cs.RO（2025-04-25）

📊 共 12 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (8 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (8 篇)

#题目一句话要点标签🔗⭐
1 Robust Push Recovery on Bipedal Robots: Leveraging Multi-Domain Hybrid Systems with Reduced-Order Model Predictive Control 提出基于降阶模型预测控制的多域混合系统，实现双足机器人鲁棒抗扰 bipedal biped locomotion
2 Sampling-Based Grasp and Collision Prediction for Assisted Teleoperation 提出一种基于采样的抓取与碰撞预测方法，用于辅助遥操作 bi-manual teleoperation
3 Depth-Constrained ASV Navigation with Deep RL and Limited Sensing 提出深度约束下的ASV导航强化学习框架，解决浅水环境有限感知问题 sim-to-real reinforcement learning metric depth
4 Boxi: Design Decisions in the Context of Algorithmic Performance for Robotics Boxi：针对机器人算法性能优化的多模态传感器融合平台设计 legged robot multimodal ✅
5 Opportunistic Collaborative Planning with Large Vision Model Guided Control and Joint Query-Service Optimization 提出机会主义协同规划，利用大视觉模型引导控制和联合查询-服务优化，提升自动驾驶在开放环境下的导航性能。 MPC model predictive control
6 RL-Driven Data Generation for Robust Vision-Based Dexterous Grasping 提出基于强化学习的数据生成方法，提升灵巧抓取视觉-动作模型的鲁棒性 sim-to-real reinforcement learning
7 Instrumentation for Better Demonstrations: A Case Study 通过传感器集成提升机器人示教学习质量与自动化程度 manipulation
8 AllTact Fin Ray: A Compliant Robot Gripper with Omni-Directional Tactile Sensing AllTact Fin Ray：一种具有全向触觉传感的柔顺机器人夹爪 manipulation

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

#题目一句话要点标签🔗⭐
9 Action Flow Matching for Continual Robot Learning 提出基于Action Flow Matching的持续机器人学习方法，提升动态模型适应性和任务成功率。 flow matching ✅
10 Sky-Drive: A Distributed Multi-Agent Simulation Platform for Human-AI Collaborative and Socially-Aware Future Transportation Sky-Drive：面向人机协作和社交感知的分布式多智能体交通仿真平台 reinforcement learning foundation model ✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)

#题目一句话要点标签🔗⭐
11 M2R2: MultiModal Robotic Representation for Temporal Action Segmentation 提出M2R2多模态机器人表征，用于时序动作分割，提升机器人操作性能。 multimodal

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

#题目一句话要点标签🔗⭐
12 Certifiably-Correct Mapping for Safe Navigation Despite Odometry Drift 提出可验证正确的地图构建框架，解决视觉里程计漂移下的安全导航问题 VIO

⬅️ 返回 cs.RO 首页 · 🏠 返回主页