Science RoboticsPub Date : 2025-05-28DOI: 10.1126/scirobotics.ads6192
Hyeongjun Kim, Hyunsik Oh, Jeongsoo Park, Yunho Kim, Donghoon Youm, Moonkyu Jung, Minho Lee, Jemin Hwangbo
{"title":"High-speed control and navigation for quadrupedal robots on complex and discrete terrain","authors":"Hyeongjun Kim, Hyunsik Oh, Jeongsoo Park, Yunho Kim, Donghoon Youm, Moonkyu Jung, Minho Lee, Jemin Hwangbo","doi":"10.1126/scirobotics.ads6192","DOIUrl":"https://doi.org/10.1126/scirobotics.ads6192","url":null,"abstract":"High-speed legged navigation in discrete and geometrically complex environments is a challenging task because of the high–degree-of-freedom dynamics and long-horizon, nonconvex nature of the optimization problem. In this work, we propose a hierarchical navigation pipeline for legged robots that can traverse such environments at high speed. The proposed pipeline consists of a planner and tracker module. The planner module finds physically feasible foothold plans by sampling-based optimization with fast sequential filtering using heuristics and a neural network. Subsequently, rollouts are performed in a physics simulation to identify the best foothold plan regarding the engineered cost function and to confirm its physical consistency. This hierarchical planning module is computationally efficient and physically accurate at the same time. The tracker aims to accurately step on the target footholds from the planning module. During the training stage, the foothold target distribution is given by a generative model that is trained competitively with the tracker. This process ensures that the tracker is trained in an environment with the desired difficulty. The resulting tracker can overcome terrains that are more difficult than what the previous methods could manage. We demonstrated our approach using Raibo, our in-house dynamic quadruped robot. The results were dynamic and agile motions: Raibo is capable of running on vertical walls, jumping a 1.3-meter gap, running over stepping stones at 4 meters per second, and autonomously navigating on terrains full of 30° ramps, stairs, and boxes of various sizes.","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"138 1","pages":""},"PeriodicalIF":25.0,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144165427","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}
Science RoboticsPub Date : 2025-05-28DOI: 10.1126/scirobotics.ads1292
Chi Chen, Pengju Shi, Zixiao Liu, Sidi Duan, Muqing Si, Chuanwei Zhang, Yingjie Du, Yichen Yan, Timothy J. White, Rebecca Kramer-Bottiglio, Metin Sitti, Tetsuya Iwasaki, Ximin He
{"title":"Advancing physical intelligence for autonomous soft robots","authors":"Chi Chen, Pengju Shi, Zixiao Liu, Sidi Duan, Muqing Si, Chuanwei Zhang, Yingjie Du, Yichen Yan, Timothy J. White, Rebecca Kramer-Bottiglio, Metin Sitti, Tetsuya Iwasaki, Ximin He","doi":"10.1126/scirobotics.ads1292","DOIUrl":"https://doi.org/10.1126/scirobotics.ads1292","url":null,"abstract":"Achieving lifelike autonomy remains a long-term aspiration, yet soft robots so far have mostly demonstrated rudimentary physical intelligence that relies on manipulation of external stimuli to generate continuous motion. To realize autonomous physical intelligence (API) capable of self-regulated sensing, decision-making, and actuation, a promising approach is creating nonlinear time-lag feedback embedded within materials, where a constant stimulus elicits delayed responses to enable autonomous motion. This Review explores such feedback mechanisms, traces the evolution of physically intelligent robots, outlines strategies for embedding API in soft robots under diverse environments, and further discusses challenges and future directions beyond simple locomotion.","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"58 1","pages":""},"PeriodicalIF":25.0,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144165426","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}
Science RoboticsPub Date : 2025-05-28DOI: 10.1126/scirobotics.adu3922
Yuntao Ma, Andrei Cramariuc, Farbod Farshidian, Marco Hutter
{"title":"Learning coordinated badminton skills for legged manipulators","authors":"Yuntao Ma, Andrei Cramariuc, Farbod Farshidian, Marco Hutter","doi":"10.1126/scirobotics.adu3922","DOIUrl":"https://doi.org/10.1126/scirobotics.adu3922","url":null,"abstract":"Coordinating the motion between lower and upper limbs and aligning limb control with perception are substantial challenges in robotics, particularly in dynamic environments. To this end, we introduce an approach for enabling legged mobile manipulators to play badminton, a task that requires precise coordination of perception, locomotion, and arm swinging. We propose a unified reinforcement learning–based control policy for whole-body visuomotor skills involving all degrees of freedom to achieve effective shuttlecock tracking and striking. This policy is informed by a perception noise model that uses real-world camera data, allowing for consistent perception error levels between simulation and deployment and encouraging learned active perception behaviors. Our method includes a shuttlecock prediction model and constrained reinforcement learning for robust motion control to enhance deployment readiness. Extensive experimental results in a variety of environments validate the robot’s capability to predict shuttlecock trajectories, navigate the service area effectively, and execute precise strikes against human players, demonstrating the feasibility of using legged mobile manipulators in complex and dynamic sports scenarios.","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"5 1","pages":""},"PeriodicalIF":25.0,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144165425","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}
