cs.RO（2025-08-07）

📊 共 17 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (13 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (2 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (2)

🔬 支柱一：机器人控制 (Robot Control) (13 篇)

#题目一句话要点标签🔗⭐
1 Information-Theoretic Graph Fusion with Vision-Language-Action Model for Policy Reasoning and Dual Robotic Control 提出GF-VLA框架，通过信息论图融合视觉-语言-动作模型，实现双臂机器人策略推理与控制。 bi-manual dual-arm vision-language-action
2 Examining the legibility of humanoid robot arm movements in a pointing task 研究人机交互中人形机器人手臂动作的可读性，提升意图预测准确性 humanoid humanoid robot multimodal
3 Learning to See and Act: Task-Aware Virtual View Exploration for Robotic Manipulation 提出任务感知虚拟视角探索框架TVVE，提升机器人操作任务中的3D感知和泛化能力。 manipulation representation learning vision-language-action ✅
4 Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation Genie Envisioner：用于机器人操作的统一世界基础平台 manipulation policy learning flow matching
5 Mixed-Initiative Dialog for Human-Robot Collaborative Manipulation 提出MICoBot，通过混合主动对话实现人机协作操作，提升任务成功率和用户体验。 manipulation affordance
6 Real-Time Iteration Scheme for Diffusion Policy 提出基于实时迭代的扩散策略加速方案，提升机器人操作任务的实时性。 manipulation diffusion policy distillation ✅
7 FCBV-Net: Category-Level Robotic Garment Smoothing via Feature-Conditioned Bimanual Value Prediction FCBV-Net：基于特征条件双臂价值预测的类别级机器人服装平整 manipulation bi-manual
8 CleanUpBench: Embodied Sweeping and Grasping Benchmark 提出CleanUpBench，用于评估扫地和抓取双模式移动清洁机器人的具身智能 humanoid manipulation embodied AI
9 From Canada to Japan: How 10,000 km Affect User Perception in Robot Teleoperation 研究长距离遥操作对用户感知的影响，探索其在老年人护理中的潜力 teleoperation
10 Benchmarking Shortcutting Techniques for Multi-Robot-Arm Motion Planning 多臂机器人运动规划中优化技巧的基准测试与策略融合 motion planning ✅
11 Do Robots Really Need Anthropomorphic Hands? 探讨机器人是否必须具备拟人手：手部复杂性与操作技能的权衡研究 manipulation
12 Computational Design and Fabrication of Modular Robots with Untethered Control 提出基于LCE肌肉的模块化机器人设计与计算优化框架，实现无束缚控制 locomotion
13 MAG-Nav: Language-Driven Object Navigation Leveraging Memory-Reserved Active Grounding MAG-Nav：利用记忆保留主动 grounding 实现语言驱动的物体导航 quadruped

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

#题目一句话要点标签🔗⭐
14 Integrating Vision Foundation Models with Reinforcement Learning for Enhanced Object Interaction 融合视觉基础模型与强化学习，提升AI2-THOR环境中对象交互能力 reinforcement learning PPO foundation model
15 DistillDrive: End-to-End Multi-Mode Autonomous Driving Distillation by Isomorphic Hetero-Source Planning Model DistillDrive：基于同构异源规划模型的端到端多模态自动驾驶知识蒸馏 reinforcement learning distillation ✅

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

#题目一句话要点标签🔗⭐
16 Towards Embodied Agentic AI: Review and Classification of LLM- and VLM-Driven Robot Autonomy and Interaction 综述LLM/VLM驱动的机器人自主与交互，提出Agentic AI分类体系 vision-language-action VLA large language model
17 GhostShell: Streaming LLM Function Calls for Concurrent Embodied Programming GhostShell：用于并发具身编程的流式LLM函数调用方法 large language model multimodal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页