在人工智能与机器人技术加速迭代的当下，自动驾驶算法正从虚拟测试走向真实道路与物流运输场景落地，专 业级机械臂也逐渐成为课堂示教编程的得力助手。随着行业发展，传统基础编程实践已难以满足需求，科研人 员与开发者更热衷于在仿真环境中钻研多机协同算法等前沿课题；与此同时，实验室对机器人在模拟场景下， 实现测试识别、精准抓取、智能避障、高效搬运全链路流程的要求也水涨船高。 在一背景下， 大象机器人于近日推出移动复合机器人 myAGV Pro， 为智能机器人领域的探索与实践带来新 的解决方案。 据机器人大讲堂了解，myAGV Pro是 大象机器人 旗下的 全向转向系统小车 ，适配大象机器人旗下轻量化 协作机械臂生态和市面上大部分通用协作机器人，能够完成 多目标环境检测、语音语义识别 等人工智能的相 关应用。大象机器人推出该产品主要旨在为研究人员与开发者在智能机器人领域进行 仓储搬运、教学学习、 创新应用、科研研究和竞技比赛 等场景提供理想平台。 myAGV Pro 中文宣传片 3 丰富生态，支持二次开发 原 生 搭 载 Ubuntu 22.04 ， 提 供 RVIZ 、 Gazebo 仿 真 环 境 支 持 。 同 时 ...

Core Viewpoint - The article highlights the transformation of Chinese robotics companies, particularly Efort, from being perceived as followers to becoming equal competitors on the global stage, showcasing their technological advancements and international strategies at Automatica 2025 [1][7][25]. Group 1: Historical Context - In the past, Chinese robotics companies were often labeled as "learners" or "low-end substitutes," facing significant barriers such as quality trust issues and a lack of brand recognition in high-end markets [2][4][5]. - Early challenges included reliance on imported core components, which led to quality fluctuations and hindered the establishment of a reputable brand image [2][5]. Group 2: Efort's Global Strategy - Efort has adopted a dual strategy of self-research and overseas acquisitions since 2015, investing 1.1 billion yuan to acquire leading companies in niche sectors, thereby enhancing its technological capabilities [9][11]. - The company has successfully penetrated high-demand industries such as automotive and electronics, showcasing complete robotic solutions tailored for specific industrial applications [11][12]. Group 3: Technological Advancements - Efort's products have achieved significant certifications, including CE and ATEX, and have demonstrated exceptional performance metrics, such as an average operating time of 120,000 hours for its ER300 series robots [11][12][16]. - The company has made substantial progress in core technologies, achieving a 99.90% self-research rate for its controllers and overcoming key component challenges through strategic acquisitions and domestic supply chain development [16][18]. Group 4: Market Positioning and Future Outlook - Efort is focusing on deepening local operations and enhancing brand image through initiatives like establishing training centers and participating in regional industry forums [20][22]. - The company is also integrating advanced AI technologies into its robotics systems, aiming to improve performance in complex environments and maintain a competitive edge in the evolving market landscape [22][24]. Group 5: Conclusion - Efort's presence at Automatica 2025 symbolizes a significant milestone in the evolution of Chinese robotics, reflecting a shift from merely catching up to actively competing on a global scale [25][26]. - The article emphasizes that the journey of Chinese robotics companies is not just about technological advancements but also about reshaping the global industrial landscape through innovation and strategic integration [27][28].

Core Viewpoint - The laser radar integration perception scheme is replacing the RTK/UWB + visual sensor scheme as the mainstream in the lawn mower robot field, driven by consumer demand for lightweight, convenient deployment, and higher reliability [1] Group 1: Requirements for Laser Radar in Lawn Mower Robots - Lawn mower robots require high-resolution laser radar to accurately identify small obstacles like squirrels and hedgehogs, which are more common in gardens than on roads [2] - The diverse terrain of residential lawns in Europe and North America, including slopes and pits, necessitates laser radar that can effectively distinguish different ground conditions [5] - The need for nighttime operation due to the growth rate of grass in summer requires high-resolution laser radar, as traditional cameras fail in low light [6] - Reliability is crucial for outdoor operation, with laser radar needing to withstand various weather conditions and physical impacts [9] - Users expect a long lifespan for lawn mower robots, with high-end models like the Mammotion LUBA mini AWD LiDAR offering an outdoor lifespan of over 8 years [11] Group 2: Performance Metrics for Laser Radar - The core demand for laser radar in lawn mower robots includes high resolution, high reliability, and long lifespan [14] - Vertical angular resolution is a key performance metric, with higher line counts leading to clearer imaging and better obstacle detection [15] - The E1R solid-state laser radar, chosen by high-end lawn mower brands, meets automotive-grade reliability standards and can endure harsh environmental conditions [19]

