Pub Date : 2024-07-24DOI: 10.1126/scirobotics.adk9978
Marco Pontin, Dana D. Damian
Resilience is crucial for the self-preservation of biological systems: Humans recover from wounds thanks to an immune system that autonomously enacts a multistage response to promote healing. Similar passive mechanisms can enable pneumatic soft robots to overcome common faults such as bursts originating from punctures or overpressurization. Recent technological advancements, ranging from fault-tolerant controllers for robot reconfigurability to self-healing materials, have paved the way for robot resilience. However, these techniques require powerful processors and large datasets or external hardware. How to extend the operational life span of damaged soft robots with minimal computational and physical resources remains unclear. In this study, we demonstrated a multimodal pneumatic soft valve capable of passive resilient reactions, triggered by faults, to prevent or isolate damage in soft robots. In its forward operation mode, the valve, requiring a single supply pressure, isolated punctured soft inflatable elements from the rest of the soft robot in as fast as 21 milliseconds. In its reverse operation mode, the valve can passively protect robots against overpressurization caused by external disturbances, avoiding plastic deformations and bursts. Furthermore, the two modes combined enabled the creation of an endogenously controlled valve capable of autonomous burst isolation. We demonstrated the passive and quick response and the possibility of monolithic integration of the soft valve in grippers and crawling robots. The approach proposed in this study provides a distributed small-footprint alternative to controller-based resilience and is expected to help soft robots achieve uninterrupted long-lasting operation.
{"title":"Multimodal soft valve enables physical responsiveness for preemptive resilience of soft robots","authors":"Marco Pontin, Dana D. Damian","doi":"10.1126/scirobotics.adk9978","DOIUrl":"10.1126/scirobotics.adk9978","url":null,"abstract":"<div >Resilience is crucial for the self-preservation of biological systems: Humans recover from wounds thanks to an immune system that autonomously enacts a multistage response to promote healing. Similar passive mechanisms can enable pneumatic soft robots to overcome common faults such as bursts originating from punctures or overpressurization. Recent technological advancements, ranging from fault-tolerant controllers for robot reconfigurability to self-healing materials, have paved the way for robot resilience. However, these techniques require powerful processors and large datasets or external hardware. How to extend the operational life span of damaged soft robots with minimal computational and physical resources remains unclear. In this study, we demonstrated a multimodal pneumatic soft valve capable of passive resilient reactions, triggered by faults, to prevent or isolate damage in soft robots. In its forward operation mode, the valve, requiring a single supply pressure, isolated punctured soft inflatable elements from the rest of the soft robot in as fast as 21 milliseconds. In its reverse operation mode, the valve can passively protect robots against overpressurization caused by external disturbances, avoiding plastic deformations and bursts. Furthermore, the two modes combined enabled the creation of an endogenously controlled valve capable of autonomous burst isolation. We demonstrated the passive and quick response and the possibility of monolithic integration of the soft valve in grippers and crawling robots. The approach proposed in this study provides a distributed small-footprint alternative to controller-based resilience and is expected to help soft robots achieve uninterrupted long-lasting operation.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"9 92","pages":""},"PeriodicalIF":26.1,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.science.org/doi/reader/10.1126/scirobotics.adk9978","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141755185","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 : 2024-07-24DOI: 10.1126/scirobotics.adk6664
Fabiola Diana, Lola Cañamero, Ruud Hortensius, Mariska E. Kret
Robotics, using social mechanisms like hormonal modulation, may accelerate our understanding of core sociality principles.
