cs.RO（2024-10-03）

📊 共 13 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (11 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (1 🔗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 Learning Diverse Bimanual Dexterous Manipulation Skills from Human Demonstrations BiDexHD：从人类演示中学习多样化的双臂灵巧操作技能 manipulation dexterous manipulation bi-manual
2 E2H: A Two-Stage Non-Invasive Neural Signal Driven Humanoid Robotic Whole-Body Control Framework E2H：提出一种基于非侵入式脑电信号的人形机器人全身控制两阶段框架 humanoid humanoid robot whole-body control
3 Guiding Long-Horizon Task and Motion Planning with Vision Language Models VLM-TAMP：利用视觉语言模型引导长时程任务与运动规划 motion planning task and motion planning TAMP ✅
4 Cross-Embodiment Dexterous Grasping with Reinforcement Learning 提出基于强化学习的跨具身灵巧抓取策略，实现通用机械手控制 dexterous hand teleoperation reinforcement learning
5 Real-World Cooking Robot System from Recipes Based on Food State Recognition Using Foundation Models and PDDL 提出基于基础模型和PDDL的烹饪机器人系统，实现从菜谱到真实世界烹饪行为的转换 dual-arm large language model foundation model
6 Leveraging Event Streams with Deep Reinforcement Learning for End-to-End UAV Tracking 提出基于事件流和深度强化学习的端到端无人机主动目标跟踪方法 domain randomization reinforcement learning deep reinforcement learning
7 Gait Optimization for Legged Systems Through Mixed Distribution Cross-Entropy Optimization 提出CrEGOpt，一种基于混合分布交叉熵优化的腿式机器人步态优化方法 quadruped legged robot biped
8 Custom Non-Linear Model Predictive Control for Obstacle Avoidance in Indoor and Outdoor Environments 提出基于非线性模型预测控制的无人机避障方法，适用于室内外复杂环境。 model predictive control
9 Diffusion Meets Options: Hierarchical Generative Skill Composition for Temporally-Extended Tasks DOPPLER：结合扩散模型与Options的分层生成式技能组合框架，用于时序扩展任务 manipulation reinforcement learning ✅
10 Single-Shot 6DoF Pose and 3D Size Estimation for Robotic Strawberry Harvesting 提出基于深度学习的草莓6DoF位姿与3D尺寸单次估计方法，提升机器人采摘效率 domain randomization
11 Task-agnostic Lifelong Robot Learning with Retrieval-based Weighted Local Adaptation 提出基于检索加权局部自适应的终身机器人学习框架，解决任务无关场景下的灾难性遗忘问题 manipulation

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

#题目一句话要点标签🔗⭐
12 SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environments 提出SPINE以解决不完整自然语言任务规划问题 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🔗⭐
13 Efficient Residual Learning with Mixture-of-Experts for Universal Dexterous Grasping ResDex：结合混合专家模型的残差学习提升通用灵巧抓取效率 reinforcement learning policy learning

⬅️ 返回 cs.RO 首页 · 🏠 返回主页