cs.RO（2026-02-25）

📊 共 25 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (19 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (19 篇)

#题目一句话要点标签🔗⭐
1 Iterative Closed-Loop Motion Synthesis for Scaling the Capabilities of Humanoid Control 提出迭代闭环运动合成框架，提升物理仿真人形控制器的性能与泛化性 humanoid humanoid control motion synthesis
2 Humanizing Robot Gaze Shifts: A Framework for Natural Gaze Shifts in Humanoid Robots 提出RGS框架，实现人机交互中类人机器人的自然视线转移 humanoid humanoid robot motion generation
3 Biomechanical Comparisons Reveal Divergence of Human and Humanoid Gaits 提出步态差异分析框架，量化人与人形机器人运动的生物力学差异 legged robot humanoid humanoid control
4 LiLo-VLA: Compositional Long-Horizon Manipulation via Linked Object-Centric Policies LiLo-VLA：通过链接对象中心策略实现组合式长时程操作 manipulation vision-language-action VLA ✅
5 Tacmap: Bridging the Tactile Sim-to-Real Gap via Geometry-Consistent Penetration Depth Map Tacmap：通过几何一致的穿透深度图弥合触觉Sim-to-Real差距 manipulation sim-to-real reinforcement learning
6 Jumping Control for a Quadrupedal Wheeled-Legged Robot via NMPC and DE Optimization 提出基于NMPC和DE优化的轮腿式机器人跳跃控制方法，提升其运动灵活性。 quadruped legged robot locomotion
7 DexRepNet++: Learning Dexterous Robotic Manipulation with Geometric and Spatial Hand-Object Representations DexRepNet++：提出基于几何与空间表征的灵巧操作学习方法 manipulation dexterous manipulation bi-manual
8 Self-Correcting VLA: Online Action Refinement via Sparse World Imagination 提出自校正VLA模型，通过稀疏世界想象实现机器人动作在线优化。 manipulation reinforcement learning vision-language-action ✅
9 Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wild 提出JALA：通过联合对齐潜在动作，实现野外场景下可扩展的VLA预训练。 manipulation vision-language-action VLA
10 LessMimic: Long-Horizon Humanoid Interaction with Unified Distance Field Representations LessMimic：基于统一距离场表示的长时程人型机器人交互 humanoid humanoid robot reinforcement learning
11 World Guidance: World Modeling in Condition Space for Action Generation 提出WoG，通过条件空间中的世界建模提升视觉-语言-动作模型的动作生成能力 manipulation world model vision-language-action ✅
12 ADM-DP: Adaptive Dynamic Modality Diffusion Policy through Vision-Tactile-Graph Fusion for Multi-Agent Manipulation 提出ADM-DP框架，通过视觉-触觉-图融合实现多智能体协作操作 manipulation diffusion policy
13 Force Policy: Learning Hybrid Force-Position Control Policy under Interaction Frame for Contact-Rich Manipulation 提出Force Policy以解决接触丰富操作中的力与位置控制问题 manipulation
14 FlowCorrect: Efficient Interactive Correction of Generative Flow Policies for Robotic Manipulation FlowCorrect：高效交互式修正生成式流程策略，用于机器人操作 manipulation
15 Primary-Fine Decoupling for Action Generation in Robotic Imitation 提出主次解耦动作生成框架，解决机器人模仿学习中多模态动作序列生成问题 manipulation dexterous manipulation imitation learning
16 Learning Agile and Robust Omnidirectional Aerial Motion on Overactuated Tiltable-Quadrotors 提出基于强化学习的倾转旋翼无人机敏捷鲁棒全向运动控制方法 sim-to-real domain randomization reinforcement learning
17 Behavioral Cloning for Robotic Connector Assembly: An Empirical Study 提出基于行为克隆的机器人连接器装配方法，解决线束自动化难题 teleoperation
18 Dream-SLAM: Dreaming the Unseen for Active SLAM in Dynamic Environments Dream-SLAM：通过梦境生成未见区域，解决动态环境中主动SLAM问题 motion planning
19 Enhancing Cellular-enabled Collaborative Robots Planning through GNSS data for SAR Scenarios 提出基于GNSS数据的蜂窝协作机器人搜救规划框架，优化机器人部署。 quadruped

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

#题目一句话要点标签🔗⭐
20 Are Foundation Models the Route to Full-Stack Transfer in Robotics? 探索具身智能：基础模型驱动机器人全栈迁移学习 VLA foundation model
21 Hierarchical LLM-Based Multi-Agent Framework with Prompt Optimization for Multi-Robot Task Planning 提出基于层级LLM的多智能体框架，通过提示优化解决多机器人任务规划问题 large language model
22 SPOC: Safety-Aware Planning Under Partial Observability And Physical Constraints SPOC：部分可观测与物理约束下的安全感知规划基准 large language model ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#题目一句话要点标签🔗⭐
23 Self-Curriculum Model-based Reinforcement Learning for Shape Control of Deformable Linear Objects 提出基于自适应课程模型强化学习的柔性线性物体形状控制方法 reinforcement learning policy learning
24 System Design of the Ultra Mobility Vehicle: A Driving, Balancing, and Jumping Bicycle Robot 设计超高机动性车辆：一种可驾驶、平衡和跳跃的自行车机器人 reinforcement learning zero-shot transfer

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
25 DAGS-SLAM: Dynamic-Aware 3DGS SLAM via Spatiotemporal Motion Probability and Uncertainty-Aware Scheduling DAGS-SLAM：基于时空运动概率和不确定性感知的动态场景3DGS SLAM 3D gaussian splatting 3DGS gaussian splatting

⬅️ 返回 cs.RO 首页 · 🏠 返回主页