing robots to enhance their mobility, mimicking lizards. These robotic tails are generally classified as either rigid (stiff) or flexible (soft). A rigid tail can provide a large preload for pitch-back prevention but has a limited contact area for surface adhesion to avoid sliding backward on slopes. In contrast, a flexible tail conforms to the terrain’s contours, increasing the contact area and thereby improving surface adhesion. However, it provides limited preload. Therefore, in this study, we propose a novel hybrid rigid-flexible robotic tail (HIFLEX) that achieves a balanced combination of preload and contact area. The tail structure design features double-sided inclined ribs and is divided into three modular segments (base, middle, and tip), with graded stiffness decreasing progressively from the base to the tip. The asymmetric (inclined) ribbed structure allows the tail to generate anisotropic friction, resulting in high adhesion (tail-to-surface attachment) to prevent backward sliding and low friction (tail-to-surface release) to facilitate upward climbing. The proposed tail is attached to a climbing robot via an actuator capable of pressing the tail downward to generate sufficient preload. The experimental results demonstrate that this unique tail enhances the robot’s climbing performance on rough and deformable slopes while preventing damage to the robot during falls.

Artificial neural networks can be used to solve a variety of robotic tasks. However, they risk failing catastrophically when faced with out-of-distribution (OOD) situations. Several approaches have employed a type of synaptic plasticity known as Hebbian learning that can dynamically adjust weights based on local neural activities. Research has shown that synaptic plasticity can make policies more robust and help them adapt to unforeseen changes in the environment. However, networks augmented with Hebbian learning can lead to weight divergence, resulting in network instability. Furthermore, such Hebbian networks have not yet been applied to solve legged locomotion in complex real robots with many degrees of freedom. In this work, we improve the Hebbian network with a weight normalization mechanism for preventing weight divergence, analyze the principal components of the Hebbian’s weights, and perform a thorough evaluation of network performance in locomotion control for real 18-DOF dung beetle-like and 16-DOF gecko-like robots. We find that the Hebbian-based plastic network can execute zero-shot sim-to-real adaptation locomotion and generalize to unseen conditions, such as uneven terrain and morphological damage.

Legged animals still outperform many terrestrial robots due to the complex interplay of various component subsystems. Centralization is a potential integrated design axis to help improve the performance of legged robots in variable terrain environments. Centralization arises from the coupling of multiple limbs and joints through mechanics or feedback control. Strong couplings contribute to a whole-body coordinated response (centralized) and weak couplings result in localized responses (decentralized). Rarely are both mechanical and neural couplings considered together in designing centralization. In this study, we use an empirical information theory-based approach to evaluate the emergent centralization of a hexapod robot. We independently vary the mechanical and neural coupling through adjustable joint stiffness and variable coupling of leg controllers, respectively. We found an increase in centralization as neural coupling increased. Changes in mechanical coupling did not significantly affect centralization during walking, but did change the total information processing of the neuromechanical control architecture. Information-based centralization increased with robotic performance in terms of cost of transport and speed, implying that this may be a useful metric in robotic design.

Achieving reliable navigation for autonomous drones in complex environments remains a significant challenge, particularly in low-light conditions. To address this, we propose an integrated multimodal obstacle detection and adaptive neural control system with online learning to enable drones to navigate autonomously both during the day and at night. The proposed multimodal obstacle detection system integrates two ranging LiDAR sensors and a depth camera with sensory processing techniques, including the iKD-Tree interested area search algorithm, sensor fusion, and neuro-obstacle directional feature extraction. This ensures robust obstacle detection across various conditions without requiring sensor reconfiguration. The adaptive neural control system applies Hebbian correlation-based learning and synaptic scaling plasticity principles to continuously update the control weights, allowing the drone to dynamically adapt its speed and maneuver around obstacles in real time. We evaluate the system’s performance in both simulation and real-world environments, demonstrating its effectiveness under diverse lighting conditions and obstacle types.

