宁波东方理工大学联合上海交通大学、中国科学技术大学招收机器人方向联培直博生。学生在上海交大 （或中科大）注册学籍，第一年在上海交大（或中科大）进行课程学习与科研工作，之后在东方理工从事 科研工作，双导师指导，毕业后获得上海交大（或中科大）颁发的博士学位和毕业证书。 导师：李晓聪，宁波东方理工大学助理教授（副研究员、博士生导师），同时兼任新加坡国立大学客座助 理教授（Adjunct Assistant Professor）及哈佛大学工程与应用科学学院客座研究员（Associate）。于2013年 和2017年分别获得新加坡国立大学学士学位和博士学位，曾任哈佛大学博士后以及新加坡科研局制造技术 研究院（SIMTech, A* STAR）科学家。主要研究方向为控制、学习与机器人交叉领域，并累计获得千万级 别的科研资助，以推动相关领域的研究发展。现担任国际期刊IEEE Transactions on Automation Science and Engineering (T-ASE) 和 IEEE Robotics & Automation Magazine (RAM) 副主编（Associate Editor）。 ...

点击下方 卡片 ，关注" 具身智能 之心 "公众号 >>直播和内容获取转到 → 具身智能之心知识星球 点击按钮预约直播 通过模仿学习来训练视觉运动策略（visuomotor policies）在众多机器人领域已被证明是有效的。然而，这些策略的性能严重依赖于训练示范（demonstrations）的数 量，而这需要在现实世界中进行昂贵的数据收集。本研究的目标是， 在训练视觉运动机器人策略时，通过利用来自各种具身（embodiments）——例如公开的机器 人数据集和人类摆弄物体的数据集——的现成或低成本数据，来减少数据收集的工作量。 本文的方法基于两个关键见解： 具身无关的世界模型预训练： 本文使用光流（optic flow） 作为一种具身无关的动作表示（embodiment-agnostic action representation），在跨多个具身的数据集上预 训练一个世界模型（World Model, WM），然后仅用少量目标具身的机器人数据对其进行微调（finetune）。 潜在策略引导（LPS） ： 提出了一种名为潜在策略引导（Latent Policy Steering, LPS） 的方法，通过在世 ...

Core Viewpoint - The ViSA-Flow framework represents a revolutionary approach to robot skill learning, significantly enhancing learning efficiency in data-scarce situations by extracting semantic action flows from large-scale human videos [4][36]. Group 1: Research Background and Challenges - Traditional robot imitation learning methods require extensive, meticulously curated datasets, which are costly to collect, creating a bottleneck for developing robots capable of diverse real-world tasks [7]. - Humans exhibit remarkable abilities to learn new skills through observation, focusing on semantically relevant components while filtering out irrelevant background information [8]. Group 2: Key Innovations - The core innovation of the ViSA-Flow framework is the introduction of Semantic Action Flow as an intermediate representation, capturing the essential spatiotemporal features of operator-object interactions, unaffected by surface visual differences [11]. - Key components of the framework include: 1. Semantic entity localization using pre-trained visual language models to describe and locate operators and task-related objects [11]. 2. Hand-object interaction tracking to maintain stable segmentation across frames [12]. 3. Flow-conditioned feature encoding to generate rich feature vectors while preserving visual context [13]. Group 3: Experimental Evaluation - In the CALVIN benchmark tests, ViSA-Flow outperformed all baseline methods using only 10% of annotated robot trajectories (1,768), achieving a success rate of 31.4% in completing five consecutive tasks, nearly double that of the next best method [19]. - The average sequence length of 2.96 further demonstrates ViSA-Flow's effectiveness in handling long-duration operational tasks [20]. Group 4: Ablation Studies - Ablation studies indicate that removing semantic entity localization significantly reduces performance, while omitting the time tracking phase decreases the average success length [26]. - The full ViSA-Flow model achieved a success rate of 89.0% in task completion, showcasing its robustness [21]. Group 5: Real-World Experiments - Real-world evaluations of ViSA-Flow included single-stage and long-duration operational tasks, demonstrating its ability to maintain performance across varying task complexities [23][30]. - The model's focus on operator and task-related objects allows for smooth transitions in spatial support as scenes change [31]. Group 6: Technical Advantages and Limitations - Advantages include data efficiency, cross-domain generalization, long-duration stability, and semantic consistency in task execution [40]. - Limitations involve the absence of explicit 3D geometric modeling, reliance on pre-trained components, and potential challenges in tasks requiring precise physical interactions [40]. Group 7: Future Directions - Future developments may include integrating physical modeling, reducing reliance on pre-trained components, combining with reinforcement learning algorithms, and expanding pre-training datasets [40]. Group 8: Significance and Outlook - ViSA-Flow represents a significant breakthrough in robot learning, proving the feasibility of extracting semantic representations from large-scale human videos for skill acquisition [36]. - The framework bridges the gap between human demonstration observation and robot execution, paving the way for more intelligent and efficient robotic learning systems [37].

1.【马斯克：Optimus人形机器人2027年将在火星表面行走】5月30日消息，马斯克表示，明年年 底，SpaceX将发射携带特斯拉Optimus人形机器人的星舰前往火星，按照轨道周期计算，将在2027 年抵达火星。届时，Optimus人形机器人将在火星表面行走。如果一切顺利，SpaceX将尝试送人类 前往火星。（东方财富网） 扫码订阅 AIGC 产业日报， 精选行业新闻，帮你省时间！ 此外，如果您还想 查公司、找项目、看行业，深入了解人形机器人、商业航天、AGI等热门赛道 ，欢迎加入睿兽分析会员，解锁相关行业图谱和报告等。 （活动期间加入会员可免费获赠一份 产业日报） 4.【美国能源部联手英伟达、戴尔官宣下一代超算】美国劳伦斯伯克利国家实验室29日宣布，美国能 源部已与戴尔公司签订合同，将打造一台由英伟达芯片驱动的全新旗舰超级计算机。根据该实验室发 布的新闻稿，美国能源部长克里斯·赖特当天到访实验室，其间宣布与戴尔签订合同，为美国能源部下 辖的"国家能源研究科学计算中心(NERSC)"开发下一代旗舰超级计算机。据美联社报道，赖特当天与 戴尔高管和英伟达首席执行官黄仁勋共同宣布上述合作。新闻稿说，新超算将以 ...