Sara Ahmadi Majd, Mohamad Rasoul Parsaeian, Mohsen Madani, Hadi Moradi, Abolfazl Mohammadi
{"title":"A machine learning web application for screening social anxiety disorder based on participants' emotion regulation (ML-SAD).","authors":"Sara Ahmadi Majd, Mohamad Rasoul Parsaeian, Mohsen Madani, Hadi Moradi, Abolfazl Mohammadi","doi":"10.3389/frobt.2025.1620609","DOIUrl":"10.3389/frobt.2025.1620609","url":null,"abstract":"<p><p>Social Anxiety Disorder (SAD) is called a neglected anxiety disorder since people do not realize its existence and the need to receive further treatment. Thus, it is essential to develop widely available self-screening systems to assess individuals and direct those who need further evaluation to appropriate resources. Consequently, this paper presents a web application based on machine learning to screen for SAD. The Web application comprises 10 multimedia scenarios that people with SAD may struggle with. Four hundred and eighty-eight young adults (18-35 years old) in Persian-speaking society were asked to consider themselves in these scenarios and rank their competency in dealing with each specific situation, considering three emotion regulation strategies. Participants were divided into two groups, SAD and non-SAD, based on their diagnostic history of SAD and their self-assessment of their anxiety level. Multiple machine learning models were trained and evaluated, achieving an accuracy rate of more than 80% and demonstrating the effectiveness of the tool in identifying individuals who need additional support.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1620609"},"PeriodicalIF":3.0,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12508651/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145281470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Weber-Fechner law in temporal difference learning derived from control as inference.","authors":"Keiichiro Takahashi, Taisuke Kobayashi, Tomoya Yamanokuchi, Takamitsu Matsubara","doi":"10.3389/frobt.2025.1649154","DOIUrl":"10.3389/frobt.2025.1649154","url":null,"abstract":"<p><p>This study investigates a novel nonlinear update rule for value and policy functions based on temporal difference (TD) errors in reinforcement learning (RL). The update rule in standard RL states that the TD error is linearly proportional to the degree of updates, treating all rewards equally without any bias. On the other hand, recent biological studies have revealed that there are nonlinearities in the TD error and the degree of updates, biasing policies towards being either optimistic or pessimistic. Such biases in learning due to nonlinearities are expected to be useful and intentionally leftover features in biological learning. Therefore, this research explores a theoretical framework that can leverage the nonlinearity between the degree of the update and TD errors. To this end, we focus on a <i>control as inference</i> framework utilized in the previous work, in which the uncomputable nonlinear term needed to be approximately excluded from the derivation of the standard RL. By analyzing it, the Weber-Fechner law (WFL) is found, in which perception (i.e., the degree of updates) in response to a change in stimulus (i.e., TD error) is attenuated as the stimulus intensity (i.e., the value function) increases. To numerically demonstrate the utilities of WFL on RL, we propose a practical implementation using a reward-punishment framework and modify the definition of optimality. Further analysis of this implementation reveals that two utilities can be expected: i) to accelerate escaping from the situations with small rewards and ii) to pursue the minimum punishment as much as possible. We finally investigate and discuss the expected utilities through simulations and robot experiments. As a result, the proposed RL algorithm with WFL shows the expected utilities that accelerate the reward-maximizing startup and continue to suppress punishments during learning.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1649154"},"PeriodicalIF":3.0,"publicationDate":"2025-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12507549/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145281458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Real-time traffic signal optimization for urban mobility: a reinforcement learning-enhanced framework with application to Kuwait City.","authors":"Abedalmuhdi Almomany, Eedi Eedi, Muhammed Sutcu","doi":"10.3389/frobt.2025.1669952","DOIUrl":"10.3389/frobt.2025.1669952","url":null,"abstract":"<p><strong>Introduction: </strong>This study develops an intelligent, adaptable traffic control strategy using advanced management algorithms to enhance urban mobility in smart cities. The proposed method aims to minimize wait times, reduce congestion, and improve environmental health through better traffic management.