Frontiers in Robotics and AI最新文献

{"title":"A survey of model compression techniques: past, present, and future.","authors":"Defu Liu, Yixiao Zhu, Zhe Liu, Yi Liu, Changlin Han, Jinkai Tian, Ruihao Li, Wei Yi","doi":"10.3389/frobt.2025.1518965","DOIUrl":"10.3389/frobt.2025.1518965","url":null,"abstract":"<p><p>The exceptional performance of general-purpose large models has driven various industries to focus on developing domain-specific models. However, large models are not only time-consuming and labor-intensive during the training phase but also have very high hardware requirements during the inference phase, such as large memory and high computational power. These requirements pose considerable challenges for the practical deployment of large models. As these challenges intensify, model compression has become a vital research focus to address these limitations. This paper presents a comprehensive review of the evolution of model compression techniques, from their inception to future directions. To meet the urgent demand for efficient deployment, we delve into several compression methods-such as quantization, pruning, low-rank decomposition, and knowledge distillation-emphasizing their fundamental principles, recent advancements, and innovative strategies. By offering insights into the latest developments and their implications for practical applications, this review serves as a valuable technical resource for researchers and practitioners, providing a range of strategies for model deployment and laying the groundwork for future advancements in model compression.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1518965"},"PeriodicalIF":2.9,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11965593/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143781673","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":"A flexible transoral swab sampling robot system with visual-tactile fusion approach.","authors":"Jiaxiang Dong, Peng Li, Quanquan Liu, Qi Liu, Chunbao Wang, Xuezhi Zhao, Xiping Hu","doi":"10.3389/frobt.2025.1520374","DOIUrl":"10.3389/frobt.2025.1520374","url":null,"abstract":"<p><p>A significant number of individuals have been affected by pandemic diseases, such as COVID-19 and seasonal influenza. Nucleic acid testing is a common method for identifying infected patients. However, manual sampling methods require the involvement of numerous healthcare professionals. To address this challenge, we propose a novel transoral swab sampling robot designed to autonomously perform nucleic acid sampling using a visual-tactile fusion approach. The robot comprises a series-parallel hybrid flexible mechanism for precise distal posture adjustment and a visual-tactile perception module for navigation within the subject's oral cavity. The series-parallel hybrid mechanism, driven by flexible shafts, enables omnidirectional bending through coordinated movement of the two segments of the bendable joint. The visual-tactile perception module incorporates a camera to capture oral images of the subject and recognize the nucleic acid sampling point using a deep learning method. Additionally, a force sensor positioned at the distal end of the robot provides feedback on contact force as the swab is inserted into the subject's oral cavity. The sampling robot is capable of autonomously performing transoral swab sampling while navigating using the visual-tactile perception algorithm. Preliminary experimental trials indicate that the designed robot system is feasible, safe, and accurate for sample collection from subjects.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1520374"},"PeriodicalIF":2.9,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11961991/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143774467","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":"Human-centered design and early evaluation of an interface for mobile-manipulator-mediated pediatric occupational therapy.","authors":"Rafael Morales Mayoral, Samuel W Logan, Naomi T Fitter","doi":"10.3389/frobt.2025.1520216","DOIUrl":"10.3389/frobt.2025.1520216","url":null,"abstract":"<p><p>Assistive mobile robots can play an important role in supporting individuals with disabilities. While the field of robot control interfaces for individuals with disabilities is growing, there is little work done on such systems for children end users specifically. Accordingly, we pursued the design of an adapted robot control interface for use in child pediatric occupational therapy (OT). Our target end user, a nine-year-old child with cerebral palsy, leveraged the interface to perform instrumental activities of daily living (e.g., play) with a modern mobile manipulator. We used an iterative design process to adjust and improve the interface via input from the participant's caregivers and occupational therapist, as well as objective participant performance data. Furthermore, we tested the participant's ability to utilize our interface by creating two testing cases: a control case (in which our participant performed standard ALD/IADL tasks) and an experimental case (in which our participant performed ADL/IADL practice activities more tailored toward the child). Key insights during the process included the need for sensitivity to taking up space on the child user's existing power wheelchair, the advantages of integrating technologies familiar to the child (e.g., gaming controls, iPads) in our system design, and the potential value of integrating playful mischief (including playful interactions between the child, their caregivers, and their clinicians) as a part of the playbook for pediatric OT. This work can serve to inform and augment new OT strategies for the marginalized population of young children with disabilities.