cs.RO（2026-03-11）

📊 共 28 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (24 🔗4) 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) (24 篇)

#题目一句话要点标签🔗⭐
1 Contact Coverage-Guided Exploration for General-Purpose Dexterous Manipulation 提出接触覆盖引导探索(CCGE)，用于通用灵巧操作任务，提升探索效率和成功率。 locomotion manipulation dexterous hand
2 Cybo-Waiter: A Physical Agentic Framework for Humanoid Whole-Body Locomotion-Manipulation 提出Cybo-Waiter框架，解决人型机器人在复杂环境中长时程操作任务的鲁棒性问题 humanoid humanoid locomotion locomotion
3 RL-Augmented MPC for Non-Gaited Legged and Hybrid Locomotion 提出RL增强的MPC架构，用于非步态足式和混合运动控制 humanoid humanoid robot locomotion ✅
4 SteadyTray: Learning Object Balancing Tasks in Humanoid Tray Transport via Residual Reinforcement Learning 提出ReST-RL，解决人形机器人动态行走中托盘平衡问题 humanoid bipedal biped
5 FG-CLTP: Fine-Grained Contrastive Language Tactile Pretraining for Robotic Manipulation 提出FG-CLTP以解决机器人精细操作中的触觉感知不足问题 manipulation sim-to-real flow matching
6 Learning Bimanual Cloth Manipulation with Vision-based Tactile Sensing via Single Robotic Arm 提出Touch G.O.G.，利用单臂机器人和视觉触觉进行双手动布料操作 manipulation bi-manual dual-arm
7 DepthCache: Depth-Guided Training-Free Visual Token Merging for Vision-Language-Action Model Inference 提出DepthCache，利用深度信息加速VLA模型推理，提升机器人操作效率。 manipulation vision-language-action VLA
8 FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model FutureVLA：面向视觉-语言-动作模型的联合视动预测，提升具身智能体未来预判能力。 manipulation predictive model vision-language-action
9 DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control DiT4DiT：通过联合建模视频动态和动作，实现通用机器人控制 manipulation Unitree policy learning ✅
10 Dynamic Modeling and Attitude Control of a Reaction-Wheel-Based Low-Gravity Bipedal Hopper 提出基于反作用轮的低重力双足跳跃机器人姿态动态建模与控制方法 bipedal biped locomotion
11 BinWalker: Development and Field Evaluation of a Quadruped Manipulator Platform for Sustainable Litter Collection BinWalker：用于可持续垃圾收集的四足机器人操作平台开发与实地评估 quadruped legged robot legged locomotion ✅
12 SUBTA: A Framework for Supported User-Guided Bimanual Teleoperation in Structured Assembly SUBTA：结构化装配中支持用户引导的双臂遥操作框架 bi-manual teleoperation
13 FAR-Dex: Few-shot Data Augmentation and Adaptive Residual Policy Refinement for Dexterous Manipulation FAR-Dex：基于少量数据增强和自适应残差策略优化的灵巧操作框架 manipulation dexterous manipulation
14 Interleaving Scheduling and Motion Planning with Incremental Learning of Symbolic Space-Time Motion Abstractions 提出增量学习的调度与运动规划框架以解决多目标导航问题 motion planning task and motion planning
15 AdaClearGrasp: Learning Adaptive Clearing for Zero-Shot Robust Dexterous Grasping in Densely Cluttered Environments AdaClearGrasp：学习自适应清理，实现零样本鲁棒灵巧抓取 manipulation sim-to-real reinforcement learning ✅
16 PPGuide: Steering Diffusion Policies with Performance Predictive Guidance PPGuide：利用性能预测指导扩散策略，提升机器人操作的鲁棒性 manipulation diffusion policy world model
17 ASTER: Attitude-aware Suspended-payload Quadrotor Traversal via Efficient Reinforcement Learning ASTER：基于强化学习实现姿态感知的悬挂负载四旋翼飞行器敏捷穿越 sim-to-real reinforcement learning
18 MAVEN: A Meta-Reinforcement Learning Framework for Varying-Dynamics Expertise in Agile Quadrotor Maneuvers 提出MAVEN元强化学习框架，解决四旋翼飞行器动态变化下的敏捷导航问题 sim-to-real reinforcement learning
19 Adaptive Manipulation Potential and Haptic Estimation for Tool-Mediated Interaction 提出基于自适应操作势和触觉估计的工具辅助操作框架 manipulation
20 Parallel-in-Time Nonlinear Optimal Control via GPU-native Sequential Convex Programming 提出一种基于GPU原生序列凸规划的并行时域非线性最优控制方法 model predictive control trajectory optimization
21 Rethinking Gaussian Trajectory Predictors: Calibrated Uncertainty for Safe Planning 提出基于核密度估计的校准损失函数，提升高斯轨迹预测器在安全规划中的不确定性置信度。 model predictive control motion planning
22 Learning Adaptive Force Control for Contact-Rich Sample Scraping with Heterogeneous Materials 提出一种自适应力控制框架，用于异构材料样本刮取任务 manipulation reinforcement learning
23 GRACE: A Unified 2D Multi-Robot Path Planning Simulator & Benchmark for Grid, Roadmap, And Continuous Environments GRACE：用于网格、路标和连续环境的统一2D多机器人路径规划模拟器与基准测试平台 motion planning
24 TacLoc: Global Tactile Localization on Objects from a Registration Perspective TacLoc：提出一种基于点云配准的物体全局触觉定位方法 manipulation

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

#题目一句话要点标签🔗⭐
25 ScanDP: Generalizable 3D Scanning with Diffusion Policy 提出基于扩散策略的ScanDP框架，提升3D扫描的泛化性和数据效率 reinforcement learning imitation learning diffusion policy
26 COHORT: Hybrid RL for Collaborative Large DNN Inference on Multi-Robot Systems Under Real-Time Constraints COHORT：混合强化学习解决多机器人系统实时约束下协同DNN推理问题 reinforcement learning policy learning PPO
27 MapGCLR: Geospatial Contrastive Learning of Representations for Online Vectorized HD Map Construction 提出MapGCLR，通过地理空间对比学习提升在线矢量化高清地图构建效果 contrastive learning

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

#题目一句话要点标签🔗⭐
28 AsyncMDE: Real-Time Monocular Depth Estimation via Asynchronous Spatial Memory AsyncMDE：通过异步空间记忆实现实时单目深度估计，适用于边缘机器人 depth estimation monocular depth foundation model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页