The concept of morphological computation (MC) is applied in the robotics field to improve the design and reduce the complexity of control systems. The MC uses mechanical intelligence, where stiffness properties play an important role as constraints to enhance system flexibility and to store elastic energy. This can reduce the number of required actuators. According to the MC principle, This work proposes LITHE-joint: variable stiffness compliant spherical contact joint in an under-actuated system. This compact design for a 2-degrees of freedom (DOF) compliant spherical contact joint with controllable stiffness uses a pneumatic artificial muscle (PAM). This joint requires only one PAM actuator to control stiffness in a 2-DOF system, achieving a stiffness of up to 0.38 Nm/rad with a bandwidth of 0.1967 Nm/rad. With its variable stiffness properties, the joint is able to adapt its bending behavior, enabling energy redistribution of torque and angle. The modulation of torque and bending angle is governed by joint stiffness and the passive body dynamics. The benefits of the passive, compliant joint with a variable stiffness property are demonstrated by using as the spine of an under-actuated robot, controlling the passive bending of the body and the robot’s walking direction using the adjustable stiffness.

In the oil and gas industry, scale accumulation on radiant coils within furnaces significantly reduces heat-transfer efficiency, leading to increased energy consumption. This paper introduces the REFINE-bot, a robotic system developed to improve the descaling process and operational efficiency in fired heaters. Unlike existing solutions which are mainly designed for specific tube sizes and positions and focused on inspection, the REFINE-bot integrates an adaptable clamping mechanism that adapts to both vertical and horizontal tubes of varying diameters (3"–8"), even in complex environments with narrow tube-to-tube and wall-to-tube gaps. An adaptive force control is also developed to online adjust the position of the cleaning relative to the tube surface to address uneven scale heights. We evaluated three different cleaning tools—a Knot End Brush, Wire Cup Brush, and Sandpaper—under simulated hard scale conditions in a lab environment. This evaluation revealed the cleaning tools’ limitations and helped to identify optimal safety parameters to prevent tube damage. The results showed that the 1-inch Wire Cup Brush, removing 431.1 μm of scale, achieved the highest descaling rate among the tested tools. The robot was successfully deployed in a real furnace setting to test its clamping and cleaning mechanisms on the actual scale. The real-world results demonstrated superior cleaning performance on the radiant coils of a furnace compared to traditional manual descaling methods, as evaluated by measured reductions in scale thickness and infrared thermal imaging. Furthermore, ultrasonic thickness measurements (UTM) were performed and indicated that there was no significant loss in wall thickness after the on-site experiments.

Robot locomotion learning using reinforcement learning suffers from training sample inefficiency and exhibits the non-interpretable/closed-box nature. Thus, this work presents a novel SME-Adaptable Gradient-weighting Online Learning (AGOL) to address such problems. First, sequential motion executor (SME) is a three-layer interpretable neural network, where the first produces the sequentially propagating hidden states, the second constructs the corresponding triangular bases with minor non-neighbor interference, and the third maps the bases to the motor commands. Second, the AGOL algorithm prioritizes the update of the parameters with high relevance score, allowing the learning to focus more on the highly relevant ones. Thus, these two components lead to an analyzable framework, where each sequential hidden state/basis represents the learned key poses/robot configuration. Compared to state-of-the-art methods, the SME-AGOL requires 40% fewer samples and receives 150% higher final reward/locomotion performance on a simulated hexapod robot, while taking merely 10 min of learning time from scratch on a physical hexapod robot. Taken together, this work not only proposes the SME-AGOL for sample efficient and understandable locomotion learning but also emphasizes the potential exploitation of interpretability for improving sample efficiency and learning performance.

Human Activity Recognition (HAR) has rapidly gained interest over the years due to its wide range of applications in AI-based systems, particularly healthcare monitoring. HAR methods typically involve extracting relevant features from data provided by wearable sensors, smartphone sensors, cameras, or their combinations to classify different activities. Nevertheless, a major challenge lies in achieving high classification accuracy with limited data samples, particularly when distinguishing between activities with similar signal attributes. To address this challenge, we propose a novel HAR method called BinAry sequence-augmented spectrograM with Self-attention deep learning (BAMS). Our proposed method leverages only basic wearable sensor data. It utilizes short-time Fourier transform spectrograms to extract spatio-temporal sensor information. The spectrogram is integrated with a binary sequence that captures movement direction. We integrate a scaled dot-product self-attention mechanism into the model to prioritize data from wearable sensors, thereby enhancing the model's performance. The proposed method is evaluated on a public dataset using leave-one-subject-out cross-validation for efficacy and robustness. The method is found to achieve significant improvement over other state-of-the-art methods with the classification accuracy percentage and weighted F-1 scores of 88.06±5.11 and 87.36±5.96, respectively, for a twelve-activity classification.

