cs.RO（2025-11-18）

📊 共 19 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) (5 🔗1) 支柱三：空间感知 (Perception & SLAM) (4)

🔬 支柱一：机器人控制 (Robot Control) (10 篇)

#题目一句话要点标签🔗⭐
1 Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3D Constrained Terrains Gallant：基于体素栅格的人形机器人三维约束地形运动与局部导航 humanoid humanoid locomotion locomotion
2 RoboTidy : A 3D Gaussian Splatting Household Tidying Benchmark for Embodied Navigation and Action RoboTidy：用于具身导航与操作的3D高斯溅射家庭整理基准 manipulation 3D gaussian splatting 3DGS
3 Socially aware navigation for mobile robots: a survey on deep reinforcement learning approaches 综述深度强化学习在社会意识导航中的应用与挑战 sim-to-real reinforcement learning deep reinforcement learning
4 HMC: Learning Heterogeneous Meta-Control for Contact-Rich Loco-Manipulation 提出异构元控制HMC框架，解决接触丰富的移动操作任务 humanoid humanoid robot manipulation
5 Self-Supervised Multisensory Pretraining for Contact-Rich Robot Reinforcement Learning 提出MSDP，用于接触式机器人强化学习的多模态自监督预训练。 manipulation reinforcement learning policy learning
6 Translating Cultural Choreography from Humanoid Forms to Robotic Arm 提出ROPERA框架，实现六自由度机械臂对昆曲文化动作的语义保真复现 humanoid locomotion
7 AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models AsyncVLA：面向视觉-语言-动作模型的异步流匹配，提升长时任务的稳定性和自纠错能力 manipulation flow matching ✅
8 Continuous Vision-Language-Action Co-Learning with Semantic-Physical Alignment for Behavioral Cloning 提出CCoL框架，通过语义-物理对齐的连续视觉-语言-动作协同学习提升行为克隆性能 manipulation bi-manual bimanual
9 FlexiCup: Wireless Multimodal Suction Cup with Dual-Zone Vision-Tactile Sensing FlexiCup：集成双区视觉-触觉传感的无线多模态吸盘，用于非结构化环境下的接触感知操作。 manipulation grasping grasp
10 Towards Deploying VLA without Fine-Tuning: Plug-and-Play Inference-Time VLA Policy Steering via Embodied Evolutionary Diffusion 提出VLA-Pilot，无需微调即可实现VLA模型在机器人操作任务中的即插即用策略引导。 manipulation ✅

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

#题目一句话要点标签🔗⭐
11 MA-SLAM: Active SLAM in Large-Scale Unknown Environment using Map Aware Deep Reinforcement Learning MA-SLAM：基于地图感知的深度强化学习，用于大规模未知环境的主动SLAM reinforcement learning deep reinforcement learning SLAM
12 Reinforcement Learning from Implicit Neural Feedback for Human-Aligned Robot Control 提出基于隐式神经反馈的强化学习方法，用于人机协作机器人控制 reinforcement learning policy learning MuJoCo
13 NORA-1.5: A Vision-Language-Action Model Trained using World Model- and Action-based Preference Rewards NORA-1.5：基于世界模型和动作偏好奖励训练的视觉-语言-动作模型，提升具身智能体的可靠性。 world model flow matching
14 Z-Merge: Multi-Agent Reinforcement Learning for On-Ramp Merging with Zone-Specific V2X Traffic Information Z-Merge：利用区域V2X交通信息的多智能体强化学习匝道汇流 reinforcement learning
15 Masked IRL: LLM-Guided Reward Disambiguation from Demonstrations and Language 提出Masked IRL以解决机器人奖励函数模糊问题 reinforcement learning inverse reinforcement learning ✅

🔬 支柱三：空间感知 (Perception & SLAM) (4 篇)

#题目一句话要点标签🔗⭐
16 Simultaneous Localization and 3D-Semi Dense Mapping for Micro Drones Using Monocular Camera and Inertial Sensors 提出一种轻量级单目视觉惯性SLAM系统，用于微型无人机同时定位与半稠密地图构建。 SLAM pose estimation localization
17 BIM-Discrepancy-Driven Active Sensing for Risk-Aware UAV-UGV Navigation 提出基于BIM差异驱动的主动感知框架，用于风险感知的无人机-无人车协同导航 navigation
18 Going Places: Place Recognition in Artificial and Natural Systems 综述：人工与自然系统中的地点识别研究 localization navigation
19 Robust Verification of Controllers under State Uncertainty via Hamilton-Jacobi Reachability Analysis 提出RoVer-CoRe框架，通过Hamilton-Jacobi可达性分析实现状态不确定性下控制器的鲁棒验证。 navigation

⬅️ 返回 cs.RO 首页 · 🏠 返回主页