cs.RO（2025-03-12）

📊 共 17 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (11 🔗3) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (11 篇)

#题目一句话要点标签🔗⭐
1 Unified Locomotion Transformer with Simultaneous Sim-to-Real Transfer for Quadrupeds 提出统一运动Transformer（ULT），实现四足机器人零样本Sim-to-Real迁移 quadruped locomotion locomotion policy
2 Natural Humanoid Robot Locomotion with Generative Motion Prior 提出基于生成式运动先验的人形机器人自然运动控制方法 humanoid humanoid robot locomotion
3 Vi-LAD: Vision-Language Attention Distillation for Socially-Aware Robot Navigation in Dynamic Environments 提出Vi-LAD，通过视觉-语言注意力蒸馏实现动态环境中具有社会意识的机器人导航。 MPC model predictive control motion planning
4 Rethinking Bimanual Robotic Manipulation: Learning with Decoupled Interaction Framework 提出解耦交互框架，提升双臂机器人操作中协调与非协调任务的学习能力 manipulation bi-manual bimanual manipulation
5 GarmentPile: Point-Level Visual Affordance Guided Retrieval and Adaptation for Cluttered Garments Manipulation 提出基于点级视觉可供性的检索与自适应方法，用于处理杂乱衣物操作。 manipulation affordance ✅
6 HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots HumanoidPano：面向人形机器人的混合球形全景激光雷达跨模态感知框架 humanoid humanoid robot
7 SE(3)-Equivariant Robot Learning and Control: A Tutorial Survey 综述SE(3)等变机器人学习与控制，提升机器人操作的效率和泛化性。 manipulation reinforcement learning imitation learning
8 MarineGym: A High-Performance Reinforcement Learning Platform for Underwater Robotics MarineGym：用于水下机器人的高性能强化学习平台 sim2real reinforcement learning
9 Sequential Multi-Object Grasping with One Dexterous Hand SeqMultiGrasp：提出一种基于扩散模型的四指灵巧手连续抓取多物体系统 dexterous hand ✅
10 TetraGrip: Sensor-Driven Multi-Suction Reactive Object Manipulation in Cluttered Scenes TetraGrip：基于传感器的多吸盘反应式操作，解决复杂场景下的物体抓取问题 manipulation
11 AI-based Framework for Robust Model-Based Connector Mating in Robotic Wire Harness Installation 提出基于AI的连接器自动插拔框架，提升机器人线束安装的鲁棒性与效率 manipulation multimodal ✅

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

#题目一句话要点标签🔗⭐
12 Efficient Alignment of Unconditioned Action Prior for Language-conditioned Pick and Place in Clutter 提出A$^2$方法，通过对齐动作先验提升语言条件下的杂乱场景抓取放置性能 foundation model language conditioned ✅
13 NVP-HRI: Zero Shot Natural Voice and Posture-based Human-Robot Interaction via Large Language Model 提出NVP-HRI，利用LLM实现零样本自然语音和姿态的人机交互 large language model multimodal ✅
14 ManeuverGPT Agentic Control for Safe Autonomous Stunt Maneuvers 提出ManeuverGPT，利用LLM Agent实现安全自主的特技机动控制 large language model

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

#题目一句话要点标签🔗⭐
15 Feasibility-aware Imitation Learning from Observations through a Hand-mounted Demonstration Interface 提出FABCO，通过手持示教界面实现可行性感知的观测模仿学习。 policy learning imitation learning behavior cloning
16 Multi-Agent LLM Actor-Critic Framework for Social Robot Navigation 提出SAMALM：一种用于社交机器人导航的多智能体LLM Actor-Critic框架 reinforcement learning deep reinforcement learning large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
17 MonoSLAM: Robust Monocular SLAM with Global Structure Optimization 提出融合点、线、消失点的单目SLAM，提升低纹理环境下的鲁棒性 visual SLAM

⬅️ 返回 cs.RO 首页 · 🏠 返回主页