While lower-limb exoskeletons have been increasingly used for gait assistance and rehabilitation, most of them continue to function as assistive devices in the exoskeleton-user relationship as a leader and follower. This limits the user’s ability to interactively contribute to gait control. Therefore, this study proposes an interactive user-exoskeleton control strategy to translate the exoskeletons into interactive compliant companion devices with the exoskeleton-user relationship as the collaborator. This strategy is implemented through online adaptive impedance control with gravity compensation (OAIC-GC). It relies solely on internal pose feedback (joint position) rather than external sensors such as electromyography, torque, or force, as utilized in other assist-as-needed (AAN) control methods. The OAIC-GC can automatically capture the mechanical impedance dynamics of the user’s lower limbs during walking and thus facilitate adaptive, versatile, and personalized gait assistance. It is evaluated using a real lower-limb exoskeleton system with six degrees of freedom (DOFs) across different users engaging in various activities. These activities include symmetrical and asymmetrical walking on a split-belt treadmill at different speeds, as well as walking up stairs. The results indicate a significant improvement in the exoskeleton’s performance in terms of adaptability and movement smoothness under all activities when compared to traditional control. The proposed control reduces joint assistance torque across all exoskeleton joints, enhancing user interaction and comfort. This enables users to actively control their gait patterns, enabling the exoskeleton to operate in an interactive assist-as-needed (IAAN) mode.

Conventional approaches in robotics for perceiving the environment and signaling the robot’s state or intention for human-robot interaction involve the use of separate sensing and signaling systems. This can sometimes result in high costs and complex system installations. In this study, we propose an alternative approach, integrating both robot sensing and signaling mechanisms into a single utility module (called S-BUN, Soft Bifunctional Utility module for robot sensing aNd signaling). Soft material (Ecoflex 00-10 silicone) is used to form its bun-like structure with a central cavity filled with a NaCl solution. Inspired by honeycombs, the module’s surface incorporates a hexagonal pattern to enhance structural robustness. The design of S-BUN enables it to function as a sensor for both non-contact proximity and touch sensing, utilizing the NaCl solution. Additionally, it serves as a signaling mechanism to indicate the robot’s state through the active inflation and deflation dynamics of the module, simulating lifelike breathing patterns. Through our experiments, we present S-BUN’s capabilities in proximity and touch sensing, including its ability to discern various touch intensities. Finally, we demonstrate the application of S-BUN in the context of reactive behavioral control for a crawling robot and human-robot interaction scenarios.

In this work, we address the challenges of robust precision landing maneuvers for a quadrotor on both stationary and moving ground targets in the presence of disturbances that can cause the quadrotor to deviate from its desired trajectory, leading to maneuver failure. To overcome this, we propose a novel online adaptive trajectory planning approach based on the online temporal scaling adaptation of dynamic movement primitives (DMPs). This adaptation enables the desired trajectory to be dynamically adjusted in response to tracking errors and the goal’s state. Consequently, our proposed approach enhances accuracy, precision, and safety during landing maneuvers. The effectiveness of the approach is evaluated through comprehensive experiments conducted in both physical simulations and real-world environments, covering various disturbance scenarios.

While different control approaches have been developed for smooth and safe navigation, they are limited by the needs for model-based assumptions, true training target/reward function, and/or large sample data. To overcome these limitations, this study proposes a model-free neural control architecture with a generic plug-and-play online Multiple Proactive Behavior Learning (MPL) module. The MPL adapts robot neural control policy in an online unsupervised manner with small sample data by correlating its sensory inputs to a local planner command. As a result, it allows a mobile robot to autonomously and quickly learn and balance various proactive behaviors related to smooth motion and collision avoidance. It also compensates for the limited planning update rates and the planning model mismatch of an arbitrary local motion planner. Compared with existing control approaches without the MPL, our control architecture with the MPL leads to (1) a 10% improvement in the smoothness of robot motion and 30% fewer collisions in a narrow static environment, and (2) trading motion smoothness for up to 70% fewer collisions in an unknown dynamic environment. Taken together, this study also demonstrates how to apply model-free neural control with unsupervised learning to existing model-based control (e.g., local motion planner) for efficient proactive behavior learning and control of mobile robots.