</p><p><strong>Methods: </strong>The approach thoroughly investigates and evaluates rule-based (Fixed-Time), optimization-based (Max-Pressure and Delay-Based), and machine-learning-driven (Reinforcement Learning) algorithms under various traffic conditions. This enables the system to automatically select the algorithm that most effectively minimizes wait times and reduces traffic congestion. Microscopic traffic simulations are employed to test the system, and various statistical analyses are conducted to evaluate performance. A Reinforcement Learning (RL) variant is further utilized to validate the method's effectiveness against alternative approaches.</p><p><strong>Results: </strong>The selected algorithms are executed on high-performance Field Programmable Gate Array (FPGA) platforms, which are suitable for embedded, energy-constrained smart city environments due to their lower latency and power consumption compared to general-purpose GPUs. The proposed system achieves a speedup of over 7× compared to modern high-speed general-purpose processing units (GPPUs), demonstrating the efficiency of the custom FPGA-based pipelined architecture in real-time traffic management applications.</p><p><strong>Discussion: </strong>The method not only improves traffic flow but also significantly reduces fuel consumption and carbon dioxide emissions. This study further explores how the proposed solution can be leveraged to address Kuwait's significant traffic challenges and contribute to improving air quality in the region.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1669952"},"PeriodicalIF":3.0,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12504086/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145259639","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Arash Mohammadzadeh Gonabadi, Iraklis I Pipinos, Sara A Myers, Farahnaz Fallahtafti
{"title":"Optimizing hip exoskeleton assistance pattern based on machine learning and simulation algorithms: a personalized approach to metabolic cost reduction.","authors":"Arash Mohammadzadeh Gonabadi, Iraklis I Pipinos, Sara A Myers, Farahnaz Fallahtafti","doi":"10.3389/frobt.2025.1669600","DOIUrl":"10.3389/frobt.2025.1669600","url":null,"abstract":"<p><strong>Introduction: </strong>Hip exoskeletons can lower the metabolic cost of walking in many tasks and populations, but their assistance patterns must be tailored to each user. We developed a simulation-based, human-in-the-loop (HIL) optimization framework combining machine learning (ML) and global optimization to personalize hip exoskeleton assistance patterns.</p><p><strong>Methods: </strong>Using data from ten healthy adults, we trained a Gradient Boosting (GB) surrogate model to predict normalized metabolic cost as a function of Peak Magnitude and End Timing of assistive torque. GB achieved the lowest relative absolute error percentage (RAEP) of 0.66%, outperforming Random Forest (RAEP = 0.83%) and Support Vector Regression (RAEP = 0.98%) among nine ML models. We then evaluated seven optimization algorithms, including Covariance Matrix Adaptation Evolution Strategy, Bayesian Optimization, Exploitative Bayesian Optimization, Cross-Entropy, Genetic Algorithm, Gravitational Search Algorithm (GSA), and Particle Swarm Optimization (PSO), to identify optimal assistance profiles.</p><p><strong>Results: </strong>GSA predicted the lowest metabolic cost (-1.06), equivalent to an estimated 53% reduction relative to no exoskeleton assistance, while PSO showed the highest efficiency (AUC = 0.24).</p><p><strong>Discussion: </strong>These simulated predictions, though not empirical measurements, demonstrate the framework's ability to streamline algorithm selection, reduce experimental burden, and accelerate translation of exoskeleton optimization into rehabilitation, occupational, and performance enhancement applications with broader biomechanical and clinical impact.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1669600"},"PeriodicalIF":3.0,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12504096/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145259482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhao Han, Daniel Hammer, Kevin Spevak, Mark Higger, Aaron Fanganello, Neil T Dantam, Tom Williams
{"title":"Givenness hierarchy theoretic sequencing of robot task instructions.","authors":"Zhao Han, Daniel Hammer, Kevin Spevak, Mark Higger, Aaron Fanganello, Neil T Dantam, Tom Williams","doi":"10.3389/frobt.2025.1640535","DOIUrl":"10.3389/frobt.2025.1640535","url":null,"abstract":"<p><strong>Introduction: </strong>When collaborative robots teach human teammates new tasks, they must carefully determine the order to explain different parts of the task. In robotics, this problem is especially challenging, due to the situated and dynamic nature of robot task instruction.</p><p><strong>Method: </strong>In this work, we consider how robots can leverage the Givenness Hierarchy to \"think ahead\" about the objects they must refer to so that they can sequence object references to form a coherent, easy-to-follow series of instructions.</p><p><strong>Results and discussion: </strong>Our experimental results (n = 82) show that robots using this GH-informed planner generate instructions that are more natural, fluent, understandable, and intelligent, less workload demanding, and that can be more efficiently completed.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1640535"},"PeriodicalIF":3.0,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12504070/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145259473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
