cs.RO（2025-01-28）

📊 共 12 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (9) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (9 篇)

#题目一句话要点标签🔗⭐
1 Benchmarking Model Predictive Control and Reinforcement Learning Based Control for Legged Robot Locomotion in MuJoCo Simulation 对比MPC与RL在MuJoCo中四足机器人步态控制性能，分析其优劣势。 quadruped legged robot locomotion
2 Improving Vision-Language-Action Model with Online Reinforcement Learning 提出iRe-VLA框架，通过在线强化学习提升视觉-语言-动作模型在机器人控制中的性能。 manipulation reinforcement learning vision-language-action
3 Mobile Manipulation Instruction Generation from Multiple Images with Automatic Metric Enhancement 提出一种基于多图和自动指标增强的移动操作指令生成方法 manipulation mobile manipulation large language model
4 Surena-V: A Humanoid Robot for Human-Robot Collaboration with Optimization-based Control Architecture Surena-V：基于优化控制架构的人形机器人，用于人机协作 humanoid humanoid robot
5 Strawberry Robotic Operation Interface: An Open-Source Device for Collecting Dexterous Manipulation Data in Robotic Strawberry Farming 提出草莓机器人操作界面SROI，用于收集草莓采摘灵巧操作数据 manipulation dexterous manipulation
6 Joint Decision-Making in Robot Teleoperation: When are Two Heads Better Than One? 提出基于置信度共享的机器人遥操作协同决策方法，提升复杂任务性能 teleoperation spatiotemporal
7 DIRIGENt: End-To-End Robotic Imitation of Human Demonstrations Based on a Diffusion Model DIRIGENt：基于扩散模型的端到端机器人模仿学习，实现从人类演示到机器人动作的直接生成。 humanoid humanoid robot manipulation
8 RLPP: A Residual Method for Zero-Shot Real-World Autonomous Racing on Scaled Platforms 提出RLPP残差强化学习框架，用于零样本真实环境小型赛车自主驾驶 sim-to-real reinforcement learning
9 Safety-Critical Control for Aerial Physical Interaction in Uncertain Environment 提出基于扰动观测器的安全关键控制，用于不确定环境中无人机物理交互 manipulation

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

#题目一句话要点标签🔗⭐
10 Dream to Drive with Predictive Individual World Model 提出基于预测个体世界模型的MBRL方法，用于复杂城市环境下的自主驾驶 reinforcement learning world model representation learning
11 Optimizing Efficiency of Mixed Traffic through Reinforcement Learning: A Topology-Independent Approach and Benchmark 提出一种拓扑无关的强化学习混合交通控制策略，并发布真实场景基准。 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🔗⭐
12 SSF-PAN: Semantic Scene Flow-Based Perception for Autonomous Navigation in Traffic Scenarios 提出SSF-PAN，利用语义场景流实现交通场景下自主导航 scene flow

⬅️ 返回 cs.RO 首页 · 🏠 返回主页