cs.RO（2025-07-31）

📊 共 19 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (12 🔗2) 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) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱一：机器人控制 (Robot Control) (12 篇)

#	题目	一句话要点	标签	🔗	⭐
1	H-RDT: Human Manipulation Enhanced Bimanual Robotic Manipulation	H-RDT：利用人类操作数据增强双臂机器人操作能力	manipulation bi-manual policy learning
2	BarlowWalk: Self-supervised Representation Learning for Legged Robot Terrain-adaptive Locomotion	提出BarlowWalk以解决双足机器人地形适应性运动控制问题	legged robot bipedal biped
3	Quadratic Programming-Based Posture Manipulation and Thrust-vectoring for Agile Dynamic Walking on Narrow Pathways	提出基于二次规划的姿态控制与推力矢量方法，实现四足机器人窄路敏捷动态行走	quadruped legged robot locomotion
4	CHILD (Controller for Humanoid Imitation and Live Demonstration): a Whole-Body Humanoid Teleoperation System	CHILD：一种全身人形机器人遥操作系统，实现类人模仿与实时演示	humanoid humanoid robot manipulation	✅
5	villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models	villa-X：增强视觉-语言-动作模型中的潜在动作建模，提升机器人操作策略泛化性	manipulation dexterous hand open-vocabulary
6	XRoboToolkit: A Cross-Platform Framework for Robot Teleoperation	提出XRoboToolkit，用于扩展现实的跨平台机器人遥操作框架	manipulation dexterous hand teleoperation
7	Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks	提出MTBench：大规模并行多任务强化学习机器人任务基准测试平台	locomotion manipulation reinforcement learning	✅
8	Human-Exoskeleton Kinematic Calibration to Improve Hand Tracking for Dexterous Teleoperation	提出一种外骨骼手部运动学标定框架，提升灵巧遥操作的手部追踪精度	manipulation teleoperation
9	Quantifying and Visualizing Sim-to-Real Gaps: Physics-Guided Regularization for Reproducibility	提出物理引导增益正则化方法，缩小平衡机器人Sim-to-Real差距。	sim-to-real domain randomization
10	Learning to Drift with Individual Wheel Drive: Maneuvering Autonomous Vehicle at the Handling Limits	提出基于强化学习和领域随机化的漂移控制方法，解决车辆极限工况下的操控问题	domain randomization reinforcement learning
11	Optimization of Flip-Landing Trajectories for Starship based on a Deep Learned Simulator	提出基于深度学习模拟器的星舰翻转着陆轨迹优化框架	trajectory optimization
12	Multi-Waypoint Path Planning and Motion Control for Non-holonomic Mobile Robots in Agricultural Applications	提出基于DTSP和NMPC的农业机器人多航路点路径规划与运动控制方法	model predictive control

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

#	题目	一句话要点	标签	🔗	⭐
13	User Experience Estimation in Human-Robot Interaction Via Multi-Instance Learning of Multimodal Social Signals	提出一种基于多示例学习的多模态社交信号用户体验估计方法，用于人机交互。	multimodal
14	A Unified Perception-Language-Action Framework for Adaptive Autonomous Driving	提出统一的感知-语言-动作框架，提升自动驾驶在复杂环境中的适应性	vision-language-action VLA large language model
15	Can LLM-Reasoning Models Replace Classical Planning? A Benchmark Study	评估LLM在机器人规划中的能力：能否替代经典规划器？	large language model

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

#	题目	一句话要点	标签	🔗	⭐
16	Stereo 3D Gaussian Splatting SLAM for Outdoor Urban Scenes	提出BGS-SLAM，首个用于室外城市场景的立体3D高斯溅射SLAM系统	3D gaussian splatting 3DGS gaussian splatting
17	GSFusion:Globally Optimized LiDAR-Inertial-Visual Mapping for Gaussian Splatting	GSFusion：面向高斯溅射的全局优化激光雷达-惯性-视觉融合建图	3D gaussian splatting 3DGS gaussian splatting

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

#	题目	一句话要点	标签	🔗	⭐
18	Distributed AI Agents for Cognitive Underwater Robot Autonomy	UROSA：用于水下机器人认知自主的分布式AI代理架构	reinforcement learning large language model multimodal
19	Scalable Multi-Task Reinforcement Learning for Generalizable Spatial Intelligence in Visuomotor Agents	提出基于Minecraft环境的可扩展多任务强化学习，提升具身智能体的泛化空间推理能力。	reinforcement learning

⬅️ 返回 cs.RO 首页 · 🏠 返回主页