Frontiers in Neurorobotics最新文献

{"title":"Improving performance in SNN-based deep reinforcement learning via transition-aware embeddings.","authors":"Hiroto Takigasaki, Takahiro Iwata, Seankein Yoshioka, Daisuke Miki","doi":"10.3389/fnbot.2026.1929177","DOIUrl":"https://doi.org/10.3389/fnbot.2026.1929177","url":null,"abstract":"<p><p>Deep Reinforcement Learning (DRL), which integrates reinforcement learning with deep neural networks (DNNs), has been extensively researched across diverse domains. Robotics, in particular, has seen significant advancements, as DRL enables agents to extract meaningful features from high-dimensional observations and make precise decisions within complex environments. Furthermore, in real-world control tasks, achieving high performance within a limited number of interactions is required, particularly in complex and unknown environments. In addition, since real-world trials are constrained by cost and safety considerations, designing DRL algorithms that enable high sample efficiency and stable decision-making is of critical importance. Spiking neural networks (SNNs), inspired by biological neural systems, have recently attracted increasing attention due to the binary and event-driven nature of their information processing. Motivated by these properties, there has been growing interest in integrating SNNs into DRL. Nevertheless, SNN-based DRL faces challenges in learning performance. To address this issue, this study introduces embeddings learned from environmental dynamics into SNN-based DRL. Experimental evaluations conducted on four continuous control tasks from OpenAI Gym demonstrate that the proposed method outperforms conventional SNN-based DRL methods, both in terms of maximum average rewards and accelerated reward acquisition during the early stages of learning. These results establish that leveraging transition-aware embeddings effectively enhances both performance and sample efficiency in SNN-based DRL.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1929177"},"PeriodicalIF":3.5,"publicationDate":"2026-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13677943/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149223982","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Uncertainty-aware posture quality assessment with Bayesian liquid neural networks.","authors":"Yuhua Mu, Mingliang Zhu, Zhi Tao","doi":"10.3389/fnbot.2026.1958419","DOIUrl":"10.3389/fnbot.2026.1958419","url":null,"abstract":"<p><p>Automated posture quality assessment has become increasingly important in health and wellness technology. However, existing methods predominantly provide point estimates without quantifying prediction confidence, posing a critical limitation in safety-sensitive applications where incorrect assessments may lead to improper guidance. This paper addresses this gap by introducing a reliability-oriented evaluation framework based on Bayesian Liquid Neural Networks (LNNBI). Unlike conventional approaches, our method simultaneously delivers a quality score and a principled uncertainty measure derived from Bayesian variational inference. More importantly, we incorporate a rejection mechanism that enables the model to abstain from making predictions when uncertainty exceeds a predefined threshold, establishing a built-in safeguard for practical deployment. To support this framework, we construct a longitudinal dataset comprising 50 participants over 200 sessions, decomposing four fundamental human postures into seven biomechanical indicators. Experimental results demonstrate that LNNBI achieves 0.8715 accuracy and 0.9105 precision, outperforming LSTM, MC-GRU, TSGCN, and YoNet baselines. Uncertainty analysis reveals a strong correlation between prediction error and uncertainty (Pearson's <i>r</i> = 0.73), confirming that the model reliably identifies its own low-confidence predictions. With a 15% rejection rate, the effective accuracy reaches 0.923. Correlation analysis further identifies Pelvic Position and Neutrality (<i>r</i> = 0.682) and Spinal Alignment (<i>r</i> = 0.595) as the most influential biomechanical indicators. This work offers a reliability-first perspective on automated posture assessment, with promising potential for deployment in personalized health coaching and remote guidance, particularly on GPU-accelerated systems.