Core Viewpoint - The article discusses the advancements in humanoid flying robots, highlighting the transition from science fiction to practical applications, and the potential for these technologies in various fields such as emergency rescue and industrial operations [20]. Group 1: Research and Development - Zhejiang University Huzhou Research Institute showcased a humanoid flying robot concept with a jet propulsion system at the 2025 IROS conference [6]. - A team from Caltech developed a multimodal robot named LEONARDO, which can switch between walking and flying, demonstrating a new movement method that integrates ground and aerial capabilities [9][11]. - The Jet-HR2 from Guangdong University of Technology employs a radical approach by making flying its core capability, achieving stable takeoff and hovering with a thrust-to-weight ratio of 1.17 [14][16]. Group 2: Practical Applications - The jetpack showcased by Zhejiang University is designed for practical emergency scenarios, allowing single-person flight for rescue and inspection tasks [8]. - The iRonCub3 project from the Italian Institute of Technology aims to create a flying robot capable of rapid deployment in disaster response, integrating flight and ground operations [19]. - The collaboration between Caltech and TII resulted in a multi-robot system where a humanoid robot can launch a drone, demonstrating a complete operational chain for emergency tasks [13]. Group 3: Challenges and Future Prospects - Current challenges for humanoid flying robots include limited flight duration, high costs, and restricted application scenarios [20]. - The advancements in hardware and AI control algorithms are expected to enhance the capabilities of humanoid robots, making them valuable in industrial, rescue, and even space applications [20].

在目前的视触觉传感器领域，VBTS的力估计精度受限于相机接收接触表面三维空间形变信息的缺失。有研究 者使用双层标记点来提升触觉标记点密度，到使用颜色叠加方式改进触觉传感器的传感原理，但双层标记生产 和制造难度大，且视觉传感原理的固有特性——光学形变特征与接触力间的非线性映射易受环境扰动影响，利 用双层标记的方式无疑是降低了接触的稳定性。此外，还有研究利用使用双目相机（双目系统）和结构上的改 进，接收更丰富信息形成来提升力估计精度，但不利于集成。具体而言，现有方案面临双重困境：（1）复杂 光学结构与传感器微型化需求存在根本性冲突；(2)传感原理改进引起的工艺复杂化导致传感器泛化能力不 足。 IROS 2025论文提出了 视触觉结合磁触觉的MagicGel传感器。 通过引入磁传感模态构建视觉-磁场异构数据 融合框架。其核心在于利用磁场信息补偿视觉图像的信息缺失，通过视、磁关联建立更完备的接触力学表征体 系。 MagicGel 的主体结构如 图 1 所示。其结构主要分为：涂层、强磁颗粒标记点、弹性体、灯带、霍尔传感器 和相机。此外还有接收视觉图像和磁场信息的接收模块。 MagicGel 的整体尺寸为 31*31*2 ...

迟滞是指系统在加载和卸载过程中表现出不同状态的现象。 HasMorph通过 主动利用摩擦引起的迟滞效应， 仅调整两个肌腱执行器的加载顺序与幅度，即可获得多种不同的机器人形态，实现机器人可逆、多段弯曲的变 型 而无需增加驱动器数量。这一方法突破了传统上依赖更多执行器实现灵活变形的设计思路。 为实现 HasMorph ， 研究团队 还设计了一种 倒置 锯齿形腱鞘传动机构 ，并结合尖端生长机制，使机器人 能够在探测环境中实现 "领航跟随"式的灵活、无摩擦运动。实验结果显示，该机器人在非结构化环境中具有 优异的适应性与操作灵活性。 该研究不仅 解决了尖端生长软体机器人的转向及形状驱动难题， 还 提出了一种紧凑、高灵活性的软体机器 人驱动方案。 传统上，迟滞现象通常被视为系统误差或不稳定因素，而 该研究则从正向角度利用 迟滞 特性 拓展了其在软体机器人领域的应用边界 。 在人类难以进入的 狭窄 空间中进行操作，一直是机器人技术面临的一项标志性挑战。突破这一技术瓶颈，将 有望在多个领域提升任务实施的可行性、安全性、效率与经济性，例如微创手术、地下管道（水 /石油/天然 气）维护，以及飞机机翼和发动机的航空航天检测等。 蛇 ...