机器人利用激素调节等社会机制，可能会加速我们对社会性核心原理的理解。
{"title":"Merging sociality and robotics through an evolutionary perspective","authors":"Fabiola Diana, Lola Cañamero, Ruud Hortensius, Mariska E. Kret","doi":"10.1126/scirobotics.adk6664","DOIUrl":"10.1126/scirobotics.adk6664","url":null,"abstract":"<div >Robotics, using social mechanisms like hormonal modulation, may accelerate our understanding of core sociality principles.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"9 92","pages":""},"PeriodicalIF":26.1,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141762946","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 : 2024-07-24DOI: 10.1126/scirobotics.adk6717
Jae In Kim, Jaeyoun Choi, Junhyung Kim, Junkyung Song, Jaebum Park, Yong-Lae Park
Lumbar spine injuries resulting from heavy or repetitive lifting remain a prevalent concern in workplaces. Back-support devices have been developed to mitigate these injuries by aiding workers during lifting tasks. However, existing devices often fall short in providing multidimensional force assistance for asymmetric lifting, an essential feature for practical workplace use. In addition, validation of device safety across the entire human spine has been lacking. This paper introduces the Bilateral Back Extensor Exosuit (BBEX), a robotic back-support device designed to address both functionality and safety concerns. The design of the BBEX draws inspiration from the anatomical characteristics of the human spine and back extensor muscles. Using a multi–degree-of-freedom architecture and serially connected linear actuators, the device’s components are strategically arranged to closely mimic the biomechanics of the human spine and back extensor muscles. To establish the efficacy and safety of the BBEX, a series of experiments with human participants was conducted. Eleven healthy male participants engaged in symmetric and asymmetric lifting tasks while wearing the BBEX. The results confirm the ability of the BBEX to provide effective multidimensional force assistance. Moreover, comprehensive safety validation was achieved through analyses of muscle fatigue in the upper and the lower erector spinae muscles, as well as mechanical loading on spinal joints during both lifting scenarios. By seamlessly integrating functionality inspired by human biomechanics with a focus on safety, this study offers a promising solution to address the persistent challenge of preventing lumbar spine injuries in demanding work environments.
{"title":"Bilateral Back Extensor Exosuit for multidimensional assistance and prevention of spinal injuries","authors":"Jae In Kim, Jaeyoun Choi, Junhyung Kim, Junkyung Song, Jaebum Park, Yong-Lae Park","doi":"10.1126/scirobotics.adk6717","DOIUrl":"10.1126/scirobotics.adk6717","url":null,"abstract":"<div >Lumbar spine injuries resulting from heavy or repetitive lifting remain a prevalent concern in workplaces. Back-support devices have been developed to mitigate these injuries by aiding workers during lifting tasks. However, existing devices often fall short in providing multidimensional force assistance for asymmetric lifting, an essential feature for practical workplace use. In addition, validation of device safety across the entire human spine has been lacking. This paper introduces the Bilateral Back Extensor Exosuit (BBEX), a robotic back-support device designed to address both functionality and safety concerns. The design of the BBEX draws inspiration from the anatomical characteristics of the human spine and back extensor muscles. Using a multi–degree-of-freedom architecture and serially connected linear actuators, the device’s components are strategically arranged to closely mimic the biomechanics of the human spine and back extensor muscles. To establish the efficacy and safety of the BBEX, a series of experiments with human participants was conducted. Eleven healthy male participants engaged in symmetric and asymmetric lifting tasks while wearing the BBEX. The results confirm the ability of the BBEX to provide effective multidimensional force assistance. Moreover, comprehensive safety validation was achieved through analyses of muscle fatigue in the upper and the lower erector spinae muscles, as well as mechanical loading on spinal joints during both lifting scenarios. By seamlessly integrating functionality inspired by human biomechanics with a focus on safety, this study offers a promising solution to address the persistent challenge of preventing lumbar spine injuries in demanding work environments.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"9 92","pages":""},"PeriodicalIF":26.1,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141755186","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 : 2024-07-17DOI: 10.1126/scirobotics.adk4533
Terry Ching, Joseph Zhi Wei Lee, Shane Kyi Hla Win, Luke Soe Thura Win, Danial Sufiyan, Charlotte Pei Xuan Lim, Nidhi Nagaraju, Yi-Chin Toh, Shaohui Foong, Michinao Hashimoto
This paper introduces an approach to fabricating lightweight, untethered soft robots capable of diverse biomimetic locomotion. Untethering soft robotics from electrical or pneumatic power remains one of the prominent challenges within the field. The development of functional untethered soft robotic systems hinges heavily on mitigating their weight; however, the conventional weight of pneumatic network actuators (pneu-nets) in soft robots has hindered untethered operations. To address this challenge, we developed film-balloon (FiBa) modules that drastically reduced the weight of soft actuators. FiBa modules combine transversely curved polymer thin films and three-dimensionally printed pneumatic balloons to achieve varied locomotion modes. These lightweight FiBa modules serve as building blocks to create untethered soft robots mimicking natural movement strategies. These modules substantially reduce overall robot weight, allowing the integration of components such as pumps, valves, batteries, and control boards, thereby enabling untethered operation. FiBa modules integrated with electronic components demonstrated four bioinspired modes of locomotion, including turtle-inspired crawling, inchworm-inspired climbing, bat-inspired perching, and ladybug-inspired flying. Overall, our study offers an alternative tool for designing and customizing lightweight, untethered soft robots with advanced functionalities. The reduction of the weight of soft robots enabled by our approach opens doors to a wide range of applications, including disaster relief, space exploration, remote sensing, and search and rescue operations, where lightweight, untethered soft robotic systems are essential.
