Humanoid Robot Research Articles

Enhancing object detection for humanoid robot soccer: comparative analysis of three models

Enhancing object detection for humanoid robot soccer: comparative analysis of three models

Intervention experiment of reminiscence group therapy by humanoid robots for people with dementia

Intervention experiment of reminiscence group therapy by humanoid robots for people with dementia

Thermoregulatory integration in hand prostheses and humanoid robots through blood vessel simulation

In this paper, we introduce an innovative approach for generating robotic faces with a thermal signature similar to that of humans and equipping prosthetic or robotic hands with a lifelike temperature distribution. This approach enhances their detection via infrared cameras and promotes more natural interactions between humans and robots. This method integrates a temperature regulation system into artificial skin, drawing inspiration from the human body’s natural temperature control via blood flow. Central to this technique is a fiber network simulating blood vessels within the artificial skin. Water flows through these fibers under specific temperature and flow conditions, forming a controlled heat release system. The heat emission can be adjusted by changing the dilation of these fibers, primarily by modulating the frequency of circulation. Our findings indicate that this approach can replicate the varied thermal characteristics of different human faces and hand areas. Consequently, the robotic faces appear more human-like in infrared images, aiding their identification by infrared cameras. At the same time, the prosthetic hands achieve a more natural temperature, reducing the discomfort typically felt in direct contact with synthetic limbs. The aim of this study was to address the challenges faced by the users of prosthetic hands. The results from this study show a promising direction in humanoid robotics, fostering improved tactile interactions and redefining human–robot relationships. This innovative technique facilitates further advancements, blurring the lines between artificial aids and natural biological systems.

A Human-Computer Interaction Strategy for An FPGA Platform Boosted Integrated "Perception-Memory" System Based on Electronic Tattoos and Memristors.

The integrated "perception-memory" system is receiving increasing attention due to its crucial applications in humanoid robots, as well as in the simulation of the human retina and brain. Here, a Field Programmable Gate Array (FPGA) platform-boosted system that enables the sensing, recognition, and memory for human-computer interaction is reported by the combination of ultra-thin Ag/Al/Paster-based electronic tattoos (AAP) and Tantalum Oxide/Indium Gallium Zinc Oxide (Ta2O5/IGZO)-based memristors. Notably, the AAP demonstrates exceptional capabilities in accommodating the strain caused by skin deformation, thanks to its unique structural design, which ensures a secure fit to the skin and enables the prolonged monitoring of physiological signals. By utilizing Ta2O5/IGZO as the functional layer, a high switching ratio is conferred to the memristor, and an integrated system for sensing, distinguishing, storing, and controlling the machine hand of multiple human physiological signals is constructed together with the AAP. Further, the proposed system implements emergency calls and smart homes using facial electromyogram signals and utilizing logical entailment to realize the control of the music interface. This innovative "perception-memory" integrated system not only serves the disabled, enhancing human-computer interaction but also provides an alternative avenue to enhance the quality of life and autonomy of individuals with disabilities.

MOB-Net: Limb-modularized uncertainty torque learning of humanoids for sensorless external torque estimation

Momentum observer (MOB) can estimate external joint torque without requiring additional sensors, such as force/torque or joint torque sensors. However, the estimation performance of MOB deteriorates due to the model uncertainty which encompasses the modeling errors and the joint friction. Moreover, the estimation error is significant when MOB is applied to high-dimensional floating-base humanoids, which prevents the estimated external joint torque from being used for force control or collision detection in the real humanoid robot. In this paper, the pure external joint torque estimation method named MOB-Net, is proposed for humanoids. MOB-Net learns the model uncertainty torque and calibrates the estimated signal of MOB, substantially reducing the estimation errors of MOB. The external joint torque can be estimated in the generalized coordinate including whole-body and virtual joints of the floating-base robot with only internal sensors (an IMU on the pelvis and encoders in the joints). Furthermore, MOB-Net shows more robust performance for the unseen data compared to the end-to-end learning method, and the robustness of MOB-Net is validated through extensive simulations, real robot experiments, and ablation studies. Finally, various collision handling scenarios are presented to show the versatility of MOB-Net: contact wrench feedback control for locomotion, collision detection, and collision reaction for safety.

