cs.RO（2025-05-06）

📊 共 24 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (12 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱三：空间感知与语义 (Perception & Semantics) (3) 支柱七：动作重定向 (Motion Retargeting) (2 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (12 篇)

#题目一句话要点标签🔗⭐
1 Meta-Optimization and Program Search using Language Models for Task and Motion Planning 提出基于元优化和程序搜索的语言模型方法，用于任务与运动规划。 manipulation trajectory optimization motion planning
2 GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data GraspVLA：基于十亿级合成动作数据预训练的抓取基础模型 sim-to-real domain randomization flow matching
3 AMO: Adaptive Motion Optimization for Hyper-Dexterous Humanoid Whole-Body Control 提出自适应运动优化（AMO）框架，用于超灵巧人形机器人全身控制。 humanoid humanoid robot whole-body control
4 Visual Imitation Enables Contextual Humanoid Control VIDEOMIMIC：通过视觉模仿实现人型机器人的环境感知控制 humanoid humanoid robot humanoid control
5 OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation 提出OpenHelix：一个开源双系统VLA模型，用于机器人操作的实证分析与优化。 manipulation vision-language-action VLA ✅
6 The Unreasonable Effectiveness of Discrete-Time Gaussian Process Mixtures for Robot Policy Learning 提出MiDiGap，一种基于离散时间高斯过程混合模型的机器人策略学习方法 manipulation policy learning imitation learning
7 Learn to Swim: Data-Driven LSTM Hydrodynamic Model for Quadruped Robot Gait Optimization 提出基于数据驱动LSTM的水动力学模型，用于水下四足机器人步态优化 quadruped legged robot locomotion
8 NMPC-Lander: Nonlinear MPC with Barrier Function for UAV Landing on a Mobile Platform 提出NMPC-Lander，结合NMPC与CBF，实现无人机在移动平台上的精准安全着陆 MPC model predictive control
9 Self-Supervised Learning for Robotic Leaf Manipulation: A Hybrid Geometric-Neural Approach 提出一种混合几何-神经自监督学习方法，用于农业机器人叶片操作。 manipulation depth estimation
10 Automated Action Generation based on Action Field for Robotic Garment Manipulation 提出基于动作场的机器人服装操作方法，提升精度并降低计算时间 manipulation
11 Latent Adaptive Planner for Dynamic Manipulation 提出隐空间自适应规划器LAP，解决动态操作中的实时适应性问题 manipulation
12 Enabling Robots to Autonomously Search Dynamic Cluttered Post-Disaster Environments 提出一种集成控制框架，用于灾后动态环境中搜索救援机器人的自主导航。 motion planning motion tracking

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

#题目一句话要点标签🔗⭐
13 RobotxR1: Enabling Embodied Robotic Intelligence on Large Language Models through Closed-Loop Reinforcement Learning 提出RobotxR1，通过闭环强化学习赋能小型LLM实现具身机器人智能 reinforcement learning distillation embodied AI
14 Robust Understanding of Human-Robot Social Interactions through Multimodal Distillation 提出基于多模态知识蒸馏的社交机器人交互理解框架，提升鲁棒性和效率。 distillation multimodal
15 Effective Reinforcement Learning Control using Conservative Soft Actor-Critic 提出保守软演员-评论家(CSAC)算法，提升强化学习控制的稳定性和效率。 reinforcement learning PPO SAC
16 Close-Fitting Dressing Assistance Based on State Estimation of Feet and Garments with Semantic-based Visual Attention 提出基于语义视觉注意的足部和衣物状态估计方法，辅助机器人完成贴身衣物穿戴 diffusion policy spatial relationship

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
17 LogisticsVLN: Vision-Language Navigation For Low-Altitude Terminal Delivery Based on Agentic UAVs 提出LogisticsVLN，基于智能无人机实现低空终端配送的视觉-语言导航 VLN large language model foundation model
18 Automated Data Curation Using GPS & NLP to Generate Instruction-Action Pairs for Autonomous Vehicle Vision-Language Navigation Datasets 提出基于GPS和NLP的自动数据标注方法，用于生成自动驾驶视觉-语言导航数据集 vision-language-action VLA VLN
19 Task Reconstruction and Extrapolation for $π_0$ using Text Latent 提出基于文本隐变量插值的任务重构与外推方法，提升VLA在组合任务中的泛化能力。 vision-language-action VLA

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
20 SynSHRP2: A Synthetic Multimodal Benchmark for Driving Safety-critical Events Derived from Real-world Driving Data SynSHRP2：基于真实驾驶数据合成多模态数据集，用于驾驶安全事件研究。 scene understanding multimodal
21 AquaticVision: Benchmarking Visual SLAM in Underwater Environment with Events and Frames AquaticVision：发布水下事件相机与帧数据视觉SLAM基准数据集 visual SLAM
22 Thermal-LiDAR Fusion for Robust Tunnel Localization in GNSS-Denied and Low-Visibility Conditions 提出热成像-激光雷达融合方法，解决隧道等GNSS拒止和低能见度环境下的鲁棒定位问题 visual odometry

🔬 支柱七：动作重定向 (Motion Retargeting) (2 篇)

#题目一句话要点标签🔗⭐
23 RoboOS: A Hierarchical Embodied Framework for Cross-Embodiment and Multi-Agent Collaboration 提出RoboOS：一个用于跨具身和多智能体协作的分层具身框架 cross-embodiment spatiotemporal VLA ✅
24 PyRoki: A Modular Toolkit for Robot Kinematic Optimization PyRoki：用于机器人运动学优化的模块化、跨平台工具包 motion retargeting

⬅️ 返回 cs.RO 首页 · 🏠 返回主页