Humanoid Character Research Articles

Comparative analysis of transitions generated using the Unity game development platform

This paper conducts a comparative analysis of transitions generated using the Unity engine. It selects fifteen animations featuring a humanoid character, introduces breaks in marker trajectories, and fills them with transitions generated by the game engine's animator. These transitions are then compared with the unmodified original character animation. The study compares animations by calculating the average deviation in bone rotation and position between the original and generated motion throughout the animation. The results show that the Unity engine excels in generating transitions for slow animations involving the lower body limbs, with the largest errors occurring in the bones at the extremities of the limbs.

Biomac3D: 2D-to-3D Human Pose Analysis Model for Tele-Rehabilitation Based on Pareto Optimized Deep-Learning Architecture

The research introduces a unique deep-learning-based technique for remote rehabilitative analysis of image-captured human movements and postures. We present a ploninomial Pareto-optimized deep-learning architecture for processing inverse kinematics for sorting out and rearranging human skeleton joints generated by RGB-based two-dimensional (2D) skeleton recognition algorithms, with the goal of producing a full 3D model as a final result. The suggested method extracts the entire humanoid character motion curve, which is then connected to a three-dimensional (3D) mesh for real-time preview. Our method maintains high joint mapping accuracy with smooth motion frames while ensuring anthropometric regularity, producing a mean average precision (mAP) of 0.950 for the task of predicting the joint position of a single subject. Furthermore, the suggested system, trained on the MoVi dataset, enables a seamless evaluation of posture in a 3D environment, allowing participants to be examined from numerous perspectives using a single recorded camera feed. The results of evaluation on our own self-collected dataset of human posture videos and cross-validation on the benchmark MPII and KIMORE datasets are presented.

메타휴먼을 활용한 디지털 휴먼 제작 교육 프로그램 개발

Recently, as the scope of use of digital contents has expanded, the demand for a digital human, a humanoid character, has increased. However, creating realistic virtual characters is much more difficult than creating ordinary virtual objects. Unreal Engine's MetaHuman, released in 2021, was developed to make it easy for anyone to create highly realistic humanoid characters. In this paper, we survey various technical elements of the virtual character production system. Among them, we focus on MetaHuman technology, a realistic digital human production system, and we examine the systemic characteristics and possibilities of MetaHuman. Afterwards we develop a new education program of digital human creation using MetaHuman and analyze the results that can be obtained when educating students through an actual curriculum. The students easily adapted to the new production environment of MetaHuman and created their own character to represent the school. After they set the personality in detail, they proceeded with an exterior design that reflected it. The main keywords derived by the students were ‘passion, courage, art, challenge, collaboration, creativity, communication, and technology’. Keywords such as ‘freedom, lively, subjective, unique, curious, fun and pleasant, attractive, young, well suited to red, dignified, modern woman, full of passion’ were also used. The gender of the virtual influencer representing the school is not biased to one side, and the male-to-female ratio is produced similarly. They created a unique virtual influencer rather than a pretty character. As the field of digital humans is expected to expand in line with the expansion of the Metaverse in the future, the concept and production ability of digital humans learned through this curriculum will be able to contribute to nurturing future talent.

„Jutro należy do kotów”. Problemy (eco) science fiction w powieści Bernarda Werbera

Why tomorrow should not belong to humans, but to another species? Science fiction seems to answer this question with alarmingly accurate arguments. SF texts often seem like prophecies that predict the future. We most willingly accept visions in which man is the author of innovative technologies as well as cultural and economic progress. What if this development is not ascribed to the human race, but for example: to monkeys or cats? The classic repertoire of science fiction heroes, apart from humans, includes robots, cyborgs, androids or newcomers from another planet (aliens). Their humanoid character — anthropomorphic features of appearance, behavior, development of the species in the form of created (or mid creation) civilization and culture — is designed to break the anthropocentric view of man. The function of the Other in science fiction can, however, be taken over by a creature much closer and longer known to man than a newcomer from a foreign planet or a creature of highly developed technology — an animal. The essay is an attempt to analyze Bernard Werber’s novel Tomorrow the cats from the perspective of general science fiction and ecofiction issues. At the same time, the issue of species chauvinism and the ways in which it manifests itself in literature are discussed.

Computational Modeling: Human Dynamic Model.

Improvements in quantitative measurements of human physical activity are proving extraordinarily useful for studying the underlying musculoskeletal system. Dynamic models of human movement support clinical efforts to analyze, rehabilitate injuries. They are also used in biomechanics to understand and diagnose motor pathologies, find new motor strategies that decrease the risk of injury, and predict potential problems from a particular procedure. In addition, they provide valuable constraints for understanding neural circuits. This paper describes a physics-based movement analysis method for analyzing and simulating bipedal humanoid movements. The model includes the major body segments and joints to report human movements' energetic components. Its 48 degrees of freedom strike a balance between very detailed models that include muscle models and straightforward two-dimensional models. It has sufficient accuracy to analyze and synthesize movements captured in real-time interactive applications, such as psychophysics experiments using virtual reality or human-in-the-loop teleoperation of a simulated robotic system. The dynamic model is fast and robust while still providing results sufficiently accurate to be used to animate a humanoid character. It can also estimate internal joint forces used during a movement to create effort-contingent stimuli and support controlled experiments to measure the dynamics generating human behaviors systematically. The paper describes the innovative features that allow the model to integrate its dynamic equations accurately and illustrates its performance and accuracy with demonstrations. The model has a two-foot stance ability, capable of generating results comparable with an experiment done with subjects, and illustrates the uncontrolled manifold concept. Additionally, the model's facility to capture large energetic databases opens new possibilities for theorizing as to human movement function. The model is freely available.

