cs.RO（2026-06-09）

📊 共 33 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (25 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱六：视频提取与匹配 (Video Extraction) (1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (25 篇)

#题目一句话要点标签🔗⭐
1 OMG: Omni-Modal Motion Generation for Generalist Humanoid Control 提出OMG以解决通用人形机器人控制的多模态运动生成问题 humanoid humanoid robot humanoid control
2 GuideWalk: Learning Unified Autonomous Navigation and Locomotion for Humanoid Robots across Versatile Terrains 提出GuideWalk以解决人形机器人在多样地形中的导航问题 humanoid humanoid robot humanoid locomotion
3 TacForeSight: Force-Guided Tactile World Model for Contact-Rich Manipulation 提出TacForeSight以解决动态接触操作中的感知与控制问题 manipulation imitation learning world model ✅
4 RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement Learning 提出RoboNaldo以解决人形机器人足球射门稳定性与准确性问题 humanoid motion tracking locomotion
5 MARCH: Model-Assisted Reinforcement Learning for the Perceptive Control of Humanoids over Sparse Footholds 提出模型辅助强化学习以解决稀疏足迹上的人形机器人控制问题 humanoid humanoid robot bipedal
6 MV-Actor: Aligning Multi-View Semantics and Spatial Awareness for Bimanual Manipulation 提出MV-Actor以解决双手操作中的多视角语义与空间感知问题 manipulation bi-manual bimanual manipulation
7 Hand-centric Human-to-Robot Trajectory Transfer from Video Demonstrations via Open-World Contact Localization 提出HOWTransfer以解决人类视频演示中的轨迹转移问题 manipulation contact-aware motion retargeting
8 AgniNav: Configuration-Driven Cross-Embodiment Local Planning for Robot Navigation 提出AgniNav以解决机器人导航中的跨体态迁移问题 quadruped humanoid Unitree
9 HiMem-WAM: Hierarchical Memory-Gated World Action Models for Robotic Manipulation 提出HiMem-WAM以解决长时间机器人操作中的记忆问题 manipulation world action model world action models
10 What Matters in Orchestrating Robot Policies: A Systematic Study of Hierarchical VLA Agents 提出统一设计原则以优化层次化VLA机器人策略 manipulation vision-language-action VLA
11 Dexterous Point Policy: Learning Point-based Dexterous Hand Policies from Human Demonstrations 提出Dexterous Point Policy以解决机器人示范数据不足问题 manipulation dexterous hand dexterous manipulation
12 Locomotion analysis of a quadruped interacting with the lunar granular surface 提出基于强化学习的四足机器人月球表面行走分析方法 quadruped legged robot locomotion
13 SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic Manipulation 提出SARM2以解决长时间操作中的奖励建模问题 manipulation reinforcement learning behavior cloning ✅
14 VeriSpace: Spatially Grounded Action Verification for Vision-Language-Action Models 提出VeriSpace以解决VLA模型的动作验证问题 manipulation vision-language-action VLA
15 IMPACT: Learning Internal-Model Predictive Control for Forceful Robotic Manipulation 提出IMPACT框架以解决机器人强力操控问题 manipulation model predictive control imitation learning
16 JOIN: Anchor-Grasp-Conditioned Joining via Opposition, Inference, and Navigation for Bimanual Assistive Manipulation 提出JOIN系统以解决双手辅助操作中的条件连接问题 manipulation bi-manual
17 EM-Fall: Embodied mmWave Sensing for Day-and-Night Fall Detection on Humanoid Robots 提出EM-Fall以解决居家环境中的跌倒检测问题 humanoid humanoid robot
18 UniDexTok: A Unified Dexterous Hand Tokenizer from Real Data 提出UniDexTok以解决灵巧手数据碎片化问题 manipulation dexterous hand cross-embodiment
19 Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion Policies 提出TAKO以解决机器人视觉政策的对抗性劫持问题 manipulation diffusion policy flow matching
20 GUIDE: Goal-Initialized Directional Understanding for End-to-End Visual Navigation 提出GUIDE框架以解决腿部机器人导航中的目标更新问题 quadruped legged robot reinforcement learning
21 A Spiking Neural Architecture for Coordinating Arm and Locomotor Control 提出一种脉冲神经网络架构以协调手臂与步态控制 humanoid humanoid robot bipedal
22 Vehicle Prediction Model for Enhanced MPC Path Tracking in Formula Student Driverless 提出实时预测模型以提升Formula Student Driverless的路径跟踪精度 MPC model predictive control
23 LieIPM: Lie Group Interior Point Method for Direct Trajectory Optimization of Rigid Bodies 提出LieIPM以解决刚体轨迹优化中的约束问题 trajectory optimization motion planning
24 UMI-Bench 1.0: An Open and Reproducible Real-World Benchmark for Tabletop Robotic Manipulation with UMI Data 提出UMI-Bench 1.0以解决真实环境下机器人操作评估问题 manipulation
25 Task Robustness via Re-Labelling Vision-Action Robot Data 提出TREAD框架以解决机器人任务鲁棒性问题 manipulation language conditioned

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

#题目一句话要点标签🔗⭐
26 Uncovering Vulnerability of Vision-Language-Action Models under Joint-Level Physical Faults 提出J-PARC以解决视觉-语言-动作模型在关节故障下的脆弱性问题 vision-language-action VLA
27 A Practical Recipe Towards Improving Sim-and-Real Correlation for VLA Evaluation 提出统一框架以提升视觉-语言-动作评估中的仿真与现实相关性 vision-language-action VLA
28 AgenticNav: Zero-Shot Vision-and-Language Navigation as a Tool-Calling Harness 提出AgenticNav以解决零-shot视觉语言导航中的工具调用问题 VLN

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

#题目一句话要点标签🔗⭐
29 AllDayNav: Lifelong Navigation via Real-World Reinforcement Learning 提出AllDayNav以解决动态环境中的终身导航问题 reinforcement learning scene understanding open-vocabulary
30 Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action Models 提出SALSA框架以解决安全社交导航问题 behavior cloning vision-language-action VLA

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
31 Hierarchical Policies from Verbal and Egocentric Human Signals for Natural Human-Robot Interaction 提出EDITH框架以解决人机交互中的非语言信号利用问题 egocentric first-person view

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
32 Gradient based Bilevel for Inverse Optimal Control, a Riemannian approach 提出Riemannian逆最优控制方法以解决传统方法的计算瓶颈问题 human motion

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

#题目一句话要点标签🔗⭐
33 Rethinking Embodied Navigation via Relational Inductive Bias 提出DB-Nav框架以解决对象导航中的信任问题 open-vocabulary open vocabulary

⬅️ 返回 cs.RO 首页 · 🏠 返回主页