本文介绍了一种制造轻型无系软体机器人的方法，这种机器人能够进行各种仿生物运动。将软体机器人从电力或气动动力中解脱出来仍然是该领域面临的突出挑战之一。开发功能性无系链软体机器人系统在很大程度上取决于减轻其重量；然而，软体机器人中气动网络致动器（气动网）的传统重量阻碍了无系链操作。为了应对这一挑战，我们开发了薄膜气球（FiBa）模块，大大减轻了软致动器的重量。FiBa 模块将横向弯曲的聚合物薄膜和三维打印的气动气球结合在一起，实现了各种运动模式。这些轻质的 FiBa 模块可作为模仿自然运动策略的无系软体机器人的构建模块。这些模块大大减轻了机器人的整体重量，可集成泵、阀门、电池和控制板等组件，从而实现无系绳操作。集成了电子元件的 FiBa 模块展示了四种生物启发运动模式，包括乌龟启发的爬行、尺蠖启发的攀爬、蝙蝠启发的栖息和瓢虫启发的飞行。总之，我们的研究为设计和定制具有高级功能的轻型无系软体机器人提供了另一种工具。我们的方法减轻了软体机器人的重量，为包括救灾、太空探索、遥感和搜救行动在内的广泛应用打开了大门，在这些应用中，轻型、无系绳软体机器人系统是必不可少的。
{"title":"Crawling, climbing, perching, and flying by FiBa soft robots","authors":"Terry Ching, Joseph Zhi Wei Lee, Shane Kyi Hla Win, Luke Soe Thura Win, Danial Sufiyan, Charlotte Pei Xuan Lim, Nidhi Nagaraju, Yi-Chin Toh, Shaohui Foong, Michinao Hashimoto","doi":"10.1126/scirobotics.adk4533","DOIUrl":"10.1126/scirobotics.adk4533","url":null,"abstract":"<div >This paper introduces an approach to fabricating lightweight, untethered soft robots capable of diverse biomimetic locomotion. Untethering soft robotics from electrical or pneumatic power remains one of the prominent challenges within the field. The development of functional untethered soft robotic systems hinges heavily on mitigating their weight; however, the conventional weight of pneumatic network actuators (pneu-nets) in soft robots has hindered untethered operations. To address this challenge, we developed film-balloon (FiBa) modules that drastically reduced the weight of soft actuators. FiBa modules combine transversely curved polymer thin films and three-dimensionally printed pneumatic balloons to achieve varied locomotion modes. These lightweight FiBa modules serve as building blocks to create untethered soft robots mimicking natural movement strategies. These modules substantially reduce overall robot weight, allowing the integration of components such as pumps, valves, batteries, and control boards, thereby enabling untethered operation. FiBa modules integrated with electronic components demonstrated four bioinspired modes of locomotion, including turtle-inspired crawling, inchworm-inspired climbing, bat-inspired perching, and ladybug-inspired flying. Overall, our study offers an alternative tool for designing and customizing lightweight, untethered soft robots with advanced functionalities. The reduction of the weight of soft robots enabled by our approach opens doors to a wide range of applications, including disaster relief, space exploration, remote sensing, and search and rescue operations, where lightweight, untethered soft robotic systems are essential.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"9 92","pages":""},"PeriodicalIF":26.1,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141636005","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 : 2024-07-17DOI: 10.1126/scirobotics.adk0310
Tom van Dijk, Christophe De Wagter, Guido C. H. E. de Croon
Navigation is an essential capability for autonomous robots. In particular, visual navigation has been a major research topic in robotics because cameras are lightweight, power-efficient sensors that provide rich information on the environment. However, the main challenge of visual navigation is that it requires substantial computational power and memory for visual processing and storage of the results. As of yet, this has precluded its use on small, extremely resource-constrained robots such as lightweight drones. Inspired by the parsimony of natural intelligence, we propose an insect-inspired approach toward visual navigation that is specifically aimed at extremely resource-restricted robots. It is a route-following approach in which a robot’s outbound trajectory is stored as a collection of highly compressed panoramic images together with their spatial relationships as measured with odometry. During the inbound journey, the robot uses a combination of odometry and visual homing to return to the stored locations, with visual homing preventing the buildup of odometric drift. A main advancement of the proposed strategy is that the number of stored compressed images is minimized by spacing them apart as far as the accuracy of odometry allows. To demonstrate the suitability for small systems, we implemented the strategy on a tiny 56-gram drone. The drone could successfully follow routes up to 100 meters with a trajectory representation that consumed less than 20 bytes per meter. The presented method forms a substantial step toward the autonomous visual navigation of tiny robots, facilitating their more widespread application.
