cs.RO（2025-12-15）

📊 共 20 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (14 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (14 篇)

#题目一句话要点标签🔗⭐
1 Learning Terrain Aware Bipedal Locomotion via Reduced Dimensional Perceptual Representations 提出一种基于降维感知表示的地形感知双足运动学习方法 bipedal biped locomotion
2 PvP: Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representations 提出PvP框架，利用本体感受特权对比学习提升人形机器人数据效率 humanoid humanoid robot whole-body control
3 OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learning 提出OXE-AugE，通过大规模机器人增强扩展OXE数据集，提升跨具身策略学习能力。 manipulation policy learning cross-embodiment ✅
4 World Models Can Leverage Human Videos for Dexterous Manipulation 提出DexWM，利用人类视频提升灵巧操作世界模型的预测能力 manipulation dexterous manipulation diffusion policy
5 Humanoid Robot Running Through Random Stepping Stones and Jumping Over Obstacles: Step Adaptation Using Spring-Mass Trajectories 提出基于弹簧-质量轨迹的人形机器人步态自适应框架，实现复杂地形运动。 humanoid humanoid robot whole-body control
6 Universal Dexterous Functional Grasping via Demonstration-Editing Reinforcement Learning 提出DemoFunGrasp，通过演示编辑强化学习实现通用灵巧的功能性抓取 manipulation sim-to-real reinforcement learning
7 START: Traversing Sparse Footholds with Terrain Reconstruction START：基于地形重建的稀疏落脚点四足机器人运动 quadruped locomotion height map
8 NL2SpaTiaL: Generating Geometric Spatio-Temporal Logic Specifications from Natural Language for Manipulation Tasks 提出NL2SpaTiaL数据集和翻译验证框架，用于机器人操作任务中的自然语言到时空逻辑转换。 manipulation instruction following
9 Multi-Robot Motion Planning from Vision and Language using Heat-Inspired Diffusion 提出基于热扩散的多机器人视觉语言运动规划框架LCHD motion planning language conditioned
10 Reinforcement Learning based 6-DoF Maneuvers for Microgravity Intravehicular Docking: A Simulation Study with Int-Ball2 in ISS-JEM 提出基于强化学习的6自由度微重力舱内对接方法，用于国际空间站Int-Ball2机器人。 sim-to-real reinforcement learning PPO
11 Fast Policy Learning for 6-DOF Position Control of Underwater Vehicles 提出基于GPU加速强化学习的AUV六自由度位姿控制方法 sim-to-real reinforcement learning policy learning
12 Multi-directional Safe Rectangle Corridor-Based MPC for Nonholonomic Robots Navigation in Cluttered Environment 提出基于多方向安全矩形走廊的MPC方法，解决非完整机器人复杂环境导航问题 MPC model predictive control
13 Iterative Tuning of Nonlinear Model Predictive Control for Robotic Manufacturing Tasks 提出一种基于任务级反馈的非线性模型预测控制迭代调优框架，用于机器人制造任务。 model predictive control
14 RoboTracer: Mastering Spatial Trace with Reasoning in Vision-Language Models for Robotics RoboTracer：利用视觉-语言模型中的推理能力，掌握机器人空间轨迹跟踪 humanoid ✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
15 PrediFlow: A Flow-Based Prediction-Refinement Framework for Real-Time Human Motion Prediction in Human-Robot Collaboration PrediFlow：面向人机协作的实时人体运动预测优化框架 flow matching human motion human motion prediction
16 Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videos 提出基于视觉-物理对齐的空间感知VLA预训练方法，提升机器人策略学习中的3D空间理解能力。 policy learning vision-language-action VLA
17 Tackling Snow-Induced Challenges: Safe Autonomous Lane-Keeping with Robust Reinforcement Learning 提出两种基于鲁棒强化学习的车道保持算法，解决雪地自动驾驶难题 reinforcement learning deep reinforcement learning DRL
18 Control of a Twin Rotor using Twin Delayed Deep Deterministic Policy Gradient (TD3) 提出基于TD3的强化学习框架，用于控制双旋翼飞行器稳定飞行与轨迹跟踪。 reinforcement learning TD3

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

#题目一句话要点标签🔗⭐
19 SLIM-VDB: A Real-Time 3D Probabilistic Semantic Mapping Framework SLIM-VDB：一种用于实时三维概率语义地图构建的轻量级框架 scene understanding semantic mapping semantic map ✅

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

#题目一句话要点标签🔗⭐
20 A Unified Framework for Automated Assembly Sequence and Production Line Planning using Graph-based Optimization 提出PyCAALP框架，通过图优化实现自动化装配序列与生产线规划 spatial relationship ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页