Group 1: Neuralink Developments - Neuralink has made significant progress with 7 participants, including 4 spinal cord injury patients and 3 ALS patients, who use the device for an average of 50 hours per week, peaking over 100 hours [1] - Future plans include increasing electrode count to 3,000 by 2026 to help the first Blindsight participant regain vision, and expanding to over 25,000 channels by 2028 to access any part of the brain [1] Group 2: Kepler Robotics A Round Financing - Kepler Robotics announced A round financing and strategic partnerships with leading companies such as Zhejiang Zhaofeng Electromechanical and Hanwei Technology Group [5] - The partnerships aim to explore technology in smart factories and develop embodied intelligent humanoid robot solutions [5] Group 3: Huagong Technology's Laser Weeding Robot - Huagong Technology unveiled China's first all-weather intelligent laser weeding robot, capable of precisely targeting weeds without harming crops [8] - The robot has undergone algorithm validation in various test fields and is expected to enter mass production next year, potentially eliminating the need for herbicides [8] Group 4: Amazon's Vulcan Robot Breakthrough - Amazon's Vulcan robot has achieved breakthroughs with touch technology, allowing it to handle goods like a human, which contrasts with traditional robots that avoid contact [11] - The Vulcan Stow robots are currently in pilot testing, with plans for beta testing and large-scale deployment in Germany [11] Group 5: Global First Robot 6S Store in Shenzhen - Shenzhen is set to open the world's first robot 6S store by the end of July, offering sales, rentals, customization, and maintenance services [14] - This initiative is part of a broader effort to create an AI-driven district, integrating real-world applications and various business models [14]

近期北京邮电大学方斌教授团队联合清华大学、 意大利比萨圣安娜大学、英国伦敦国王学院和德国汉堡大学 发布了基于掌状视触觉传感器的柔性接触仿真与操作学习，为基于视触觉传感器的柔性操作提供了新的思路。 相关工作发表在机器人、自动化领域 JCR Q1 期刊 IEEE Transactions on Automation Science and Engineering 。 研究背景： 可变形物体操控是机器人领域一个经典且极具挑战性的任务。相较于刚性物体，可变性物体具复杂的变形特性 （包括弹性变形、塑性变形和弹塑性变形），大量的自由度 (DOF) 需要复杂的建模方法，这使该问题更加复 杂。同时，可变形物体广泛存在于医院、工业和家庭环境中。因此，可变形物体操控在机器人技术发展中发挥 着至关重要的作用。 为此，本文开发了一款可变形物体与基于视觉的触觉传感器之间的软接触模拟器，该模拟器能够模拟视触觉传 感器与弹性、塑性以及弹塑性物体之间的接触变形。在此模拟器的基础上，本文提出了基于视触觉传感器的可 变形物体操控基准，包括可迁移的观测值、任务和专家演示系统。最后，本文搭建了相应的实验平台，完成了 相关任务的 Sim-to-rea ...

数据被视为具身智能（Embodied Intelligence）落地的"最后一公里"，其核心在于，数据直接决定了智能体能 否从虚拟训练环境无缝迁移至复杂多变的物理世界，并实现稳定可靠的交互与决策。 与大语言模型数据不同，具身智能需要采集物理交互中的高维动态数据（如力反馈、材质摩擦、碰撞响应 等），但真实场景数据获取依赖精密传感器和硬件设备，且受限于场景多样性、安全风险及隐私等问题，目前 全国范围内具身智能最大开源数据集规模也只有百万级别，相比自动驾驶领域的单日上亿条数据，相差百倍以 上。 除数据规模外，在涉及具体智能体物理交互的相关问题（例如"抓取力度""滑动摩擦系数"）时，这些数据难以 用语言进行精准描述。数据标注工作需结合动作意图与环境反馈，正因如此，大量数据的标注任务仍需依赖人 工完成。 针对具身智能数据问题，近日2025北京智源大会 上 孙富春、赵明国、王鹤、庞江淼、赵同阳、仉尚航、卢宗 青、高阳、唐剑 等行 业领军人物 ，分享了他们在具身智能数据方面的思考。 ▍ 孙富春：未来团队将采集200万条轨迹、数据总量52 TB 远超英伟达数据规模 清华大学计算机科学与技术系教授、中国人工智能学会副理事长孙富 ...

Core Insights - The article discusses the challenges and opportunities in the humanoid robot industry, particularly focusing on battery technology and energy requirements for operational efficiency [1][2][4]. Group 1: Market Potential - The global humanoid robot market is projected to reach between $30 billion to $50 billion by 2035, and $1.4 trillion to $1.7 trillion by 2050, with an expected annual production of 86 million units by 2050 [1]. - The demand for lithium batteries in humanoid robots is anticipated to exceed 100 million yuan by 2025, with a market size of 36 billion yuan by 2035 due to increased applications in various sectors [1]. Group 2: Battery Technology Challenges - Humanoid robots require higher energy density batteries, targeting over 300 Wh/kg, and need fast charging capabilities to minimize downtime in industrial applications [2]. - Current lithium-ion batteries improve at a slow rate of about 7% per year, indicating a need for disruptive innovations to meet the operational demands of humanoid robots [2]. Group 3: Alternative Energy Solutions - Solar panels have been explored as a potential energy source for robots, but their power output is insufficient for high-energy tasks, making them more suitable for low-power or stationary applications [4]. - Fast-charging technologies, such as sodium-ion batteries, can reduce downtime but may compromise battery lifespan and require substantial charging infrastructure [4]. Group 4: Solid-State Battery Developments - Solid-state batteries theoretically offer energy densities of 400-600 Wh/kg, but current production faces challenges, leading to a focus on hybrid approaches combining different technologies [5]. - Companies like Nandu Power and Delong Technology are advancing solid-state battery technologies, with Nandu Power achieving significant safety testing milestones and Delong planning substantial investments in production capabilities [7][9]. Group 5: Company Innovations - Companies such as Better Ray and Haopeng Technology are developing innovative battery solutions tailored for humanoid robots, focusing on safety, fast charging, and energy density improvements [12][13]. - Yiwei Lithium Energy is advancing solid-state battery technology with plans for mass production by 2025, while also achieving significant milestones in cylindrical battery production [15]. Group 6: Industry Collaborations - Various companies are forming strategic partnerships to enhance battery technology and applications, such as Nandu Power collaborating with Taillan New Energy and Yadi Company for solid-state battery innovations [8][12]. - The industry is witnessing a trend towards integrating AI and advanced monitoring systems in battery management to enhance safety and performance in extreme conditions [13].

