Animals leverage their full embodiment to achieve multimodal, redundant, and subtle communication. To achieve the same for robots, they must similarly exploit their brain-body-environment interactions or their embodied intelligence. To advance this approach, we propose a framework building on Shannon’s information channel theory for communication to provide the key principles and benchmarks for advancing human-robot communication.
{"title":"Embodied intelligence paradigm for human-robot communication","authors":"Nana Obayashi, Arsen Abdulali, Fumiya Iida, Josie Hughes","doi":"10.1126/scirobotics.ads8528","DOIUrl":"10.1126/scirobotics.ads8528","url":null,"abstract":"<div >Animals leverage their full embodiment to achieve multimodal, redundant, and subtle communication. To achieve the same for robots, they must similarly exploit their brain-body-environment interactions or their embodied intelligence. To advance this approach, we propose a framework building on Shannon’s information channel theory for communication to provide the key principles and benchmarks for advancing human-robot communication.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"10 105","pages":""},"PeriodicalIF":27.5,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-08-20DOI: 10.1126/scirobotics.adu6007
Yeji Lee, Vineeth K. Bandari, John S. McCaskill, Pranathi Adluri, Daniil Karnaushenko, Dmitriy D. Karnaushenko, Oliver G. Schmidt
Modular microrobotics can potentially address many information-intensive microtasks in medicine, manufacturing, and the environment. However, surface area has limited the natural powering, communication, functional integration, and self-assembly of smart mass-fabricated modular robotic devices at small scales. We demonstrate the integrated self-folding and self-rolling of functionalized patterned interior and exterior membrane surfaces resulting in programmable, self-assembling, intercommunicating, and self-locomoting micromodules (smartlets ≤ 1 cubic millimeter) with interior chambers for onboard buoyancy control. The microrobotic divers, with 360° solar harvesting rolls, functioned with sufficient ambient power for communication and programmed locomotion in water via electrolysis. The interior folding faces carried rigid microcomponents, including silicon chiplets (Si chiplets) as microprocessors and micro–light-emitting diodes (LEDs) for communication. The exterior faces were able to engage in specific patterned docking interactions between smartlets. The heterogeneous integration is mass producible and affordable through two-dimensional (2D)–automated lithography and microchiplet bump-bonding processes, here shown to be compatible with subsequent autonomous 3D folding and rolling. The robotic modules functioned in natural aqueous environments, and the technology was analyzed as scalable down to microscopic dimensions. Selectively addressed communication with individual smartlets was enhanced via frequency-specific optical signals and enabled precise control, allowing each smartlet to be activated independently within a collective system. The work remodels modular microrobotics closer to the surface-rich modular autonomy of biological cells and provides an economical platform for microscopic applications.
{"title":"Si chiplet–controlled 3D modular microrobots with smart communication in natural aqueous environments","authors":"Yeji Lee, Vineeth K. Bandari, John S. McCaskill, Pranathi Adluri, Daniil Karnaushenko, Dmitriy D. Karnaushenko, Oliver G. Schmidt","doi":"10.1126/scirobotics.adu6007","DOIUrl":"10.1126/scirobotics.adu6007","url":null,"abstract":"<div >Modular microrobotics can potentially address many information-intensive microtasks in medicine, manufacturing, and the environment. However, surface area has limited the natural powering, communication, functional integration, and self-assembly of smart mass-fabricated modular robotic devices at small scales. We demonstrate the integrated self-folding and self-rolling of functionalized patterned interior and exterior membrane surfaces resulting in programmable, self-assembling, intercommunicating, and self-locomoting micromodules (smartlets ≤ 1 cubic millimeter) with interior chambers for onboard buoyancy control. The microrobotic divers, with 360° solar harvesting rolls, functioned with sufficient ambient power for communication and programmed locomotion in water via electrolysis. The interior folding faces carried rigid microcomponents, including silicon chiplets (Si chiplets) as microprocessors and micro–light-emitting diodes (LEDs) for communication. The exterior faces were able to engage in specific patterned docking interactions between smartlets. The heterogeneous integration is mass producible and affordable through two-dimensional (2D)–automated lithography and microchiplet bump-bonding processes, here shown to be compatible with subsequent autonomous 3D folding and rolling. The robotic modules functioned in natural aqueous environments, and the technology was analyzed as scalable down to microscopic dimensions. Selectively addressed communication with individual smartlets was enhanced via frequency-specific optical signals and enabled precise control, allowing each smartlet to be activated independently within a collective system. The work remodels modular microrobotics closer to the surface-rich modular autonomy of biological cells and provides an economical platform for microscopic applications.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"10 105","pages":""},"PeriodicalIF":27.5,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-08-20DOI: 10.1126/scirobotics.ads6790