Core Insights - The article discusses the rise of Weiyi Intelligent Manufacturing, a company aiming to become the first publicly listed industrial embodied intelligent robot supplier in Hong Kong, addressing key industry pain points and achieving significant revenue growth [1][3]. EIIR Growth Insights - Weiyi Intelligent Manufacturing has built a comprehensive technology chain focusing on "hands, eyes, brain, and cloud" to facilitate rapid digital transformation in industrial enterprises [3]. - The company was established in 2018 and initially operated as an "industrial AI technology equipment solution integrator," entering the defect detection market with AI and robotic arms [5]. - In December 2022, the company made a pivotal acquisition of Jiangsu Zhiyun Tiangong, enhancing its algorithm and platform development capabilities [5]. - The leadership change brought by Zhang Zhiqi, a former executive from Baidu and Alibaba, led to a product-centric transformation, resulting in a profitable turnaround in 2024 [5][6]. Financial Performance - Revenue increased from 221 million yuan in 2022 to 600 million yuan in 2024, reflecting a compound annual growth rate (CAGR) of 64.7% [6]. - In the first half of 2025, revenue surged by 187% year-on-year, reaching 412 million yuan [6]. - The EIIR product line became the main revenue driver, with its contribution to total revenue rising from 15.3% in 2022 to 53.6% in the first half of 2025 [7]. Market Position and Recognition - Weiyi Intelligent Manufacturing is recognized as the largest supplier of industrial embodied intelligent robots in China, holding the top market share in 2024 [9]. - The company addresses critical industry challenges, such as flexibility and high deployment costs associated with traditional robotic arms, by offering adaptable and cost-effective EIIR solutions [10][11]. Technological Advancements - The EIIR products are designed to operate without complex programming, allowing for quick deployment and adaptability across various tasks and industries [14][16]. - The company's technology framework integrates cloud, edge, and terminal systems, enabling enhanced flexibility and efficiency in manufacturing processes [16]. Global Expansion Strategy - Weiyi Intelligent Manufacturing plans to expand internationally, targeting major manufacturing markets in the U.S. and Europe starting in 2025 [19]. - The company aims to establish a localized overseas sales and service network, enhancing its global business footprint [22]. Conclusion - The rise of Weiyi Intelligent Manufacturing signifies a transformative shift in the industrial robotics sector, moving from traditional automation to intelligent solutions [23].

10 月 23 日，在中国杭州举行的 2025 IEEE/RSJ 智能机器人与系统国际会议（ IROS 2025 ）上，元化智 能科技（深圳）有限公司首席科学家、南方科技大学讲席教授孟庆虎院士荣获 IROS Harashima Award for Innovative Technologies （创新技术奖），成为该奖项自 2007 年设立以来的第十二位获奖者，同时也是 中国大陆学者首位获此殊荣的科学家。 IROS Harashima Award 是国际智能机器人与系统领域最具权威性的个人荣誉之一，旨在表彰在机器人与智 能系统方向作出开创性贡献的杰出科学家。该奖项由国际机器人学术界权威专家委员会严格评选，代表全球机 器人技术创新的最高水准。孟庆虎院士此次获奖，是对其在医疗机器人与服务机器人领域的感知与智能技术方 面取得卓越成就的高度认可。 ▍ 推动 IROS 发展，助力中国成为全球机器人创新中心 作为中国机器人学术界的领军人物之一，孟庆虎院士长期致力于推动国际学术交流与技术进步。 2005 年， 他与张宏院士共同主办 IROS 2005 ，当时参会人数约 800 人；而 2025 年在杭州举办的 IROS 大 ...

