cs.RO（2025-10-02）

📊 共 27 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (23 🔗4) 支柱三：空间感知与语义 (Perception & Semantics) (3) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (23 篇)

#题目一句话要点标签🔗⭐
1 Retargeting Matters: General Motion Retargeting for Humanoid Motion Tracking 提出通用运动重定向(GMR)方法，提升人型机器人运动跟踪策略的鲁棒性和真实性。 humanoid humanoid robot domain randomization ✅
2 PolySim: Bridging the Sim-to-Real Gap for Humanoid Control via Multi-Simulator Dynamics Randomization PolySim：通过多模拟器动态随机化弥合人形机器人控制的Sim-to-Real差距 humanoid humanoid control whole-body control
3 Like Playing a Video Game: Spatial-Temporal Optimization of Foot Trajectories for Controlled Football Kicking in Bipedal Robots 针对双足机器人足球踢球，提出时空优化足部轨迹规划方法 quadruped legged robot humanoid
4 A Recipe for Efficient Sim-to-Real Transfer in Manipulation with Online Imitation-Pretrained World Models 提出基于世界模型的在线模仿预训练方法，提升机械臂操作的Sim-to-Real迁移效率 manipulation sim-to-real imitation learning
5 FailSafe: Reasoning and Recovery from Failures in Vision-Language-Action Models FailSafe：为视觉-语言-动作模型构建失败推理与恢复系统 manipulation vision-language-action VLA
6 ActiveUMI: Robotic Manipulation with Active Perception from Robot-Free Human Demonstrations ActiveUMI：通过机器人自由的人类演示进行主动感知的机器人操作 manipulation bi-manual bimanual manipulation
7 Contrastive Representation Regularization for Vision-Language-Action Models 提出机器人状态感知对比损失，提升视觉-语言-动作模型在机器人操作中的性能。 manipulation representation learning vision-language-action
8 SIMSplat: Predictive Driving Scene Editing with Language-aligned 4D Gaussian Splatting SIMSplat：提出基于语言对齐4D高斯溅射的预测性驾驶场景编辑方法 manipulation gaussian splatting splatting ✅
9 Performance-Guided Refinement for Visual Aerial Navigation using Editable Gaussian Splatting in FalconGym 2.0 提出基于可编辑高斯溅射和性能引导优化的视觉无人机导航方法 sim-to-real gaussian splatting splatting
10 Real-time Multi-Plane Segmentation Based on GPU Accelerated High-Resolution 3D Voxel Mapping for Legged Robot Locomotion 提出基于GPU加速高分辨率3D体素地图的实时多平面分割方法，用于提升腿式机器人运动性能。 legged robot locomotion height map
11 Symskill: Symbol and Skill Co-Invention for Data-Efficient and Real-Time Long-Horizon Manipulation SymSkill：用于数据高效和实时长时程操作的符号与技能协同发明 manipulation motion planning imitation learning
12 MiniBEE: A New Form Factor for Compact Bimanual Dexterity 提出MiniBEE以解决双手灵巧操作的复杂性问题 manipulation bi-manual bimanual manipulation
13 Do You Know Where Your Camera Is? View-Invariant Policy Learning with Camera Conditioning 提出相机条件View-Invariant策略学习，提升机器人操作任务中视角泛化能力 manipulation policy learning imitation learning ✅
14 SPARC: Spine with Prismatic and Revolute Compliance for Quadruped Robot SPARC：用于四足机器人的具有棱柱和旋转柔顺性的脊柱模块 quadruped legged locomotion locomotion
15 U-LAG: Uncertainty-Aware, Lag-Adaptive Goal Retargeting for Robotic Manipulation 提出U-LAG，解决机器人操作中感知滞后和不确定性下的目标重定位问题 manipulation motion retargeting
16 Efficient Optimal Path Planning in Dynamic Environments Using Koopman MPC 提出基于Koopman MPC的高效动态环境最优路径规划方法 MPC model predictive control
17 ARMADA: Autonomous Online Failure Detection and Human Shared Control Empower Scalable Real-world Deployment and Adaptation ARMADA：结合自主故障检测与人机共享控制，实现机器人部署与自适应的扩展 shared control imitation learning
18 LangGrasp: Leveraging Fine-Tuned LLMs for Language Interactive Robot Grasping with Ambiguous Instructions LangGrasp：利用微调LLM实现语言交互式机器人抓取，解决指令歧义问题 manipulation large language model ✅
19 ERUPT: An Open Toolkit for Interfacing with Robot Motion Planners in Extended Reality ERUPT：用于扩展现实中机器人运动规划交互的开放工具包 manipulation motion planning
20 Stand Up, NAO! Increasing the Reliability of Stand-Up Motions Through Error Compensation in Position Control 针对NAO机器人，提出基于误差补偿的站立运动可靠性提升方案 humanoid humanoid robot
21 Reducing Discomfort in Driving Simulators: Motion Cueing for Motion Sickness Mitigation 提出基于MPC的运动提示算法，降低驾驶模拟器中的晕动症 MPC model predictive control
22 UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies UMI-on-Air：提出具身感知引导的通用操作策略，解决空中机器人操作难题。 manipulation diffusion policy
23 Geometric Backstepping Control of Omnidirectional Tiltrotors Incorporating Servo-Rotor Dynamics for Robustness against Sudden Disturbances 针对倾转旋翼飞行器，提出考虑伺服-旋翼动态特性的几何反步控制，提升抗扰动能力。 actuator dynamics

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
24 RSV-SLAM: Toward Real-Time Semantic Visual SLAM in Indoor Dynamic Environments 提出RSV-SLAM，用于室内动态环境中实时语义视觉SLAM visual SLAM
25 Statistical Uncertainty Learning for Robust Visual-Inertial State Estimation 提出基于统计不确定性学习的鲁棒视觉惯性状态估计方法 VIO geometric consistency
26 GreenhouseSplat: A Dataset of Photorealistic Greenhouse Simulations for Mobile Robotics GreenhouseSplat：用于移动机器人的光照逼真温室模拟数据集 gaussian splatting splatting

🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)

#题目一句话要点标签🔗⭐
27 Gemini Robotics 1.5: Pushing the Frontier of Generalist Robots with Advanced Embodied Reasoning, Thinking, and Motion Transfer Gemini Robotics 1.5：通过具身推理、思考和运动迁移推进通用机器人前沿 vision-language-action VLA

⬅️ 返回 cs.RO 首页 · 🏠 返回主页