Jose A. Barreiros, Aykut Özgün Önol, Mengchao Zhang, Sam Creasey, Aimee Goncalves, Andrew Beaulieu, Aditya Bhat, Kate M. Tsui, Alex Alspach
Humans use diverse skills and strategies to effectively manipulate various objects, ranging from dexterous in-hand manipulation (fine motor skills) to complex whole-body manipulation (gross motor skills). The latter involves full-body engagement and extensive contact with various body parts beyond just the hands, where the compliance of our skin and muscles plays a crucial role in increasing contact stability and mitigating uncertainty. For robots, synthesizing these contact-rich behaviors has fundamental challenges because of the rapidly growing combinatorics inherent to this amount of contact, making explicit reasoning about all contact interactions intractable. We explore the use of example-guided reinforcement learning to generate robust whole-body skills for the manipulation of large and unwieldy objects. Our method’s effectiveness is demonstrated on Toyota Research Institute’s Punyo robot, a humanoid upper body with highly deformable, pressure-sensing skin. Training was conducted in simulation with only a single example motion per object manipulation task, and policies were easily transferred to hardware owing to domain randomization and the robot’s compliance. The resulting agent can manipulate various everyday objects, such as a water jug and large boxes, in a similar fashion to the example motion. In addition, we show blind dexterous whole-body manipulation, relying solely on proprioceptive and tactile feedback without object pose tracking. Our analysis highlights the critical role of compliance in facilitating whole-body manipulation with humanoid robots.
{"title":"Learning contact-rich whole-body manipulation with example-guided reinforcement learning","authors":"Jose A. Barreiros, Aykut Özgün Önol, Mengchao Zhang, Sam Creasey, Aimee Goncalves, Andrew Beaulieu, Aditya Bhat, Kate M. Tsui, Alex Alspach","doi":"10.1126/scirobotics.ads6790","DOIUrl":"10.1126/scirobotics.ads6790","url":null,"abstract":"<div >Humans use diverse skills and strategies to effectively manipulate various objects, ranging from dexterous in-hand manipulation (fine motor skills) to complex whole-body manipulation (gross motor skills). The latter involves full-body engagement and extensive contact with various body parts beyond just the hands, where the compliance of our skin and muscles plays a crucial role in increasing contact stability and mitigating uncertainty. For robots, synthesizing these contact-rich behaviors has fundamental challenges because of the rapidly growing combinatorics inherent to this amount of contact, making explicit reasoning about all contact interactions intractable. We explore the use of example-guided reinforcement learning to generate robust whole-body skills for the manipulation of large and unwieldy objects. Our method’s effectiveness is demonstrated on Toyota Research Institute’s Punyo robot, a humanoid upper body with highly deformable, pressure-sensing skin. Training was conducted in simulation with only a single example motion per object manipulation task, and policies were easily transferred to hardware owing to domain randomization and the robot’s compliance. The resulting agent can manipulate various everyday objects, such as a water jug and large boxes, in a similar fashion to the example motion. In addition, we show blind dexterous whole-body manipulation, relying solely on proprioceptive and tactile feedback without object pose tracking. Our analysis highlights the critical role of compliance in facilitating whole-body manipulation with humanoid robots.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"10 105","pages":""},"PeriodicalIF":27.5,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-08-20DOI: 10.1126/scirobotics.ads5033
Jianlan Luo, Charles Xu, Jeffrey Wu, Sergey Levine
Robotic manipulation remains one of the most difficult challenges in robotics, with approaches ranging from classical model-based control to modern imitation learning. Although these methods have enabled substantial progress, they often require extensive manual design, struggle with performance, and demand large-scale data collection. These limitations hinder their real-world deployment at scale, where reliability, speed, and robustness are essential. Reinforcement learning (RL) offers a powerful alternative by enabling robots to autonomously acquire complex manipulation skills through interaction. However, realizing the full potential of RL in the real world remains challenging because of issues of sample efficiency and safety. We present a human-in-the-loop, vision-based RL system that achieved strong performance on a wide range of dexterous manipulation tasks, including precise assembly, dynamic manipulation, and dual-arm coordination. These tasks reflect realistic industrial tolerances, with small but critical variations in initial object placements that demand sophisticated reactive control. Our method integrates demonstrations, human corrections, sample-efficient RL algorithms, and system-level design to directly learn RL policies in the real world. Within 1 to 2.5 hours of real-world training, our approach outperformed other baselines by improving task success by 2×, achieving near-perfect success rates, and executing 1.8× faster on average. Through extensive experiments and analysis, our results suggest that RL can learn a wide range of complex vision-based manipulation policies directly in the real world within practical training times. We hope that this work will inspire a new generation of learned robotic manipulation techniques, benefiting both industrial applications and research advancements.