{"title":"Visual route following for tiny autonomous robots","authors":"Tom van Dijk, Christophe De Wagter, Guido C. H. E. de Croon","doi":"10.1126/scirobotics.adk0310","DOIUrl":"10.1126/scirobotics.adk0310","url":null,"abstract":"<div >Navigation is an essential capability for autonomous robots. In particular, visual navigation has been a major research topic in robotics because cameras are lightweight, power-efficient sensors that provide rich information on the environment. However, the main challenge of visual navigation is that it requires substantial computational power and memory for visual processing and storage of the results. As of yet, this has precluded its use on small, extremely resource-constrained robots such as lightweight drones. Inspired by the parsimony of natural intelligence, we propose an insect-inspired approach toward visual navigation that is specifically aimed at extremely resource-restricted robots. It is a route-following approach in which a robot’s outbound trajectory is stored as a collection of highly compressed panoramic images together with their spatial relationships as measured with odometry. During the inbound journey, the robot uses a combination of odometry and visual homing to return to the stored locations, with visual homing preventing the buildup of odometric drift. A main advancement of the proposed strategy is that the number of stored compressed images is minimized by spacing them apart as far as the accuracy of odometry allows. To demonstrate the suitability for small systems, we implemented the strategy on a tiny 56-gram drone. The drone could successfully follow routes up to 100 meters with a trajectory representation that consumed less than 20 bytes per meter. The presented method forms a substantial step toward the autonomous visual navigation of tiny robots, facilitating their more widespread application.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"9 92","pages":""},"PeriodicalIF":26.1,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.science.org/doi/reader/10.1126/scirobotics.adk0310","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141636007","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 : 2024-07-17DOI: 10.1126/scirobotics.adl0307
Tianyu Chen, Xudong Yang, Bojian Zhang, Junwei Li, Jie Pan, Yifan Wang
Biological organisms often have remarkable multifunctionality through intricate structures, such as concurrent shape morphing and stiffness variation in the octopus. Soft robots, which are inspired by natural creatures, usually require the integration of separate modules to achieve these various functions. As a result, the whole structure is cumbersome, and the control system is complex, often involving multiple control loops to finish a required task. Here, inspired by the scales that cover creatures like pangolins and fish, we developed a robotic structure that can vary its stiffness and change shape simultaneously in a highly integrated, compact body. The scale-inspired layered structure (SAILS) was enabled by the inversely designed programmable surface patterns of the scales. After fabrication, SAILS was inherently soft and flexible. When sealed in an elastic envelope and subjected to negative confining pressure, it transitioned to its designated shape and concurrently became stiff. SAILS could be actuated at frequencies as high as 5 hertz and achieved an apparent bending modulus change of up to 53 times between its soft and stiff states. We further demonstrated both the versatility of SAILS by developing a soft robot that is amphibious and adaptive and tunable landing systems for drones with the capacity to accommodate different loads.