Partner diversity is known to be crucial for training a robust generalist cooperative agent. In this paper, we show that partner specialization, in addition to diversity, is crucial for the robustness of a downstream generalist agent. We propose a principled method for quantifying both the diversity and specialization of a partner population based on the concept of mutual information. Then, we observe that the recently proposed cross-play minimization (XP-min) technique produces diverse and specialized partners. However, the generated partners are overfit, reducing their usefulness as training partners. To address this, we propose simple methods, based on reinforcement learning and supervised learning, for extracting the diverse and specialized behaviors of XP-min generated partners but not their overfitness. We demonstrate empirically that the proposed method effectively removes overfitness, and extracted populations produce more robust generalist agents compared to the source XP-min populations.

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.

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.

The paper introduces a new structure of Liquid State Machine (LSM) characterised by local connectivity within the excitatory neurons of the reservoir layer. The architecture learning and testing capabilities are compared with the classical LSM network on an important robotic task of estimating exteroceptive information from proprioceptive signals coming from a simulated quadruped robot. The main advantages of the proposed architecture are discussed. The actual arrangement of the network resembles specific learning structures within the insect brain, endowed with interesting reaction-diffusion dynamics and classification capabilities. Simulation results are reported and compared with those ones obtained using a classic LSM. The proposed architecture, resembling typical biological solutions present in simple brains, through reaction-diffusion local mechanisms, significantly reduces the computational requirements needed by standard massively-connected neural network solutions. Moreover, the robustness of the introduced network, against faults in the sensory system, is demonstrated. In these conditions, the network is able to partially reconstruct the lacking sensory input signal from the learned relation with the other sensory input streams.

In this work, we introduce a biomorphic soft robotic skin for a hexapod robot platform and a Central Pattern Generator (CPG) based neural controller to generate respiratory-like motions on the skin. The design enables visio-haptic nonverbal communication between humans and robots and improves the robot’s aesthetics by enhancing its biomorphic qualities. We investigated if the soft robotic skin could increase user ratings of the robot’s warmth (RoSAS) and reported trust levels during interaction (MDMT). Contrary to our expectations and earlier findings, we did not find any increase in neither warmth nor trust from adding the soft robotic part. Furthermore, comments received from study participants indicate that trust in the robot is influenced by multiple factors, including appearance, movements, haptic qualities, and contextual factors. Based on our results, we propose directions for further research on pneumatically actuated soft robotic skins as means for nonverbal communication in human-robot interaction.

Personal assistive devices for rehabilitation will be in increasing demand during the coming decades due to demographic change, i.e., an aging society. Among the elderly population, difficulty in walking is the most common problem. Even though there are commercially available lower limb exoskeleton systems, the coordination between user and device still needs to be improved to achieve versatile personalized gaits. To tackle this issue, an advanced EXOskeleton framework for Versatile personalized gaIt generation with a Seamless user–exo interface (called “EXOVIS”) is proposed in this study. The main control of the framework uses adaptive bio-inspired modular neural mechanisms. These mechanisms include decoupled central pattern generators (CPGs) with Hebbian-based synaptic plasticity and adaptive CPG postprocessing networks with error-based learning. The control method facilitates the rapid online learning of personalized walking gaits described by the walking frequency as well as hip, knee, and ankle joint patterns. The method is verified on a real lower limb exoskeleton system with six degrees of freedom (DOFs) on different subjects under static and dynamic conditions, such as flat terrain and a split-belt treadmill. The results show that the proposed method can not only automatically learn to generate personalized symmetrical gaits, but also asymmetrical gaits, which have not been explicitly shown by other approaches so far.

