JournalTOCs

International Journal of Humanoid Robotics
Journal Prestige (SJR): 0.495

Citation Impact (citeScore): 1
Number of Followers: 6

Hybrid journal (It can contain Open Access articles)
ISSN (Print) 0219-8436 - ISSN (Online) 1793-6942
Published by World Scientific

[121 journals]

Research on Multimodal Information Processing and Behavior Generation for
Humanoid Robots Based on PaLM 2 and Multimodal Transformer Architecture
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Authors: Jie Fang, Wenliang Ju, Feng Xiao, Rubing Huang, Yanjun Liu
  Abstract: International Journal of Humanoid Robotics, Ahead of Print.
  With the rapid development of artificial intelligence technology, the demand for applying humanoid robots in complex environments is gradually increasing. How to effectively process multimodal information and improve the efficiency of behavioral decision-making has become a hot topic in current research. In response to the low efficiency of behavior decision-making and generation for humanoid robots, single data modality, and difficulty in effectively integrating information from different modalities, this paper combines Pathways Language Model 2 (PaLM 2) and multimodal Transformer architecture to study the multimodal information processing and behavior generation of humanoid robots. The experiment is based on preprocessed visual, tactile, and auditory data. A multimodal Transformer architecture is designed to fuse the multimodal data, and a soft attention mechanism is used for preliminary feature fusion. It further processes and optimizes the fused features through a multi-head attention mechanism, outputs high-dimensional feature vectors, and then uses the PaLM 2 model to understand natural speech instructions and model the context to generate accurate task descriptions. Finally, the Deep Q-Network (DQN) algorithm can be used to create behavior for humanoid robots, and a [math]-greedy strategy can be adopted to select actions, improving the efficiency of multimodal information processing and behavior generation for humanoid robots. The experiment is based on the public normal-robots behavior dataset and the field collection and recording data of the humanoid robot company, combined with the multimodal Transformer-Pathways Language Model 2-Deep Q-Network (Transformer-PaLM 2-DQN). The humanoid robot can more accurately understand the multimodal data in complex environments, and show higher adaptability and efficiency in behavior generation and task execution. The generation efficiency reached 92.67% and 7.38% higher than Deep Deterministic Policy Gradient (DDPG) and 10.22% higher than unimodal visual information, proving the key role of multimodal information fusion in improving robot intelligent decision-making. The results show that using the PaLM 2 model and multimodal Transformer architecture to generate humanoid robot behavior using DQN greatly improves generation efficiency and accuracy, integrates information from different modalities, has certain adaptability to the environment, and promotes the widespread application of humanoid robots in today’s society.
  Citation: International Journal of Humanoid Robotics
  PubDate: 2025-07-07T07:00:00Z
  DOI: 10.1142/S021984362540002X
Structural Design and Link Optimization for a Lower Limb Exoskeleton with
Four Link Knee Joints
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Authors: Meng Fei, Zhang Zhenhai, Xiao Mohui, Xu Younan
  Abstract: International Journal of Humanoid Robotics, Ahead of Print.
  To help individuals alleviate pressure on the knees and enhance mobility. In this paper, a lower limb exoskeleton with a multi-link lower limb is designed. In order to design a lower limb exoskeleton coupled with human motion, the behavior of the human lower limb is analyzed. The stress and deformation of the lower limb exoskeleton under different loads are analyzed by ANSYS Workbench. The results show that the exoskeleton can effectively bear external loads. The kinematics of the lower extremity exoskeleton are analyzed based on the D-H method. Then the lower limb exoskeleton modeling is simulated and analyzed through the Matlab Robot toolbox, which verifies the movement correctness of the designed lower limb exoskeleton. The force transmission model of the multi-link lower limb exoskeleton is established, and the length of links and the torque transmission performance of the knee joint are optimized by the Genetic Algorithm. The results show that when the knee joint is at [math]–[math], the optimized lower limb exoskeleton can obtain 0–32.5[math]NM more output torque than the original lower limb exoskeleton.
  Citation: International Journal of Humanoid Robotics
  PubDate: 2025-05-30T07:00:00Z
  DOI: 10.1142/S0219843625500033
Social Robots as Decision-Making Companions: Exploring the Impact of
Social Cues on Human Responses
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Authors: Aimi Shazwani Ghazali, Hariz Hafizalshah, Shahrul Naim Sidek, Hazlina Md Yusof, Jaap Ham
  Abstract: International Journal of Humanoid Robotics, Ahead of Print.
  Making decisions, particularly ones fraught with ambiguity, inherently induces stress, which is a recognized contributor to long-term mental health issues. In high-stakes or uncertain environments, stress can significantly impair decision quality and well-being. Social robots offer a promising solution by potentially providing companionship and cognitive assistance in such scenarios. This study investigates the influence of verbal social cues used by social robots on human responses. In a laboratory setting, 60 participants interacted with the Alpha Mini robot, a programmable social agent, for 30[math]min. The robot offered advice using combinations of controlling language (high versus low) and social praise (absent versus present) in a between-subject design setup while playing a decision-making computer game. Post-interaction, social responses were measured using questionnaires. Results revealed strong, positive correlations between participants’ enjoyment of interacting with the robot and their intention to use it again in the future, as well as their liking and trust in the robot’s advice. These correlations were statistically significant ([math]) and suggest that positive user experiences can translate into continued engagement. Positive responses were observed regardless of the specific social cues employed. To design effective human–robot interactions (HRI), multiple social cues should be integrated using high controlling language for clarity and direction paired with social praise to soften the tone in order to enhance trust, enjoyment, and effectiveness. Future work might enhance the current findings by integrating physiological data into the measures used to assess emotional responses to the robot and its cues. Additionally, expanding participant demographics and incorporating longitudinal studies could further validate and extend these results.
  Citation: International Journal of Humanoid Robotics
  PubDate: 2025-05-20T07:00:00Z
  DOI: 10.1142/S0219843625500021
Control Barrier Function-based Whole-body Control Framework for Humanoid
Robots
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Authors: Pin-Tsun Chen, Han-Pang Huang, Jia-Hsun Lo, Shun-Kai Chang
  Abstract: International Journal of Humanoid Robotics, Ahead of Print.
  This paper addresses the challenge of deploying high-Degree-of-Freedom (DoF) humanoid robots in real-world scenarios, a critical issue in robotics. Previous approaches often relied on oversimplified assumptions, limiting robots’ adaptability. This work emphasizes the need for a flexible control framework for operational efficacy and safety. Significant advancements include floating-based kinematics for expanded robot workspace and stability, and a recursive algorithm for the Centroidal Momentum Matrix (CMM), enhancing motion planning. A novel self-collision avoidance algorithm employing boundary spheres and Control Barrier Functions (CBFs) ensures operational safety. A major contribution is the development of a control barrier function-based Quadratic Programming (QP)-based control framework integrating Proportional-Derivative (PD) control for stable walking. The paper simplifies trajectory design by categorizing motion tasks and enhances dynamic stability using a new angular momentum rate change compensation method with force-torque sensor feedback. These improvements mark a substantial leap in humanoid robotics, enhancing efficiency, functionality, and adaptability, and paving the way for their broader integration into human society.
  Citation: International Journal of Humanoid Robotics
  PubDate: 2025-05-06T07:00:00Z
  DOI: 10.1142/S0219843625400018
A Bionic Bipedal Balancing Control Based on Control Priority and Target
Attitude Adjustments
- Free pre-print version: Loading...
  Rate this result: What is this?
  
