cs.RO（2026-03-25）

📊 共 15 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (11 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱九：具身大模型 (Embodied Foundation Models) (1 🔗1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱一：机器人控制 (Robot Control) (11 篇)

#题目一句话要点标签🔗⭐
1 3D-Mix for VLA: A Plug-and-Play Module for Integrating VGGT-based 3D Information into Vision-Language-Action Models 提出3D-Mix模块，提升VLA模型在机器人控制任务中的3D空间感知能力 manipulation VGGT vision-language-action
2 QuadFM: Foundational Text-Driven Quadruped Motion Dataset for Generation and Control QuadFM：用于生成与控制的文本驱动四足机器人运动数据集 quadruped locomotion text-to-motion ✅
3 SafeFlow: Real-Time Text-Driven Humanoid Whole-Body Control via Physics-Guided Rectified Flow and Selective Safety Gating SafeFlow：通过物理引导的Rectified Flow和选择性安全门控实现实时文本驱动的人形机器人全身控制 humanoid whole-body control Unitree
4 PCHC: Enabling Preference Conditioned Humanoid Control via Multi-Objective Reinforcement Learning 提出基于多目标强化学习的偏好条件人形机器人控制框架 humanoid humanoid robot humanoid control
5 Knowledge-Guided Manipulation Using Multi-Task Reinforcement Learning 提出KG-M3PO框架，利用知识图谱增强多任务机器人操作的泛化性和鲁棒性 manipulation reinforcement learning open-vocabulary
6 MIRROR: Visual Motion Imitation via Real-time Retargeting and Teleoperation with Parallel Differential Inverse Kinematics 提出基于GPU并行和连续化的微分逆运动学方法，用于实时人形机器人遥操作。 humanoid humanoid robot teleoperation
7 Chameleon: Episodic Memory for Long-Horizon Robotic Manipulation Chameleon：利用情景记忆增强长时程机器人操作的可靠性与控制能力 manipulation multimodal
8 Accelerated Spline-Based Time-Optimal Motion Planning with Continuous Safety Guarantees for Non-Differentially Flat Systems 提出解耦式样条运动规划方法，加速非微分平坦系统的时间最优安全轨迹生成。 motion planning
9 Event-Driven Proactive Assistive Manipulation with Grounded Vision-Language Planning 提出基于事件驱动的具身视觉-语言规划框架，实现协作操作中的主动辅助 manipulation
10 A Sensorless, Inherently Compliant Anthropomorphic Musculoskeletal Hand Driven by Electrohydraulic Actuators 提出一种基于电液驱动和Peano-HASEL肌肉骨骼手，实现无传感器、本征柔顺的人形操作 manipulation contact-aware
11 Toward Generalist Neural Motion Planners for Robotic Manipulators: Challenges and Opportunities 综述：面向机器人操作的通用神经运动规划器，分析挑战与机遇 manipulation motion planning ✅

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

#题目一句话要点标签🔗⭐
12 LATS: Large Language Model Assisted Teacher-Student Framework for Multi-Agent Reinforcement Learning in Traffic Signal Control 提出LATS框架，利用LLM辅助MARL解决交通信号控制中的泛化性问题 reinforcement learning representation learning teacher-student
13 Decentralized End-to-End Multi-AAV Pursuit Using Predictive Spatio-Temporal Observation via Deep Reinforcement Learning 提出基于预测时空观测的去中心化端到端多智能体强化学习追逐框架 reinforcement learning deep reinforcement learning egocentric

🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)

#题目一句话要点标签🔗⭐
14 SOMA: Strategic Orchestration and Memory-Augmented System for Vision-Language-Action Model Robustness via In-Context Adaptation SOMA：通过上下文适应增强视觉-语言-动作模型鲁棒性的策略编排与记忆增强系统 vision-language-action VLA large language model ✅

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
15 Environment-Grounded Multi-Agent Workflow for Autonomous Penetration Testing 提出环境感知的多智能体工作流，用于自主渗透测试机器人系统 penetration large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页