{"title":"Precise and dexterous robotic manipulation via human-in-the-loop reinforcement learning","authors":"Jianlan Luo, Charles Xu, Jeffrey Wu, Sergey Levine","doi":"10.1126/scirobotics.ads5033","DOIUrl":"10.1126/scirobotics.ads5033","url":null,"abstract":"<div >Robotic manipulation remains one of the most difficult challenges in robotics, with approaches ranging from classical model-based control to modern imitation learning. Although these methods have enabled substantial progress, they often require extensive manual design, struggle with performance, and demand large-scale data collection. These limitations hinder their real-world deployment at scale, where reliability, speed, and robustness are essential. Reinforcement learning (RL) offers a powerful alternative by enabling robots to autonomously acquire complex manipulation skills through interaction. However, realizing the full potential of RL in the real world remains challenging because of issues of sample efficiency and safety. We present a human-in-the-loop, vision-based RL system that achieved strong performance on a wide range of dexterous manipulation tasks, including precise assembly, dynamic manipulation, and dual-arm coordination. These tasks reflect realistic industrial tolerances, with small but critical variations in initial object placements that demand sophisticated reactive control. Our method integrates demonstrations, human corrections, sample-efficient RL algorithms, and system-level design to directly learn RL policies in the real world. Within 1 to 2.5 hours of real-world training, our approach outperformed other baselines by improving task success by 2×, achieving near-perfect success rates, and executing 1.8× faster on average. Through extensive experiments and analysis, our results suggest that RL can learn a wide range of complex vision-based manipulation policies directly in the real world within practical training times. We hope that this work will inspire a new generation of learned robotic manipulation techniques, benefiting both industrial applications and research advancements.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"10 105","pages":""},"PeriodicalIF":27.5,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144881604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-08-13DOI: 10.1126/scirobotics.aea7372
Robin R. Murphy
Science fiction argues for specialized robots, not general-purpose humanoid robots, for unloading of cargo and parcels.
科幻小说主张使用专门的机器人，而不是通用的人形机器人来卸载货物和包裹。
{"title":"Robots in science fiction unload assumptions about freight logistics","authors":"Robin R. Murphy","doi":"10.1126/scirobotics.aea7372","DOIUrl":"10.1126/scirobotics.aea7372","url":null,"abstract":"<div >Science fiction argues for specialized robots, not general-purpose humanoid robots, for unloading of cargo and parcels.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"10 105","pages":""},"PeriodicalIF":27.5,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144833371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-08-13DOI: 10.1126/scirobotics.adt7461
Revanth Konda, Timothy A. Brumfiel, Zachary L. Bercu, Jonathan A. Grossberg, Jaydev P. Desai
Research on robotically steerable guidewires has surged in the past decade because of their potential in addressing difficulties related to endovascular interventions. These microscale devices exhibit unique challenges in design, fabrication, and control, not necessarily present in mesoscale continuum robots such as robotic catheters and endoscopes. Existing literature on surgical robots mainly addresses advancements in robotic surgery with a focus on current trends in specific clinical procedures. Our article aims to bridge this gap by reviewing current clinical practices in endovascular interventions, highlighting the clinical motivations for the development of robotically steerable guidewires, and detailing the current advancements and future prospects in topics related to these devices.