{"title":"Scale-inspired programmable robotic structures with concurrent shape morphing and stiffness variation","authors":"Tianyu Chen, Xudong Yang, Bojian Zhang, Junwei Li, Jie Pan, Yifan Wang","doi":"10.1126/scirobotics.adl0307","DOIUrl":"10.1126/scirobotics.adl0307","url":null,"abstract":"<div >Biological organisms often have remarkable multifunctionality through intricate structures, such as concurrent shape morphing and stiffness variation in the octopus. Soft robots, which are inspired by natural creatures, usually require the integration of separate modules to achieve these various functions. As a result, the whole structure is cumbersome, and the control system is complex, often involving multiple control loops to finish a required task. Here, inspired by the scales that cover creatures like pangolins and fish, we developed a robotic structure that can vary its stiffness and change shape simultaneously in a highly integrated, compact body. The scale-inspired layered structure (SAILS) was enabled by the inversely designed programmable surface patterns of the scales. After fabrication, SAILS was inherently soft and flexible. When sealed in an elastic envelope and subjected to negative confining pressure, it transitioned to its designated shape and concurrently became stiff. SAILS could be actuated at frequencies as high as 5 hertz and achieved an apparent bending modulus change of up to 53 times between its soft and stiff states. We further demonstrated both the versatility of SAILS by developing a soft robot that is amphibious and adaptive and tunable landing systems for drones with the capacity to accommodate different loads.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"9 92","pages":""},"PeriodicalIF":26.1,"publicationDate":"2024-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141636006","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 : 2024-06-26DOI: 10.1126/scirobotics.adj3665
Uma Prashant Navare, Francesca Ciardo, Kyveli Kompatsiari, Davide De Tommaso, Agnieszka Wykowska
Sense of joint agency (SoJA) is the sense of control experienced by humans when acting with others to bring about changes in the shared environment. SoJA is proposed to arise from the sensorimotor predictive processes underlying action control and monitoring. Because SoJA is a ubiquitous phenomenon occurring when we perform actions with other humans, it is of great interest and importance to understand whether—and under what conditions—SoJA occurs in collaborative tasks with humanoid robots. In this study, using behavioral measures and neural responses measured by electroencephalography (EEG), we aimed to evaluate whether SoJA occurs in joint action with the humanoid robot iCub and whether its emergence is influenced by the perceived intentionality of the robot. Behavioral results show that participants experienced SoJA with the robot partner when it was presented as an intentional agent but not when it was presented as a mechanical artifact. EEG results show that the mechanism that influences the emergence of SoJA in the condition when the robot is presented as an intentional agent is the ability to form similarly accurate predictions about the sensory consequences of our own and others’ actions, leading to similar modulatory activity over sensory processing. Together, our results shed light on the joint sensorimotor processing mechanisms underlying the emergence of SoJA in human-robot interaction and underscore the importance of attribution of intentionality to the robot in human-robot collaboration.
联合代理感（SoJA）是指人类在与他人共同行动以改变共同环境时所体验到的控制感。SoJA 的产生源于作为行动控制和监测基础的感觉运动预测过程。由于 SoJA 是我们与其他人一起行动时普遍存在的现象，因此了解在与仿人机器人协作任务中是否会出现 SoJA 以及在什么条件下会出现 SoJA 是非常有意义和重要的。在这项研究中，我们利用行为测量和脑电图（EEG）测量神经反应，旨在评估在与仿人机器人 iCub 共同行动时是否会出现 SoJA，以及 SoJA 的出现是否会受到机器人感知到的意向性的影响。行为结果表明，当机器人伙伴作为一个有意图的代理出现时，参与者会体验到 SoJA，而当机器人伙伴作为一个机械人工制品出现时，参与者则不会体验到 SoJA。脑电图结果表明，在机器人作为有意行为主体出现的情况下，影响 SoJA 出现的机制是，人们能够对自己和他人行为的感官后果形成类似的准确预测，从而对感官处理产生类似的调节活动。总之，我们的研究结果揭示了人机交互中出现 SoJA 所依据的联合感觉运动处理机制，并强调了在人机协作中将意向性归因于机器人的重要性。
{"title":"When performing actions with robots, attribution of intentionality affects the sense of joint agency","authors":"Uma Prashant Navare, Francesca Ciardo, Kyveli Kompatsiari, Davide De Tommaso, Agnieszka Wykowska","doi":"10.1126/scirobotics.adj3665","DOIUrl":"10.1126/scirobotics.adj3665","url":null,"abstract":"<div >Sense of joint agency (SoJA) is the sense of control experienced by humans when acting with others to bring about changes in the shared environment. SoJA is proposed to arise from the sensorimotor predictive processes underlying action control and monitoring. Because SoJA is a ubiquitous phenomenon occurring when we perform actions with other humans, it is of great interest and importance to understand whether—and under what conditions—SoJA occurs in collaborative tasks with humanoid robots. In this study, using behavioral measures and neural responses measured by electroencephalography (EEG), we aimed to evaluate whether SoJA occurs in joint action with the humanoid robot iCub and whether its emergence is influenced by the perceived intentionality of the robot. Behavioral results show that participants experienced SoJA with the robot partner when it was presented as an intentional agent but not when it was presented as a mechanical artifact. EEG results show that the mechanism that influences the emergence of SoJA in the condition when the robot is presented as an intentional agent is the ability to form similarly accurate predictions about the sensory consequences of our own and others’ actions, leading to similar modulatory activity over sensory processing. Together, our results shed light on the joint sensorimotor processing mechanisms underlying the emergence of SoJA in human-robot interaction and underscore the importance of attribution of intentionality to the robot in human-robot collaboration.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"9 91","pages":""},"PeriodicalIF":26.1,"publicationDate":"2024-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141460910","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 : 2024-06-26DOI: 10.1126/scirobotics.adq6361
Robin R. Murphy
Project Hail Mary reflects real-world technical readiness assessment processes for robotics.
