cs.RO（2025-09-01）

📊 共 17 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (9) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱三：空间感知与语义 (Perception & Semantics) (2 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2)

🔬 支柱一：机器人控制 (Robot Control) (9 篇)

#题目一句话要点标签🔗⭐
1 MoTo: A Zero-shot Plug-in Interaction-aware Navigation for General Mobile Manipulation MoTo：一种零样本即插即用的交互感知导航方法，用于通用移动操作 manipulation mobile manipulation trajectory optimization
2 Non-conflicting Energy Minimization in Reinforcement Learning based Robot Control 提出一种无超参数的策略梯度投影方法，用于强化学习机器人节能控制 quadruped humanoid locomotion
3 ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training ManiFlow：基于一致性流训练的通用机器人操作策略 humanoid humanoid robot manipulation
4 Articulated Object Estimation in the Wild ArtiPoint：提出一种在动态环境中估计铰接物体运动的新框架。 manipulation mobile manipulation motion planning
5 Disentangled Multi-Context Meta-Learning: Unlocking robust and Generalized Task Learning 提出解耦多上下文元学习框架，提升任务泛化性和鲁棒性 quadruped locomotion sim-to-real
6 Fail2Progress: Learning from Real-World Robot Failures with Stein Variational Inference Fail2Progress：利用Stein变分推断从真实机器人失败中学习，提升长时程操作技能 manipulation mobile manipulation
7 Model Predictive Control for a Soft Robotic Finger with Stochastic Behavior based on Fokker-Planck Equation 提出基于Fokker-Planck方程的模型预测控制以解决软机器人不确定性问题 MPC model predictive control
8 Hierarchical Reactive Grasping via Task-Space Velocity Fields and Joint-Space Quadratic Programming 提出层次化反应抓取框架以解决高自由度系统的实时规划问题 motion planning
9 TARA: A Low-Cost 3D-Printed Robotic Arm for Accessible Robotics Education 提出TARA以解决高成本机器人教育问题 manipulation

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
10 Constrained Decoding for Robotics Foundation Models SafeDec：针对机器人Foundation Model的约束解码框架，保障动作安全性 foundation model multimodal
11 Metamorphic Testing of Multimodal Human Trajectory Prediction 提出一种基于变质测试的多模态人类轨迹预测模型评估框架，解决缺乏测试预言的问题。 multimodal
12 Plantbot: Integrating Plant and Robot through LLM Modular Agent Networks Plantbot：通过LLM模块化代理网络集成植物与机器人，实现自主环境响应。 large language model multimodal
13 TopoNav: Topological Graphs as a Key Enabler for Advanced Object Navigation TopoNav：利用拓扑图增强ObjectNav任务中的长期记忆与推理能力 large language model

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

#题目一句话要点标签🔗⭐
14 OpenMulti: Open-Vocabulary Instance-Level Multi-Agent Distributed Implicit Mapping OpenMulti：开放词汇的多智能体分布式隐式实例级地图构建 open-vocabulary open vocabulary ✅
15 FGO-SLAM: Enhancing Gaussian SLAM with Globally Consistent Opacity Radiance Field FGO-SLAM：利用全局一致的不透明度辐射场增强高斯SLAM的几何重建性能 visual SLAM scene reconstruction embodied AI

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

#题目一句话要点标签🔗⭐
16 A Hybrid Input based Deep Reinforcement Learning for Lane Change Decision-Making of Autonomous Vehicle 提出一种混合输入深度强化学习算法，用于提升自动驾驶车辆的变道决策安全性。 reinforcement learning deep reinforcement learning DRL
17 Data Retrieval with Importance Weights for Few-Shot Imitation Learning 提出重要性加权检索(IWR)方法，提升小样本模仿学习的数据检索质量。 imitation learning

⬅️ 返回 cs.RO 首页 · 🏠 返回主页