Humanoid Robot Platform Research Articles

Single Sequential Trajectory Optimization with Centroidal Dynamics and Whole-Body Kinematics for Vertical Jump of Humanoid Robot.

High vertical jumping motion, which enables a humanoid robot to leap over obstacles, is a direct reflection of its extreme motion capabilities. This article proposes a single sequential kino-dynamic trajectory optimization method to solve the whole-body motion trajectory for high vertical jumping motion. The trajectory optimization process is decomposed into two sequential optimization parts: optimization computation of centroidal dynamics and coherent whole-body kinematics. Both optimization problems converge on the common variables (the center of mass, momentum, and foot position) using cost functions while allowing for some tolerance in the consistency of the foot position. Additionally, complementarity conditions and a pre-defined contact sequence are implemented to constrain the contact force and foot position during the launching and flight phases. The whole-body trajectory, including the launching and flight phases, can be efficiently solved by a single sequential optimization, which is an efficient solution for the vertical jumping motion. Finally, the whole-body trajectory generated by the proposed optimized method is demonstrated on a real humanoid robot platform, and a vertical jumping motion of 0.5 m in height (foot lifting distance) is achieved.

TacSuit: A Wearable Large-Area, Bioinspired Multimodal Tactile Skin for Collaborative Robots

Robots are now working more and more closely with humans outside of traditional fences in industrial scenes. Their real-time tactile interaction perception is crucial to the safety of human–robot collaboration (HRC). In this work, we present a customized, wearable and modular robot skin (TacSuit), which is scalable for large-area surface coverage of robot with easily accessible multi-modal sensors, including pressure, proximity, acceleration and temperature sensors. The TacSuit is co-designed for mechanical structure and data fusion algorithm, consisting of three levels of design: sensor, cell (of multi-modal sensors) and block (of multiple cells). These sensors are stored with custom-designed and 3D printed capsules to achieve the conformity, scalability and easy installation to the arbitrary robot surface. A multi-level event-driven data fusion algorithm enables efficient information processing for large number of tactile sensors. Furthermore, a virtual interaction force fusion method takes both the proximity and force perception information into consideration in order to achieve safety of whole interaction process before and after direct physical contacts. A humanoid robotic platform successfully realizes the TacSuit wear of 159 tactile cells. Validation experiments of obstacle detection demonstrate the effective collision avoidance capability of the TacSuit for safe HRC.

Vertical Jump of a Humanoid Robot With CoP-Guided Angular Momentum Control and Impact Absorption

Highly dynamic movements such as jumping are important to improve the agility and environmental adaptation of humanoid robots. This article proposes an online optimization method to realize a vertical jump with centroidal angular momentum (CAM) control and landing impact absorption for a humanoid robot. First, the robot's center of mass (CoM) trajectory is generated by nonlinear optimization. Then, a quasi-sliding mode controller is designed to ensure that the robot tracks the CoM trajectory accurately. To avoid unexpected spinning in the flight phase, a center-of-pressure-guided angular momentum controller is designed to stabilize the CAM. The modifications of CoM and CAM are realized by online optimization of dynamic components and inverse dynamics. Two quadratic programming optimizations are utilized to generate feasible contact force/torque and joint acceleration referring to uplevel CoM and CAM controllers. In addition, a viscoelastic model-based controller is designed to absorb the vibration caused by a large contact impact. A simulation and experiment of a 0.5-m high (foot lifting distance) vertical jump are achieved on a humanoid robot platform in this article (Fig. 1).

A Variable Stiffness Sole for Biped Robot and Its Experimental Verification

Abstract The foot sole of the biped robot is an important factor for stable walking. In this study, the limitations of existing bipedal robot soles are introduced and the necessity for the development of a new sole mechanism is presented. Inspired by a robot sole based on the granular jamming effect, we have developed a variable stiffness sole (VSS), which adapts to the shape of obstacles on the ground in compliant mode and provides robust support in stiff mode. Finally, the performance of the VSS is verified by several experiments integrating the VSS with the real humanoid robot platform RoK-3. The experimental results verified that the VSS is advantageous in uneven terrain walking.