万福玛丽项目反映了现实世界中的机器人技术就绪评估过程。
{"title":"Would you risk humanity’s survival on a robot built in two years?","authors":"Robin R. Murphy","doi":"10.1126/scirobotics.adq6361","DOIUrl":"10.1126/scirobotics.adq6361","url":null,"abstract":"<div ><i>Project Hail Mary</i> reflects real-world technical readiness assessment processes for robotics.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"9 91","pages":""},"PeriodicalIF":26.1,"publicationDate":"2024-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141460911","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 : 2024-06-26DOI: 10.1126/scirobotics.adi8808
Maria Bauza, Antonia Bronars, Yifan Hou, Ian Taylor, Nikhil Chavan-Dafle, Alberto Rodriguez
Existing robotic systems have a tension between generality and precision. Deployed solutions for robotic manipulation tend to fall into the paradigm of one robot solving a single task, lacking “precise generalization,” or the ability to solve many tasks without compromising on precision. This paper explores solutions for precise and general pick and place. In precise pick and place, or kitting, the robot transforms an unstructured arrangement of objects into an organized arrangement, which can facilitate further manipulation. We propose SimPLE (Simulation to Pick Localize and placE) as a solution to precise pick and place. SimPLE learns to pick, regrasp, and place objects given the object’s computer-aided design model and no prior experience. We developed three main components: task-aware grasping, visuotactile perception, and regrasp planning. Task-aware grasping computes affordances of grasps that are stable, observable, and favorable to placing. The visuotactile perception model relies on matching real observations against a set of simulated ones through supervised learning to estimate a distribution of likely object poses. Last, we computed a multistep pick-and-place plan by solving a shortest-path problem on a graph of hand-to-hand regrasps. On a dual-arm robot equipped with visuotactile sensing, SimPLE demonstrated pick and place of 15 diverse objects. The objects spanned a wide range of shapes, and SimPLE achieved successful placements into structured arrangements with 1-mm clearance more than 90% of the time for six objects and more than 80% of the time for 11 objects.
{"title":"SimPLE, a visuotactile method learned in simulation to precisely pick, localize, regrasp, and place objects","authors":"Maria Bauza, Antonia Bronars, Yifan Hou, Ian Taylor, Nikhil Chavan-Dafle, Alberto Rodriguez","doi":"10.1126/scirobotics.adi8808","DOIUrl":"10.1126/scirobotics.adi8808","url":null,"abstract":"<div >Existing robotic systems have a tension between generality and precision. Deployed solutions for robotic manipulation tend to fall into the paradigm of one robot solving a single task, lacking “precise generalization,” or the ability to solve many tasks without compromising on precision. This paper explores solutions for precise and general pick and place. In precise pick and place, or kitting, the robot transforms an unstructured arrangement of objects into an organized arrangement, which can facilitate further manipulation. We propose SimPLE (Simulation to Pick Localize and placE) as a solution to precise pick and place. SimPLE learns to pick, regrasp, and place objects given the object’s computer-aided design model and no prior experience. We developed three main components: task-aware grasping, visuotactile perception, and regrasp planning. Task-aware grasping computes affordances of grasps that are stable, observable, and favorable to placing. The visuotactile perception model relies on matching real observations against a set of simulated ones through supervised learning to estimate a distribution of likely object poses. Last, we computed a multistep pick-and-place plan by solving a shortest-path problem on a graph of hand-to-hand regrasps. On a dual-arm robot equipped with visuotactile sensing, SimPLE demonstrated pick and place of 15 diverse objects. The objects spanned a wide range of shapes, and SimPLE achieved successful placements into structured arrangements with 1-mm clearance more than 90% of the time for six objects and more than 80% of the time for 11 objects.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"9 91","pages":""},"PeriodicalIF":26.1,"publicationDate":"2024-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141460908","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