{"title":"Robotically steerable guidewires—Current trends and future directions","authors":"Revanth Konda, Timothy A. Brumfiel, Zachary L. Bercu, Jonathan A. Grossberg, Jaydev P. Desai","doi":"10.1126/scirobotics.adt7461","DOIUrl":"10.1126/scirobotics.adt7461","url":null,"abstract":"<div >Research on robotically steerable guidewires has surged in the past decade because of their potential in addressing difficulties related to endovascular interventions. These microscale devices exhibit unique challenges in design, fabrication, and control, not necessarily present in mesoscale continuum robots such as robotic catheters and endoscopes. Existing literature on surgical robots mainly addresses advancements in robotic surgery with a focus on current trends in specific clinical procedures. Our article aims to bridge this gap by reviewing current clinical practices in endovascular interventions, highlighting the clinical motivations for the development of robotically steerable guidewires, and detailing the current advancements and future prospects in topics related to these devices.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"10 105","pages":""},"PeriodicalIF":27.5,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144833408","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Soft robots, with their compliant bodies, minimal environmental disturbance, and ability to withstand ambient pressures, offer promising solutions for deep-sea exploration. However, a common challenge of stiffening in soft materials impairs their effective actuation in harsh conditions. In this work, we integrated a liquid dielectric plasticizer within an electrohydraulic soft robot, serving dual critical functions as a softening agent to maintain the softness of the polymer shell and an electrohydraulic fluid for efficient actuation. In addition, by using the surrounding seawater as alternating electrodes, we prevented charge retention in dielectric layers, enabling sustained actuation performance. Field tests at depths of ~1360, 3176, and ~4071 meters confirmed the robot’s ability to sense the environment, navigate complex trajectories, and withstand unsteady disturbances. Our work offers a generalized and straightforward framework for developing soft materials tailored for deep-sea applications, paving the way for soft robots to execute real-world missions.
{"title":"Plasticized electrohydraulic robot autopilots in the deep sea","authors":"Guorui Li, Peng Shen, Tuck-Whye Wong, Mingyu Liu, Zhenxiang Sun, Xinyu Liu, Yongzai Chen, Xianghan Wang, Hao Zhang, Bingxu Hu, Deli Chen, Zhihan Zhang, Chao Zhang, Rongchen Wang, Wenhao Zhang, Shuai Nie, Xinyue Zhang, Jie-Wei Wong, Haofei Zhou, Wenbo Li, Hao Wang, Qian Zhang, Shenlong Wang, Zhiwen Yu, Hai Li, Hongyu Zhao, Qingyun Zeng, Shiping Wang, Zhilong Huang, Cong Ye, A-Man Zhang, Tiefeng Li","doi":"10.1126/scirobotics.adt8054","DOIUrl":"10.1126/scirobotics.adt8054","url":null,"abstract":"<div >Soft robots, with their compliant bodies, minimal environmental disturbance, and ability to withstand ambient pressures, offer promising solutions for deep-sea exploration. However, a common challenge of stiffening in soft materials impairs their effective actuation in harsh conditions. In this work, we integrated a liquid dielectric plasticizer within an electrohydraulic soft robot, serving dual critical functions as a softening agent to maintain the softness of the polymer shell and an electrohydraulic fluid for efficient actuation. In addition, by using the surrounding seawater as alternating electrodes, we prevented charge retention in dielectric layers, enabling sustained actuation performance. Field tests at depths of ~1360, 3176, and ~4071 meters confirmed the robot’s ability to sense the environment, navigate complex trajectories, and withstand unsteady disturbances. Our work offers a generalized and straightforward framework for developing soft materials tailored for deep-sea applications, paving the way for soft robots to execute real-world missions.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"10 105","pages":""},"PeriodicalIF":27.5,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144833404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-08-13DOI: 10.1126/scirobotics.adj9699
Raúl Domínguez, Carlos Pérez-del-Pulgar, Gonzalo J. Paz-Delgado, Fabio Polisano, Jonathan Babel, Thierry Germa, Iulia Dragomir, Valérie Ciarletti, Anne-Claire Berthet, Leon Cedric Danter, Frank Kirchner
Exploration of lava caves on the surface of planetary bodies near Earth is of high importance for scientific research and space exploration. The natural shielding that these caves offer against radiation and small meteorites makes them well suited for preserving exobiological signatures and protecting human-made facilities. The use of a robot team arises as the safest and most cost-efficient way to explore extraterrestrial lava caves because they are difficult to access. Although the approach has been demonstrated in similar scenarios on Earth, its adaptation to space conditions needs further research. Here, we define a lava cave exploration mission concept, including four mission phases that are performed by a heterogeneous team of three robots equipped with the required hardware and software. This mission concept was validated in a relevant scenario, a lava cave on Lanzarote island (Spain), where the team of robots was able to build a three-dimensional model of the surrounding area and skylight, introducing a scout rover through rappelling and exploring the inner part of the cave. The results obtained demonstrate the proposed mission concept’s feasibility, including three next-generation planetary exploration rovers that were coordinated to obtain meaningful information about the lava cave’s external and internal morphology.