José-Antonio Cervantes, Luis-Felipe Rodriguez, J Octavio Gutierrez-Garcia, Francisco Cervantes-Alvarez, Miguel Vargas Martin, Sandra Baldassarri
{"title":"Editorial: Artificial intelligence and social robotics for mental healthcare.","authors":"José-Antonio Cervantes, Luis-Felipe Rodriguez, J Octavio Gutierrez-Garcia, Francisco Cervantes-Alvarez, Miguel Vargas Martin, Sandra Baldassarri","doi":"10.3389/frobt.2025.1665800","DOIUrl":"10.3389/frobt.2025.1665800","url":null,"abstract":"","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1665800"},"PeriodicalIF":3.0,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12501527/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145253298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Shifa Sulaiman, Francesco Schetter, Ebrahim Shahabi, Fanny Ficuciello
{"title":"A learning based impedance control strategy implemented on a soft prosthetic wrist in joint-space.","authors":"Shifa Sulaiman, Francesco Schetter, Ebrahim Shahabi, Fanny Ficuciello","doi":"10.3389/frobt.2025.1665267","DOIUrl":"10.3389/frobt.2025.1665267","url":null,"abstract":"<p><p>The development of advanced control strategies for prosthetic hands is essential for improving performance and user experience. Soft prosthetic wrists pose substantial control challenges due to their compliant structures and nonlinear dynamics. This work presents a learning-based impedance control strategy for a tendon-driven soft continuum wrist, integrated with the PRISMA HAND II prosthesis, aimed at achieving stable and adaptive joint-space control. The proposed method combines physics-based modeling using Euler-Bernoulli beam theory and the Euler-Lagrange approach with a neural network trained to estimate unmodeled nonlinearities. Simulations achieved a Root Mean Square Error (RMSE) of <math><mrow><mn>3.04</mn> <mo>×</mo> <mn>1</mn> <msup><mrow><mn>0</mn></mrow> <mrow><mo>-</mo> <mn>4</mn></mrow> </msup> </mrow> </math> rad and a settling time of 3.1 s under nominal conditions. Experimental trials recorded an average RMSE of <math><mrow><mn>2.7</mn> <mo>×</mo> <mn>1</mn> <msup><mrow><mn>0</mn></mrow> <mrow><mo>-</mo> <mn>2</mn></mrow> </msup> </mrow> </math> rad and confirmed the controller's ability to recover target trajectories under unknown external forces. The method supports compliant interaction, robust motion tracking, and trajectory recovery, positioning it as a viable solution for personalized prosthetic rehabilitation. Compared to traditional controllers like Sliding Mode Controller (SMC), Model Reference Adaptive Controller (MRAC), and Model Predictive Controller (MPC), the proposed method achieved superior accuracy and stability. This hybrid approach successfully balances analytical precision with data-driven adaptability, offering a promising pathway towards intelligent control in next-generation soft prosthetic systems.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1665267"},"PeriodicalIF":3.0,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12497997/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145245434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Vision driven trailer loading for autonomous surface vehicles in dynamic environments.","authors":"Jianwen Li, Jalil Chavez-Galaviz, Nina Mahmoudian","doi":"10.3389/frobt.2025.1607676","DOIUrl":"10.3389/frobt.2025.1607676","url":null,"abstract":"<p><p>Automated docking technologies for marine vessels have advanced significantly, yet trailer loading, a critical and routine task for autonomous surface vehicles (ASVs), remains largely underexplored. This paper presents a novel, vision-based framework for autonomous trailer loading that operates without GPS, making it adaptable to dynamic and unstructured environments. The proposed method integrates real-time computer vision with a finite state machine (FSM) control strategy to detect, approach, and align the ASV with the trailer using visual cues such as LED panels and bunk boards. A realistic simulation environment, modeled after real-world conditions and incorporating wave disturbances, was developed to validate the approach and is available. Experimental results using the WAM-V 16 ASV in Gazebo demonstrated a 100% success rate under calm to medium wave disturbances and a 90% success rate under high wave conditions. These findings highlight the robustness and adaptability of the vision-driven system, offering a promising solution for fully autonomous trailer loading in GPS-denied scenarios.