Frontiers in Robotics and AI最新文献

{"title":"A platform for investigating prompt framing as interface parameters in foundation models for robotics.","authors":"Anup Tuladhar, Eli Kinney-Lang","doi":"10.3389/frobt.2026.1771992","DOIUrl":"https://doi.org/10.3389/frobt.2026.1771992","url":null,"abstract":"<p><p>Foundation models, in particular large language models (LLMs), are finding increasing popularity when used in describing goals for robotic control, decision making, and execution. Recently, proposals for hybrid paradigms leveraging strengths of reinforcement learning (RL) agents in tandem with LLMs for robotic control have been demonstrated. The interface between the RL agents and the language model however offers a unique opportunity to explore how prompt framing may affect such hybrid systems. This work presents a controlled experimental platform to measure and better understand how manipulation of the interface between RL agents and an LLM impacts behaviour of a hybrid advisor-arbiter architecture. We compared three agents under matched evaluation protocols and initializations in a simulated navigation environment: (i) RL-only tabular Q-learning; (ii) LLM-only (stateless) action selection; and (iii) a hybrid LLM + RL agent. Under a constrained interaction budget (10 episodes per world), the hybrid LLM + RL agent achieves higher mean success and higher mean cumulative reward than both RL-only and LLM-only baselines. Advisor-channel ablations (random recommendations and null recommendations) reduce performance, indicating that structured advice contributes beyond adding extra text. We further demonstrate prompt framing as a controlled factor by evaluating navigation-role personas, narrative personas, and relational variants of a caregiver prompt under matched conditions, yielding heterogeneous effects across framings. The contribution of this work is to provide a structured testbed and evaluation approach for investigating the impact of prompt framing on multi-step decision making and control tasks.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1771992"},"PeriodicalIF":3.0,"publicationDate":"2026-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13143583/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147844421","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":"Digital transformation in restaurants: key aspects of service robot deployment from project initiation to evaluation.","authors":"Anniken Susanne T Karlsen, Bjørn Andersen, Solvår Elverum Heirsaunet, Elin Indergård, Kristina Nevstad, Wenche Aarseth","doi":"10.3389/frobt.2026.1793138","DOIUrl":"https://doi.org/10.3389/frobt.2026.1793138","url":null,"abstract":"<p><p>This study examines the deployment of service robots designed to support waitstaff in food delivery within Norwegian restaurants, which are national pioneers in adopting this technology. It investigates key aspects of service robot deployment, from project initiation through evaluation, and the approach used to ensure that robot functionality aligns with restaurant workflows and spatial configurations. Using an exploratory-explanatory case study design, the research draws on 22 interviews with 34 participants, complemented by observational fieldwork to strengthen contextual understanding. The findings offer an integrated view of the digital transformation process, identifying important considerations across all project phases. One example is the importance of considering incorporating robot service needs into early facility planning. By addressing potential obstacles such as stairs and doorsteps during the front-end design, restaurants can avoid costly redesigns and ensure optimal robot performance. By examining real-world deployment, the study offers practical insights for project managers, hospitality leaders, and others preparing to integrate service robots into restaurant operations.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1793138"},"PeriodicalIF":3.0,"publicationDate":"2026-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13143633/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147844349","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":"Evaluation of material effects on three-dimensional cultured skeletal muscle cells for biohybrid robots.","authors":"Hirono Ohashi, Shunsuke Shigaki, Seita Fujii, Masahiro Shimizu, Koh Hosoda","doi":"10.3389/frobt.2026.1778864","DOIUrl":"https://doi.org/10.3389/frobt.2026.1778864","url":null,"abstract":"<p><p>Robots are traditionally confined to controlled environments such as factories, where human interactions are limited. However, the demand for robots that are capable of collaborating with humans is increasing. To achieve symbiosis, integrating the physical flexibility and environmental adaptability of living organisms into robotic systems is crucial. An example of such a robot is a biohybrid robot driven by three-dimensional (3D) cultured skeletal muscle cells. These muscle cells, which are composed of myoblasts and an extracellular matrix (ECM), contract and generate force in response to external stimuli. The standardization of such 3D-cultured skeletal muscle cells is essential for practical applications. However, their complete standardization has not yet been achieved. The contractile force of 3D-cultured skeletal muscle cells produced via 3D printing is still insufficient for practical applications as actuators in biohybrid robots. In a previous study, we developed a simple fabrication