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1520216"},"PeriodicalIF":2.9,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11958963/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143765413","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":"Development of human-collaborative robots to perform daily tasks based on multimodal vital information with cybernics space.","authors":"Akira Uehara, Hiroaki Kawamoto, Yoshiyuki Sankai","doi":"10.3389/frobt.2025.1462243","DOIUrl":"10.3389/frobt.2025.1462243","url":null,"abstract":"<p><p>Due to the increasing employment of people with disabilities, support for the elderly, and childcare needs, enhancing the independence and freedom across generations and spaces is necessary. This study aimed to develop a human-collaborative robot using multimodal vital information as input with cybernics space, which is fused \"human\" and \"Cyber/Physical Space,\" and confirm its feasibility experimentally. The robot allows the user to operate it via gaze and bio-electrical signals (BES), reflecting the user's intentions, and seamlessly transition among three modes (i.e., assistant, jockey, and ghost). In the assistant mode, the user collaborates with the robot in the physical space using a system that includes a head-mounted display (HMD) for gaze measurement, BES measurement unit, personal mobility system, and an arm-hand system. The HMD can be flipped up and down for hands-free control. The BES measurement unit captures leaked weak signals from the skin surface, indicating the user's voluntary movement intentions, which are processed by the main unit to generate control commands for the various actuators. The personal mobility system features omni-wheels for tight turning, and the arm-hand system can handle payloads up to 500 g. In the jockey mode, the user remotely operates a small mobile base with a display and camera, moving it through the physical space. In the ghost mode, the user navigates and inputs commands in a virtual space using a smart key and remote-control device integrated with IoT and wireless communication. The switching of each control mode is estimated using the BES from the user's upper arm, gaze direction, and position, thereby enabling movement, mobility, and manipulation without physical body movement. In basic experiments involving able-bodied participants, the macro averages of recall, precision, and F score were 1.00, 0.90, and 0.94, respectively, in the assistant mode. The macro averages of recall, precision, and F score were 0.85, 0.92, and 0.88, respectively, in the ghost mode. Therefore, the human-collaborative robot utilizing multimodal vital information has feasibility for supporting daily life tasks, contributing to a safer and more secure society by addressing various daily life challenges.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1462243"},"PeriodicalIF":2.9,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11959013/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143765412","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":"A child-robot theater afterschool program can promote children's conceptualization of social robots' mental capacities and engagement in learning.","authors":"Jiayuan Dong, Shuqi Yu, Koeun Choi, Myounghoon Jeon","doi":"10.3389/frobt.2025.1529421","DOIUrl":"10.3389/frobt.2025.1529421","url":null,"abstract":"<p><p>Research on integrating emerging technologies, such as robots, into K-12 education has been growing because of their benefits in creating engaging learning environments and preparing children for appropriate human-robot interactions in the future. However, most studies have focused on the impact of robots in formal educational settings, leaving their effectiveness in informal settings, such as afterschool programs, unclear. The present study developed a 9-week afterschool program in an elementary school to promote STEAM (STEM + Art) education for elementary school students. The program incorporated four modules (Acting, Dancing, Music & Sounds, and Drawing), each with specific learning objectives and concluding with a theater play at the end. This program facilitated hands-on activities with social robots to create engaging learning experiences for children. A total of 38 students, aged 6-10 years, participated in the afterschool program. Among these students, 21 took part in research activities, which included answering questions about their perceptions of robots compared to other entities (i.e., babies and beetles), learning interest and curiosity, and their opinions about robots. In addition, four teachers and staff participated in interviews, sharing their reflections on children's learning experiences with robots and their perceptions of the program. Our results showed that 1) children perceived robots as having limited affective and social capabilities but gained a more realistic understanding of their physiological senses and agentic capabilities; 2) children were enthusiastic about interacting with robots and learning about robot-related technologies, and 3) teachers recognized the importance of embodied learning and the benefits of using robots in the afterschool program; however, they also expressed concerns that robots could be potential distractions and negatively impact students' interpersonal relationships with peers in educational settings. These findings suggest how robots can shape children's perceptions of robots and their learning experiences in informal education, providing design guidelines for future educational programs that incorporate social robots for young learners.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1529421"},"PeriodicalIF":2.9,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11949813/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143754941","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: Failures and repairs in human-robot communication.","authors":"Frank Förster, Patrick Holthaus","doi":"10.3389/frobt.2025.1583911","DOIUrl":"10.3389/frobt.2025.1583911","url":null,"abstract":"","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1583911"},"PeriodicalIF":2.9,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11931154/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143701745","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":"Sliding-mode control based on prescribed performance function and its application to a SEA-Based lower limb exoskeleton.","authors":"Feilong Zhang, Tian Wang, Liang Zhang, Enming Shi, Chengchao Wang, Ning Li, Yu Lu, Bi Zhang","doi":"10.3389/frobt.2025.1534040","DOIUrl":"10.3389/frobt.2025.1534040","url":null,"abstract":"<p><p>A sliding-mode control based on a prescribed performance function is proposed for discrete-time single-input single-output systems. The controller design aims to maintain the tracking error in a predefined convergence zone described by a performance function. However, due to the fixed structure of the controller, the applicability and universality of this method are limited. To address this issue, we separate the controller into two parts and analyze the principle of the prescribed performance control (PPC) method. Then we can replace the linear part of the controller with model-based control methods to adapt to the specific characteristics of the controlled system. Compared with current works, when the established system model is inaccurate, we can enhance the smoothness or response speed of the system by introducing a penalty constant to alter the system's transient characteristics while the tracking error is within the prescribed domain. Finally, numerical comparison simulations and a lower limb exoskeleton experiment illustrate the established results and the effectiveness of the proposed method.