Due to demographic change, health and elderly care systems are facing a shortage of qualified caregivers. This issue can be addressed by introducing welfare robots into people’s homes, hospitals, and care institutions. To provide useful support, such robots must adapt to individual users and smoothly interact with them. From this perspective, we present advances on the development of proactive control for online individual user adaptation in a welfare robot guidance scenario, with the integration of three main modules: 1) navigation control; 2) visual human detection; and 3) temporal error correlation-based neural learning. The proposed control approach can drive a mobile robot to autonomously navigate in relevant indoor environments. At the same time, it can predict human walking speed based on visual information without prior knowledge of personality and preferences (i.e., walking speed). The robot then uses this prediction to continuously adapt its speed to individual users in a proactive online manner. We validate the performance of the proposed proactive robot control in different real-world environments with various users, including an elderly resident of a Danish elderly care center. The results show that the robot successfully and smoothly guided various users of different ages and average walking speeds (e.g., 0.2 m/s, 0.7 m/s, and 1.1 m/s) to target locations over distances of 25–60 m. All in all, this study captures a wide range of research from robot control technology development to technological validity in a relevant environment and system prototype demonstration in an operational environment (i.e., an elderly care center).

This paper aims to investigate the Liquid State Machines (LSMs) learning capability and robustness of a complex robot-environment interaction. The goal is to design an efficient robot state estimation method based on reservoir computing. The method maps local proprioceptive information acquired at the level of the leg joints of a simulated quadruped robot. The robot taken into account is the simulated version of Lilibot, a small-sized and reconfigurable bio-inspired robot with multiple real-time sensory feedback. Global information was provided from the ground reaction forces acquired on the tips of each leg. Simulation results are reported and compared, also in presence of faulty conditions in the sensory system.

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.

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.

A conventional adopted method for operating a waiter robot is based on the static position control, where predefined goal positions are marked on a map. However, this solution is not optimal in a dynamic setting, such as in a coffee shop or an outdoor catering event, because the customers often change their positions. This article explores an alternative human-robot interface design where a human operator communicates the identity of the customer to the robot instead. Inspired by how human communicates, we propose a framework for communicating a visual goal to the robot, through interactive two-way communications. The framework exploits concepts from two machine learning domains: human-in-the-loop machine learning, where active learning is used to acquire informative data, and deep metric learning, where a suitable embedding can improve the learning ability of a classifier. We also propose novel class imbalance handling techniques, which aim to actively alleviate the class imbalance problem found to be important in this mode of communication. The framework is evaluated using publicly available pedestrian datasets. We demonstrate that the proposed framework can help reduce the number of required two-way interactions and increases the robustness of the predictive model. We successfully implement the framework on a mobile robot for a delivery service in a cafe-like environment. Through the online visual goal human-robot communication, the robot can detect, recognize, and autonomously navigate to the target customer.

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.

Interactive (mechanical) impedance and finger fatigues are important topics, which have not been well investigated. To tackle this problem, we developed a soft lightweight (0.25 kg) finger exoskeleton (TIE-EXO) for quantifying interactive impedance and finger fatigue. A resist-as-needed (RAN) controller was used to produce variable resistance in fingers’ exercises. The TIE-EXO’s feedback and RAN’s parameters were applied to quantify the relationship between interactive impedance and finger fatigue. This quantification was validated in the index and middle fingers of three subjects. This validation shows that the RAN control enables the TIE-EXO to produce online resistance adaptations to different subjects and finger fatigue. Moreover, it indicates a variation and invariance in finger impedance control. We argue that the proposed method provides a novel way for investigating interactive impedance and finger fatigue.

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.

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.

In order to use walking robots for exploration in a real complex environment, an adaptive control system is required to allow them to successfully and efficiently traverse the terrains. To achieve this, we propose here our adaptive locomotion control technique of a walking robot. It is based on a modular structure, combining neural control with an artificial hormone system. The neural control coordinates all leg joints of the robot and generates its locomotion with various insect-like gaits. In parallel, the artificial hormone system uses the motor commands from the neural control and foot contact feedback to estimate the walking state and automatically adapt the joint movements with respect to the terrain. The adaptability is quickly achieved in an online manner within a few seconds. Robot walking experiments show that this adaptive control technique enables a six-legged robot to adapt to various difficult terrains with energy efficiency. Such terrains include sand (loose ground), sponge with different softness levels (soft/compliant ground), grass (vegetated ground), and floor/pavement (hard ground). The technique does not require robot kinematics or an environmental model; and can, therefore, be potentially applied to different legged robots to achieve stable online adaptation and energy-efficient locomotion on unpredictable (compliant) terrains.