method for 3D-cultured skeletal muscle cells. These bio-cultured artificial muscle (BiCAM) cells can control the shape and cell alignment of tissues. Differences in the composition of an ECM have been suggested to affect the contractile force of 3D skeletal muscle tissues; however, their impact on the response characteristics remains poorly understood. In this study, we investigated how the ECM composition influences the contractile force of 3D skeletal muscle cells in biohybrid robots as a step toward their eventual standardization. Compared with tissues cultured under MF conditions, in which electrically induced contraction was previously confirmed, tissues cultured under CM conditions exhibited an approximately two-fold greater contractile force at voltage amplitudes of 10 and 30 V. Furthermore, the fabrication success rate was 100 <math><mrow><mi>%</mi></mrow> </math> under CM conditions but only 62.5-70 <math><mrow><mi>%</mi></mrow> </math> under other ECM conditions. In contrast, although CM tissues generated larger forces, tissues cultured under MgF and CMg conditions exhibited higher-frequency response. These findings demonstrated that the BiCAM is a viable actuator and offers new possibilities for the design of biohybrid robots.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1778864"},"PeriodicalIF":3.0,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13138982/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147844406","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":"Robot-assisted pedicle screw placement by using optical navigation.","authors":"Ayoob Davoodi, Ruixuan Li, Aidana Massalimova, Fabio Carrillo, Gianni Borghesan, Christoph J Laux, Philipp Fürnstahl, Kathleen Denis, Emmanuel Vander Poorten","doi":"10.3389/frobt.2026.1774473","DOIUrl":"https://doi.org/10.3389/frobt.2026.1774473","url":null,"abstract":"<p><p>Pedicle screw placement is the gold standard for spinal pathologies that require surgical stabilization. Accurate screw placement is important to avoid severe complications, but ensuring accuracy remains a challenge. This work proposes an optical camera-based robot-assisted drilling system for spine surgery. Preoperative CT scans are used to plan screw trajectories in both synthetic phantoms and <i>ex-vivo</i> ovine spines. After robotic drilling, postoperative scans are registered to the preoperative plan to quantify drilling accuracy. In total, 48 screws are drilled into <i>ex-vivo</i> ovine spines, producing a median entry point distance error of 1.51 mm (IQR 0.91mm, 2.10 mm) and an angle error of <math><mrow><mn>2.30</mn> <mo>°</mo></mrow> </math> (IQR <math><mrow><mn>1.28</mn> <mo>°</mo></mrow> </math> , <math><mrow><mn>3.13</mn> <mo>°</mo></mrow> </math> ), where 95.83% of the placements were clinically successful. Optical camera-based robot-assisted drilling system for spine surgery may increase accuracy by providing precise spatial registration between the patient anatomy and the robotic system, enabling accurate alignment and execution of the drilling task.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1774473"},"PeriodicalIF":3.0,"publicationDate":"2026-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13124635/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147822239","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":"Design of a mixed reality-based digital twin human-machine interaction system for special working conditions.","authors":"Shuai Li, Yifei Hu, Huiyu Li, Junjie Xu, Ming Li, Yunqiang Zhang, Qingting Ren","doi":"10.3389/frobt.2026.1774317","DOIUrl":"https://doi.org/10.3389/frobt.2026.1774317","url":null,"abstract":"<p><p>Operational robots have demonstrated significant potential in complex scenarios such as live-line maintenance and medical surgery. Existing research on Mixed Reality (MR) and Digital Twin (DT) systems has primarily focused on unidirectional data visualization and passive state monitoring. Existing research on Mixed Reality (MR) and Digital Twin (DT) systems has primarily focused on unidirectional data visualization and passive state monitoring, acting as \"open-loop\" observation tools that fail to address low operational precision and inefficient human-robot synergy in dynamic, high-risk environments. For the first time, we integrate an MR-based closed-loop digital twin operating system for human-robot collaborative operation into the task execution of live-line operation equipment to address the above challenges. Moving beyond simple visualization, the proposed framework establishes an integrated operational paradigm that bridges the gap between immersive perception and real-time interventional control. This framework comprises three integral components: (1) the construction of a high-fidelity virtual digital twin; (2) the development of a human-computer interaction paradigm based on MR technology; and (3) the establishment of an MR-based human-machine collaborative operation mode. Building upon this framework, a system was implemented for live-line working robots. Experimental results indicate that, compared with traditional control methods, the proposed system reduces the task completion time of live-line equipment tasks by 14.3% on average, verifying the feasibility and effectiveness of the pioneering application of the closed-loop digital twin operating system in live-line operation equipment.