cs.RO（2026-06-04）

📊 共 31 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) 支柱二：RL算法与架构 (RL & Architecture) (5) 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 HANDOFF: Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers 提出HANDOFF以解决人形机器人全身控制的指令空间问题 humanoid humanoid robot whole-body control
2 Sample-efficient Low-level Motion Planning for Robotic Manipulation Tasks via Zero-shot Transfer Learning 提出iCEM+TL框架以解决复杂机器人运动规划问题 manipulation motion planning zero-shot transfer
3 TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies 提出TempoVLA以解决机器人操作速度控制问题 manipulation reinforcement learning vision-language-action
4 TAM: Torque Adaptation Module for Robust Motion Transfer in Manipulation 提出扭矩适应模块TAM以解决机器人运动转移问题 manipulation sim-to-real domain randomization
5 Accelerating and Scaling MPC-Guided Reinforcement Learning for Humanoid Locomotion and Manipulation 提出MPC-RL以加速和扩展类人机器人运动控制 humanoid humanoid locomotion locomotion ✅
6 AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding 提出AffordanceVLA以解决视觉语言模型与动作策略间的结构不匹配问题 manipulation affordance affordance-aware
7 MotionDisco: Motion Discovery for Extreme Humanoid Loco-Manipulation 提出MotionDisco以解决极端人形机器人运动发现问题 humanoid humanoid robot manipulation
8 PiL-World: A Chunk-Wise World Model for VLA Policy-in-the-Loop Evaluation 提出PiL-World以解决闭环VLA评估问题 manipulation dual-arm world model
9 LadderMan: Learning Humanoid Perceptive Ladder Climbing 提出LadderMan以解决人形机器人爬梯子问题 humanoid humanoid robot motion tracking
10 TAGA: Terrain-aware Active Gaze Learning for Generalizable Agile Humanoid Locomotion 提出TAGA框架以解决复杂地形下人形机器人运动控制问题 humanoid humanoid control humanoid locomotion
11 RealDexUMI: A Wearable Universal Manipulation Interface for Dexterous Robot Learning 提出RealDexUMI以解决灵巧机器人学习中的操作界面问题 manipulation dexterous hand dexterous manipulation
12 L-SDPPO: Policy Optimization of Spiking Diffusion Policy for Intra-vehicular Robotic Manipulation 提出L-SDPPO以解决航天器内机器人操作的能量消耗问题 manipulation reinforcement learning diffusion policy
13 Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation 提出跨层分析框架以提升长时间任务中的安全性 manipulation embodied AI
14 Multi-Resolution Tactile Imitation Learning for Contact-Rich Robotic Manipulation 提出多分辨率触觉模仿学习以解决接触丰富的机器人操控问题 manipulation imitation learning flow matching
15 Towards a Data Flywheel for Embodied Intelligence in Logistics 构建物流领域的智能数据飞轮以提升机器人操作能力 manipulation policy learning imitation learning
16 DexFuture: Hierarchical Future-State Visuomotor Targeting for Bimanual Dexterous Tool Use 提出DexFuture以解决双手灵巧工具使用中的动态一致性问题 bi-manual world model world models
17 AxisGuide: Grounding Robot Action Coordinate System in RGB Observations for Robust Visuomotor Manipulation 提出AxisGuide以解决机器人动作坐标系统理解不足问题 manipulation behavior cloning scene understanding
18 PhyRoGen: Synthetic Generation of Physical Robot Manipulation Puzzles Using Procedural Content Generation 提出PhyRoGen以解决机器人操控物理拼图数据集生成问题 manipulation foundation model
19 A Conversational Framework for Human-Robot Collaborative Manipulation with Distributed Generative AI models 提出分布式对话框架以解决人机协作操作问题 manipulation visual grounding ✅
20 Merging model-based control with multi-agent reinforcement learning for multi-agent cooperative teaming strategies 提出多智能体演员-评论家模型预测控制以解决协作任务中的安全性问题 MPC model predictive control reinforcement learning
21 ActiveMimic: Egocentric Video Pretraining with Active Perception 提出ActiveMimic以解决人类视频预训练不足问题 manipulation egocentric
22 What Matters When Cotraining Robot Manipulation Policies on Everyday Human Videos? 提出基于日常视频的机器人操作策略协同训练方法 manipulation
23 Flow-based Policy Adaptation without Policy Updates 提出GLOVES以解决机器人技能适应性不足问题 shared control foundation model
24 VOLT: Vision and Language Trajectory Segmentation for Faster-than-Demonstration Policies 提出VOLT以解决机器人任务加速执行问题 manipulation imitation learning diffusion policy
25 Optimal Control Approach for Non-prehensile Ball Juggling Using a 7-DoF Manipulator 提出基于最优控制的7自由度机械手非抓取式球类 juggling 方法 manipulation

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
26 MPCoT: Reward-Guided Multi-Path Latent Reasoning for Test-Time Scalable Vision-Language-Action 提出MPCoT以解决长时间跨度和高不确定性控制中的脆弱性问题 world model world models vision-language-action
27 Robots Need More than VLA and World Models 提出新机制以提升机器人从非结构化数据中学习能力 policy learning world model world models
28 World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis 提出世界-语言-动作模型以实现统一的世界建模与任务推理 world model world models egocentric
29 Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning 提出Discrete-WAM以解决自主驾驶中的因果推理问题 policy learning world model world models
30 Auditing Demonstration Curation Metrics: Action-Only Scorers Fail on the Structural Defects That Degrade Imitation Policies 提出审计演示策划指标以解决模仿学习中的结构缺陷问题 imitation learning behavior cloning

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

#题目一句话要点标签🔗⭐
31 SCOUT: Semantic scene COverage via Uncertainty-guided Traversal 提出SCOUT框架以解决机器人场景理解不足问题 semantic mapping semantic map open-vocabulary

⬅️ 返回 cs.RO 首页 · 🏠 返回主页