Recently, drones have been involved in several critical tasks such as infrastructure inspection, crisis response, and search and rescue operations. Such drones mostly use sophisticated computer vision techniques to effectively avoid obstacles and, thereby, require high computational power. Therefore, this work tuned and tested a computationally inexpensive algorithm, previously developed by the authors, for adaptive obstacle avoidance control of a drone. The algorithm aims at protecting the drone from entering in complex situations such as deadlocks and corners. The algorithm has been validated through simulation and implemented on a newly developed drone platform for infrastructure inspection. The design of the drone platform and the experimental results are presented in this study.

Many quadruped robots have been developed to imitate their biological counterparts, several of which show excellent performance. However, the biological neural control mechanisms responsible for self-organized adaptive quadruped locomotion remain elusive. By drawing lessons from biological findings and using an artificial neural approach, we simulated a mammal-like quadruped robot and used it as our simulation platform to investigate and develop neural control mechanisms. In this study, we proposed an adaptive neural control network that can autonomously generate self-organized emergent locomotion with adaptability for the robot. The control network consists of three main components: Decoupled neural central pattern generator circuits (one for each leg), sensory feedback adaptation with dual-rate learning, and multiple neural reflex mechanisms. Simulation results show that the robot can perform quadruped-like gaits in a self-organized manner and adapt its gait to negotiate an obstacle. In addition, this work also suggests that the tight combination of the body-environment interaction and adaptive neural control, guided by sensory feedback adaptation and neural reflexes, is a powerful approach to better understand and solve self-organized adaptive coordination problems in quadruped locomotion.

The control of multilegged animal walking is a neuromechanical process, and to achieve this in an adaptive and energy efficient way is a difficult and challenging problem. This is due to the fact that this process needs in real time: 1) to coordinate very many degrees of freedom of jointed legs; 2) to generate the proper leg stiffness (i.e., compliance); and 3) to determine joint angles that give rise to particular positions at the endpoints of the legs. To tackle this problem for a robotic application, here we present a neuromechanical controller coupled with sensorimotor learning. The controller consists of a modular neural network for coordinating 18 joints and several virtual agonist-antagonist muscle mechanisms (VAAMs) for variable compliant joint motions. In addition, sensorimotor learning, including forward models and dual-rate learning processes, is introduced for predicting foot force feedback and for online tuning the VAAMs' stiffness parameters. The control and learning mechanisms enable the hexapod robot advanced mobility sensor driven-walking device (AMOS) to achieve variable compliant walking that accommodates different gaits and surfaces. As a consequence, AMOS can perform more energy efficient walking, compared to other small legged robots. In addition, this paper also shows that the tight combination of neural control with tunable muscle-like functions, guided by sensory feedback and coupled with sensorimotor learning, is a way forward to better understand and solve adaptive coordination problems in multilegged locomotion.

Animals show remarkable capabilities in navigating their habitat in a fully autonomous and energy-efficient way. In many species, these capabilities rely on a process called path integration, which enables them to estimate their current location and to find their way back home after long-distance journeys. Path integration is achieved by integrating compass and odometric cues. Here we introduce a neural path integration mechanism that interacts with a neural locomotion control to simulate homing behavior and path integration-related behaviors observed in animals. The mechanism is applied to a simulated six-legged artificial agent. Input signals from an allothetic compass and odometry are sustained through leaky neural integrator circuits, which are then used to compute the home vector by local excitation-global inhibition interactions. The home vector is computed and represented in circular arrays of neurons, where compass directions are population-coded and linear displacements are rate-coded. The mechanism allows for robust homing behavior in the presence of external sensory noise. The emergent behavior of the controlled agent does not only show a robust solution for the problem of autonomous agent navigation, but it also reproduces various aspects of animal navigation. Finally, we discuss how the proposed path integration mechanism may be used as a scaffold for spatial learning in terms of vector navigation.