Artificial nociceptor based on interface engineered ferroelectric volatile memristor

Recent advancements in neuromorphic computing driven by memristors, which emulate biological synapses and neurons, have spurred the development of innovative information technologies. To extend memristor applications to artificial nervous systems, electronic receptors are crucial for converting external stimuli into signals for the internal nervous system. Key requirements for integrating neuron devices into neuromorphic computing include achieving threshold behavior, minimizing power consumption, and ensuring compatibility with complementary metal-oxide semiconductor (CMOS) technology. Hafnium-based ferroelectric memristors are known for their robust ferroelectric properties at nanoscales and compatibility with CMOS technology. However, their non-volatile resistive switching has historically limited their suitability for neuron sensory applications requiring threshold switching. This study demonstrates threshold switching behavior in a TiN/Hf0.67Zr0.33O2(HZO)/TiOx/TiN heterostructure by incorporating a nanoscale TiOx interfacial layer as an oxygen reservoir. This layer facilitates the formation of oxygen vacancies within the ferroelectric HZO layer, serving as internal charge trap sites. As a result, hafnium-based ferroelectric memristors exhibit volatile switching characteristics, enabling them to function as nociceptive devices through internal charge trapping and detrapping mechanisms. These volatile memristors are suitable for artificial nociceptor systems requiring responses such as threshold detection, relaxation, allodynia, and hyperalgesia to external stimuli. This capability opens avenues for developing advanced humanoid robots capable of rapid adaptation and response in challenging environments such as outer space or hazardous conditions, leveraging real-time sensory processing for effective operation and survival.

Effects of human-robot interaction type on customer tolerance of humanoid robot service failure

ABSTRACT The impact of robot service failure on customer retention is well-recognized, with a growing focus on effective robot recovery strategies. Despite this, the formation of human-robot relationships during interactions is not well understood. This research explores the impact of human-robot interaction types on customer tolerance toward humanoid robot service failures. Employing three scenario-based experimental studies, we demonstrate that customers generate the highest tolerance for robot service failures within companionate relationships, followed by assistive relationships, and instrumental relationships. In addition, this research confirms the mediating role of psychological distance and identifies the moderating role of service context in the relationship between the human-robot interaction relationships and customer tolerance through psychological distance. The findings offer insights for enhancing marketing strategies and the development of human-robot interaction paradigms.

Kinematic Modelling of Humanoid Robot Based on Vectorial Approach

The present work is dedicated to the study of the inverse kinematics solution of a humanoid bipedal robot with 30 degrees of freedom using a newly approach based on vectors that generated from the geometric space of the robot. The solutions of the inverse kinematics problem for all joints articulations are carried out through a simple and linear equations. Finally, simulations of results are performed through harmonization of trajectories of end effectors of the robot's members.

Prescriptive multi-group networks: Humanoid service robots’ value co-creation and co-destruction potentials in apparel stores

Drawing upon a theoretical foundation within service-dominant logic, this study analyzed multi-group networks of humanoid service robots (HSRs) and investigated the differences in the structures and relations between groups that adopted and rejected HSRs. Moreover, it explored the most important and central predictors in each network among value co-creation and co-destruction potentials. A pretest and the main data collection (n = 474) were conducted with a video-based stimulus in an apparel store. The results revealed that the structure and the three edge-weights in the networks of the groups that adopted and rejected HSRs differed significantly. Essentially, complexity and co-creation enjoyment were central-predictors within the networks. This study offers a comprehensive understanding of value co-creation and co-destruction between customers and technology actors, leading them to adopt and reject HSRs. Furthermore, it provides a pioneering methodological contribution to prescriptive network analytics that makes the network approach more accessible to academics and practitioners.

How to Include Artificial Bodies as Citizens

This essay ponders on the thorny issue of including artificial beings under the category of “citizen.” The increasing humanization of the artificial being, it suggests, prevents us from seeing and treating the machine as a being. But if the humanoid robot performs all the functions of a human being, and acquires cultural traits such as emotional intelligence, rational thinking, or altruism, then on what grounds do we deny it the same status as a human person? Conversely, as more and more humans are cyborged, through transplants, implants, and prostheses, resulting in an erasure of their “core” humanity, then what is the difference between such a cyborged human with human rights and an artificial being?