Design, development, and analysis of the lower body of next-generation 3D-printed humanoid research platform: PANDORA

AbstractThe main contribution of this paper is the design and development of the lower body of PANDORA (3D-Printed Autonomous humaNoid Developed for Open-source Research Applications), a new humanoid robotic platform implementing additive manufacturing techniques. The three joint configurations (hip, knee, and ankle) along with the major three structural parts (pelvis, thigh, and shin) of the lower body are discussed. The use of 3D printing and PLA+ material makes the robot an affordable solution for humanoid robotics research that gives a high power-to-weight ratio by significantly reducing the number of parts, as well as manufacturing and assembly time. The range of motion of the lower body of PANDORA has been investigated and is found to be comparable to a human lower body. Further, finite element analysis has been performed on the major parts of the lower body of PANDORA to check the structural integrity and to avoid catastrophic failures in the robot. The use of in-house developed actuators and robot electronics reduces the overall cost of the robot and makes PANDORA easily accessible to the research communities working in the field of humanoids. Overall, PANDORA has the potential for becoming popular between researchers and designers for investigating applications in the field of humanoid robotics, healthcare, and manufacturing, just to mention a few. The mechanical designs presented in this work are available open source to lower the knowledge barrier in developing and conducting research on bipedal robots.

A versatile humanoid robot platform for dexterous manipulation and human–robot collaboration

AbstractHumanoid robots have attracted much attention by virtue of their compatibility with human environments. However, biped humanoids with immense promise still cannot function steadily and reliably in real‐world settings in the current state. Hence, rationally combining a humanoid robot with different stable mobile platforms is a favoured solution for diverse scenarios. Here, a new versatile humanoid robot platform, aiming to provide a generic solution that can be flexibly deployed in diverse scenarios, for example, indoors and fields is presented. Versatile humanoid robot platform incorporates multimodal perception, and extensible interfaces on hardware and software, allowing it to be rapidly integrated with different mobile platforms and end‐effectors, only through easy‐to‐assemble interfaces. Additionally, the platform has achieved impressive integration, lightness, dexterity, and strength in its class, with human‐like size and rich perception, targeted to have human‐intelligent manipulation skills for human‐engineered environments. Overall, this article elaborates on the reasoning behind the design choices, and outlines each subsystem. Lastly, the essential performance of the platform is successfully demonstrated in a set of experiments with precise and dexterous manipulation, and human–robot collaboration requirements.

Lightweight mechatronic system for humanoid robot

Abstract This paper presents the technical specifications of a lightweight humanoid robot platform named Robinion Sr. including its mechanical and electrical design. We describe a versatile and robust mechatronic system, efficient walking gait, and software architecture of the humanoid robot. The humanoid robot platform is targeted for use in a range of applications, including research and development, competitions, and the service industry. A reduced platform cost was an essential consideration in our design. We introduce a specialized and inexpensive mechanical design, which includes a parallel-kinematics leg design, external gears, and low-cost controllers and sensors. The humanoid robot is equipped with an efficient electronic structure and a tablet computer for task scheduling, control, and perception, as well as an embedded controller for solving forward & inverse kinematics and low-level actuator control. The perception system recognizes objects at real-time inference with Deep Learning-based detection algorithms without a dedicated GPU. We present and evaluate the capabilities of our newly developed advanced humanoid robot and believe it is a suitable platform for the academic and industrial robotics community.

Memristive Circuit Design of Brain-Like Emotional Learning and Generation.

In this work, a bionic memristive circuit with the functions of emotional learning and generation is proposed, which can perform brain-like emotional learning and generation based on various types of input information. The proposed circuit is designed based on the brain emotional learning theory in the limbic system, which mainly includes three layers of design: 1) the bottom layer is the design of the basic unit modules, such as neuron and synapse; 2) the middle layer is the design of the functional modules related to emotional learning in the limbic system, such as the amygdala, thalamus, and so on; and 3) the top layer is the design of the overall circuit, which is used to realize the function of the emotional generation. A 2-D emotional space composed of valence and arousal signals is adopted. According to the above bottom-up circuit design method, the valence and arousal signals can be generated, respectively, by designing corresponding emotional learning circuits, so as to form continuous emotions. The volatile and nonvolatile memristors are mainly used to mimic the functions of the neuron and synapse at the bottom layer of the circuit to achieve the core emotional learning function of the middle layer, thereby constructing a brain-like information processing architecture to realize the function of the emotional generation in the top layer. The simulation results in PSPICE show that the proposed circuit can learn and generate emotions like humans. If the proposed circuit is applied to a humanoid robot platform through further research, the robot may have the ability of personalized emotional interaction with humans, so that it can be effectively used in emotional companionship and other aspects.

