机器人与具身智能领域的最新论文，以及每篇对产业的意义。
Open concrete canals play a vital role in water transportation, serving as primary water infrastructure for millions of people across the Phoenix, Arizona, metro area. Over time, the concrete canals can experience a range of issues, including canal lining deformation, cracked concrete, and sediment buildup on the canal floor.
DiffWAM 是 arXiv 预印本提出的导航世界动作模型，它从冻结视频模型的中间预测表征中直接生成连续相机轨迹，部署时无需完成未来视频生成和几何重建。在自建 DiffWAM-1000 基准上，DiffWAM 轨迹 RMSE 为 0.3492 米，端点成功率为 74.40%；机载 DiffWAM-Flash 在 NVIDIA Jetson AGX Thor 上模型管道延迟为 1.08 秒。该工作表明预测视频表征可被高效地落地为连续三维运动，为生成再重建的导航管线提供了直接替代方案。
Vision-language-action (VLA) models can exceed 90% success on in-distribution tasks and withstand nuisance changes that preserve the required action, yet fail under counterfactual changes that demand a different action. Aggregate robustness scores can therefore conceal a more specific failure, in which a policy responds to both language and vision yet does not combine them to select the action the task requires.
We focus on legible robot motion generation in social navigation settings. Legibility in human-robot interaction (HRI) is often described as the property of robot motion that enables an observer to confidently infer the robot's intent.
Voluntary movements have long been hypothesised to be comprised of discrete primitives called submovements, as a descriptive model of human motor behaviour. However, existing methods scale poorly, and no principled method exists to determine whether a decomposition is informative.
Egocentric human data provides a scalable source of experience for robot learning, but varies substantially in human-robot alignment, behavioral coverage, and available supervision. Existing work shows favorable scaling with increasing human data, but it remains unclear which data properties drive downstream robot gains and how to use such data throughout the training pipeline.
Continuum robots are well suited for gentle manipulation because of their inherent compliance and ability to adapt to complex environments. However, their continuously deformable structure makes accurate configuration estimation challenging, particularly when external vision systems are unavailable or obstructed.
Video generation models (VGMs) offer strong spatiotemporal priors for embodied observation--action modeling. However, joint-space action vectors lack explicit image-space structure and vary in dimensionality and semantics across embodiments, making it challenging to directly leverage the rich spatiotemporal priors of VGMs.
该预印本提出一种基于拓扑优化的多向软气动执行器（mdiSPA）系统设计方法，采用三场鲁棒公式和达西定律建模压力载荷，并用MMA求解。优化得到的非传统气腔在Abaqus仿真中表现出多方向弯曲，由三臂构成的夹持器可沿不同方向自适应抓取。研究基于数值模拟，尚未进行实物制造或实验验证。
Marine litter is a growing threat to the underwater ecosystem, driving demand for autonomous survey methods that can locate debris efficiently over large areas. Existing survey methods typically follow predefined paths or operate with a single sensing modality, typically a camera (with image quality suffering in poor-visibility conditions) or sonar (usually noisy and low-resolution).
World-action models (WAMs) augment robot policies with action-conditioned environment dynamics, yet existing approaches largely rely on future observation reconstruction or generic latent prediction and lack structured, control-oriented world representations tightly coupled with action generation. We introduce Magic-W0, a world-action foundation model that jointly models structured physical state evolution and continuous actions.
这是一篇预印本论文。作者提出 GroundingPI，一个基于点和边界框等视觉基元的 4B 参数接地基础模型，在 34 个接地基准上达到 73.68% 平均得分，超过更大的 GPT-6 Astra（71.54%）。该模型作为视觉骨干用于机器人操作和自动驾驶时，在 RoboTwin 2.0 全部四个分布外设置中优于所有主流骨干，相对最强基线最高提升 24.8%，并在 RoboCasa-GR1 上以 50% 演示数据超过其他基线用 75% 数据的表现。这项工作表明专门的接地预训练可成为物理智能的感知基础，尤其适合系统1的快速执行。
该预印本提出统一框架，将局部全身VLA行为组合为场景级空中操作。在仿真中完成21/50个跨站点任务（42.0%），物理平台验证了2/5次取水浇花任务。关键贡献包括无需真实平台演示的合成训练、MPAR对齐异步动作块，以及场景图引导的可行交接与拓扑转移。
We present PrefPI (Preference-Guided Policy Iteration), an iterative framework for steering pretrained generative robot policies using only relative preferences over self-generated trajectories. Unlike prior preference-learning methods that primarily sharpen modes already represented by the policy, we study steering beyond the initial effective support, where desired behaviors are rarely or never observed under the initial policy.
Vision-Language Navigation (VLN) requires embodied agents to generate actions based on instructions and observations. General-purpose multimodal agents offer a promising basis for this task, but selecting plausible local actions does not ensure that execution remains consistent with the intended route, particularly in long-horizon tasks.
MVP-SLAM是一篇预印本，提出一种多相机视觉惯性SLAM系统，利用建筑楼层平面图在线校正漂移。在Hilti–Trimble SLAM Challenge 2026中，它在Localization任务以0.29米平均RMSE排名第2，SLAM任务以0.24米排名第5，是所有在线运行、整合平面图并定位到楼层平面图中的方法中成绩最好的。这项工作表明，仅靠相机和IMU也能在施工场景利用平面图先验在线持续抑制累积误差。
这篇预印本提出一种由8×8个3自由度Delta机器人和弹性膜组成的分布式操控系统，通过将64个离散接触点变成连续表面，消除了执行器间距对物体尺寸的下限。在硬件上，该系统可操控15至90毫米的物体，跨度是执行器间距43.3毫米的六倍范围；强化学习策略在仿真中命令19个Delta邻域达到95.1%成功率，并在未调整的情况下以76%成功率迁移到真机。
Cable-suspended aerial manipulation offers a lightweight architecture for cooperative transportation and physical interaction, yet the passive mechanical response perceived at the load remains insufficiently understood and systematically exploited. This work interprets aerial vehicles as movable compliant anchors and develops a gravity-aware quasi-static theory for predicting and shaping the passive Cartesian stiffness of a suspended load.
这是一篇预印本。作者针对视觉多无人机飞行中仅用位置测量导致高阶状态估计延迟的问题，提出融合视觉检测器提供的倾斜信息，并设计了一种线性推力约束卡尔曼滤波器。在三个数据集上，姿态感知估计将速度和加速度误差平均降低40%和57%，闭环仿真中支持超过2g的横向机动跟踪。
机器人AI模型每次预测一段未来动作，执行多少步之后再重新观察环境，过去大多由工程师手动设为固定值。清华大学、北京智源人工智能研究院（BAAI）等机构发布的这篇预印本提出一个即插即用模块，在运行中自动决定这一步数，无需重新训练，就提升了Physical Intelligence和英伟达现有模型在仿真和真实双臂机器人上的成功率。
论文来自 arXiv 机器人领域。尚未生成摘要的论文，显示摘要开头部分。