cs.RO（2026-04-23）

📊 共 20 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (13) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱八：物理动画 (Physics-based Animation) (1) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱一：机器人控制 (Robot Control) (13 篇)

#题目一句话要点标签🔗⭐
1 X2-N: A Transformable Wheel-legged Humanoid Robot with Dual-mode Locomotion and Manipulation X2-N：一种可变形轮腿式人形机器人，具备双模态运动和操作能力 legged robot legged locomotion humanoid
2 Long-Horizon Manipulation via Trace-Conditioned VLA Planning LoHo-Manip：基于轨迹条件VLA规划的长程操作框架 manipulation vision-language-action VLA
3 Learn Weightlessness: Imitate Non-Self-Stabilizing Motions on Humanoid Robot 提出基于“失重机制”的模仿学习方法，实现人型机器人非自稳运动 humanoid humanoid robot humanoid control
4 RPG: Robust Policy Gating for Smooth Multi-Skill Transitions in Humanoid Fighting 提出RPG框架，实现人形机器人格斗中平滑多技能过渡 humanoid humanoid robot whole-body control
5 FingerViP: Learning Real-World Dexterous Manipulation with Fingertip Visual Perception FingerViP：利用指尖视觉感知学习真实世界灵巧操作 manipulation dexterous manipulation contact-aware
6 How VLAs (Really) Work In Open-World Environments 分析VLA在开放世界环境中的真实表现，揭示现有评估方法的局限性 manipulation vision-language-action VLA
7 VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis VistaBot：提出时空感知视图合成方法，提升机器人操作的视角鲁棒性 manipulation spatiotemporal
8 Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training Hi-WM：利用世界模型实现可扩展的机器人后训练，提升人机协作效率。 manipulation world model world models
9 A Replicable Robotics Awareness Method Using LLM-Enabled Robotics Interaction: Evidence from a Corporate Challenge 提出基于LLM的人机交互方法，提升非专业人士对机器人技术的认知 humanoid humanoid robot embodied AI
10 Wiggle and Go! System Identification for Zero-Shot Dynamic Rope Manipulation 提出Wiggle and Go!，通过系统辨识实现绳索零样本动态操作。 manipulation
11 MISTY: High-Throughput Motion Planning via Mixer-based Single-step Drifting MISTY：基于Mixer的单步漂移动作规划，实现高吞吐量自动驾驶。 motion planning
12 Dynamic Coupling and Indirect Control of Jointed Robots Rolling Atop A Moving Platform 研究移动平台上双连杆滚动机器人的动态耦合与间接控制方法 locomotion
13 Full-Body Dynamic Safety for Robot Manipulators: 3D Poisson Safety Functions for CBF-Based Safety Filters 提出基于3D泊松安全函数的CBF安全滤波器，实现机器人机械臂全身动态安全避障 manipulation

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

#题目一句话要点标签🔗⭐
14 TRACE: Topology-aware Reconstruction of Accidents in CARLA for AV Evaluation 提出TRACE以解决自动驾驶车辆评估中的事故重建问题 large language model
15 SNGR: Selective Non-Gaussian Refinement for Ambiguous SLAM Factor Graphs SNGR：用于解决模糊SLAM因子图问题的选择性非高斯优化 multimodal
16 A Deployable Embodied Vision-Language Navigation System with Hierarchical Cognition and Context-Aware Exploration 提出一种可部署的视觉语言导航系统以解决智能机器人导航效率问题 VLN

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
17 DM$^3$-Nav: Decentralized Multi-Agent Multimodal Multi-Object Semantic Navigation 提出DM$^3$-Nav，解决多智能体多模态多目标语义导航中的去中心化协同问题 open-vocabulary open vocabulary multimodal
18 Reasoning About Traversability: Language-Guided Off-Road 3D Trajectory Planning 提出语言引导的越野三维轨迹规划方法，提升复杂地形的自主导航能力 traversability

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

#题目一句话要点标签🔗⭐
19 From Noise to Intent: Anchoring Generative VLA Policies with Residual Bridges ResVLA：通过残差桥接锚定生成式VLA策略，提升具身智能控制 spatiotemporal VLA

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

#题目一句话要点标签🔗⭐
20 CorridorVLA: Explicit Spatial Constraints for Generative Action Heads via Sparse Anchors CorridorVLA：通过稀疏锚点显式空间约束生成动作头，提升VLA模型性能 flow matching VLA multimodal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页