Contrastive learning based facial action unit detection in children with hearing impairment for a socially assistive robot platform

• Novel application of two different domain adaptation methods (distinguished by the information transfer source as adults, and children) to improve the facial action unit detection performance of children with hearing impairments. • Contrastive learning as a domain adaptation method with a cosine distance metric. • Integration of a new parameter, β , into the loss function of the contrastive learning method to smooth the contribution of the similar samples. This paper presents a contrastive learning-based facial action unit detection system for children with hearing impairments to be used on a socially assistive humanoid robot platform. The spontaneous facial data of children with hearing impairments was collected during an interaction study with Pepper humanoid robot, and tablet-based game. Since the collected dataset is composed of limited number of instances, a novel domain adaptation extension is applied to improve facial action unit detection performance, using some well-known labelled datasets of adults and children. Furthermore, since facial action unit detection is a multi-label classification problem, a new smoothing parameter, β , is introduced to adjust the contribution of similar samples to the loss function of the contrastive learning. The results show that the domain adaptation approach using children’s data (CAFE) performs better than using adult’s data (DISFA). In addition, using the smoothing parameter β leads to a significant improvement on the recognition performance.

The use of social robots with children and young people on the autism spectrum: A systematic review and meta-analysis.

Robot-mediated interventions show promise in supporting the development of children on the autism spectrum. In this systematic review and meta-analysis, we summarize key features of available evidence on robot-interventions for children and young people on the autism spectrum aged up to 18 years old, as well as consider their efficacy for specific domains of learning. PubMed, Scopus, EBSCOhost, Google Scholar, Cochrane Library, ACM Digital Library, and IEEE Xplore. Grey literature was also searched using PsycExtra, OpenGrey, British Library EThOS, and the British Library Catalogue. Databases were searched from inception until April (6th) 2021. Searches undertaken across seven databases yielded 2145 articles. Forty studies met our review inclusion criteria of which 17 were randomized control trials. The methodological quality of studies was conducted with the Quality Assessment Tool for Quantitative Studies. A narrative synthesis summarised the findings. A meta-analysis was conducted with 12 RCTs. Most interventions used humanoid (67%) robotic platforms, were predominantly based in clinics (37%) followed home, schools and laboratory (17% respectively) environments and targeted at improving social and communication skills (77%). Focusing on the most common outcomes, a random effects meta-analysis of RCTs showed that robot-mediated interventions significantly improved social functioning (g = 0.35 [95%CI 0.09 to 0.61; k = 7). By contrast, robots did not improve emotional (g = 0.63 [95%CI -1.43 to 2.69]; k = 2) or motor outcomes (g = -0.10 [95%CI -1.08 to 0.89]; k = 3), but the numbers of trials were very small. Meta-regression revealed that age accounted for almost one-third of the variance in effect sizes, with greater benefits being found in younger children. Overall, our findings support the use of robot-mediated interventions for autistic children and youth, and we propose several recommendations for future research to aid learning and enhance implementation in everyday settings. Our methods were preregistered in the PROSPERO database (CRD42019148981).

Quori: A Community-Informed Design of a Socially Interactive Humanoid Robot

Hardware platforms for socially interactive robotics can be limited by cost or lack of functionality. This article presents the overall system—design, hardware, and software—for Quori, a novel, affordable, socially interactive humanoid robot platform for facilitating noncontact human–robot interaction (HRI) research. The design of the system is motivated by feedback sampled from the HRI research community. The overall design maintains a balance of affordability and functionality. Initial Quori testing and a six-month deployment are presented. Ten Quori platforms have been awarded to a diverse group of researchers from across the United States to facilitate HRI research to build a community database from a common platform.

Kid-size robot humanoid walking with heel-contact and toe-off motion.

Human-like features, like toe-off, heel-strike can enhance the performance of bipedal robots. However, few studies have considered the anthropomorphism of walking planning. Fewer studies have achieved their toe-off, heel-strike gait planning framework in a child-sized humanoid robot platform. This paper presents a human-like walking control framework based on the Divergent Component of Motion (DCM) com planning method that enables a child-sized humanoid robot to walk with a humanoid pattern with a speed of 0.6 s per step a strike of 30 cm. The control framework consists of three parts: the human-like gait generation of the center of mass (CoM) and swings foot trajectory, the dynamic replan in phase switch and the upper body stabilization controller. The dynamic replanning of the CoM and foot trajectory can efficiently decrease the vibration in the step-phase switch. The up-body stabilization controller can reduce the up-body swing in walking and increase the robot's stability while walking. The robot uses a mems-based inertial measurement unit (IMU) and joint position encoders to estimate the current state of the robot and use force-sensitive resistors (FSR) on the robot foot to identify the actual step phase of the robot. None of these solutions is high-cost or difficult to integrate with a child-size robot. Software simulations and walking experiments are using to verify the motion control algorithm. The effectiveness of the pattern generation and the controller can realize more human-like walking styles in a child-size robot are confirmed.