Walking animals show fascinating locomotor abilities and complex behaviors. Biological study has revealed that such complex behaviors is a result of a combination of biomechanics and neural mechanisms. While biomechanics allows for flexibility and a variety of movements, neural mechanisms generate locomotion, make predictions, and provide adaptation. Inspired by this finding, we present here an artificial bio-inspired walking system which combines biomechanics (in terms of its body and leg structures) and neural mechanisms. The neural mechanisms consist of 1) central pattern generator-based control for generating basic rhythmic patterns and coordinated movements, 2) reservoir-based adaptive forward models with efference copies for sensory prediction as well as state estimation, and 3) searching and elevation control for adapting the movement of an individual leg to deal with different environmental conditions. Simulation results show that this bio-inspired approach allows the walking robot to perform complex locomotor abilities including walking on undulated terrains, crossing a large gap, as well as climbing over a high obstacle and a fleet of stairs.

Central pattern generators (CPGs) play a crucial role for animal locomotion control. They can be entrained by sensory feedback to induce proper rhythmic patterns and even store the entrained patterns through connection weights. Inspired by this biological finding, we use four adaptive neural oscillators with synaptic plasticity as CPGs for locomotion control of our real snake-like robot with screw-drive mechanism. Each oscillator consists of only three neurons and uses adaptive mechanisms based on frequency adaptation and Hebbian-type learning rules. It autonomously generates proper periodic patterns for the robot locomotion and can be entrained by sensory feedback to memorize the patterns. The adaptive CPG system in conjunction with a simple control strategy enables the robot to perform self-tuning behavior which is robust against short-time perturbations. The generated behavior is also energy efficient. In addition, the robot can also cope with corners as well as move through a complex environment with obstacles.

In this paper, we investigated the dynamics of a hexapod robot model whose legs are driven by nonlinear oscillators with a phase modulation mechanism including phase resetting and inhibition. This mechanism changes the oscillation period of the oscillator depending solely on the timing of the foot's contact. This strategy is based on observation of animals. The performance of the controller is evaluated using a physical simulation environment. Our simulation results show that the robot produces some stable gaits depending on the locomotion speed due to the phase modulation mechanism, which are simillar to the gaits of insects.

Learning of goal-directed behaviors in biological systems is broadly based on associations between conditional and unconditional stimuli. This can be further classified as classical conditioning (correlation-based learning) and operant conditioning (reward-based learning). Although traditionally modeled as separate learning systems in artificial agents, numerous animal experiments point towards their co-operative role in behavioral learning. Based on this concept, the recently introduced framework of neural combinatorial learning combines the two systems where both the systems run in parallel to guide the overall learned behavior. Such a combinatorial learning demonstrates a faster and efficient learner. In this work, we further improve the framework by applying a reservoir computing network (RC) as an adaptive critic unit and reward modulated Hebbian plasticity. Using a mobile robot system for goal-directed behavior learning, we clearly demonstrate that the reservoir critic outperforms traditional radial basis function (RBF) critics in terms of stability of convergence and learning time. Furthermore the temporal memory in RC allows the system to learn partially observable markov decision process scenario, in contrast to a memory less RBF critic.

Insects, e.g. cockroaches and stick insects, have found fascinating solutions for the problem of locomotion, especially climbing over a large variety of obstacles. Research on behavioral neurobiology has identified key behavioral patterns of these animals (i.e., body flexion, center of mass elevation, and local leg reflexes) necessary for climbing. Inspired by this finding, we develop a neural control mechanism for hexapod robots which generates basic walking behavior and especially enables them to effectively perform reactive climbing behavior. The mechanism is composed of three main neural circuits: locomotion control, reactive backbone joint control, and local leg reflex control. It was developed and tested using a physical simulation environment, and was then successfully transferred to a physical six-legged walking machine, called AMOS II. Experimental results show that the controller allows the robot to overcome obstacles of various heights (e.g., ~ 75% of its leg length, which are higher than those that other comparable legged robots have achieved so far). The generated climbing behavior is also comparable to the one observed in cockroaches.