Core Concept - The article presents a novel multi-modal bionic robotic hand that combines magnetic silicone skin with a rigid skeleton, integrating a vacuum suction cup at the fingertips to achieve three gripping modes: wrapping, parallel, and adsorption [2]. Group 1: Design and Mechanism - The bionic fingers utilize a rigid skeletal structure wrapped in soft muscle tissue, providing excellent cushioning and shock absorption for grasping flexible objects [2]. - The internal Hall sensor units detect the deformation of the magnetic silicone film, allowing real-time monitoring of the gripping information [4]. - The silicone film, mixed with magnetic powder, transforms non-magnetic particles into magnetic ones upon unidirectional magnetization, creating a regular magnetic field that changes with deformation during contact with external objects [5]. Group 2: Gripping Phases and Data Collection - The gripping process is divided into four stages: approaching the object, squeezing the object, lifting the object, and releasing the object, with distinct data trends observed in the first two stages [7]. - The first stage shows a lower rate of change in magnetic data compared to the second stage, indicating different interactions during the approach and squeeze phases [7]. - A control system collects magnetic field data every 0.25 seconds to establish a relationship between the change in magnetic field (∆B) and the diameter of the object being grasped [9]. Group 3: Experimental Setup - An experimental platform was established using an RM65 robotic arm and a D455 depth camera to test the robotic hand's grasping capabilities in real-world scenarios, enabling autonomous grasping operations [10].

Core Viewpoint - The article discusses the advancements in humanoid robots, particularly focusing on the latest H2 humanoid robot by Yushu, which features enhanced perception capabilities through a new "robot eye" system that integrates dToF LiDAR technology for improved environmental understanding and interaction [1][15]. Group 1: Humanoid Robot Advancements - Yushu's H2 humanoid robot showcases high dynamic capabilities, including the ability to perform complex movements like dancing while maintaining 360-degree environmental awareness through its advanced head and eye system [1]. - The integration of dToF LiDAR technology allows for precise 3D spatial measurements, overcoming limitations faced by traditional visual sensors, especially in varying lighting conditions [4][6]. Group 2: Importance of Perception in Robotics - The evolution of robotic perception is crucial as humanoid robots transition into unstructured environments, necessitating rapid understanding and interaction with their surroundings [3][12]. - Traditional visual systems struggle with depth estimation and synchronization, leading to challenges in complex task execution, which dToF LiDAR effectively addresses by providing accurate and reliable depth information [4][7]. Group 3: Technological Integration - The article emphasizes the need for hardware-level synchronization among various sensors (dToF LiDAR, RGB cameras, IMUs) to ensure accurate data collection and processing, which is essential for real-time decision-making in dynamic environments [7][9]. - The AC2 sensor system, developed by Sutech, exemplifies this integration, achieving a synchronization precision of 1ms, significantly enhancing the reliability of robotic perception [8][11]. Group 4: Future of Humanoid Robotics - The future of humanoid robots lies in their ability to achieve high-precision, high-consistency perception across various environments, enabling them to perform complex tasks and interact effectively with humans and objects [12][16]. - As humanoid robots evolve from mere tools to autonomous intelligent agents, the development of advanced perception systems will be pivotal in facilitating their integration into everyday life and various industries [15][16].

Core Viewpoint - The article discusses the development of a groundbreaking medical robot, FIREFLI, designed for the diagnosis of acute mesenteric ischemia (AMI), a condition with a high mortality rate of up to 55% due to delayed diagnosis and treatment [1][3]. Group 1: FIREFLI Capsule Design and Technology - The FIREFLI capsule is inspired by the bioluminescent properties of fireflies, utilizing a "light-emitting - light-sensing" mechanism to detect changes in light reflection caused by ischemic conditions in the intestines [4]. - The capsule features a pH-responsive polymer coating that ensures it activates only in the small intestine, preventing premature activation in the stomach [4]. - Inside the capsule, three sets of flexible printed circuit boards (PCBs) are integrated, each containing a white LED and a 10-channel photodiode sensor, allowing for the detection of light reflection across a spectrum of 350-1000 nm [5]. Group 2: Diagnostic Performance and Validation - Animal studies using pigs demonstrated that the FIREFLI capsule could accurately diagnose ischemia, achieving a diagnostic accuracy of 89%, sensitivity of 98%, and specificity of 88% based on the "tissue brightness" biomarker [8][10]. - The study found that the "tissue brightness" indicator was more effective than color change indicators, which had a lower diagnostic accuracy of 65% and sensitivity of only 37% [10]. - The system maintained consistent performance over time, with ischemic tissue brightness remaining below the threshold during a 5-hour monitoring period, providing reliable data for clinical decision-making [11]. Group 3: Safety and Practicality - Safety trials indicated that the FIREFLI capsule passed through the gastrointestinal tract without causing any obstruction or retention, confirming its design's safety [12]. - The capsule is designed for efficient power management, allowing it to operate for over 5 hours on a single charge, which is sufficient to cover the average transit time through the small intestine [14].