Catch & Carry

We address the longstanding challenge of producing flexible, realistic humanoid character controllers that can perform diverse whole-body tasks involving object interactions. This challenge is central to a variety of fields, from graphics and animation to robotics and motor neuroscience. Our physics-based environment uses realistic actuation and first-person perception - including touch sensors and egocentric vision - with a view to producing active-sensing behaviors (e.g. gaze direction), transferability to real robots, and comparisons to the biology. We develop an integrated neural-network based approach consisting of a motor primitive module, human demonstrations, and an instructed reinforcement learning regime with curricula and task variations. We demonstrate the utility of our approach for several tasks, including goal-conditioned box carrying and ball catching, and we characterize its behavioral robustness. The resulting controllers can be deployed in real-time on a standard PC. 1

From Analog to Virtual: Visual Stylizations of Humanoid Characters Across Media

Visual stylization and its impact on different aspects of the perception of digital human beings are commonly debated. This study investigated how fictional and non-fictional characters are represented in various media from the perspective of digital humanoid character design. Based on Zangwill’s theory of Moderate Aesthetic Formalism, this study focused on the formalistic aspect of visual analysis and interpretation of media artifacts ranging from older media such as paintings to newer media, such as animations, interactive video games and mobile apps. This paper also explores several case studies of how humanoid digital characters are represented via visual stylizations across different media. This article underlines the importance of visual stylization as an opportunity to find unique and innovative ways of communicating with visual means.

VR‐OCKS: A virtual reality game for learning the basic concepts of programming

AbstractThis paper presents a prototype of a virtual reality (VR) system to teach the basic concepts of programming called VR‐OCKS. The system is inspired by other visual languages such as Scratch or Kodu, and it works by proposing to the user the resolution of simple puzzles in a 3D environment. Several basic commands to a humanoid character, such as advance or turn, together with control flow structures like iteration and conditional selections, are needed to provide a solution for increasingly difficult challenges. Our aim is to attract users, usually children and teenagers, into the world of programming by taking advantage of the appeal and potential of VR. The use of VR‐OCKS strengthened the spatial orientation and autonomy of the users, in addition to enhancing common sense, creative thinking, and systematic reasoning. In our experiments, VR‐OCKS was accepted by adults and children alike and it showed great potential as an educational tool.

Performance Driven-biped Control for Animated Human Model with Motion Synthesis Data

Games and 3D movies are mostly supported by realistic character animation performance. The behaviour of the humanoid character it is depend on the motion data itself. Therefore the complexity of character movement will determine the realism of their behaviour. Generally, Motion Capture device will provide the raw data that previously recorded from human/actor movement. However there are some problems remains challenges such as controller, physic effect, or motion combination. Our proposed approach will read the data from motion capture device then transformed into realistic behaviour in virtual environment. However, there are few difficulties on realizing this idea, such as user objective and the appropriate behaviour of virtual human. Therefore, we solve this issue by providing the biped control to overcome the complexity of motion synthesis data when it will be applied into character animation. The controller is capable to perform motion blending with inverse and forward kinematics, as a result it able to generate the realistic behaviour along with user intention. There is three main behaviour walking, steady and jogging that has value 0-100. As a result of experiment, the biped interface control is able to read data from motion capture then load and control the virtual human by manipulating the joint forces power in every movement of the characters. As future works, the external physical forces can be added as additional forces in humanoid model to provide certain effect such as: falling down, jumping or kicking and punching to generate realistic motion synthesis.

Unreal Interactive Puppet Game Development Using Leap Motion

This paper proposed a novel puppet play method utilizing recent technology. An interactive puppet game has been developed based on the theme of a famous Chinese classical novel. This project was implemented using Unreal Engine, which is a leading software of integrated tools for developers to design and build games. On the other hand, Leap Motion Controller is a sensor device for recognizing hand movements and gestures. It is commonly used in systems which require close-range finger-based user interaction. In order to manipulate puppets’ movements, the developed program employs the Leap Motion SDK, which provides a friendly way to add motion-controlled 3D hands to an Unreal game. The novelty of our project is to replace 3D model of rigged hands by two 3D humanoid rigged characters. The challenges of this task are two folds. First, the skeleton structure of a human hand and a humanoid character (i.e., puppets) are totally different. Making the puppets to follow the hand poses of the user and yet ensuring reasonable puppets’ movements has not been discussed in the literatures nor in the developer forums. Second, there are only a limited number of built-in recognizable hand gestures. More recognizable hand gestures need to be created for the interactive game. This paper reports the proposed solutions to these challenges.