A Differentiable Extended Kalman Filter for Object Tracking Under Sliding Regime.

Tactile sensing represents a valuable source of information in robotics for perception of the state of objects and their properties. Modern soft tactile sensors allow perceiving orthogonal forces and, in some cases, relative motions along the surface of the object. Detecting and measuring this kind of lateral motion is fundamental to react to possibly uncontrolled slipping and sliding of the object being manipulated. Object slip detection and prediction have been extensively studied in the robotic community leading to solutions with good accuracy and suitable for closed-loop grip stabilization. However, algorithms for object perception, such as in-hand object pose estimation and tracking algorithms, often assume no relative motion between the object and the hand and rarely consider the problem of tracking the pose of the object subjected to slipping and sliding motions. In this work, we propose a differentiable Extended Kalman filter that can be trained to track the position and the velocity of an object under translational sliding regime from tactile observations alone. Experiments with several objects, carried out on the iCub humanoid robot platform, show that the proposed approach allows achieving an average position tracking error in the order of 0.6 cm, and that the provided estimate of the object state can be used to take control decisions using tactile feedback alone. A video of the experiments is available as Supplementary Material.

Simulation-aided walking pattern generation for a humanoid robotic platform

Bipedal locomotion is one of the main research topics in humanoid robotics due to the complexity of generating dynamically stable gait patterns in robots that are generally very unstable. Good walking performance requires diverse and complex control strategies based on a mathematical model of the robot. Here, a methodology to easily generate stable bipedal locomotion patterns in a humanoid robotic platform is presented. Using a simulation environment and a simple programming method, the robot gait, stability and general behaviour are first simulated and then transferred to the actual machine. Three gait patterns are developed according to the biomechanics of human walking and validated using a humanoid robot platform. The robot exhibits good performance in terms of stability, displacement and velocity. The proposed methodology allows the study of locomotion in biped robots and can serve as a basis for developing controls in closed-loop schemes.

Knowledge Acquisition and Design Using Semantics and Perception: A Case Study for Autonomous Robots

The pervasive use of artificial intelligence and neural networks in several different research fields has noticeably improved multiple aspects of human life. The application of these techniques to machines has made them progressively more “intelligent” and able to solve tasks considered extremely complex for a human being. This technological evolution has deeply influenced the way we interact with machines. Purely symbolic artificial intelligence and techniques like ontologies, have also been successfully used in the past applied to robotics, but have also shown some limitations and failings in the knowledge construction task. In fact, the exhibited “intelligence” is rarely the result of a real autonomous decision, but it is rather hard-encoded in the machine. While a number of approaches have already been proposed in literature concerning knowledge acquisition from the surrounding environment, they are either exclusively based on low-level features or they involve solely high-level semantics-based attributes. Moreover, they often don’t use a general high-level knowledge base for grounding the acquired knowledge. In this contexts, the use of semantics technologies, such as ontologies, is mostly employed for action-oriented tasks. In this article we propose an extension of a novel approach for knowledge acquisition based on a general semantic knowledge-base and the fusion of semantics and visual information by means of neural networks and ontologies. The proposed approach has been implemented on a humanoid robotic platform and the experimental results are shown and discussed.

The Design of Memristive Circuit for Affective Multi-Associative Learning

In this work, a memristive circuit with affective multi-associative learning function is proposed, which mimics the process of human affective formation. It mainly contains three modules: affective associative learning, affective formation, affective expression. The first module is composed of several affective single-associative learning circuits consisting of memristive neurons and synapses. Memristive neuron will be activated and output pulses if its input exceeds the threshold. After it is activated, memristive neuron can automatically return to the inactive state. Memristive synapse can realize learning and forgetting functions based on the signals from pre- and post-neurons. The learning rule is pre-neuron activated lags behind post-neuron for a short time; the forgetting rule is to repeatedly activate pre-neuron after the emotion is learned. The process of learning or forgetting corresponds to facilitating or inhibiting synaptic weight, that is, decreasing or increasing memristance continuously. Different voltage signals applied to memristors and different parameters of memristors would lead to different synaptic weights which indicate different affective association. The second module can convert affective signals to corresponding emotions. The formed emotions can be shown in a face by the third module. The simulation results in PSPICE show that the proposed circuit system can learn, forget and form emotions like human. If the proposed circuit is further used on a humanoid robot platform through further research, the robot will have the ability of affective interaction with human so that it can be effectively used in affective company and other aspects.