10 月 24 日，以 " 合作共赢 、协同创新 "为主题的"潮起钱江智汇萧山"IROS Startup Forum创业者与投资人 见面会在杭州萧山成功举行。作为2025年国际智能机器人与系统大会（IROS）的官方重点活动，本次见面会 精准聚焦机器人与智能系统领域，汇聚了百余名来自全球的顶尖学者、创新创业先锋、资深投资人及产业代 表，共同搭建了一个"产学研资政媒"六位一体的高能级对话平台，为全球机器人技术的成果转化与产业创新注 入澎湃动能。 本次活动由杭州市萧山区人民政府与 IROS 2025 组委会联合主办，萧山区委人才办、萧山区科技局、萧山区 科协共同承办，并得到了西安电子科技大学杭州研究院、浙江大学控制科学与工程学院、浙江省自动化学会、 杭州立德鼎机科技有限公司等单位的大力支持。 IROS 2025 大会 主席 、 上海交通大学特聘教授 、浦江国际学院院长 王贺升，杭州市科技局党组成员、副 局长俞钧 ， 杭州市科协党组成员、副主席陈韵雯 ，杭州市萧山区 人民政府副区长朱国军 ， 萧山区委组织部 副部长 、 区委人才办常务副主任易海平 ， 萧山区科技局党组书记、局长高源 ， 萧山区科协主席许益飞以及 来自 ...

Core Viewpoint - The 2025 International Conference on Intelligent Robots and Systems (IROS) in Hangzhou showcased cutting-edge robotics technology and highlighted the "Chinese Path" to industrialization in the robotics sector, with Fao Robotics presenting its full-stack manufacturing solutions and humanoid robots [1][18]. Group 1: Full-Stack Humanoid Robot Solutions - Fao Robotics positions itself as a Tier-1 supplier of full-stack humanoid robot solutions, showcasing a complete technology chain from core components to complete systems [1]. - The joint module serves as the "power core" of humanoid robots, featuring high load capacity and lightweight structure, significantly reducing energy consumption and space requirements while ensuring precise and stable motion response [3]. - The humanoid robotic arm, with 7 degrees of freedom, is designed for flexible movement and can adapt to various operational tasks, enhancing deployment and maintenance efficiency [3]. Group 2: Semi-Humanoid Execution Units - The semi-humanoid execution unit integrates the humanoid robotic arm, control systems, perception modules, and end-effectors, reflecting Fao's understanding of the industrialization path for robotics [5]. - This highly integrated design reduces the technical barriers for external device integration, accelerating the application of robots across various industries [5]. - The humanoid robot provides a complete solution for all-scenario operations, emphasizing flexibility and adaptability in real-world applications [5]. Group 3: Intelligent Dual-Arm Robots - The intelligent dual-arm robot, showcased at IROS, combines mobile capabilities, dual-arm operation, and multi-sensory interaction, breaking the limitations of traditional industrial robots [7]. - Its high-precision flexible operation allows for intricate tasks, making it suitable for diverse production environments [7][10]. - The robot's dialogue interaction feature enables natural communication with operators, significantly lowering the usage threshold for non-technical users [11]. Group 4: Software and Algorithm Innovations - Fao's AIRLab platform serves as the "smart brain" of its full-stack solutions, enhancing the efficiency of sorting and picking operations by 50% through AI-driven systems [14]. - The 3D vision-based welding solution exemplifies a closed-loop system that integrates perception, decision-making, and execution, improving efficiency and consistency in complex welding tasks [16]. - Fao's comprehensive product matrix covers collaborative robots with payloads ranging from 3 to 30 kg, catering to various application scenarios [12]. Group 5: Future Outlook - Fao Robotics aims to integrate collaborative robots with AI, vision, and sensing technologies, providing intelligent systems across multiple industries [18]. - The company has established over 40 service centers globally, enhancing its market reach and ability to adapt to local technological innovations and market demands [18]. - The innovations presented at IROS are just the beginning, with more advanced solutions expected to emerge as Fao continues to develop its core technologies and strategic initiatives [18].