cs.RO（2025-11-24）

📊 共 22 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (15 🔗1) 支柱三：空间感知 (Perception & SLAM) (6) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱一：机器人控制 (Robot Control) (15 篇)

#题目一句话要点标签🔗⭐
1 Whole-Body Inverse Dynamics MPC for Legged Loco-Manipulation 提出基于全身逆动力学MPC的腿式机器人Loco-manipulation方法，实现运动与力规划的统一优化。 quadruped whole-body motion locomotion
2 AutoOdom: Learning Auto-regressive Proprioceptive Odometry for Legged Locomotion AutoOdom：用于足式机器人运动的自回归本体系里程计学习方法 legged robot legged locomotion humanoid
3 Reference-Free Sampling-Based Model Predictive Control 提出一种无参考采样模型预测控制框架，实现四足和人形机器人的涌现式运动控制。 quadruped quadrupedal humanoid
4 SENTINEL: A Fully End-to-End Language-Action Model for Humanoid Whole Body Control SENTINEL：用于人形机器人全身控制的端到端语言-动作模型 humanoid humanoid robot humanoid control
5 Head Stabilization for Wheeled Bipedal Robots via Force-Estimation-Based Admittance Control 提出基于力估计的导纳控制，用于轮式双足机器人头部稳定 bipedal bipedal robot biped
6 Accelerating Reinforcement Learning via Error-Related Human Brain Signals 通过脑电信号加速复杂机器人操作中的强化学习 locomotion manipulation reinforcement learning
7 Compressor-VLA: Instruction-Guided Visual Token Compression for Efficient Robotic Manipulation 提出Compressor-VLA，通过指令引导的视觉Token压缩提升机器人操作效率。 manipulation dual-arm sim-to-real
8 Development of a Testbed for Autonomous Vehicles: Integrating MPC Control with Monocular Camera Lane Detection 提出基于单目视觉车道线检测与MPC控制的自动驾驶车辆测试平台 MPC model predictive control
9 Asynchronous Distributed Multi-Robot Motion Planning Under Imperfect Communication 提出延迟感知ADMM算法，解决非完美通信下多机器人异步分布式运动规划问题 trajectory optimization motion planning
10 Rethinking Intermediate Representation for VLM-based Robot Manipulation 提出基于VLM的机器人操作语义组装表示SEAM，提升泛化性和可理解性。 manipulation
11 Reconfigurable Auxetic Devices (RADs) for Robotic Surface Manipulation 提出可重构负泊松比设备(RADs)用于机器人表面操作，实现可变形界面 manipulation
12 Online Learning-Enhanced Lie Algebraic MPC for Robust Trajectory Tracking of Autonomous Surface Vehicles 提出基于李群误差状态MPC与在线学习的自主水面艇鲁棒轨迹跟踪方法 MPC
13 Discover, Learn, and Reinforce: Scaling Vision-Language-Action Pretraining with Diverse RL-Generated Trajectories 提出DLR框架，通过强化学习生成多样化轨迹，提升VLA模型预训练效果。 manipulation teleoperation reinforcement learning
14 SpeedAug: Policy Acceleration via Tempo-Enriched Policy and RL Fine-Tuning SpeedAug：通过速度增强策略和强化学习微调加速机器人策略学习 manipulation reinforcement learning policy learning
15 Mixture of Horizons in Action Chunking 提出混合视野动作分块（MoH）策略，提升机器人操作中VLA模型的性能和泛化性。 manipulation ✅

🔬 支柱三：空间感知 (Perception & SLAM) (6 篇)

#题目一句话要点标签🔗⭐
16 SP-VINS: A Hybrid Stereo Visual Inertial Navigation System based on Implicit Environmental Map 提出基于隐式环境地图的立体视觉惯性导航系统SP-VINS，提升长时高精度定位性能。 SLAM visual-inertial localization
17 Multi-Agent Monocular Dense SLAM With 3D Reconstruction Priors 提出基于3D重建先验的多智能体单目稠密SLAM系统，提升计算效率。 SLAM localization
18 An Efficient Closed-Form Solution to Full Visual-Inertial State Initialization 提出一种高效的视觉惯性状态初始化闭式解法，无需非线性优化。 visual-inertial
19 CNN-Based Camera Pose Estimation and Localisation of Scan Images for Aircraft Visual Inspection 提出基于CNN的飞机视觉检测相机位姿估计与定位方法，无需额外基础设施。 pose estimation
20 Stable Multi-Drone GNSS Tracking System for Marine Robots 提出一种基于多无人机GNSS的稳定水面机器人跟踪系统 SLAM localization navigation
21 Analysis of Deep-Learning Methods in an ISO/TS 15066-Compliant Human-Robot Safety Framework 提出基于深度学习的人机安全框架，动态调整机器人速度以优化协作效率。 pose estimation

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

#题目一句话要点标签🔗⭐
22 A Virtual Mechanical Interaction Layer Enables Resilient Human-to-Robot Object Handovers 提出基于虚拟机械交互层的机器人控制方法，提升人机物体递送的鲁棒性 human-to-robot human to robot

⬅️ 返回 cs.RO 首页 · 🏠 返回主页