cs.RO（2026-02-02）

📊 共 29 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (20 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱一：机器人控制 (Robot Control) (20 篇)

#题目一句话要点标签🔗⭐
1 A Closed-Form Geometric Retargeting Solver for Upper Body Humanoid Robot Teleoperation 提出SEW-Mimic，用于上肢人形机器人遥操作的闭式几何重定向解算器 humanoid humanoid robot manipulation
2 FD-VLA: Force-Distilled Vision-Language-Action Model for Contact-Rich Manipulation FD-VLA：用于接触式操作的力蒸馏视觉-语言-动作模型 manipulation dexterous manipulation distillation
3 RFS: Reinforcement learning with Residual flow steering for dexterous manipulation 提出RFS，通过残差流引导强化学习提升灵巧操作泛化性 manipulation dexterous manipulation reinforcement learning ✅
4 RAPT: Model-Predictive Out-of-Distribution Detection and Failure Diagnosis for Sim-to-Real Humanoid Robots RAPT：基于模型预测的分布外检测与故障诊断，用于Sim-to-Real人形机器人 humanoid humanoid robot humanoid control
5 World-Gymnast: Training Robots with Reinforcement Learning in a World Model World-Gymnast：利用世界模型中的强化学习训练机器人，提升泛化能力。 manipulation sim-to-real reinforcement learning
6 PRISM: Performer RS-IMLE for Single-pass Multisensory Imitation Learning PRISM：基于Performer RS-IMLE的单程多感官模仿学习策略 manipulation loco-manipulation Unitree
7 TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkour 提出TTT-Parkour以解决机器人在复杂地形上动态运动问题 humanoid humanoid robot locomotion
8 Flow Policy Gradients for Robot Control 提出基于Flow Matching的策略梯度方法，提升机器人控制任务性能 legged locomotion humanoid humanoid robot
9 HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos HumanX：从人类视频中学习敏捷且泛化的类人机器人交互技能 humanoid humanoid robot Unitree
10 From Knowing to Doing Precisely: A General Self-Correction and Termination Framework for VLA models VLA-SCT：面向VLA模型的自校正与终止通用框架，提升操作精度与任务完成度 manipulation vision-language-action VLA
11 Towards Exploratory and Focused Manipulation with Bimanual Active Perception: A New Problem, Benchmark and Strategy 提出探索与聚焦操作（EFM）问题，并设计双臂主动感知（BAP）策略 manipulation bi-manual imitation learning
12 Relationship-Aware Hierarchical 3D Scene Graph for Task Reasoning 提出关系感知的分层3D场景图，用于四足机器人任务推理。 quadruped semantic mapping semantic map
13 Bridging the Sim-to-Real Gap with multipanda ros2: A Real-Time ROS2 Framework for Multimanual Systems 提出multipanda_ros2以解决多机器人实时控制问题 dual-arm sim-to-real sim2real
14 Uncertainty-Aware Non-Prehensile Manipulation with Mobile Manipulators under Object-Induced Occlusion 提出CURA-PPO，解决移动机械臂非抓取操作中物体遮挡带来的不确定性问题 manipulation reinforcement learning PPO
15 SoMA: A Real-to-Sim Neural Simulator for Robotic Soft-body Manipulation SoMA：用于机器人软体操作的真实到仿真神经模拟器 manipulation
16 A Unified Control Architecture for Macro-Micro Manipulation using a Active Remote Center of Compliance for Manufacturing Applications 提出一种宏微操作一体化控制架构，利用主动遥控柔顺中心提升制造应用性能。 manipulation
17 GSR: Learning Structured Reasoning for Embodied Manipulation GSR：学习具身操作的结构化推理，提升泛化性和长时任务完成度 manipulation
18 AgenticLab: A Real-World Robot Agent Platform that Can See, Think, and Act AgenticLab：一个具备视觉、思考和行动能力的真实世界机器人代理平台 manipulation open-vocabulary open vocabulary
19 Tilt-Ropter: A Novel Hybrid Aerial and Terrestrial Vehicle with Tilt Rotors and Passive Wheels Tilt-Ropter：一种新型倾转旋翼混合陆空飞行器，实现高效多模态运动 locomotion model predictive control
20 BTGenBot-2: Efficient Behavior Tree Generation with Small Language Models BTGenBot-2：利用小型语言模型高效生成行为树，用于机器人任务规划 manipulation

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

#题目一句话要点标签🔗⭐
21 TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments 提出TIC-VLA模型，解决动态环境中机器人导航的语义推理延迟问题 reinforcement learning imitation learning vision-language-action ✅
22 UniDWM: Towards a Unified Driving World Model via Multifaceted Representation Learning UniDWM：通过多方面表征学习构建统一的驾驶世界模型 world model representation learning ✅
23 ForSim: Stepwise Forward Simulation for Traffic Policy Fine-Tuning ForSim：用于交通策略微调的逐步前向仿真方法 imitation learning spatiotemporal multimodal ✅

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

#题目一句话要点标签🔗⭐
24 Multimodal Large Language Models for Real-Time Situated Reasoning 结合GPT-4o与TurtleBot 4，实现机器人实时情境推理与价值对齐决策 large language model multimodal
25 Concept-Based Dictionary Learning for Inference-Time Safety in Vision Language Action Models 提出基于概念字典学习的VLA模型推理时安全控制方法 vision-language-action VLA multimodal
26 3D Foundation Model-Based Loop Closing for Decentralized Collaborative SLAM 基于3D基础模型的去中心化协同SLAM闭环检测方法 foundation model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#题目一句话要点标签🔗⭐
27 LIEREx: Language-Image Embeddings for Robotic Exploration LIEREx：利用语言-图像嵌入实现机器人自主探索 semantic map foundation model
28 Multi-Task Learning for Robot Perception with Imbalanced Data 提出一种多任务学习方法，解决机器人感知中数据不平衡问题。 depth estimation

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
29 Frictional Contact Solving for Material Point Method 提出基于ADMM的MPM摩擦接触求解方法，提升机器人等领域仿真精度与鲁棒性 penetration PULSE

⬅️ 返回 cs.RO 首页 · 🏠 返回主页