cs.RO（2025-09-04）

📊 共 19 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 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱九：具身大模型 (Embodied Foundation Models) (2)

🔬 支柱一：机器人控制 (Robot Control) (12 篇)

#	题目	一句话要点	标签	🔗	⭐
1	EMMA: Scaling Mobile Manipulation via Egocentric Human Data	EMMA：利用以人为中心的视觉数据扩展移动操作模仿学习	manipulation mobile manipulation teleoperation	✅
2	Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models	提出自适应强化流匹配(ARFM)，提升VLA模型在复杂机器人操作任务中的动作精度。	manipulation reinforcement learning offline RL
3	FPC-VLA: A Vision-Language-Action Framework with a Supervisor for Failure Prediction and Correction	提出FPC-VLA框架，通过监督器进行失败预测与纠正，提升机器人操作的可靠性。	manipulation vision-language-action VLA
4	Solving Robotics Tasks with Prior Demonstration via Exploration-Efficient Deep Reinforcement Learning	提出一种探索高效的深度强化学习框架DRLR，利用先验演示解决机器人任务。	sim2real reinforcement learning deep reinforcement learning
5	Reactive In-Air Clothing Manipulation with Confidence-Aware Dense Correspondence and Visuotactile Affordance	提出基于置信度感知稠密对应和触觉可供性的服装空中操作方法	manipulation dual-arm affordance
6	Surformer v2: A Multimodal Classifier for Surface Understanding from Touch and Vision	Surformer v2：用于触觉与视觉表面理解的多模态分类器	manipulation multimodal
7	DEXOP: A Device for Robotic Transfer of Dexterous Human Manipulation	DEXOP：一种用于机器人灵巧操作迁移的设备	manipulation dexterous manipulation teleoperation
8	Learning Multi-Stage Pick-and-Place with a Legged Mobile Manipulator	提出基于强化学习的多阶段移动操作方法，解决四足机器人复杂操作任务	quadruped manipulation mobile manipulation	✅
9	Object-Reconstruction-Aware Whole-body Control of Mobile Manipulators	提出一种面向移动机械臂的、基于目标重建感知的全身控制方法，提升三维重建效率。	whole-body control
10	Keypoint-based Diffusion for Robotic Motion Planning on the NICOL Robot	提出基于关键点的扩散模型，加速NICOL机器人运动规划。	motion planning
11	Planning from Point Clouds over Continuous Actions for Multi-object Rearrangement	提出SPOT：一种基于点云变换搜索的多物体重排规划方法	manipulation policy learning
12	Lightweight Kinematic and Static Modeling of Cable-Driven Continuum Robots via Actuation-Space Energy Formulation	提出LASEM框架，用于轻量化建模缆索驱动连续体机器人，实现实时运动规划与控制。	motion planning

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

#	题目	一句话要点	标签	🔗	⭐
13	Long-Horizon Visual Imitation Learning via Plan and Code Reflection	提出基于Plan和Code反射的长时程视觉模仿学习框架，解决复杂动作序列的时序和空间关系建模难题。	imitation learning spatial relationship
14	Bootstrapping Reinforcement Learning with Sub-optimal Policies for Autonomous Driving	利用次优策略引导强化学习，提升自动驾驶策略训练效率	reinforcement learning SAC
15	Action Chunking with Transformers for Image-Based Spacecraft Guidance and Control	提出基于Transformer的动作分块方法ACT，用于图像化航天器制导与控制	reinforcement learning imitation learning

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
16	OVGrasp: Open-Vocabulary Grasping Assistance via Multimodal Intent Detection	OVGrasp：通过多模态意图检测实现开放词汇抓取辅助	open-vocabulary open vocabulary egocentric
17	Odometry Calibration and Pose Estimation of a 4WIS4WID Mobile Wall Climbing Robot	针对壁面爬行机器人，提出融合多模态数据的里程计标定与位姿估计方法	visual odometry multimodal

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

#	题目	一句话要点	标签	🔗	⭐
18	INGRID: Intelligent Generative Robotic Design Using Large Language Models	INGRID：利用大型语言模型实现智能生成式机器人设计	embodied AI large language model
19	SRWToolkit: An Open Source Wizard of Oz Toolkit to Create Social Robotic Avatars	SRWToolkit：一个开源的社会机器人化身快速原型设计工具	large language model multimodal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页