cs.RO（2025-04-23）

📊 共 15 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

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

🔬 支柱一：机器人控制 (Robot Control) (11 篇)

#题目一句话要点标签🔗⭐
1 Physically Consistent Humanoid Loco-Manipulation using Latent Diffusion Models 利用潜在扩散模型生成引导，实现物理一致的人形机器人操作规划 humanoid manipulation loco-manipulation
2 Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots 提出RWM-U模型，解决离线MBRL在真实机器人上的应用难题 quadruped humanoid locomotion
3 ManipDreamer: Boosting Robotic Manipulation World Model with Action Tree and Visual Guidance ManipDreamer：利用动作树和视觉引导增强机器人操作世界模型 manipulation world model dreamer
4 Zero-shot Sim-to-Real Transfer for Reinforcement Learning-based Visual Servoing of Soft Continuum Arms 提出基于强化学习的软体连续臂视觉伺服零样本迁移方法 sim-to-real motion planning reinforcement learning
5 Latent Diffusion Planning for Imitation Learning 提出Latent Diffusion Planning，利用无动作和次优数据提升模仿学习效果 manipulation imitation learning multimodal
6 MOSAIC: A Skill-Centric Algorithmic Framework for Long-Horizon Manipulation Planning MOSAIC：一种面向技能的长程操作规划算法框架 manipulation motion planning
7 Fast Online Adaptive Neural MPC via Meta-Learning 提出基于元学习的快速在线自适应神经MPC，提升机器人控制性能。 MPC model predictive control
8 PP-Tac: Paper Picking Using Tactile Feedback in Dexterous Robotic Hands PP-Tac：利用触觉反馈的灵巧手进行纸张拾取 dexterous hand motion generation embodied AI ✅
9 Fast and Modular Whole-Body Lagrangian Dynamics of Legged Robots with Changing Morphology 提出一种快速模块化的腿式机器人全身拉格朗日动力学建模方法，适应形态变化。 legged robot
10 DYNUS: Uncertainty-aware Trajectory Planner in Dynamic Unknown Environments DYNUS：面向动态未知环境的不确定性感知轨迹规划器 quadruped
11 Eigendecomposition Parameterization of Penalty Matrices for Enhanced Control Design: Aerospace Applications 提出基于特征分解的惩罚矩阵参数化方法，提升航天控制系统设计性能 model predictive control

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

#题目一句话要点标签🔗⭐
12 Robo-Troj: Attacking LLM-based Task Planners 提出Robo-Troj，针对基于LLM的任务规划器进行多触发后门攻击。 large language model
13 MorphoNavi: Aerial-Ground Robot Navigation with Object Oriented Mapping in Digital Twin MorphoNavi：数字孪生中基于对象识别的空地机器人导航 multimodal

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

#题目一句话要点标签🔗⭐
14 Graph2Nav: 3D Object-Relation Graph Generation to Robot Navigation Graph2Nav：面向机器人导航的三维对象关系图生成框架 semantic mapping semantic map large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#题目一句话要点标签🔗⭐
15 HERB: Human-augmented Efficient Reinforcement learning for Bin-packing HERB：人机协同强化学习解决机器人异形物体装箱难题 reinforcement learning

⬅️ 返回 cs.RO 首页 · 🏠 返回主页