cs.RO（2025-11-14）

📊 共 16 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (13) 支柱二：RL算法与架构 (RL & Architecture) (3)

🔬 支柱一：机器人控制 (Robot Control) (13 篇)

#题目一句话要点标签🔗⭐
1 Experiences from Benchmarking Vision-Language-Action Models for Robotic Manipulation 对机器人操作的视觉-语言-动作模型进行基准测试与经验分析。 manipulation vision-language-action VLA
2 Humanoid Whole-Body Badminton via Multi-Stage Reinforcement Learning 提出基于多阶段强化学习的人形机器人羽毛球全身体控制方法 humanoid humanoid robot whole-body control
3 Large Language Models and 3D Vision for Intelligent Robotic Perception and Autonomy 融合LLM与3D视觉，提升机器人感知与自主性 manipulation scene understanding large language model
4 Dexterous Manipulation Transfer via Progressive Kinematic-Dynamic Alignment 提出一种渐进式运动学-动力学对齐方法，实现灵巧操作的迁移学习。 manipulation dexterous hand dexterous manipulation
5 Collaborative Multi-Robot Non-Prehensile Manipulation via Flow-Matching Co-Generation 提出基于流匹配协同生成的多机器人非抓取操作框架，解决复杂环境下的多目标重定位问题 manipulation motion planning flow matching
6 Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective 提出Embodied-SlotSSM，解决机器人操作中长时记忆和对象跟踪难题。 manipulation vision-language-action VLA
7 Scalable Policy Evaluation with Video World Models 提出基于视频世界模型的策略评估方法，提升机器人策略评估的可扩展性。 manipulation sim-to-real world model
8 AdaptPNP: Integrating Prehensile and Non-Prehensile Skills for Adaptive Robotic Manipulation AdaptPNP：融合抓取与非抓取技能的自适应机器人操作框架 manipulation motion planning task and motion planning
9 Efficient Image-Goal Navigation with Representative Latent World Model 提出ReL-NWM，利用代表性隐空间世界模型高效实现图像目标导航 humanoid humanoid robot Unitree
10 Sashimi-Bot: Autonomous Tri-manual Advanced Manipulation and Cutting of Deformable Objects Sashimi-Bot：面向柔性物体的自主三臂机器人高级操作与切割系统 manipulation reinforcement learning deep reinforcement learning
11 Scalable Coverage Trajectory Synthesis on GPUs as Statistical Inference 提出基于GPU加速的覆盖轨迹合成方法，解决传统方法计算效率瓶颈。 motion planning flow matching
12 Volumetric Ergodic Control 提出基于体积状态表示的遍历控制方法，提升机器人空间覆盖效率 manipulation
13 WetExplorer: Automating Wetland Greenhouse-Gas Surveys with an Autonomous Mobile Robot WetExplorer：一种用于湿地温室气体自动调查的自主移动机器人 locomotion motion planning localization

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
14 MATT-Diff: Multimodal Active Target Tracking by Diffusion Policy 提出MATT-Diff，通过扩散策略实现多模态主动多目标跟踪。 behavior cloning diffusion policy egocentric
15 Collaborative Representation Learning for Alignment of Tactile, Language, and Vision Modalities 提出TLV-CoRe，用于触觉、语言和视觉模态对齐的协同表征学习 representation learning multimodal
16 VISTAv2: World Imagination for Indoor Vision-and-Language Navigation VISTAv2：用于室内视觉-语言导航的生成式世界模型 world model egocentric VLN

⬅️ 返回 cs.RO 首页 · 🏠 返回主页