cs.RO（2025-08-14）

📊 共 18 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (10 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (10 篇)

#题目一句话要点标签🔗⭐
1 MLM: Learning Multi-task Loco-Manipulation Whole-Body Control for Quadruped Robot with Arm 提出MLM框架，解决带机械臂的四足机器人多任务全身运动操作控制问题 quadruped whole-body control manipulation
2 MASH: Cooperative-Heterogeneous Multi-Agent Reinforcement Learning for Single Humanoid Robot Locomotion 提出MASH方法以优化单一类人机器人运动控制 humanoid humanoid robot humanoid locomotion
3 Hybrid Data-Driven Predictive Control for Robust and Reactive Exoskeleton Locomotion Synthesis 提出混合数据驱动预测控制，实现外骨骼稳健和反应式步态合成 bipedal biped locomotion
4 3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulation 提出3D FlowMatch Actor，加速3D机器人操作策略学习，并在单双臂任务上取得领先。 manipulation bi-manual dual-arm
5 ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver ReconVLA：提出重建式视觉-语言-动作模型，提升机器人感知能力 manipulation vision-language-action VLA ✅
6 GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement Learning GenFlowRL：利用生成式对象中心光流塑造奖励，提升视觉强化学习性能 manipulation reinforcement learning cross-embodiment ✅
7 Robot Policy Evaluation for Sim-to-Real Transfer: A Benchmarking Perspective 提出机器人策略评估基准，提升模拟到真实环境的策略迁移能力 manipulation sim-to-real
8 GhostObjects: Instructing Robots by Manipulating Spatially Aligned Virtual Twins in Augmented Reality 通过操控虚拟双胞胎GhostObjects指导机器人以解决人机交互问题 manipulation teleoperation
9 Utilizing Vision-Language Models as Action Models for Intent Recognition and Assistance 利用视觉-语言模型增强机器人意图识别与辅助能力 manipulation
10 Learning Stack-of-Tasks Management for Redundant Robots 提出基于遗传编程的Stack-of-Tasks学习框架，用于冗余机器人控制 dual-arm

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
11 Large Model Empowered Embodied AI: A Survey on Decision-Making and Embodied Learning 综述：大模型赋能的具身智能，聚焦决策制定与具身学习 reinforcement learning imitation learning world model
12 Few-shot Vision-based Human Activity Recognition with MLLM-based Visual Reinforcement Learning 提出基于MLLM和视觉强化学习的FAVOR，用于小样本视觉人体活动识别 reinforcement learning large language model multimodal
13 KDPE: A Kernel Density Estimation Strategy for Diffusion Policy Trajectory Selection 提出KDPE以解决扩散策略轨迹选择中的多模态问题 behavior cloning diffusion policy multimodal ✅
14 TLE-Based A2C Agent for Terrestrial Coverage Orbital Path Planning 提出基于TLE的A2C算法，解决LEO卫星地面覆盖轨道规划问题。 reinforcement learning PPO

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

#题目一句话要点标签🔗⭐
15 CorrectNav: Self-Correction Flywheel Empowers Vision-Language-Action Navigation Model 提出CorrectNav，利用自校正飞轮机制提升视觉-语言-动作导航模型性能 vision-language-action VLA instruction following
16 A Multimodal Neural Network for Recognizing Subjective Self-Disclosure Towards Social Robots 提出一种多模态神经网络，用于识别社交机器人交互中的主观自我暴露。 multimodal
17 A Semantic-Aware Framework for Safe and Intent-Integrative Assistance in Upper-Limb Exoskeletons 提出一种语义感知框架，用于上肢外骨骼的安全和意图集成辅助 large language model

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

#题目一句话要点标签🔗⭐
18 CVIRO: A Consistent and Tightly-Coupled Visual-Inertial-Ranging Odometry on Lie Groups 提出基于李群的一致性视觉-惯性-测距里程计CVIRO，解决UWB辅助VIO中的不一致性问题。 VIO

⬅️ 返回 cs.RO 首页 · 🏠 返回主页