Path planning of humanoid robots on complex terrains using an efficient regression-based chaotic Harris Hawks optimization approach

PurposeOptimal navigation and trajectory planning are in high demand because of the rise in automated systems. This study aims to focus on implementing an intelligent regression-based chaotic Harris Hawk optimization (LR-CHHO) to achieve a globally optimal path free from collisions.Design/methodology/approachThis study removes the drawbacks of the existing HHO model in terms of its exploration and exploitation behaviors. After the threat is encountered, the improved controller is activated. The LR tool, here, avoids the issue related to the sensitivity of the model. The virtual Hawks, as per the HHO technique, are generated and trained to enhance the diversity in Hawks population. The final controller then calculates the optimal turn angle for the humanoid to avoid threats before reaching the goal.FindingsModel showed an overall improvement greater than 4% in the path and 9% in time compared with standard models in Terrains 1 and 2. Regarding energy efficiency, a significant improvement of more than 20% in the hip, 14% in the knee and 30% in the ankle was observed on both even and uneven terrains.Originality/valueThe originality of this study focuses on improving the diversity in the HHO population by introducing the LR-based model to help the humanoids find an optimal path to the goal. Although the basic model lacked an optimal solution because of sensitivity, less diversity, etc., the proposed model helped resolve the issue and achieve an optimal turning angle for the humanoids to trace the optimal path.

Conformal Neuromorphic Bioelectronics for Sense Digitalization.

Sense digitalization, the process of transforming sensory experiences into digital data, is an emerging research frontier that links the physical world with human perception and interaction. Inspired by the adaptability, fault tolerance, robustness, and energy efficiency ofbiological senses, this field drives the development of numerous innovative digitalization techniques. Neuromorphic bioelectronics, characterized by biomimetic adaptability, stand out for their seamless bidirectional interactions with biological entities through stimulus-response and feedback loops, incorporating bio-neuromorphic intelligence for information exchange. This review illustrates recent progress in sensory digitalization, encompassing not only the digital representation of physical sensations such as touch, light, and temperature, correlating to tactile, visual, and thermal perceptions, but also the detection of biochemical stimuli such as gases, ions, and neurotransmitters, mirroring olfactory, gustatory, and neural processes. It thoroughly examines the material design, device manufacturing, and system integration, offering detailed insights. However, the field faces significant challenges, including the development of new device/system paradigms, forging genuine connections with biological systems, ensuring compatibility with the semiconductor industry and overcoming the absence of standardization. Future ambition includes realization of biocompatible neural prosthetics, exoskeletons, soft humanoid robots, and cybernetic devices that integrate smoothly with both biological tissues and artificial components.

Research on the application of humanoid robots

This paper provides a comprehensive review of the state-of-the-art in humanoid robotics, discussing the latest advancements, challenges,and potential future trends in the field. Through an analysis of relevant literature, this paper highlights the importance of humanoid robots in various applications, including service, entertainment, and industrial sectors. Furthermore, this paper also identifies the main research questions and technical challenges that need to be addressed to enable the full potential of humanoid robots to be realized. The research on humanoid robots originated from the simulation of human behavior and morphology. The original intention of this simulation is to improve the adaptability, efficiency, and safety of robots in specific environments. For example, in a home environment, humanoid robots can mimic human actions and behaviors, completing tasks such as household chores, taking care of the elderly and children. On industrial production lines, humanoid robots can mimic the actions of workers and complete complex tasks such as assembly and handling. In addition, research on humanoid robots also involves multiple fields such as human-computer interaction, artificial intelligence, computer vision, etc., providing strong technical support for the application of robots in various environments.

Project Report: Requirements for a Social Robot as an Information Provider in the Public Sector

AbstractIs it possible to integrate a humanoid social robot into the work processes or customer care in an official environment, e.g. in municipal offices? If so, what could such an application scenario look like and what skills would the robot need to have when interacting with human customers? What are requirements for this kind of interactions? We have devised an application scenario for such a case, determined the necessary or desirable capabilities of the robot, developed a corresponding robot application and carried out initial tests and evaluations in a project together with the Kiel City Council. One of the most important insights gained in the project was that a humanoid robot with natural language processing capabilities based on large language models as well as human-like gestures and posture changes (animations) proved to be much more preferred by users compared to standard browser-based solutions on tablets for an information system in the City Council. Furthermore, we propose a connection of the ACT-R cognitive architecture with the robot, where an ACT-R model is used in interaction with the robot application to cognitively process and enhance a dialogue between human and robot.