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1958419"},"PeriodicalIF":3.5,"publicationDate":"2026-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13672587/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149215992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Low-cost fine-tuning of SmolVLA with smoothness regularization and chunk-aware auxiliary supervision for language-conditioned manipulation.","authors":"Chenkai He","doi":"10.3389/fnbot.2026.1890245","DOIUrl":"10.3389/fnbot.2026.1890245","url":null,"abstract":"<p><p>Vision-Language-Action (VLA) models offer a unified interface for language-conditioned manipulation. This paper reports a negative result: a low-cost post-training recipe for SmolVLA with LoRA, a temporal smoothness regularizer, and chunk-aware auxiliary supervision from action-variation pseudo labels does not improve manipulation success under a 30,000-step budget (approximately 1/67 of the original 2,000,000-step SmolVLA recipe). Because the auxiliary classifier is used only during training and the runtime chunk length remains fixed at <i>k</i> = 8, we denote the configuration SmolVLA+LoRA+S&C (smoothness and chunk-aware auxiliary losses) rather than \"adaptive.\" We evaluate four LIBERO suites with a unified protocol of 500 episodes per cell (50 episodes × 10 task variants). Over three training seeds, the matched fixed-chunk <i>k</i> = 8 baseline reaches a four-suite macro success rate of 10.9%±1.1, whereas SmolVLA+LoRA+S&C reaches 3.5%±1.4; the pre-specified primary comparison shows significant deficits on LIBERO-Spatial (-16.4 percentage points, exact sign-flip permutation <i>p</i> = 0.004) and LIBERO-Object (-17.5 pp, <i>p</i> = 0.002), with matched-pairs rank-biserial effect sizes of -0.96 and -1.0. Matched component ablations isolate the smoothness loss as the harmful term (smoothness-only collapses performance; chunk-classifier-only approximately matches the baseline), and executed-action logs show the regularizer <i>triples</i> trajectory jerk (1.69 vs. 0.59 RMS)-the opposite of its intent. A training-free inference-time temporal-ensembling baseline, by contrast, more than doubles success on the two suites where the baseline is competent (Spatial 36.2 vs. 19.0%; Object 56.2 vs. 24.0%) at a 2.3 × step-rate cost, and a 10-100K budget sweep shows the S&C deficit never closes. We conclude that, for the tested configuration, budgets, and benchmark, the added action-side losses are not competitive with a well-tuned fixed chunk, and inference-time ensembling is the stronger use of the same compute.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1890245"},"PeriodicalIF":3.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13669200/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149215987","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"CADA-Net: cross-altitude domain-adaptive perception for label-efficient onboard sensing in autonomous UAVs.","authors":"Liya Cai","doi":"10.3389/fnbot.2026.1926034","DOIUrl":"10.3389/fnbot.2026.1926034","url":null,"abstract":"<p><p>Autonomous unmanned aerial vehicles (UAVs) depend on onboard perception as the front end of their sensing-decision-control loop, where each detection feeds directly into the navigation, avoidance, and tracking decisions made in flight. Yet detectors trained at one altitude routinely degrade when the platform is redeployed at another, because the underlying distribution shift couples scale, viewpoint, and target density. This study addresses the cross-altitude transfer gap by proposing CADA-Net, an altitude-conditioned detector for onboard UAV perception that treats altitude as an exploitable domain variable rather than a nuisance to be removed. The framework injects a categorical altitude prior into multi-scale features through feature-wise linear modulation, aligns cross-altitude representations via a gradient-reversal adversarial discriminator attached to each pyramid level, and generates target-domain pseudo-supervision through a weak-to-strong teacher-student self-training stream, all sharing a single conditioned encoder. Together these components target not raw recognition accuracy alone but perception that remains stable as the platform's viewing geometry and object density change through flight. Evaluated on the UAVDT benchmark under a low → high adaptation protocol, CADA-Net reaches 46.3 mAP@0.5 on the high-altitude band, surpassing the source-only baseline by 17.9 points and the strongest domain-adaptive competitor by 7.2 points, while leaving only a 6.3-point gap to a fully-supervised upper bound; with 5% of target labels, accuracy rises to 48.1 mAP@0.5. Onboard profiling on a Jetson AGX Orin sustains 42 FPS at INT8 precision within a 27.4 W envelope, indicating that the accuracy gain survives the throughput and power limits of embedded inference, which is a precondition for onboard use rather than evidence of closed-loop flight. These findings indicate that rendering a geometric prior explicit can support label-efficient perception at embedded inference rates for UAV platforms operating across altitude transitions.