Science RoboticsPub Date : 2025-05-21DOI: 10.1126/scirobotics.ads0200
Emanuele Aucone,Stefano Mintchev
{"title":"Embodied aerial physical interaction: Combining body and brain for robust interaction with unstructured environments.","authors":"Emanuele Aucone,Stefano Mintchev","doi":"10.1126/scirobotics.ads0200","DOIUrl":"https://doi.org/10.1126/scirobotics.ads0200","url":null,"abstract":"Using body morphology and touch sensing to simplify control strategies can boost versatility in aerial physical interaction.","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"17 1","pages":"eads0200"},"PeriodicalIF":25.0,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144114132","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}
Science RoboticsPub Date : 2025-05-21DOI: 10.1126/scirobotics.adi5582
J. J. Bowkett, S. A. Chien, Y. Marchetti, J. Nash, D. P. Moreno, C. F. Basich, M. L. Gildner, D. I. Kim, J. A. Russino, D. Wang, J. P. de la Croix, G. Lim, C. T. Wagner, L. R. Shiraishi, P. Y. Twu, N. Z. Georgiev, B. J. Emanuel, M. E. Cameron, Y. Iwashita, K. P. Hand, C. B. Phillips, S. P. Tepsuporn, C. R. Mauceri, G. H. Tan-Wang, G. E. Reeves, P. G. Backes
{"title":"Autonomous surface sampling for the Europa Lander mission concept","authors":"J. J. Bowkett, S. A. Chien, Y. Marchetti, J. Nash, D. P. Moreno, C. F. Basich, M. L. Gildner, D. I. Kim, J. A. Russino, D. Wang, J. P. de la Croix, G. Lim, C. T. Wagner, L. R. Shiraishi, P. Y. Twu, N. Z. Georgiev, B. J. Emanuel, M. E. Cameron, Y. Iwashita, K. P. Hand, C. B. Phillips, S. P. Tepsuporn, C. R. Mauceri, G. H. Tan-Wang, G. E. Reeves, P. G. Backes","doi":"10.1126/scirobotics.adi5582","DOIUrl":"10.1126/scirobotics.adi5582","url":null,"abstract":"<div >Europa, a moon of Jupiter, is a high-priority target for space exploration because of its potential to harbor life. A landed mission concept to collect and analyze samples for signs of life was developed over the past decade. Operationally, a critical challenge for such a mission is that the surface environment at the spatial scale of the lander is not well known, requiring that such a mission be capable of acquiring samples in a wide range of surface conditions. Furthermore, the 85.2-hour orbit of Europa around Jupiter limits direct-to-Earth communications to half the orbital period. Last, power constraints and charged-particle irradiation could limit the lifetime of such a mission to several months. This article describes an effort to develop sampling hardware and autonomous software to enable such a Europa surface mission. This multiyear effort leveraged development across multiple simulation and test-bed venues, culminating in a field campaign on the Matanuska Glacier, Alaska, USA, where a cross-disciplinary team demonstrated autonomous end-to-end sampling activities with representative lander hardware.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"10 102","pages":""},"PeriodicalIF":26.1,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144104368","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}
Science RoboticsPub Date : 2025-05-21DOI: 10.1126/scirobotics.adw7660
Edoardo Milana,Cosimo Della Santina,Benjamin Gorissen,Philipp Rothemund
{"title":"Physical control: A new avenue to achieve intelligence in soft robotics.","authors":"Edoardo Milana,Cosimo Della Santina,Benjamin Gorissen,Philipp Rothemund","doi":"10.1126/scirobotics.adw7660","DOIUrl":"https://doi.org/10.1126/scirobotics.adw7660","url":null,"abstract":"Physical control embodies motion intelligence in soft robots via self-regulating oscillations, sequences, and reactions.","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"130 1","pages":"eadw7660"},"PeriodicalIF":25.0,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144114133","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}
Science RoboticsPub Date : 2025-05-21DOI: 10.1126/scirobotics.ady5090
Robin R. Murphy
{"title":"The robots in the Val Kilmer movie Red Planet predated Perseverance and Ingenuity","authors":"Robin R. Murphy","doi":"10.1126/scirobotics.ady5090","DOIUrl":"10.1126/scirobotics.ady5090","url":null,"abstract":"<div >A big-budget flop about terraforming Mars had a ground-aerial robot team predating Perseverance and Ingenuity.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"10 102","pages":""},"PeriodicalIF":26.1,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144109014","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}