Computational Modeling of Prefrontal Cortex for Meta-Cognition of a Humanoid Robot

For robot intelligence and human-robot interaction (HRI), complex decision-making, interpretation, and adaptive planning processes are great challenges. These require recursive task processing and meta-cognitive reasoning mechanism. Naturally, the human brain realizes these cognitive skills by prefrontal cortex which is a part of the neocortex. Previous studies about neurocognitive robotics would not meet these requirements. Thus, it is aimed at developing a brain-inspired robot control architecture that performs spatial-temporal and emotional reasoning. In this study, we present a novel solution that covers a computational model of the prefrontal cortex for humanoid robots. Computational mechanisms are mainly placed on the bio-physical plausible neural structures embodied in different dynamics. The main components of the system are composed of several computational modules including dorsolateral, ventrolateral, anterior, and medial prefrontal regions. Also, it is responsible for organizing the working memory. A reinforcement meta-learning based explainable artificial intelligence (xAI) procedure is applied to the working memory regions of the computational prefrontal cortex model. Experimental evaluation and verification tests are processed by the developed software framework embodied in the humanoid robot platform. The humanoid robots’ perceptual states and cognitive processes including emotion, attention, and intention-based reasoning skills can be observed and controlled via the developed software. Several interaction scenarios are implemented to monitor and evaluate the model’s performance.

A Study on Sparse Hierarchical Inverse Kinematics Algorithms for Humanoid Robots

In humanoid robotic platforms, classical inverse kinematics algorithms, based on L2-regularization of joint velocities or accelerations, tends to engage the motion of all the available degrees of freedom, resulting in movements of the whole robot structure, which are inherently not sparse. The role of sparsity in motion control has recently gained interest in the robotics community for various reasons, e.g., human-like motions, and human-robot interaction, actuation parsimony, yet an exhaustive mathematical analysis is still missing. In order to address this topic, we here propose and compare possible sparse optimization approaches applied to hierarchical inverse kinematics for humanoid robots. This is achieved through LASSO regression and MILP optimization to resolve the IK problem. A first order formulation of the sparse regression problem is further introduced to reduce chattering on the joint velocity profiles. This article presents the theory behind the proposed approaches and performs a comparison analysis based on simulated and real experiments on different humanoid platforms.

Contact Force/Torque Control Based on Viscoelastic Model for Stable Bipedal Walking on Indefinite Uneven Terrain

Humanoid robots are being designed to perform tasks currently carried out by human workers in industry, manufacturing, service, and disaster assistance. To this end, the humanoid robot should be able to walk stably across many types of terrain. However, when traversing a complex unknown environment, it is difficult to realize accurate terrain perception immediately through large data collected by the sensor system, leading to a difference between planned foot landing positions and actual foot landing positions. As a result, an unexpected contact force/torque may affect the stability of the robot. This paper adopts active contact perception instead of terrain perception and proposes a contact force/torque control method based on the viscoelastic model to address this problem. In addition, we design a body stability controller based on tracking the trajectories of the virtual repellent point (VRP) and the divergent component of motion (DCM) to restrain the disturbance caused by the unexpected contact force/torque. Simulations and experiments on the BHR-6P humanoid robot platform demonstrate the proposed contact force/torque control method for walking on indefinite uneven terrain. Note to Practitioners —This paper presents a contact force/torque controller based on a viscoelastic model, which unifies contact perception and adaptive reaction. Using the viscoelastic model, we get the relationship between the end position/posture and the first-order differential of the contact force/torque, from which a state equation can be established and used to design a state feedback controller. Combining with body stabilization, we adopt this controller to modify the trajectory of both landing and support feet simultaneously for humanoid robots to realize stable bipedal walking on indefinite uneven terrain, which is validated in both simulations and experiments on the BHR-6P humanoid robot. In addition, this method can be employed for other robots or equipment when the contact force/torque control is needed; e.g., industry manipulators and quadruped robots.

Stability Control and Turning Algorithm of an Alpine Skiing Robot.

This paper proposes a general stability control method that uses the concept of zero-moment-point (ZMP) and a turning algorithm with a light detection and ranging (LiDAR) sensor for a bipedal alpine skiing robot. There is no elaborate simulator for skiing robots since the snow has complicated characteristics, such as compression and melting. However, real experiments are laborious because of the many varied skiing conditions. The proposed skiing simulator could be used, so that a humanoid robot can track its desired turning radius by modeled forces that are similar to real ones in the snow. Subsequently, the robot will be able to pass through gates with LiDAR sensors. By using ZMP control, the robot can avoid falling down while tracking its desired path. The performance of the proposed stabilization method and autonomous turning algorithm are verified by a dynamics simulation software, Webots, and the simulation results are obtained while using the small humanoid robot platform DARwIn-OP.