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1774317"},"PeriodicalIF":3.0,"publicationDate":"2026-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13124514/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147822265","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":"Editorial: Errors and mistakes in human-robot interactions.","authors":"Manuel Giuliani, Leimin Tian, Maha Salem, Nicole Mirnig","doi":"10.3389/frobt.2026.1813746","DOIUrl":"https://doi.org/10.3389/frobt.2026.1813746","url":null,"abstract":"","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1813746"},"PeriodicalIF":3.0,"publicationDate":"2026-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13127160/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147822311","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":"Multi-party open-ended conversation with a social robot.","authors":"Giulio Antonio Abbo, Maria Jose Pinto-Bernal, Martijn Catrycke, Tony Belpaeme","doi":"10.3389/frobt.2026.1766383","DOIUrl":"https://doi.org/10.3389/frobt.2026.1766383","url":null,"abstract":"<p><p>Multi-party open-ended conversation remains a major challenge in human-robot interaction, particularly when robots must recognise speakers, allocate turns, and respond coherently under overlapping or rapidly shifting dialogue. This paper presents a multi-party conversational system that combines multimodal perception (voice direction of arrival, speaker diarisation, face recognition) with a large language model for response generation. Implemented on the Furhat robot, the system was evaluated with 30 participants across two scenarios: (i) parallel, separate conversations and (ii) shared group discussion. Results show that the system maintains coherent and engaging conversations, achieving high addressee accuracy in parallel settings <math><mrow><mo>(</mo> <mrow><mn>92.6</mn> <mi>%</mi></mrow> <mo>)</mo></mrow> </math> and strong face recognition reliability <math><mrow><mo>(</mo> <mrow><mn>80</mn> <mtext>-</mtext> <mn>94</mn> <mi>%</mi></mrow> <mo>)</mo></mrow> </math> . Participants reported clear social presence and positive engagement, although technical barriers such as audio-based speaker recognition errors and response latency affected the fluidity of group interactions. The results highlight both the promise and limitations of LLM-based multi-party interaction and outline concrete directions for improving multimodal cue integration and responsiveness in future social robots.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1766383"},"PeriodicalIF":3.0,"publicationDate":"2026-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13124475/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147822290","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":"What ethical AI and robots could mean: a conceptual and ethical reflection.","authors":"Jana Sedlakova","doi":"10.3389/frobt.2026.1769361","DOIUrl":"https://doi.org/10.3389/frobt.2026.1769361","url":null,"abstract":"","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1769361"},"PeriodicalIF":3.0,"publicationDate":"2026-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13111092/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147785744","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":"Editorial: Innovative robotics for lunar exploration and on-orbit servicing.","authors":"Serdar Sean Kalaycioglu, Anton De Ruiter, Arun Misra, Kazuya Yoshida","doi":"10.3389/frobt.2026.1835560","DOIUrl":"https://doi.org/10.3389/frobt.2026.1835560","url":null,"abstract":"","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1835560"},"PeriodicalIF":3.0,"publicationDate":"2026-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13102609/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147785665","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":"Optimizing avian flight dynamics with a synergetic bio-inspired and machine learning approach.","authors":"Waleed Khalid, Valentina Leontiuk, Innokentiy Kastalskiy, Victor B Kazantsev","doi":"10.3389/frobt.2026.1788627","DOIUrl":"https://doi.org/10.3389/frobt.2026.1788627","url":null,"abstract":"<p><p>This study presents a composite numerical and machine learning framework to enhance the aerodynamic performance of a bio-inspired flapping wing. The wing kinematics were extracted from biological flight data using a multi-step process: the DeepLabCut tool was applied to extract body point coordinates from avian flight videos, followed by data digitization in Google Colab and trajectory post-processing in Python. These kinematics were then prescribed to a three-dimensional wing model for high-fidelity unsteady Reynolds-Averaged Navier-Stokes (URANS) simulations of incompressible turbulent flow in ANSYS Fluent, utilizing a user-defined function (UDF) and a sliding mesh technique. Validated against existing experimental data, the numerical model serves as a reliable data generation tool. Subsequently, a machine learning model was developed to explore the design space and identify kinematic parameters that optimize aerodynamic efficiency. The results demonstrate that the proposed framework effectively bridges biological observation with computational optimization, offering a robust approach for the performance enhancement of bio-inspired flapping wings.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"13 ","pages":"1788627"},"PeriodicalIF":3.0,"publicationDate":"2026-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13095514/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147785691","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}