In chaos control, an originally chaotic system is modified so that periodic dynamics arise. One application of this is to use the periodic dynamics of a single chaotic system as walking patterns in legged robots. In our previous work we applied such a controlled chaotic system as a central pattern generator (CPG) to generate different gait patterns of our hexapod robot AMOSII. However, if one or more legs break, its control fails. Specifically, in the scenario presented here, its movement permanently deviates from a desired trajectory. This is in contrast to the movement of real insects as they can compensate for body damages, for instance, by adjusting the remaining legs' frequency. To achieve this for our hexapod robot, we extend the system from one chaotic system serving as a single CPG to multiple chaotic systems, performing as multiple CPGs. Without damage, the chaotic systems synchronize and their dynamics is identical (similar to a single CPG). With damage, they can lose synchronization leading to independent dynamics. In both simulations and real experiments, we can tune the oscillation frequency of every CPG manually so that the controller can indeed compensate for leg damage. In comparison to the trajectory of the robot controlled by only a single CPG, the trajectory produced by multiple chaotic CPG controllers resembles the original trajectory by far better. Thus, multiple chaotic systems that synchronize for normal behavior but can stay desynchronized in other circumstances are an effective way to control complex behaviors where, for instance, different body parts have to do independent movements like after leg damage.

This paper presents a reconfigurable spherical robot. The reconfigurable spherical robot can be reconfigured into a form of two interconnected hemispheres with three legs equipped with three omni-directional wheels. A stable reconfiguration control algorithm is constructed to change the robot from spherical shape to two halves of interconnected hemispheres and three legged-wheeled expansions. This work also constructs a transformation controller for the robot which uses an accelerometer to sense its orientation. The performance analysis shows that our reconfigurable robot prototype can transform from spherical shape (dormant mode) into two inter connected hemispheres where the three leg-wheels are projected out of the shells (transformed mode) and vice versa. After the transformation into the three leg-wheel configuration, the robot can autonomously move in L-shaped and U-shaped areas as well as narrowing pathways.

In this paper the authors present the architecture of the planar biped robot "RunBot". It has been developed on the basis of three hierarchical levels: biomechanical, local and central. The biomechanical level concerns an appropriate biomechanical design of RunBot which utilizes some principles of passive walkers to ensure stability. The local level is a low-level neuronal structure which generates dynamically stable gaits as well as fast motions with some degree of self-stabilization to guarantee basic robustness. In the central level, we simulate a mechanism for synaptic plasticity which allows RunBot to autonomously learn to adapt its locomotion to different terrains, e.g. level floor versus up or down a ramp. As a result, the structural coupling of all these levels generates adaptive, fast dynamic walking of RunBot.

Human walking is a dynamic, partly self-stabilizing process relying on the interaction of the biomechanical design with its neuronal control. The coordination of this process is a very difficult problem, and it has been suggested that it involves a hierarchy of levels, where the lower ones, e.g., interactions between muscles and the spinal cord, are largely autonomous, and where higher level control (e.g., cortical) arises only pointwise, as needed. This requires an architecture of several nested, sensori-motor loops where the walking process provides feedback signals to the walker's sensory systems, which can be used to coordinate its movements. To complicate the situation, at a maximal walking speed of more than four leg-lengths per second, the cycle period available to coordinate all these loops is rather short. In this study we present a planar biped robot, which uses the design principle of nested loops to combine the self-stabilizing properties of its biomechanical design with several levels of neuronal control. Specifically, we show how to adapt control by including online learning mechanisms based on simulated synaptic plasticity. This robot can walk with a high speed (>3.0 leg length/s), self-adapting to minor disturbances, and reacting in a robust way to abruptly induced gait changes. At the same time, it can learn walking on different terrains, requiring only few learning experiences. This study shows that the tight coupling of physical with neuronal control, guided by sensory feedback from the walking pattern itself, combined with synaptic learning may be a way forward to better understand and solve coordination problems in other complex motor tasks.

In Figure The incorrect Froude number given for human walking (0.24) corresponds to 1.5m/s, which is closer to the preferred speed of human walking. The correct number now given (2.4) corresponds to a speed of about 4.6m/s.