cs.RO（2026-06-10）

📊 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) (22 🔗4) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱一：机器人控制 (Robot Control) (22 篇)

#题目一句话要点标签🔗⭐
1 DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action model 提出DAM-VLA以解决多模态视觉语言动作模型的时序不匹配问题 manipulation vision-language-action VLA ✅
2 Blind Dexterous Grasping via Real2Sim2Real Tactile Policy Learning 提出盲抓取框架以解决触觉信号稀疏问题 manipulation dexterous hand sim-to-real
3 Bridging the Morphology Gap: Adapting VLA Models to Dexterous Manipulation via Intent-Conditioned Fine-Tuning 提出InDex框架以解决VLA模型在灵巧操作中的适应性问题 manipulation dexterous hand dexterous manipulation
4 DuoBench: A Reproducible Benchmark for Bimanual Manipulation in Simulation and the Real World 提出DuoBench以解决双臂机器人操作基准测试的挑战 manipulation bi-manual dual-arm
5 Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-Manipulation 提出双重评论者架构以提升类人机器人运动与操作的效率 humanoid humanoid robot locomotion
6 TacCoRL: Integrating Tactile Feedback into VLA via Simulation 提出TacCoRL框架以解决视觉语言行动模型中的触觉反馈缺失问题 manipulation bi-manual reinforcement learning
7 World Pilot: Steering Vision-Language-Action Models with World-Action Priors 提出World Pilot以解决VLA模型在动态操作中的局限性 manipulation world model world models
8 APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies 提出APT以改善视觉-语言-动作策略的指令泛化能力 manipulation vision-language-action VLA ✅
9 VICX: Generalizable Robot Manipulation via Video Generation and In-Context Operator Network 提出VICX框架以解决机器人操作的泛化问题 manipulation cross-embodiment embodiment transfer ✅
10 KinematicRL: A Sim-to-Real Reinforcement Learning Framework For Social Navigation With Kinodynamic Feasibility 提出KinematicRL框架以解决社交导航中的动态可行性问题 sim-to-real reinforcement learning deep reinforcement learning
11 Learning Object Manipulation from Scratch via Contrastive Interaction 提出交互加权重采样以解决对象操作中的动态变化问题 locomotion manipulation sim-to-real
12 Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics 提出环境扩散策略以解决机器人模仿学习中的次优数据问题 sim-to-real imitation learning diffusion policy
13 FACTR 2: Learning External Force Sensing for Commodity Robot Arms Improves Policy Learning 提出NEXT与FIRST以提升低成本机器人臂的政策学习能力 manipulation teleoperation policy learning
14 Human-Guided Co-Manipulation of Carbon Fiber Plies 提出多模态控制方法以解决碳纤维层的协同操作问题 manipulation multimodal
15 DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners? 提出DIRECT框架以优化嵌入式规划中的测试时间计算分配 manipulation multimodal chain-of-thought
16 Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends 提出智能自动化方法以构建具身基准，解决评估瓶颈问题 manipulation foundation model multimodal
17 LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition 提出LUCID框架以从非结构化人类视频中学习机器人技能 manipulation dexterous hand zero-shot transfer ✅
18 UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning 提出UniIntervene以解决人机协作强化学习中的干预成本问题 manipulation reinforcement learning
19 Fibration Trees: A Unified Approach to Multi-Robot Motion Planning 提出纤维树以统一解决多机器人运动规划问题 motion planning
20 Learning Unions of Convex Sets via Invertible Latent Decomposition for Path Planning 提出可逆潜在分解以解决碰撞自由路径规划问题 manipulation bi-manual implicit representation
21 MPPI-based Informative Trajectory Planning for Search and Capture of Drifting Targets with ASVs 提出基于MPPI的轨迹规划方法以解决漂流目标搜索与捕获问题 model predictive control spatiotemporal
22 Deformable In-Hand Slip-Aware Tactile Sensor with Integrated Velocity, Force/Torque, and Pressure Map Sensing 提出一种变形的触觉传感器以解决滑动感知问题 manipulation in-hand manipulation

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

#题目一句话要点标签🔗⭐
23 Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering 提出交互式语言序列搜索框架以提升VLA任务性能 vision-language-action VLA
24 CHORUS: Decentralized Multi-Embodiment Collaboration with One VLA Policy 提出CHORUS框架以解决多机器人协作中的信息共享问题 vision-language-action VLA
25 SAFER-Nav: Enhancing Safety for Visual Robot Navigation via Segmentation-Aware Fine-Tuning 提出SAFER-Nav以解决视觉机器人导航安全性问题 foundation model

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

#题目一句话要点标签🔗⭐
26 DrivingAgent: Design and Scheduling Agents for Autonomous Driving Systems 提出DrivingAgent以解决自主驾驶系统设计与调度问题 reinforcement learning large language model foundation model
27 Distortion-Resilient Robotic Imitation Learning for Autonomous Cable Routing 提出一种抗失真机器人模仿学习框架以解决电缆布线问题 imitation learning

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
28 Traceable Virtual Sea Trials in the Marine Robotics Unity Simulator for Manoeuvring Assessment of Unmanned Surface Vehicles 提出标准化虚拟海试框架以提升无人水面艇操控评估 IMoS

⬅️ 返回 cs.RO 首页 · 🏠 返回主页