Science Robotics最新文献

High-speed control and navigation for quadrupedal robots on complex and discrete terrain 复杂离散地形下四足机器人的高速控制与导航

IF 25 1区计算机科学

Science Robotics Pub Date : 2025-05-28 DOI: 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}

引用次数: 0

Advancing physical intelligence for autonomous soft robots 推进自主软体机器人的物理智能

IF 25 1区计算机科学

Science Robotics Pub Date : 2025-05-28 DOI: 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

引用次数: 0

Learning coordinated badminton skills for legged manipulators 学习腿式操纵器的羽毛球协调技巧

IF 25 1区计算机科学

Science Robotics Pub Date : 2025-05-28 DOI: 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}

引用次数: 0

Embodied aerial physical interaction: Combining body and brain for robust interaction with unstructured environments. 具体化的空中物理互动：结合身体和大脑与非结构化环境的强大互动。

IF 25 1区计算机科学

Science Robotics Pub Date : 2025-05-21 DOI: 10.1126/scirobotics.ads0200

Emanuele Aucone,Stefano Mintchev

引用次数: 0

Autonomous surface sampling for the Europa Lander mission concept 欧罗巴着陆器任务概念的自主表面采样

IF 26.1 1区计算机科学

Science Robotics Pub Date : 2025-05-21 DOI: 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}

引用次数: 0

Physical control: A new avenue to achieve intelligence in soft robotics. 物理控制：软机器人实现智能的新途径。

IF 25 1区计算机科学

Science Robotics Pub Date : 2025-05-21 DOI: 10.1126/scirobotics.adw7660

Edoardo Milana,Cosimo Della Santina,Benjamin Gorissen,Philipp Rothemund

引用次数: 0

The robots in the Val Kilmer movie Red Planet predated Perseverance and Ingenuity 瓦尔·基尔默（Val Kilmer）的电影《红色星球》（Red Planet）中的机器人早于《毅力》和《创造力》

IF 26.1 1区计算机科学

Science Robotics Pub Date : 2025-05-21 DOI: 10.1126/scirobotics.ady5090

Robin R. Murphy

引用次数: 0

Embodied manipulation with past and future morphologies through an open parametric hand design 通过开放的参数化手设计，体现了过去和未来形态的操作

IF 25 1区计算机科学

Science Robotics Pub Date : 2025-05-14 DOI: 10.1126/scirobotics.ads6437

Kieran Gilday, Chapa Sirithunge, Fumiya Iida, Josie Hughes

{"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}

引用次数: 0

Neuroprosthesis converts brain activity to speech 神经假肢将大脑活动转化为语言

IF 26.1 1区计算机科学

Science Robotics Pub Date : 2025-05-14 DOI: 10.1126/scirobotics.ady7192

Melisa Yashinski

引用次数: 0

Embodying soft robots with octopus-inspired hierarchical suction intelligence 体现软体机器人与章鱼启发的分层吸力智能

IF 25 1区计算机科学

Science Robotics Pub Date : 2025-05-14 DOI: 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}

引用次数: 0