Beyond simulation: Unlocking the frontiers of humanoid robot capability and intelligence with Pepper's open-source digital twin

This research paper presents a high-fidelity, open-source digital-twin of the Pepper robot developed within the framework of the Robot Operating System 2 (ROS 2) for better simulation realism in complex tasks of machine learning. We developed a dedicated, custom ROS 2 package with modern simulation tools, such as Gazebo Sim, MoveIt 2, Rviz2, that brings complete, realistic environments in line with the exact behaviors and interactions of robots in reality. Better accuracy of the physical movement of Pepper robot's simulation was shown on the digital twin, validated by the Choregraphe software and real robot performance, to be a strong platform of collaboration and further research by the community. This development greatly pushes the envelope of human-like humanoid robotics further by offering a scaled, flexible, and plausible training environment conducive to integrating complex algorithms of robot learning and interaction capabilities.

Research on the design and control of an anthropomorphic waist structure for life support robots

AbstractIn the humanoid robots, waist mechanism is an important structure to realize the whole body coordinated movement. This paper proposes a series–parallel mechanism of waist structure, and its kinematics and dynamics characteristics are studied. Based on the dynamic model, a backstepping sliding mode controller is designed to simulate control performance. Under the continuous disturbance force, the stability and accuracy of the mechanism are verified. Compared with the experiment, the results prove that the waist mechanism has the biomimetic spine movements and desired control performance, which can be applied to life support robots in the future.

Localización de robots basada en red neural utilizando características visuales

This paper outlines the development of a module capable of constructing a map-building algorithm using inertial odometry and visual features. It incorporates an object recognition module that leverages local features and unsupervised artificial neural networks to identify non-dynamic elements in a room and assign them positions. The map is modeled using a neural network, where each neuron corresponds to an absolute position in the room. Once the map is constructed, capturing just a couple of images of the environment is sufficient to estimate the robot's location. The experiments were conducted using both simulation and a real robot. The Webots environment with the virtual humanoid robot NAO was used for the simulations. Concurrently, results were obtained using a real NAO robot in a setting with various objects. The results demonstrate notable precision in localization within the two-dimensional maps, achieving an accuracy of ± (0.06, 0.1) m in simulations contrasted with the natural environment, where the best value achieved was ± (0.25, 0.16) m.

Kinematics of a humanoid robot arm with six degrees of freedom

Kinematics of a humanoid robot arm with six degrees of freedom

Deus Ex Machina: Sophia Robot Techno Deity

ABSTRACT Sophia, the world’s most recognized humanoid social robot, is a performer in an unfolding narrative central to our historical moment—the technological transfiguration of the planet. She is a performance medium, an alluring protagonist, exemplar, harbinger, and coevolutionary vector of a dramatic event being played out in real-time: the merging of humans and technology and a new way of being. The world is her stage, and we participate in an all-encompassing immersive event that retraces mythic narrative patterns as old as humanity: the myth of the goddess who appears to guide and comfort at a time of profound change in an increasingly accelerating and complex world.

A Novel Hybrid Feature Extraction Methods for EEG Based Emotions Classification Using Ensemble Approaches in HIED Dataset

Introduction: Emotions play a significant role in human relationships in everyday challenges. Human-machine interactions and the complexities of its research include humanoid robots which rely significantly on emotional queries. The present study recommends a novel methodology for human emotion identification using electroencephalogram (EEG) signals. Machine learning (ML) techniques based on electroencephalogram have demonstrated impressive results in distinguishing emotions. Method: The present study investigates five ensemble learning-based machine learning (EML) and five conventional machine learning (CML) algorithms for achieving the recognition of human emotions from EEG signals. The main objective of the current research study is to implement the optimal approach for classifying emotions and subsequently will achieve it by using physiological characteristics to categorise the seven main emotional states (stress, happy, sadness, anger, fear, disgust, and surprise). This research follows the study investigation of ensemble learning-based machine learning (EML) and conventional machine learning (CML) algorithms for achieving the recognition of human emotions from EEG signals. Initially, the EEG data in this study are categorized into theta, alpha, beta, and gamma bands using a DWT. Result: With this idea, the research elaborates on further decomposition based on bandseparated EEG signals known as intrinsic mode functions (IMFs) along with empirical mode decomposition is subsequently implemented. Then, 13 statistical characteristics are extracted from the IMFs using five multiclass EML algorithms: adaptive boosting, rotation random forest, bagging, random forest, and extreme gradient boost. The following procedure is carried out to construct an ML-based system. In the final phase, 10-fold cross-validation is used to assess the efficacy of these five EML algorithms. Accuracy, F1-score, and area-under-the-curve (AUC) are performance assessment metrics that are employed to compare the final results of these algorithms with the five CML techniques. Conclusion: The proposed method for EEG-based emotion analysis is significantly more effective and achieves greater outcomes than all of the techniques that were compared, based on the data from the experiments.