{"title":"Cooperative robotic exploration of a planetary skylight surface and lava cave","authors":"Raúl Domínguez, Carlos Pérez-del-Pulgar, Gonzalo J. Paz-Delgado, Fabio Polisano, Jonathan Babel, Thierry Germa, Iulia Dragomir, Valérie Ciarletti, Anne-Claire Berthet, Leon Cedric Danter, Frank Kirchner","doi":"10.1126/scirobotics.adj9699","DOIUrl":"10.1126/scirobotics.adj9699","url":null,"abstract":"<div >Exploration of lava caves on the surface of planetary bodies near Earth is of high importance for scientific research and space exploration. The natural shielding that these caves offer against radiation and small meteorites makes them well suited for preserving exobiological signatures and protecting human-made facilities. The use of a robot team arises as the safest and most cost-efficient way to explore extraterrestrial lava caves because they are difficult to access. Although the approach has been demonstrated in similar scenarios on Earth, its adaptation to space conditions needs further research. Here, we define a lava cave exploration mission concept, including four mission phases that are performed by a heterogeneous team of three robots equipped with the required hardware and software. This mission concept was validated in a relevant scenario, a lava cave on Lanzarote island (Spain), where the team of robots was able to build a three-dimensional model of the surrounding area and skylight, introducing a scout rover through rappelling and exploring the inner part of the cave. The results obtained demonstrate the proposed mission concept’s feasibility, including three next-generation planetary exploration rovers that were coordinated to obtain meaningful information about the lava cave’s external and internal morphology.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"10 105","pages":""},"PeriodicalIF":27.5,"publicationDate":"2025-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.science.org/doi/reader/10.1126/scirobotics.adj9699","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144833388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"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}
Pub Date : 2025-07-30DOI: 10.1126/scirobotics.adt7329
Herman van der Kooij, Edwin H. F. van Asseldonk, Massimo Sartori, Chiara Basla, Adrian Esser, Robert Riener
Therapeutic and assistive exoskeletons and exosuits show promise in both clinical and real-world settings. Improving their autonomy can enhance usability, effectiveness, and cost efficiency. This Review presents a generic control framework for autonomous operation of upper and lower limb devices and reviews current advancements and future directions. We highlight how data-driven machine learning aids in intention recognition, synchronization, patient assessment, and task-agnostic control. In addition, we discuss how reinforcement learning optimizes control policies through digital human twins and how generative AI supports therapy planning and patient engagement. Richer patient-specific data and more accurate digital twins are needed for clinical validation and widespread deployment.
{"title":"AI in therapeutic and assistive exoskeletons and exosuits: Influences on performance and autonomy","authors":"Herman van der Kooij, Edwin H. F. van Asseldonk, Massimo Sartori, Chiara Basla, Adrian Esser, Robert Riener","doi":"10.1126/scirobotics.adt7329","DOIUrl":"https://doi.org/10.1126/scirobotics.adt7329","url":null,"abstract":"Therapeutic and assistive exoskeletons and exosuits show promise in both clinical and real-world settings. Improving their autonomy can enhance usability, effectiveness, and cost efficiency. This Review presents a generic control framework for autonomous operation of upper and lower limb devices and reviews current advancements and future directions. We highlight how data-driven machine learning aids in intention recognition, synchronization, patient assessment, and task-agnostic control. In addition, we discuss how reinforcement learning optimizes control policies through digital human twins and how generative AI supports therapy planning and patient engagement. Richer patient-specific data and more accurate digital twins are needed for clinical validation and widespread deployment.","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"20 1","pages":""},"PeriodicalIF":25.0,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144737522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-07-30DOI: 10.1126/scirobotics.adz8279
Pierre E. Dupont, Alperen Degirmenci
Most medical robots depend on human operators for sensing, decision-making, and action during procedures. Future progress depends on enabling robots to take on these capabilities. Although learning-based approaches provide remarkable promise toward achieving this goal, notable challenges must be addressed to unlock these robots’ full potential in clinical settings.
{"title":"The grand challenges of learning medical robot autonomy","authors":"Pierre E. Dupont, Alperen Degirmenci","doi":"10.1126/scirobotics.adz8279","DOIUrl":"https://doi.org/10.1126/scirobotics.adz8279","url":null,"abstract":"Most medical robots depend on human operators for sensing, decision-making, and action during procedures. Future progress depends on enabling robots to take on these capabilities. Although learning-based approaches provide remarkable promise toward achieving this goal, notable challenges must be addressed to unlock these robots’ full potential in clinical settings.","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"7 1","pages":""},"PeriodicalIF":25.0,"publicationDate":"2025-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144737773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号