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1926034"},"PeriodicalIF":3.5,"publicationDate":"2026-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13668863/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149216053","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Assisted exploration of difficult transitions in humanoid motion tracking.","authors":"Chaojie Fu, Chengkai Su, Lei Jiang, Chengwei Zhuo, Kaixin Lan, Shaowen Cheng, Hongtao Wang","doi":"10.3389/fnbot.2026.1920711","DOIUrl":"10.3389/fnbot.2026.1920711","url":null,"abstract":"<p><p>Humanoid motion tracking provides a scalable interface for transferring kinematic human motion to whole-body robot control, but highly dynamic and contact-rich references remain difficult because underactuation and discontinuous contacts can restrict the closed-loop state distributions explored during training. External wrenches can reduce dynamic mismatch during imitation, but retaining such assistance in the final controller can compromise physical realism. This paper proposes residual-wrench-assisted reinforcement learning (RWARL), a two-stage framework that uses base residual wrenches as a temporary optimization scaffold. RWARL first solves a relaxed tracking problem with residual-wrench assistance and then anneals the residual-wrench strength while adapting early-termination bounds and segment sampling to observed training difficulty. To keep the policy adaptable as the training distribution shifts from assisted to unassisted dynamics, RWARL incorporates plasticity-preserving mechanisms during relaxation. Experiments on highly dynamic and contact-rich references show that RWARL generally improves global tracking accuracy, with the largest gains near difficult transitions where standard training tends to produce conservative behavior. Compared with the baseline, the final unassisted RWARL policies reduce global body-position tracking error by 8.6%-37.8% on the highly agile and contact-rich motions examined in this work and achieve the largest successful-frame-rate gain of 41.8 percentage points on <i>jump twist</i>. A closed-loop predecessor-state diagnostic further links these gains to more favorable predecessor-state distributions around critical phases. We deploy the final unassisted controllers on Unitree G1 hardware, demonstrating that the learned policies remain executable after residual assistance is removed. Together, these findings suggest that RWARL uses residual wrenches to reshape learning around difficult, low-reachability transitions, allowing the final unassisted policy to inherit better tracking behavior in phases that standard training tends to underexplore.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1920711"},"PeriodicalIF":3.5,"publicationDate":"2026-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13661928/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149181190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Toward brain-trained humanoid robots.","authors":"Maël Donoso","doi":"10.3389/fnbot.2026.1903423","DOIUrl":"10.3389/fnbot.2026.1903423","url":null,"abstract":"<p><p>A growing corpus of experimental research demonstrates that neuroimaging data can be leveraged to improve the performance of artificial intelligence models, including reinforcement learning models in robotics. However, most existing studies have focused on vision, audition, language, or reward and error signals recorded while the human brain acts as an observer. In this paper, we argue that humanoid robots, although not equivalent to humans, could offer a unique opportunity to use the neural signals associated with touch, or other embodiment-dependent neural signals. As a result, humanoid robots could significantly expand the range of brain regions and functional networks that could be targeted for brain-trained artificial intelligence, and open new horizons in terms of alignment and reasoning. We discuss the improvements that neuroimaging data could potentially unlock in the context of sensorimotor tasks, spatial navigation, sensorimotor integration, embodied alignment, embodied reasoning, and social integration, as well as the broader challenges and opportunities related to brain-trained humanoid robots.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1903423"},"PeriodicalIF":3.5,"publicationDate":"2026-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13655105/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149164155","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"WIS: world-guided instruction semantic diffusion policy for predictive bimanual manipulation.","authors":"Xukun Liu, Liguo Hou, Pu Cheng, Xiaoping Luo, Fengjuan Xie, Jiqing Wei, Feng Wang, Aifeng Liu","doi":"10.3389/fnbot.2026.1940438","DOIUrl":"https://doi.org/10.3389/fnbot.2026.1940438","url":null,"abstract":"<p><strong>Introduction: </strong>Robotic bimanual manipulation poses significant challenges for reactive visuomotor policies, which inherently lack the capacity to anticipate future environmental dynamics, especially in long-horizon and semantically complex tasks. To address this limitation, there is a critical need for frameworks that integrate predictive modeling with task-level reasoning to enable coordinated, forward-looking dual-arm control.