cs.RO（2025-09-22）

📊 共 29 篇论文 | 🔗 6 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (21 🔗4) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (21 篇)

#题目一句话要点标签🔗⭐
1 RL-augmented Adaptive Model Predictive Control for Bipedal Locomotion over Challenging Terrain 提出基于强化学习增强的自适应模型预测控制，用于双足机器人复杂地形行走 quadruped humanoid bipedal
2 GeCCo -- a Generalist Contact-Conditioned Policy for Loco-Manipulation Skills on Legged Robots GeCCo：一种用于腿式机器人运动操作技能的通用接触条件策略 quadruped legged robot locomotion
3 HuMam: Humanoid Motion Control via End-to-End Deep Reinforcement Learning with Mamba HuMam：利用Mamba的端到端深度强化学习实现人形机器人运动控制 humanoid humanoid locomotion locomotion
4 Tac2Motion: Contact-Aware Reinforcement Learning with Tactile Feedback for Robotic Hand Manipulation 提出Tac2Motion以解决接触感知的机器人手部操作问题 manipulation in-hand manipulation reinforcement learning
5 Latent Action Pretraining Through World Modeling 提出LAWM，通过世界建模进行潜在动作预训练，提升机器人操作任务效率。 manipulation teleoperation imitation learning
6 DyDexHandover: Human-like Bimanual Dynamic Dexterous Handover using RGB-only Perception DyDexHandover：提出一种基于RGB感知的类人双臂动态灵巧物体传递方法 dexterous hand bi-manual dual-arm
7 The Surprising Effectiveness of Linear Models for Whole-Body Model-Predictive Control 线性模型在全身模型预测控制中表现出惊人的有效性 quadruped legged robot humanoid
8 Learning Dexterous Manipulation with Quantized Hand State DQ-RISE：通过量化手部状态学习灵巧操作，解耦臂手控制。 manipulation dexterous manipulation ✅
9 Prepare Before You Act: Learning From Humans to Rearrange Initial States 提出ReSET，通过模仿学习人类预处理环境，提升机器人操作任务的泛化性。 manipulation teleoperation imitation learning
10 Fast Trajectory Planner with a Reinforcement Learning-based Controller for Robotic Manipulators 提出基于强化学习控制器的快速轨迹规划器，用于机器人操作臂在复杂环境中进行实时避障。 sim-to-real motion planning reinforcement learning
11 PEEK: Guiding and Minimal Image Representations for Zero-Shot Generalization of Robot Manipulation Policies PEEK：利用引导式极简图像表征实现机器人操作策略的零样本泛化 manipulation VLA ✅
12 Learning Geometry-Aware Nonprehensile Pushing and Pulling with Dexterous Hands 提出几何感知灵巧手推拉方法GD2P，实现复杂环境下非抓取操作 manipulation dexterous hand
13 AD-VF: LLM-Automatic Differentiation Enables Fine-Tuning-Free Robot Planning from Formal Methods Feedback AD-VF：基于LLM自动微分与形式化反馈的免微调机器人规划 manipulation DPO direct preference optimization
14 Language-in-the-Loop Culvert Inspection on the Erie Canal 提出VISION系统，利用语言引导的视觉模型实现伊利运河涵洞的自主巡检。 quadruped stereo depth open-vocabulary
15 RoboSeek: You Need to Interact with Your Objects RoboSeek：通过交互式探索优化机器人操作，实现长时程任务 manipulation sim2real real2sim ✅
16 MotionTrans: Human VR Data Enable Motion-Level Learning for Robotic Manipulation Policies MotionTrans：利用人类VR数据实现机器人操作策略的运动级学习 manipulation imitation learning ✅
17 3D Printable Soft Liquid Metal Sensors for Delicate Manipulation Tasks 提出基于3D打印软体液态金属传感器的精细操作方法，用于脆弱物品操作 manipulation reinforcement learning
18 Robotic Skill Diversification via Active Mutation of Reward Functions in Reinforcement Learning During a Liquid Pouring Task 提出基于奖励函数主动变异的强化学习方法，用于机器人液体倾倒任务中的技能多样化 manipulation reinforcement learning
19 Haptic Communication in Human-Human and Human-Robot Co-Manipulation 研究人-人与人-机器人协同操作中的触觉通信差异 manipulation
20 Towards Learning Boulder Excavation with Hydraulic Excavators 提出基于强化学习的挖掘机巨石挖掘方法，无需专用夹具。 manipulation reinforcement learning
21 PrioriTouch: Adapting to User Contact Preferences for Whole-Arm Physical Human-Robot Interaction PrioriTouch：通过学习用户接触偏好实现全身物理人机交互 operational space control

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
22 M3ET: Efficient Vision-Language Learning for Robotics based on Multimodal Mamba-Enhanced Transformer 提出M3ET：一种高效的基于多模态Mamba增强Transformer的机器人视觉-语言学习方法 Mamba multimodal
23 DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving DriveDPO：面向端到端自动驾驶的安全DPO策略学习 policy learning imitation learning DPO
24 ComposableNav: Instruction-Following Navigation in Dynamic Environments via Composable Diffusion ComposableNav：通过可组合扩散模型实现动态环境中指令跟随导航 reinforcement learning instruction following
25 Sight Over Site: Perception-Aware Reinforcement Learning for Efficient Robotic Inspection 提出感知驱动的强化学习框架以提高机器人检查效率 reinforcement learning
26 Fine-Tuning Robot Policies While Maintaining User Privacy 提出PRoP框架，在个性化机器人策略微调的同时保护用户隐私 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🔗⭐
27 FGGS-LiDAR: Ultra-Fast, GPU-Accelerated Simulation from General 3DGS Models to LiDAR FGGS-LiDAR：基于通用3DGS模型的超快速GPU加速LiDAR仿真 3D gaussian splatting 3DGS gaussian splatting ✅
28 RadarSFD: Single-Frame Diffusion with Pretrained Priors for Radar Point Clouds RadarSFD：基于单帧雷达点云和预训练先验的扩散模型 monocular depth

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

#题目一句话要点标签🔗⭐
29 V2V-GoT: Vehicle-to-Vehicle Cooperative Autonomous Driving with Multimodal Large Language Models and Graph-of-Thoughts 提出V2V-GoT，利用多模态大语言模型和图推理解决V2V协同自动驾驶中的遮挡问题。 large language model multimodal ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页