cs.RO（2025-09-10）

📊 共 17 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (9 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (4 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱一：机器人控制 (Robot Control) (9 篇)

#题目一句话要点标签🔗⭐
1 RoboMatch: A Unified Mobile-Manipulation Teleoperation Platform with Auto-Matching Network Architecture for Long-Horizon Tasks RoboMatch：面向长时程任务的统一移动操作遥操作平台与自匹配网络架构 manipulation mobile manipulation dual-arm
2 Calib3R: A 3D Foundation Model for Multi-Camera to Robot Calibration and 3D Metric-Scaled Scene Reconstruction Calib3R：基于3D基础模型的多相机-机器人联合标定与尺度重建 manipulation scene reconstruction foundation model
3 A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulator 综述：CARLA模拟器中基于强化学习的自动驾驶研究 sim-to-real reinforcement learning deep reinforcement learning
4 PegasusFlow: Parallel Rolling-Denoising Score Sampling for Robot Diffusion Planner Flow Matching PegasusFlow：用于机器人扩散规划器流匹配的并行滚动去噪分数采样 locomotion trajectory optimization motion planning ✅
5 Input-gated Bilateral Teleoperation: An Easy-to-implement Force Feedback Teleoperation Method for Low-cost Hardware 提出一种易于实现的力反馈遥操作方法，适用于低成本硬件 manipulation teleoperation imitation learning
6 Joint Model-based Model-free Diffusion for Planning with Constraints 提出JM2D框架，通过联合扩散模型实现带约束的机器人运动规划。 manipulation motion planning offline RL ✅
7 Grasp Like Humans: Learning Generalizable Multi-Fingered Grasping from Human Proprioceptive Sensorimotor Integration 提出基于触觉-运动感知融合的模仿学习框架，实现机器人通用多指灵巧抓取 manipulation dexterous manipulation imitation learning
8 CLAP: Clustering to Localize Across n Possibilities, A Simple, Robust Geometric Approach in the Presence of Symmetries CLAP：一种基于聚类的鲁棒几何定位方法，解决对称环境下的定位问题 humanoid
9 Dual-Stage Safe Herding Framework for Adversarial Attacker in Dynamic Environment 提出双阶段安全引导框架，解决动态环境中防御机器人引导对抗智能体问题 motion planning

🔬 支柱三：空间感知与语义 (Perception & Semantics) (4 篇)

#题目一句话要点标签🔗⭐
10 SocialNav-SUB: Benchmarking VLMs for Scene Understanding in Social Robot Navigation 提出SocialNav-SUB基准，评估VLM在社交机器人导航场景理解中的能力 scene understanding spatiotemporal foundation model ✅
11 Deep Visual Odometry for Stereo Event Cameras 提出Stereo-DEVO，一种用于立体事件相机的深度视觉里程计，提升了在HDR环境下的位姿估计精度。 visual odometry depth estimation optical flow
12 TANGO: Traversability-Aware Navigation with Local Metric Control for Topological Goals TANGO：基于可通行性感知和局部度量控制的拓扑目标导航 monocular depth traversability ✅
13 Good Deep Features to Track: Self-Supervised Feature Extraction and Tracking in Visual Odometry 提出自监督特征提取与跟踪方法，提升视觉里程计在复杂环境下的鲁棒性。 visual odometry

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
14 RoboChemist: Long-Horizon and Safety-Compliant Robotic Chemical Experimentation RoboChemist：面向长期任务和安全合规的机器人化学实验框架 vision-language-action VLA VoxPoser
15 Foundation Models for Autonomous Driving Perception: A Survey Through Core Capabilities 综述：自动驾驶感知中的基础模型及其核心能力 foundation model

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

#题目一句话要点标签🔗⭐
16 Symmetry-Guided Multi-Agent Inverse Reinforcement Learning 提出对称引导的多智能体逆强化学习以提升样本效率 reinforcement learning inverse reinforcement learning
17 Sample-Efficient Online Control Policy Learning with Real-Time Recursive Model Updates 提出递归Koopman学习(RKL)，实现高样本效率的在线控制策略学习。 policy learning

⬅️ 返回 cs.RO 首页 · 🏠 返回主页