</p><p><strong>Methods: </strong>We introduce the World-guided Instruction Semantic Diffusion Policy (WIS), a novel hierarchical framework that tightly integrates a language-driven world model with a diffusion-based policy for dual-arm coordination. The architecture comprises three core modules: (1) a multimodal language-visual perception module that fuses 3D point cloud features with natural language embeddings via cross-modal attention for task-relevant semantic grounding; (2) a language-conditioned world model that explicitly forecasts future state trajectories conditioned on current states, action sequences, and language instructions, providing forward-looking predictive reasoning; and (3) a hierarchical diffusion policy with a high-level latent planner and a low-level diffusion controller, wherein the world model's predictions actively guide action refinement through a prediction-aware sampling mechanism. This design cleanly separates high-level task reasoning from low-level motor generation while ensuring every action remains grounded in both immediate observations and anticipated future outcomes. We extensively evaluated WIS on the RoboTwin 2.0 platform using Aloha-AgileX bimanual robots across multiple challenging manipulation tasks.</p><p><strong>Results: </strong>Experimental results on the RoboTwin 2.0 benchmark demonstrate that WIS consistently outperforms strong baselines, achieving superior success rates across all evaluated tasks.</p><p><strong>Discussion: </strong>The proposed method offers an efficient and robust solution for temporally coherent bimanual manipulation, with minimal computational overhead relative to baseline approaches. These findings underscore the value of integrating predictive world models with semantic instructions to enhance both the foresight and dexterity of robotic dual-arm systems in complex, real-world settings.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1940438"},"PeriodicalIF":3.5,"publicationDate":"2026-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13630928/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149108396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Brain-inspired cognitive state modeling of complex English discourse reading: an LLM-parameterized hierarchical semi-Markov approach.","authors":"Bing Xie, Yongjin Hu, Linlin Zhao","doi":"10.3389/fnbot.2026.1930227","DOIUrl":"https://doi.org/10.3389/fnbot.2026.1930227","url":null,"abstract":"<p><strong>Introduction: </strong>Complex English discourse reading requires readers to integrate lexical access, syntactic parsing, local meaning construction, cross-sentence inference, and discourse monitoring over time.</p><p><strong>Methods: </strong>We developed a brain-inspired, large-language-model-parameterized hierarchical hidden semi-Markov model that encodes lexical-, sentence-, and discourse-level representations and maps contextual embeddings to state-emission, transition, and duration parameters. Discourse-structure and cognitive-load constraints were incorporated into global decoding.</p><p><strong>Results: </strong>Experiments on 1,200 English reading passages achieved a macro-F1 of 0.860, a boundary accuracy of 0.83, a duration MAE of 0.52, and a discourse-consistency correlation of 0.76.</p><p><strong>Discussion: </strong>The results suggest that duration-aware latent-state modeling can provide an interpretable computational account of adaptive discourse comprehension while preserving explicit temporal structure.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1930227"},"PeriodicalIF":3.5,"publicationDate":"2026-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13632470/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149108402","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ISEED: an always-on cognitive architecture for experience-driven interaction-oriented humanoid robots.","authors":"Dario Pasquali, Francesco Rea, Pietro Morasso, Giulio Sandini, Alessandra Sciutti","doi":"10.3389/fnbot.2026.1920808","DOIUrl":"https://doi.org/10.3389/fnbot.2026.1920808","url":null,"abstract":"<p><p>Current cognitive architectures for social robots, even when conceived as autonomous and adaptable, remain largely grounded in fully digital, von Neumann-style paradigms, where acquired