cs.RO（2026-01-20）

📊 共 13 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (8) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱一：机器人控制 (Robot Control) (8 篇)

#题目一句话要点标签🔗⭐
1 A General One-Shot Multimodal Active Perception Framework for Robotic Manipulation: Learning to Predict Optimal Viewpoint 提出一种通用单次多模态主动感知框架，用于机器人操作中的最优视角预测 manipulation sim-to-real domain randomization
2 DroneVLA: VLA based Aerial Manipulation 提出基于VLA的无人机空中操作系统，实现自然语言指令控制下的物体抓取与递送。 manipulation vision-language-action VLA
3 Communication-Free Collective Navigation for a Swarm of UAVs via LiDAR-Based Deep Reinforcement Learning 提出基于激光雷达和深度强化学习的无人机集群无通信自主导航方法 sim-to-real reinforcement learning deep reinforcement learning
4 RoboBrain 2.5: Depth in Sight, Time in Mind RoboBrain 2.5：通过时空监督学习，提升具身智能体的3D空间推理和时间建模能力。 manipulation spatiotemporal embodied AI
5 TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformers TwinBrainVLA：通过非对称混合Transformer释放通用VLM在具身任务中的潜力 manipulation flow matching vision-language-action
6 Active Cross-Modal Visuo-Tactile Perception of Deformable Linear Objects 提出基于主动跨模态视觉-触觉融合的柔性线性物体三维重建方法 manipulation foundation model
7 SandWorm: Event-based Visuotactile Perception with Active Vibration for Screw-Actuated Robot in Granular Media SandWorm：基于事件相机的振动触觉感知系统，用于颗粒介质中螺杆驱动机器人 locomotion
8 Group-Invariant Unsupervised Skill Discovery: Symmetry-aware Skill Representations for Generalizable Behavior 提出群不变技能发现框架，提升对称环境中无监督技能学习的泛化性与效率。 locomotion

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
9 LogicEnvGen: Task-Logic Driven Generation of Diverse Simulated Environments for Embodied AI LogicEnvGen：提出任务逻辑驱动的环境生成方法，提升具身智能体测试多样性 embodied AI large language model
10 Efficient Coordination with the System-Level Shared State: An Embodied-AI Native Modular Framework 提出ANCHOR框架，解决具身智能系统模块化部署中的解耦和鲁棒性问题 embodied AI
11 Zero-shot adaptable task planning for autonomous construction robots: a comparative study of lightweight single and multi-AI agent systems 提出基于轻量级LLM和VLM的多智能体系统，提升建筑机器人零样本任务规划能力。 large language model foundation model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
12 Diffusion-Guided Backdoor Attacks in Real-World Reinforcement Learning 提出扩散引导的后门攻击框架，提升真实机器人强化学习系统中的攻击成功率。 reinforcement learning

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
13 Sample Efficient Learning of Body-Environment Interaction of an Under-Actuated System 研究欠驱动机器人与环境交互，提出基于运动基元的运动策略学习方法 motion tracking

⬅️ 返回 cs.RO 首页 · 🏠 返回主页