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1607676"},"PeriodicalIF":3.0,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12497588/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145245507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Modeling arbitrarily applicable relational responding with the non-axiomatic reasoning system: a Machine Psychology approach.","authors":"Robert Johansson","doi":"10.3389/frobt.2025.1586033","DOIUrl":"10.3389/frobt.2025.1586033","url":null,"abstract":"<p><p>Arbitrarily Applicable Relational Responding (AARR) is a cornerstone of human language and reasoning, referring to the learned ability to relate symbols in flexible, context-dependent ways. In this paper, we present a novel theoretical approach for modeling AARR within an artificial intelligence framework using the Non-Axiomatic Reasoning System (NARS). NARS is an adaptive reasoning system designed for learning under uncertainty. We introduce a theoretical mechanism called <i>acquired relations</i>, enabling NARS to derive symbolic relational knowledge directly from sensorimotor experiences. By integrating principles from Relational Frame Theory-the behavioral psychology account of AARR-with the reasoning mechanisms of NARS, we conceptually demonstrate how key properties of AARR (mutual entailment, combinatorial entailment, and transformation of stimulus functions) can emerge from NARS's inference rules and memory structures. Two theoretical demonstrations illustrate this approach: one modeling stimulus equivalence and transfer of function, and another modeling complex relational networks involving opposition frames. In both cases, the system logically demonstrates the derivation of untrained relations and context-sensitive transformations of stimulus functions, mirroring established human cognitive phenomena. These results suggest that AARR-long considered uniquely human-can be conceptually captured by suitably designed AI systems, emphasizing the value of integrating behavioral science insights into artificial general intelligence (AGI) research. Empirical validation of this theoretical approach remains an essential future direction.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1586033"},"PeriodicalIF":3.0,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12497618/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145245472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Information vs situation: balancing transparency and autonomy for trustworthy autonomous vehicles.","authors":"Ana Tanevska, Katie Winkle, Ginevra Castellano","doi":"10.3389/frobt.2025.1657857","DOIUrl":"10.3389/frobt.2025.1657857","url":null,"abstract":"<p><p>With the rapid advancement of autonomous vehicle (AV) technology, AVs move beyond their initial purpose of only providing a self-driving and/or assistive driving experience, and progressively transform into interactive agents with some level of autonomy, as well as some context-dependent social features. This introduces new challenges and questions, already relevant in other areas of human-robot interaction (HRI), such as: if an AV is perceived as a social agent by the human with whom it is interacting or collaborating, how are the various facets of its interface and behaviour impacting its human partner? And how do we foster a successful collaboration between the human driver and the AV, maximizing the driver's comfort, agency, and trust in the AV? Our specific research goal in this area is to explore how the human's perception of the AV can vary across different levels of information sharing and autonomy of the AV. More precisely, in this work we sought to understand the various factors that could influence naïve participants' acceptance and trustworthiness of AV. In a between-subjects online study, informed by participatory design, we investigated the effects of different AV interfaces with different information levels on participants' perceptions of the AV, specifically their trust and comfort ratings. We also sought to understand how much the environment and the AV's behaviour play a role in determining the level of autonomy users will grant to the AV. We found that the transparency of the AV (described by the amount of information shared with the users) had a significant impact on people's trust and comfort in the car. Participants' relationship with the AV's autonomy however was more complex, and was influenced both by the AV's transparency, but also by the driving environment and the specific events happening in the scenes.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1657857"},"PeriodicalIF":3.0,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12497998/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145245541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}