  Please help us test our new pre-print finding feature by giving the pre-print link a rating.
  A 5 star rating indicates the linked pre-print has the exact same content as the published article.
  
  Authors: Chen Jingnong, Zhang Xia, Song Jie, Li Yi, Dong Shaojiang
  Abstract: International Journal of Humanoid Robotics, Ahead of Print.
  To achieve rapid balance recovery of humanoid robots under external shocks, a bionic bipedal balance control approach based on control priority and target attitude adjustment was developed. In order to successfully restore equilibrium, the system first automatically modifies the control priority based on the impact magnitude and stability margin. This means that when the center of mass approaches the support border, it receives a higher attitude control priority. Second, the discriminating mechanism for the shock confrontation and balance recovery stages was designed, and the target attitude of the robot’s centroid of mass was modified appropriately for each stage. The optimum three-dimensional force at the foot end was then obtained by combining MPC’s state prediction in the future time domain with a quadratic programming solution, allowing the robot to quickly restore its equilibrium after being disturbed by the external environment. External force striking test were conducted on flat and irregular ground while the robot was standing bipedally. The results suggest that the proposed strategy can improve the robot’s ability to withstand stronger external shocks and swiftly recover balance following external hits.
  Citation: International Journal of Humanoid Robotics
  PubDate: 2024-12-11T08:00:00Z
  DOI: 10.1142/S0219843624400012

HOME > Browse the 73 Subjects covered by JournalTOCs
Subject	Total Journals