{"title":"Embodied manipulation with past and future morphologies through an open parametric hand design","authors":"Kieran Gilday, Chapa Sirithunge, Fumiya Iida, Josie Hughes","doi":"10.1126/scirobotics.ads6437","DOIUrl":"https://doi.org/10.1126/scirobotics.ads6437","url":null,"abstract":"A human-shaped robotic hand offers unparalleled versatility and fine motor skills, enabling it to perform a broad spectrum of tasks with precision, power, and robustness. Across the paleontological record and animal kingdom, we see a wide range of alternative hand and actuation designs. Understanding the morphological design space and the resulting emergent behaviors can not only aid our understanding of dexterous manipulation and its evolution but also assist with design optimization, achieving and ultimately surpassing human capabilities. Exploration of hand embodiment has, to date, been limited by challenges of accessibility in customizable hands in the real world and by the reality gap in simulation of complex interactions. We introduce an open parametric design that integrates techniques for simplified customization, fabrication, and control with design features to maximize behavioral diversity. Nonlinear rolling joints, anatomical tendon routing, and a low–degree-of-freedom modulating actuation system enable rapid production of single-piece 3D-printable hands without compromising dexterous behaviors. To demonstrate this, we evaluated the low-level behavior range and stability of the design, showing variable stiffness over two orders of magnitude. In addition, we fabricated three hand designs: human, mirrored human with two thumbs, and aye-aye hands. Manipulation tests evaluated the variation in each hand’s proficiency at handling diverse objects and demonstrated emergent behaviors unique to each design. Overall, we introduce diverse designs for robotic hands, provide a design space to compare and contrast different hand morphologies and structural configurations, and share a practical and open-source design for investigating embodied manipulation.","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"1 1","pages":""},"PeriodicalIF":25.0,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143979629","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}
Science RoboticsPub Date : 2025-05-14DOI: 10.1126/scirobotics.ady7192
Melisa Yashinski
{"title":"Neuroprosthesis converts brain activity to speech","authors":"Melisa Yashinski","doi":"10.1126/scirobotics.ady7192","DOIUrl":"10.1126/scirobotics.ady7192","url":null,"abstract":"<div >A neuroprosthesis decodes short bits of neural activity and synthesizes speech synchronously with a user’s vocal intent.</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"10 102","pages":""},"PeriodicalIF":26.1,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143950617","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}
Science RoboticsPub Date : 2025-05-14DOI: 10.1126/scirobotics.adr4264
Tianqi Yue, Chenghua Lu, Kailuan Tang, Qiukai Qi, Zhenyu Lu, Loong Yi Lee, Hermes Bloomfield-Gadȇlha, Jonathan Rossiter
{"title":"Embodying soft robots with octopus-inspired hierarchical suction intelligence","authors":"Tianqi Yue, Chenghua Lu, Kailuan Tang, Qiukai Qi, Zhenyu Lu, Loong Yi Lee, Hermes Bloomfield-Gadȇlha, Jonathan Rossiter","doi":"10.1126/scirobotics.adr4264","DOIUrl":"https://doi.org/10.1126/scirobotics.adr4264","url":null,"abstract":"Octopuses exploit an efficient neuromuscular hierarchy to achieve complex dexterous body manipulation, integrating sensor-rich suckers, in-arm embodied computation, and centralized higher-level reasoning. Here, we take inspiration from the hierarchical intelligence of the octopus and demonstrate how, by exploiting the fluidic energy and information capacity of simple suction cups, soft computational elements, and soft actuators, we can mimic key aspects of the neuromuscular structure of the octopus in soft robotic systems. The presented suction intelligence works at two levels: By coupling suction flow with local fluidic circuitry, soft robots can achieve octopus-like low-level embodied intelligence, including gently grasping delicate objects, adaptive curling, and encapsulating objects of unknown geometries, and by decoding the pressure response from a suction cup, robots can achieve multimodal high-level perception, including contact detection, classification of an environmental medium and surface roughness, and prediction of an interactive pulling force. As in octopuses, suction intelligence executes most of its computation within lower-level local fluidic circuitries, and minimum information is transmitted to the high-level decision-making of the “brain.” This development provides insights into octopus-inspired machine intelligence through low-cost, simple, and easy-to-integrate methods. The presented suction intelligence can be readily integrated into fluidic-driven soft robots to enhance their intelligence and reduce their computational requirement and can be applied widely, from industrial object handling and robotic manufacturing to robot-assisted harvesting and interventional health care.","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"55 1","pages":""},"PeriodicalIF":25.0,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143979613","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}