目前 已有的基于 Koopman算子的方法难以补偿不确定性和干扰，导致训练与现实之间的差距，从而造成性 能不佳。由于连续机器人天生的易受干扰性，这一差距很容易在实际场景中削弱其任务空间性能。 连续机器人控制中的鲁棒性与泛化能力 同时， 机器人可能需要在训练过程中未覆盖的区域进行操作，而且连续机器人的结构多样性进一步增加了控 制的复杂性。此外，现有基于 Koopman算子的控制方法的收敛性和鲁棒性尚未从理论或实验角度得到验证。 因此， 开发一种具有显著增强的鲁棒性、高计算效率、强泛化能力和严谨理论分析的数据驱动控制算法，对 于连续机器人而言至关重要 。 连续体机器人在近几十年受到了越来越多的关注。它们的柔顺性和灵活性使其在医疗、工业、农业和航空航天 等诸多领域具有重要应用价值。充分发挥其能力需要设计有效、高效且可靠的控制系统，而由于其结构复杂 性，这一任务仍然具有很大的挑战。 传统的连续体机器人控制方法通常依赖于对机器人物理模型的精确建模。然而，由于其柔性结构和不规则形 态，连续体机器人的建模极其困难，且容易受到环境影响，导致模型难以准确反映机器人的实际动态行为。因 此，研究人员转向了数据驱动的控制方法，尤其是 ...

近年来， 连续体机器人 凭借其高柔顺性、灵活运动能力及轻量化和小型化结构，在医疗、工业检测、人机交 互等领域展现出巨大应用潜力。然而， 如何实现精准的路径跟踪仍是各类应用普遍面临的关键技术难题。 目前， 主流的路径跟踪方法依赖于逆运动学求解 ，即通过数学模型求解末端执行器期望运动路径下驱动器的 对应运动路径，并寻找多解以避开环境障碍物碰撞。然而，和刚性机械臂不同的是，连续体机器人多采用分段 等曲率模型，该模型缺乏逆运动学求解理论，传统数值方法依赖初值，也难以找到多解。部分研究采用模型预 测控制（ MPC），通过在线优化调整控制策略，但 该方法无法保证全局最优性。 受刚性机械臂研究的启发， 有学者提出在执行器空间规划全局最优轨迹，作为前馈控制信号以提高跟踪精 度。 然而，连续体机器人的高度非线性特性使得其任务空间、配置空间和执行器空间之间的映射关系更为复 杂。 数值逆运动学算法通常只能提供单一解，且对初始值敏感，难以满足全局轨迹优化的需求。 因此，如何突破逆运动学求解的局限性，发展高效、多解、不依赖初始值的解算和规划方法，是提升连续体机 器人路径跟踪性能的关键。 ▍提出最优路径跟踪框架，实现运动控制突破性优化 ...

2024年9月，1X Technologies （以下简称 "1X"）发布全球首个人形机器人世界模型 1X World Model首证 Scaling Law（人形机器人数据显著增强扩展定律） 。 前不久， 1X对外公布了其世界模型在技术迭代和应 用场景上取得的多项突破，再度成为行业焦点。 据具身智能大讲堂了解， 1X World Model 是一种可以模拟现实世界在智能体作用下如何演变的生成式视频 模型， 其基于视频生成技术（ Sora）和自动驾驶世界模型（端到端自动驾驶，E2EAD）构建形成，能够 通 过输入图像状态与动作指令 模拟出机器人在不同动作下的未来场景，预测机器人和操作对象之间的交互效 果，帮助人形机器人完成精准交互，解决具身机器人评估难题。 本次 1X World Model 最新突破集中在 三个方面： ▍ 动作可控性：从基础动作响应到复杂物理场景精准模拟 首次公开的 1X World Model具备根据不同动作命令生成不同结果的能力 ， 通过展示以四种不同轨迹为条件 对世界模型进行的不同生成过程，且每条轨迹都从相同初始帧起始，清晰地呈现了其多样化生成特性。 在模拟物体间交互这一核心价值体现上 ...