cs.RO（2025-02-04）

📊 共 18 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (8 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (2)

🔬 支柱一：机器人控制 (Robot Control) (8 篇)

#题目一句话要点标签🔗⭐
1 VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching VLA-Cache：通过自适应Token缓存加速视觉-语言-动作操作 manipulation vision-language-action VLA
2 MuST: Multi-Head Skill Transformer for Long-Horizon Dexterous Manipulation with Skill Progress 提出MuST：用于长时程灵巧操作的多头技能Transformer manipulation dexterous manipulation
3 Rapidly Adapting Policies to the Real World via Simulation-Guided Fine-Tuning 提出Simulation-Guided Fine-tuning框架，加速机器人策略从仿真到现实的迁移。 manipulation dexterous manipulation sim-to-real ✅
4 From Human Hands to Robotic Limbs: A Study in Motor Skill Embodiment for Telemanipulation 提出基于GRU-VAE的遥操作系统，实现人手姿态到冗余机械臂运动的映射 manipulation teleoperation
5 Generalizable and Fast Surrogates: Model Predictive Control of Articulated Soft Robots using Physics-Informed Neural Networks 提出基于物理信息神经网络的快速通用软体机器人模型预测控制方法 MPC model predictive control
6 DHP: Discrete Hierarchical Planning for Hierarchical Reinforcement Learning Agents DHP：面向分层强化学习智能体的离散分层规划方法 humanoid reinforcement learning
7 Human-Aided Trajectory Planning for Automated Vehicles through Teleoperation and Arbitration Graphs 提出基于仲裁图的人工辅助轨迹规划方法，扩展自动驾驶车辆运行设计域。 teleoperation
8 Differentiable Composite Neural Signed Distance Fields for Robot Navigation in Dynamic Indoor Environments 提出可微组合神经SDF，用于动态室内环境机器人导航 trajectory optimization

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
9 Deep Reinforcement Learning Enabled Persistent Surveillance with Energy-Aware UAV-UGV Systems for Disaster Management Applications 提出基于深度强化学习的UAV-UGV协同能源感知持久监视方案，用于灾害管理。 reinforcement learning deep reinforcement learning DRL
10 MAGNNET: Multi-Agent Graph Neural Network-based Efficient Task Allocation for Autonomous Vehicles with Deep Reinforcement Learning 提出基于多智能体图神经网络的MAGNNET，解决异构无人系统高效任务分配问题 reinforcement learning deep reinforcement learning PPO
11 RAPID: Robust and Agile Planner Using Inverse Reinforcement Learning for Vision-Based Drone Navigation RAPID：基于逆强化学习的稳健敏捷视觉无人机导航规划器 reinforcement learning behavior cloning inverse reinforcement learning
12 Real-Time Operator Takeover for Visuomotor Diffusion Policy Training 提出实时操作员接管方法，用于视觉运动扩散策略训练。 diffusion policy

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

#题目一句话要点标签🔗⭐
13 Composite Gaussian Processes Flows for Learning Discontinuous Multimodal Policies 提出CGP-Flows，用于学习具有不连续性的多模态机器人控制策略。 multimodal
14 PatchPilot: A Cost-Efficient Software Engineering Agent with Early Attempts on Formal Verification PatchPilot：一种兼顾成本、效率和稳定性的软件工程智能补丁代理 large language model ✅
15 AdaptBot: Combining LLM with Knowledge Graphs and Human Input for Generic-to-Specific Task Decomposition and Knowledge Refinement AdaptBot：结合LLM、知识图谱与人工反馈，实现任务分解与知识精炼 large language model ✅
16 Anticipate & Act : Integrating LLMs and Classical Planning for Efficient Task Execution in Household Environments 结合LLM与经典规划，提升家用机器人任务执行效率 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🔗⭐
17 Online Adaptive Traversability Estimation through Interaction for Unstructured, Densely Vegetated Environments 提出一种在线自适应地形可通行性估计方法，用于密集植被环境下的机器人导航。 traversability
18 SiLVR: Scalable Lidar-Visual Radiance Field Reconstruction with Uncertainty Quantification SiLVR：基于激光雷达-视觉融合与不确定性量化的大规模辐射场重建 NeRF neural radiance field

⬅️ 返回 cs.RO 首页 · 🏠 返回主页