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1534040"},"PeriodicalIF":2.9,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11913672/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143659193","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":"Operators and their human-robot interdependencies: implications of distinct job decision latitudes for sustainable work and high performance.","authors":"Milan R Wolffgramm, Stephan Corporaal, Aard J Groen","doi":"10.3389/frobt.2025.1442319","DOIUrl":"10.3389/frobt.2025.1442319","url":null,"abstract":"<p><p>The collaborative robot (cobot) has the potential to remove barriers for individual operators when deciding on the deployment of robotics in their work. Ideally, using their opportunities to (re)design work (i.e., job decision latitudes), the operator establishes synergetic human-cobot interdependencies that enable the human-cobot production unit to achieve superior performance and foster more sustainable work perceptions than manual production units. However, it remains scientifically unclear whether the operator is both willing to and capable of using cobot-related job decision latitudes, what this means for designing human-cobot interdependencies, and whether these designs improve unit outcomes. Therefore, we built a manual and three human-cobot production units with distinct job decision latitudes. Forty students participated in the manual production unit and operated one of the human-cobot production units during an assembly simulation. Sophistically accounting for individual differences, the results illustrated that most operators used speed- and task-related job decision latitudes to design their human-cobot interdependencies. These behaviours often led to increased productivity and more motivating working conditions. At the same time, these human-cobot interdependencies frequently resulted in limited human-robot interactions, poor production reliability, and more psychological safety risks. This contribution lays a rich foundation for future research on involving individual operators in developing modern production systems.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1442319"},"PeriodicalIF":2.9,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11913812/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143659189","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":"OpenSEA: a 3D printed planetary gear series elastic actuator for a compliant elbow joint exoskeleton.","authors":"Benjamin Jenks, Hailey Levan, Filip Stefanovic","doi":"10.3389/frobt.2025.1528266","DOIUrl":"https://doi.org/10.3389/frobt.2025.1528266","url":null,"abstract":"<p><strong>Introduction: </strong>Next-generation assistive robotics rely on series elastic actuators (SEA) that enable compliant human-robot interaction. However, currently there is a deficiency of openly available SEA systems to support this development. To address this, we propose a novel design of a compliant 3D-printed SEA device for elbow movement rehabilitation exoskeletons that we make openly available.</p><p><strong>Methods: </strong>We designed a 3D-printed SEA to incorporate a planetary gear system and torsional spring, offering compliance, adaptability, and cost-effectiveness. The design provides a high-power density, that can address torque limitations in 3D printed SEA systems. Our design utilizes a 4.12 Nm motor operating at 26 RPM based on assessment of functional performance differences across healthy and post-stroke individuals. Moreover, the design of this SEA allows for easily adjustable parameters to fit different joints, or various torque output configurations, in low-cost exoskeleton applications in rehabilitation.</p><p><strong>Results: </strong>Testing demonstrated an average compliance contribution of the planetary gear and the average total system compliance of 14.80° and 22.22°, respectively. This range conforms to those expected in human-exoskeleton interaction. Similarly, an FEA analysis of the 3D printed system shows stress ranges of the SEA gears to be between 50 and 60.2 MPa, which causes a displacement of approximately 0.14 mm. This is within the operational flexural range of standard 3D printed materials such as PLA, which is 175 MPa.</p><p><strong>Discussion: </strong>The study demonstrates an openly available SEA design for 3D printed exoskeletons. This work provides an entry point for accessible exoskeleton design, specifically for rehabilitation. Future work will explore the role of segment vs joint rigidity in developing next-generation compliant exoskeletons, and improving accessibility for personalizable assistive exoskeletons. All designs presented herein are publicly available.</p>","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1528266"},"PeriodicalIF":2.9,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11906680/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143650434","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: Human factors and cognitive ergonomics in advanced industrial human-robot interaction.","authors":"Erik Billing, Federico Fraboni, Luca Gualtieri, Patricia Helen Rosen, Peter Thorvald","doi":"10.3389/frobt.2025.1564948","DOIUrl":"https://doi.org/10.3389/frobt.2025.1564948","url":null,"abstract":"","PeriodicalId":47597,"journal":{"name":"Frontiers in Robotics and AI","volume":"12 ","pages":"1564948"},"PeriodicalIF":2.9,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11906329/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143651440","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}