MOTION DEFORMATION STYLE CONTROL TECHNIQUE FOR 3D HUMANOID CHARACTER BY USING MOCAP DATA

Realistic humanoid 3D character movement is very important to apply in the computer games, movies, virtual reality and mixed reality environment. This paper presents a technique to deform motion style using Motion Capture (MoCap) data based on computer animation system. By using MoCap data, natural human action style could be deforming. However, the structure hierarchy of humanoid in MoCap Data is very complex. This method allows humanoid character to respond naturally based on user motion input. Unlike existing 3D humanoid character motion editor, our method produces realistic final result and simulates new dynamic humanoid motion style based on simple user interface control.

Women’s Attractiveness Perception of Men’s Dance Movements in Relation to Self-Reported and Perceived Personality

Recent research on women’s ratings of men’s dance movements indicates that women derive similar cues of male “quality” (e.g., physical strength) from movement as from faces and bodies. Whether this extends to personality assessment is yet unclear. We recorded dance movements of 80 men using 3D optical motion-capture technology and secured self-reports of men’s personality standings. Dance movements were applied to a uniform, shape-standardized virtual humanoid character (avatar) and presented to women as 15-s videos for attractiveness and personality ratings. Women’s ratings of dance attractiveness correlated negatively with men’s self-reports and women’s ratings of men’s neuroticism and were positively correlated with men’s self-reported extraversion and women’s ratings of men’s conscientiousness. Men’s self-reported personality scores did not correlate with women’s ratings of men’s personality standings. Findings are discussed with reference to previous research and the social significance of dance movement cues and impression formation.

An Architecture for Personality-based, Nonverbal Behavior in Affective Virtual Humanoid Character

As humans we perceive other humans as individually different based – amongst other things – on a consistent pattern of affect, cognition, and behavior. Here we propose a biologically and psychologically grounded cognitive architecture for the control of nonverbal behavior of a virtual humanoid character during dynamic interactions with human users. Key aspects of the internal states and overt behavior of the virtual character are modulated by high-level personality parameters derived from the scientific literature. The virtual character should behave naturally and consistently while responding dynamically to the environment's feedback. Our architecture strives to yield consistent patterns of behavior though personality traits that have a modulatory influence at different levels of the hierarchy. These factors affect on the one hand high-level components such as ‘emotional reactions’ and ‘coping behavior’, and on the other hand low-level parameters such as the ‘speed of movements and repetition of gestures. Psychological data models are used as a reference to create a map between personality factors and patterns of behavior. We present a novel hybrid computational model that combines the control of discrete behavior of the virtual character moving through states of the interaction with continuous updates of the emotional state of the virtual character depending on feedback from interactions with the environment. To develop and evaluate the hybrid model, a testing scenario is proposed that is based on a turn-taking interaction between a human participant and a 3D representation of the humanoid character. We believe that our work contributes to individualized, and ultimately more believable humanoid artifacts that can be deploy in a wide range of application scenarios.

Designing and fabricating mechanical automata from mocap sequences

Mechanical figures that mimic human motions continue to entertain us and capture our imagination. Creating such automata requires expertise in motion planning, knowledge of mechanism design, and familiarity with fabrication constraints. Thus, automaton design remains restricted to only a handful of experts. We propose an automatic algorithm that takes a motion sequence of a humanoid character and generates the design for a mechanical figure that approximates the input motion when driven with a single input crank. Our approach has two stages. The motion approximation stage computes a motion that approximates the input sequence as closely as possible while remaining compatible with the geometric and motion constraints of the mechanical parts in our design. Then, in the layout stage, we solve for the sizing parameters and spatial layout of all the elements, while respecting all fabrication and assembly constraints. We apply our algorithm on a range of input motions taken from motion capture databases. We also fabricate two of our designs to demonstrate the viability of our approach.

Men’s personality and women’s perception of their dance quality

Recent research shows that women judge men who show variability in their body movements as good dancers. Here we report data on women’s perception of dance quality in 48 men, aged 18–42 years, and relate them to men’s self-reported personality traits. Male participants completed a standardised personality inventory (the NEO-FFI) and then danced to a basic rhythm while their body movements were tracked with optical 3D motion-capture technology. Dance movements were applied to a featureless virtual humanoid character and judged on their dance quality by 53 women, aged 17–57 years, who viewed 15 s of the rendered video clips of each male dancer. Conscientiousness and social agreeableness was correlated positively and significantly with women’s perception of men’s dance quality. Extraversion showed a positive correlation and neuroticism and openness were associated negatively with women’s perception of men’s dance quality, though these correlations failed to reach significance. We suggest that male dance movements may convey aspects of their personality, though possible consequences in terms of female mate preferences and selection remain to be explored.