cs.RO（2026-03-26）

📊 共 23 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (10 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱一：机器人控制 (Robot Control) (10 篇)

#题目一句话要点标签🔗⭐
1 $π$, But Make It Fly: Physics-Guided Transfer of VLA Models to Aerial Manipulation AirVLA：通过物理引导迁移VLA模型至空中机器人操作 manipulation teleoperation flow matching
2 LILAC: Language-Conditioned Object-Centric Optical Flow for Open-Loop Trajectory Generation 提出LILAC，通过语言条件光流生成实现开放式轨迹生成，用于机器人操作。 manipulation optical flow vision-language-action
3 MMaDA-VLA: Large Diffusion Vision-Language-Action Model with Unified Multi-Modal Instruction and Generation 提出MMaDA-VLA，一种基于扩散模型的统一多模态指令与生成的大型视觉-语言-动作模型 manipulation world model world models
4 Towards Embodied AI with MuscleMimic: Unlocking full-body musculoskeletal motor learning at scale MuscleMimic：开源肌肉骨骼运动模仿学习框架，加速具身智能研究 humanoid locomotion manipulation ✅
5 SafeGuard ASF: SR Agentic Humanoid Robot System for Autonomous Industrial Safety SafeGuard ASF：用于自主工业安全的具身智能人形机器人系统 humanoid humanoid robot locomotion
6 A Mentalistic Interface for Probing Folk-Psychological Attribution to Non-Humanoid Robots 提出一种心理主义界面，用于研究对非人形机器人的心理归因 humanoid humanoid robot large language model
7 Connectivity-Aware Representations for Constrained Motion Planning via Multi-Scale Contrastive Learning 提出基于多尺度对比学习的连通性感知表示，用于约束运动规划。 manipulation motion planning contrastive learning
8 SoftMimicGen: A Data Generation System for Scalable Robot Learning in Deformable Object Manipulation SoftMimicGen：用于可变形物体操作中可扩展机器人学习的数据生成系统 humanoid manipulation bi-manual
9 Visualizing Impedance Control in Augmented Reality for Teleoperation: Design and User Evaluation 提出基于AR的阻抗控制可视化方法，提升远程操作中力反馈任务的性能 manipulation dual-arm teleoperation
10 A Minimum-Energy Control Approach for Redundant Mobile Manipulators in Physical Human-Robot Interaction Applications 提出一种最小能量控制方法，用于人机协作中的冗余移动机械臂控制 manipulation mobile manipulation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
11 SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models SABER：一种隐蔽的、基于智能体的黑盒攻击框架，用于视觉-语言-动作模型 vision-language-action VLA foundation model
12 Drive My Way: Preference Alignment of Vision-Language-Action Model for Personalized Driving 提出Drive My Way，对齐视觉-语言-动作模型以实现个性化驾驶 vision-language-action VLA ✅
13 ThermoAct:Thermal-Aware Vision-Language-Action Models for Robotic Perception and Decision-Making ThermoAct：提出热感知VLA模型，提升机器人感知决策在人机协作中的安全性和效率。 vision-language-action VLA
14 Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance Fast-dVLA：加速离散扩散VLA模型至实时性能，提升机器人任务泛化能力 VLA ✅
15 Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance Fast-dVLA：加速离散扩散VLA模型至实时性能，降低适应成本。 VLA ✅

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

#题目一句话要点标签🔗⭐
16 Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning 提出基于强化学习的持久机器人世界模型，稳定多步预测 reinforcement learning world model world models
17 COIN: Collaborative Interaction-Aware Multi-Agent Reinforcement Learning for Self-Driving Systems 提出COIN框架，解决多智能体自驾系统中复杂交互下的高效安全协同问题。 reinforcement learning policy learning TD3 ✅
18 Learning Rollout from Sampling:An R1-Style Tokenized Traffic Simulation Model R1Sim：一种基于强化学习和熵引导采样的token化交通仿真模型 reinforcement learning reward design large language model
19 CROSS: A Mixture-of-Experts Reinforcement Learning Framework for Generalizable Large-Scale Traffic Signal Control 提出基于混合专家强化学习的CROSS框架，解决大规模交通信号控制的泛化性问题。 reinforcement learning contrastive learning
20 Integrating Deep RL and Bayesian Inference for ObjectNav in Mobile Robotics 融合深度强化学习与贝叶斯推理，提升移动机器人ObjectNav性能 reinforcement learning deep reinforcement learning

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

#题目一句话要点标签🔗⭐
21 Accurate Surface and Reflectance Modelling from 3D Radar Data with Neural Radiance Fields 提出基于神经辐射场的雷达数据三维重建方法，提升低能见度环境下的表面建模精度。 neural radiance field implicit representation

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
22 UMBRELLA: Uncertainty-aware Multi-robot Reactive Coordination under Dynamic Temporal Logic Tasks UMBRELLA：动态时序逻辑任务下基于不确定性的多机器人反应式协同 motion prediction

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
23 IntentReact: Guiding Reactive Object-Centric Navigation via Topological Intent IntentReact：通过拓扑意图引导的反应式目标物体导航 egocentric

⬅️ 返回 cs.RO 首页 · 🏠 返回主页