knowledge is detached from individual experience. This contrasts with biological cognition, in which learning emerges from continuous, embodied interaction which leads to personal, non-copyable competencies. In this perspective, we argue that achieving truly adaptive and socially situated robotic agents requires a paradigm shift toward hybrid, bio-inspired, always-on architectures, where dynamic, and digitally implementable components coexist. Such architecture supports continuous activity, structural plasticity, and experience-dependent learning, enabling knowledge to emerge and strengthen from distributed interactions rather than from copiable parameters. We outline a roadmap in which embodiment, dynamical systems, endogenous values, and socially grounded learning mechanisms are central design principles of such cognitive architecture, and we discuss how these ideas can scale beyond sensorimotor skills toward what we believe being important for social robots. These principles are currently being explored in a bioinspired initiative (iCog) aimed at developing the ISEED (Interaction-oriented Situated Embodied Experience-Driven) cognitive architecture, a framework for humanoid social robots, meant to be a testbed for implementing and validating a hybrid, experience-driven approach for real-world cooperative robot partners.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1920808"},"PeriodicalIF":3.5,"publicationDate":"2026-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13627406/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149108357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Designing for gender, age & proficiency: an empirical study of the cognitive ergonomics of dual-task interference in industrial human-robot collaboration.","authors":"Someshwar Roy, Igal Peretz, Lior Sayfeld, Yael Edan","doi":"10.3389/fnbot.2026.1222566","DOIUrl":"10.3389/fnbot.2026.1222566","url":null,"abstract":"<p><strong>Introduction: </strong>This article reports an empirical study on Human-Robot Collaboration (HRC) under Dual-Task Interference (DTI). To the best of our knowledge, prior research has not investigated the intersection of Dual-Task Interference (DTI) and Human-Robot Collaboration (HRC) in industrial contexts. This study represents one of the first empirical attempts to understand DTI-induced human limitations in collaborative robotics, particularly in industrial HRC settings where stochastic interruptions and competing cognitive demands are common phenomena.</p><p><strong>Methods: </strong>The DTI phenomenon was implemented in a cognitive joint-assembly task involving 172 participants. Each participant collaborated with two robots while simultaneously performing a cognitive task designed to induce DTI during team-work. The performance measures included the number of Human-Robot interactions (measuring user engagement), total robot idle time (measuring team fluency), and the total number of completed cognitive tasks (measuring task performance).</p><p><strong>Results: </strong>Females exhibited significantly lower robot idle times (12%) and higher Human-Robot interactions (14%), indicating greater collaboration with the robot and more fluent team collaboration than males. Adolescents completed the cognitive task significantly faster than adults (21%) and experts (22%), whereas adults and experts demonstrated greater fluency in team collaboration. No significant differences were observed between novices and experts. Novices successfully bridged the skill gap by distributing their attention equivalently across all aspects of the team-work, resulting in performance comparable to that of experts.</p><p><strong>Discussion: </strong>The results reveal that (a) gender and age-group differences significantly influence HRC in DTI-based tasks, (b) performance speed in the primary task negatively affects the team fluency of HRC, and (c) effective team coordination skills are equally as important as task proficiency in HRC.</p><p><strong>Conclusion: </strong>This study contributes to design practice by demonstrating that collaborative robot learning algorithms can classify users into specific population clusters based on their characteristic patterns of collaboration with robots for improved performance and user experience (UX). Furthermore, task proficiency and team coordination emerge as two distinct and mutually independent skills in DTI-based tasks.</p>","PeriodicalId":12628,"journal":{"name":"Frontiers in Neurorobotics","volume":"20 ","pages":"1222566"},"PeriodicalIF":3.5,"publicationDate":"2026-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13619584/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149080716","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}