cs.RO（2025-10-07）

📊 共 18 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (15 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (1)

🔬 支柱一：机器人控制 (Robot Control) (15 篇)

#	题目	一句话要点	标签	🔗	⭐
1	VCoT-Grasp: Grasp Foundation Models with Visual Chain-of-Thought Reasoning for Language-driven Grasp Generation	提出VCoT-Grasp，利用视觉链式推理增强语言驱动的抓取生成能力	manipulation foundation model chain-of-thought	✅
2	Learning to Crawl: Latent Model-Based Reinforcement Learning for Soft Robotic Adaptive Locomotion	提出基于潜在模型的强化学习方法，用于软体机器人自适应运动控制。	locomotion reinforcement learning latent dynamics
3	FORGE-Tree: Diffusion-Forcing Tree Search for Long-Horizon Robot Manipulation	提出FORGE-Tree，通过扩散强制树搜索解决长时程机器人操作中的漂移和暴露偏差问题。	manipulation vision-language-action VLA	✅
4	EmbodiedCoder: Parameterized Embodied Mobile Manipulation via Modern Coding Model	EmbodiedCoder：利用代码模型实现参数化的具身移动操作	manipulation mobile manipulation vision-language-action	✅
5	Cross-Embodiment Dexterous Hand Articulation Generation via Morphology-Aware Learning	提出基于形态感知学习的跨体态灵巧手关节生成方法	dexterous hand cross-embodiment	✅
6	Oracle-Guided Masked Contrastive Reinforcement Learning for Visuomotor Policies	提出OMC-RL，通过示教和对比学习提升视觉运动策略学习的效率和泛化性	sim-to-real reinforcement learning policy learning
7	DeLTa: Demonstration and Language-Guided Novel Transparent Object Manipulation	DeLTa：基于单次演示和语言引导的新型透明物体操作框架	manipulation depth estimation 6D pose estimation
8	DYMO-Hair: Generalizable Volumetric Dynamics Modeling for Robot Hair Manipulation	DYMO-Hair：提出一种可泛化的头发动力学建模方法，用于机器人头发操作	manipulation zero-shot transfer	✅
9	ARRC: Advanced Reasoning Robot Control - Knowledge-Driven Autonomous Manipulation Using Retrieval-Augmented Generation	ARRC：基于检索增强生成实现知识驱动的自主机器人操作	manipulation large language model
10	Towards Autonomous Tape Handling for Robotic Wound Redressing	提出力反馈模仿学习与轨迹优化方法，实现机器人自主完成伤口换药中的胶带处理任务。	manipulation trajectory optimization teleoperation
11	Vi-TacMan: Articulated Object Manipulation via Vision and Touch	Vi-TacMan：结合视觉与触觉的铰接物体操作框架	manipulation
12	Correlation-Aware Dual-View Pose and Velocity Estimation for Dynamic Robotic Manipulation	提出一种去中心化的双视角姿态与速度估计方法以解决动态机器人操作问题	manipulation
13	Constrained Natural Language Action Planning for Resilient Embodied Systems	提出约束自然语言动作规划方法，提升具身智能系统的可靠性与可重复性。	quadruped large language model
14	The DISTANT Design for Remote Transmission and Steering Systems for Planetary Robotics	DISTANT：行星机器人远程传动与转向系统设计，提升极端环境适应性	locomotion
15	Stable Robot Motions on Manifolds: Learning Lyapunov-Constrained Neural Manifold ODEs	提出基于神经常微分方程的稳定机器人运动学习框架	motion planning

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

#	题目	一句话要点	标签	🔗	⭐
16	Avi: Action from Volumetric Inference	Avi：通过体素推理实现机器人动作生成，解决传统方法泛化性不足的问题。	policy learning scene understanding vision-language-action	✅
17	What You Don't Know Can Hurt You: How Well do Latent Safety Filters Understand Partially Observable Safety Constraints?	针对部分可观测安全约束，提出基于互信息的潜在安全滤波器评估与改进方法	world model multimodal

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

#	题目	一句话要点	标签	🔗	⭐
18	Verifier-free Test-Time Sampling for Vision Language Action Models	提出MG-Select，一种免验证器的VLA测试时采样方法，提升机器人控制精度。	vision-language-action VLA

⬅️ 返回 cs.RO 首页 · 🏠 返回主页