cs.RO（2026-05-26）

📊 共 16 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (12 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (12 篇)

#题目一句话要点标签🔗⭐
1 FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies FineVLA：用于可控视觉-语言-动作策略的细粒度指令对齐框架 manipulation dual-arm policy learning
2 Learning to Balance Motor Thermal Safety and Quadrupedal Locomotion Performance with Residual Policy 提出基于残差策略的强化学习框架，平衡四足机器人运动性能与电机热安全 quadruped legged robot locomotion
3 Can VLA Models Learn from Real-World Data Continually without Forgetting? 构建真实世界VLA持续学习数据集，揭示灾难性遗忘并探索经验回放的有效性。 manipulation vision-language-action VLA
4 TCBiRRT: Rapid Motion Planning for Tightly Coupled Dual-arm Space Manipulator Using Task-space Random Expansion 提出TCBiRRT算法，解决紧耦合双臂空间机械臂在轨组装运动规划难题。 dual-arm motion planning
5 Towards Shared Embodied Intelligence in Humanoid Robots through Optimization Development and Testing of the Human Aware ergoCub Robot 提出一种人机协作的具身智能架构，优化人机交互中人机工效学指标。 humanoid humanoid robot
6 HyperSim: A Holistic Sim-To-Real Framework For Robust Robotic Manipulation HyperSim：用于鲁棒机器人操作的整体Sim-to-Real框架 manipulation sim-to-real
7 On the Generalization Capabilities, Design Choices and Limitations of Keypoint Imitation Learning 探索关键点模仿学习的泛化能力，并提供设计指南与局限性分析。 manipulation imitation learning foundation model ✅
8 Efficient On-policy Visual-RL via Stochastic Decoupled Policy Gradient 提出随机解耦策略梯度(SDPG)，高效解决视觉强化学习中的样本效率问题。 locomotion manipulation dexterous manipulation
9 Robust Koopman Control Barrier Filters for Safe Actor-Critic Reinforcement Learning 提出鲁棒Koopman控制障碍过滤器以解决安全强化学习问题 locomotion reinforcement learning SAC ✅
10 Multi-Robot Box Transport over Different Surfaces with Decentralized Role-based Proportional Control 提出基于角色分配和比例控制的R2P2方法，解决多机器人协同搬运变质量箱体问题 manipulation motion planning task and motion planning
11 Provably Safe Motion Planning Under Unknown Disturbances 提出基于Wasserstein歧义管的运动规划算法，解决未知扰动下的机器人安全运动问题 motion planning
12 VR-DAgger: Immersive VR for Dexterous Data Collection and Uncertainty-Guided On-Policy Correction 提出VR-DAgger，利用沉浸式VR进行灵巧操作数据收集和不确定性引导的在线策略校正 manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
13 Heterogeneous AAV Logistics Task Allocation: A Reinforcement Learning Enhanced Overlapping Coalition Formation Game Approach 提出基于强化学习的重叠联盟形成博弈方法，解决异构AAV物流任务动态分配问题 reinforcement learning spatiotemporal
14 Riding the Shifting Potential: When Reactive Control Suffices for Multi-Goal Behavior 提出基于空空间投影的反应式控制，解决多目标任务中的局部极小值问题 diffusion policy world model world models
15 Trust, Geometry, and Rules: A Credibility-Aware Reinforcement Learning Framework for Safe USV Navigation under Uncertainty 提出一种可信度感知的强化学习框架，用于不确定性下安全无人艇导航。 reinforcement learning

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

#题目一句话要点标签🔗⭐
16 Object Pose and Shape Estimation for Grasping: Does it Work? 基于物体姿态和形状估计的抓取方法优于端到端抓取合成方法。 sam 3D SAM 3D language conditioned

⬅️ 返回 cs.RO 首页 · 🏠 返回主页