Science Robotics最新文献_第7页

RAPTOR: A foundation policy for quadrotor control 猛禽：四旋翼控制的基础政策

IF 27.5 1区计算机科学

Science Robotics Pub Date : 2026-05-13 DOI: 10.1126/scirobotics.aec1481

Jonas Eschmann, Dario Albani, Giuseppe Loianno

{"title":"RAPTOR: A foundation policy for quadrotor control","authors":"Jonas Eschmann, Dario Albani, Giuseppe Loianno","doi":"10.1126/scirobotics.aec1481","DOIUrl":"10.1126/scirobotics.aec1481","url":null,"abstract":"<div >Humans are remarkably data efficient when adapting to previously unseen conditions, like driving a new car. In contrast, modern robotic control systems, like neural network policies trained using reinforcement learning (RL), are highly specialized for single environments. Because of this overfitting, they are known to break down even under small differences like the simulation-to-reality gap and require system identification and retraining for even minimal changes to the system. Here, we present RAPTOR, a method for training a highly adaptive foundation policy for quadrotor control. Our method enables training a single, end-to-end neural network policy to control a wide variety of quadrotors. We tested 10 different real quadrotors, from 32 grams to 2.4 kilograms, that also differed in motor type (brushed versus brushless), frame type (soft versus rigid), propeller type (two, three, or four blades), and flight controller (PX4, Betaflight, Crazyflie, M5StampFly). We found that a tiny, three-layer policy with only 2084 parameters was sufficient for zero-shot adaptation to a wide variety of platforms. The adaptation through in-context learning was made possible by using a recurrence in the hidden layer. The policy was trained through our proposed meta-imitation learning algorithm, where we sampled 1000 quadrotors and trained a teacher policy for each of them using RL. The 1000 teachers were distilled into a single, adaptive student policy. We found that within milliseconds, the resulting foundation policy adapted zero-shot to unseen quadrotors. We tested the capabilities of the foundation policy under numerous conditions (trajectory tracking, indoor/outdoor, wind disturbance, poking, and different propellers).</div>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"11 114","pages":""},"PeriodicalIF":27.5,"publicationDate":"2026-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147924469","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

Autonomous seeking and mapping coral reef biodiversity hotspots with a multimodal AUV 基于多模式AUV的珊瑚礁生物多样性热点自主搜索与测绘

IF 27.5 1区计算机科学

Science Robotics Pub Date : 2026-05-13 DOI: 10.1126/scirobotics.adx9939

Seth McCammon, Levi Cai, Daniel Yang, John Walsh, John D. Cast, T. Aran Mooney, Yogesh Girdhar

引用次数: 0

Beyond alignment: Why robotic foundation models need context-aware safety. 超越一致性：为什么机器人基础模型需要上下文感知的安全性。

IF 27.5 1区计算机科学

Science Robotics Pub Date : 2026-04-29 DOI: 10.1126/scirobotics.aef2191

Alexander Robey, Zachary Ravichandran, Eliot Krzysztof Jones, Jared Perlo, Fazl Barez, Vijay Kumar, J Zico Kolter, Hamed Hassani, George J Pappas

引用次数: 0

Transfer learning in robotics: From promises to practice through the emerging role of foundation models. 机器人技术中的迁移学习：从承诺到实践，通过基础模型的新兴作用。

IF 27.5 1区计算机科学

Science Robotics Pub Date : 2026-04-29 DOI: 10.1126/scirobotics.aeh4374

Michael C Welle, Noémie Jaquier, Andrej Gams, Jens Lundell, Danica Kragic

引用次数: 0

Dexterous grasping with an active palm 灵活的手掌抓握。

IF 27.5 1区计算机科学

Science Robotics Pub Date : 2026-04-29 DOI: 10.1126/scirobotics.aei2046

Amos Matsiko

引用次数: 0

A retrieval-augmented framework enabling VLM spatial awareness for object-centric robot manipulation. 一个检索增强框架，使VLM空间感知以对象为中心的机器人操作。

IF 27.5 1区计算机科学

Science Robotics Pub Date : 2026-04-29 DOI: 10.1126/scirobotics.aea2092

Kai Chen, Chengkun Li, Chang Tu, Jiahui Pan, Yiyao Ma, Wei Chen, Zhongxiang Zhou, Xuecheng Xu, Stephen James, Chi-Wing Fu, Rong Xiong, Pieter Abbeel, Yun-Hui Liu, Qi Dou

{"title":"A retrieval-augmented framework enabling VLM spatial awareness for object-centric robot manipulation.","authors":"Kai Chen, Chengkun Li, Chang Tu, Jiahui Pan, Yiyao Ma, Wei Chen, Zhongxiang Zhou, Xuecheng Xu, Stephen James, Chi-Wing Fu, Rong Xiong, Pieter Abbeel, Yun-Hui Liu, Qi Dou","doi":"10.1126/scirobotics.aea2092","DOIUrl":"https://doi.org/10.1126/scirobotics.aea2092","url":null,"abstract":"<p><p>Connecting the semantic reasoning of vision-language models (VLMs) to the precise geometric demands of robotic manipulation remains a fundamental challenge. Although VLMs can interpret high-level commands, they lack the intrinsic spatial intelligence required for tasks demanding precise object placement, orientation, and physical reasoning. Here, we introduce Retrieval-Augmented Manipulation (RAM), an object-centric framework that endows general-purpose vision foundation models with the spatial reasoning necessary for robust manipulation. RAM bridges the semantic-to-geometric gap by grounding abstract concepts into an explicit, object-centric three-dimensional (3D) representation. This grounded information is then provided as augmented context to the VLM, empowering it to decompose complex instructions into a sequence of spatially precise and physically plausible subgoals. We demonstrate that RAM, in a zero-shot setting on a real-world robot, can execute these subgoals to fulfill complex spatial language instructions, complete spatially aware manipulation under the guidance of a single 2D image, and adaptively replan tasks by reasoning about physical constraints like object size and collisions. Quantitative evaluations on the Common Object in 3D (CO3D) dataset also validated that RAM's core vision module generalizes to previously unseen object categories and is robust to variations in shape and occlusions. By providing a structured bridge between semantic intent and geometric execution, RAM represents a critical step toward developing more physically intelligent and general-purpose robotic systems.</p>","PeriodicalId":56029,"journal":{"name":"Science Robotics","volume":"11 113","pages":"eaea2092"},"PeriodicalIF":27.5,"publicationDate":"2026-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147790061","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

How foundation models will revolutionize robot swarms. 基础模型将如何彻底改变机器人群。

IF 27.5 1区计算机科学

Science Robotics Pub Date : 2026-04-29 DOI: 10.1126/scirobotics.adz1543

Volker Strobel, Marco Dorigo, Mario Fritz

引用次数: 0

Robot farm elegy 机器人农场的挽歌。

IF 27.5 1区计算机科学

Science Robotics Pub Date : 2026-04-22 DOI: 10.1126/scirobotics.aeh3279

Robin R. Murphy

引用次数: 0

From autonomy to alliance: Robotic foundation models must learn with us, not just for us 从自主到联盟：机器人基础模型必须与我们一起学习，而不仅仅是为我们学习