cs.RO（2024-10-08）

📊 共 21 篇论文

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (14) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱九：具身大模型 (Embodied Foundation Models) (2)

🔬 支柱一：机器人控制 (Robot Control) (14 篇)

#题目一句话要点标签🔗⭐
1 OrionNav: Online Planning for Robot Autonomy with Context-Aware LLM and Open-Vocabulary Semantic Scene Graphs OrionNav：利用上下文感知LLM和开放词汇语义场景图实现机器人自主在线规划 quadruped scene understanding open-vocabulary
2 Effort Allocation for Deadline-Aware Task and Motion Planning: A Metareasoning Approach 针对截止时间约束的任务与运动规划，提出基于元推理的计算资源分配方法 motion planning reinforcement learning task and motion planning
3 BUMBLE: Unifying Reasoning and Acting with Vision-Language Models for Building-wide Mobile Manipulation BUMBLE：利用视觉-语言模型统一推理与行动，实现楼宇级移动操作 manipulation mobile manipulation foundation model
4 SplaTraj: Camera Trajectory Generation with Semantic Gaussian Splatting SplaTraj：基于语义高斯溅射的相机轨迹生成方法 trajectory optimization gaussian splatting splatting
5 Learning the Generalizable Manipulation Skills on Soft-body Tasks via Guided Self-attention Behavior Cloning Policy 提出GP2E策略，通过引导自注意力行为克隆学习软体操作的通用技能 manipulation behavior cloning embodied AI
6 Whole-Body Dynamic Throwing with Legged Manipulators 提出基于深度强化学习的全身动态投掷方法，提升腿式机器人的投掷性能 quadruped legged robot humanoid
7 Meta-Learning Augmented MPC for Disturbance-Aware Motion Planning and Control of Quadrotors 提出基于元学习增强MPC的四旋翼扰动感知运动规划与控制框架 MPC motion planning
8 A Robust Quadruped Robot with Twisting Waist for Flexible Motions 提出一种带扭腰关节的鲁棒四足机器人Solo9，提升运动灵活性 quadruped locomotion imitation learning
9 Learning to Drift in Extreme Turning with Active Exploration and Gaussian Process Based MPC 提出基于高斯过程回归MPC漂移控制器，通过主动探索提升极限转弯控制精度。 MPC model predictive control
10 GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation GR-2：基于Web规模知识的生成式视频-语言-动作模型，用于机器人操作 manipulation policy learning
11 Construction of Musculoskeletal Simulation for Shoulder Complex with Ligaments and Its Validation via Model Predictive Control 构建含韧带肩关节复合体肌肉骨骼仿真，并通过模型预测控制进行验证 model predictive control
12 A General Formulation for Path Constrained Time-Optimized Trajectory Planning with Environmental and Object Contacts 提出一种通用路径约束的时间优化轨迹规划方法，适用于环境和物体接触场景。 manipulation trajectory optimization
13 Learning Force Distribution Estimation for the GelSight Mini Optical Tactile Sensor Based on Finite Element Analysis 提出基于有限元分析训练的U-Net模型，用于GelSight Mini触觉传感器力分布估计 manipulation
14 Single Actuator Undulation Soft-bodied Robots Using A Precompressed Variable Thickness Flexible Beam 提出基于预压缩变厚度柔性梁的单驱动软体蠕动机器人方案 locomotion

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
15 Solving Multi-Goal Robotic Tasks with Decision Transformer 提出基于决策Transformer的离线多目标机器人强化学习方法 reinforcement learning offline reinforcement learning decision transformer
16 A GPT-based Decision Transformer for Multi-Vehicle Coordination at Unsignalized Intersections 提出基于GPT的决策Transformer，用于无信号交叉口多车辆协同 decision transformer
17 Demonstration Based Explainable AI for Learning from Demonstration Methods 提出基于演示的可解释AI，提升模仿学习中新手教师的教学效率和机器人性能 reinforcement learning inverse reinforcement learning

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

#题目一句话要点标签🔗⭐
18 GSLoc: Visual Localization with 3D Gaussian Splatting GSLoc：利用3D高斯溅射实现视觉定位，解决纹理缺失环境下的定位难题。 3D gaussian splatting 3DGS gaussian splatting
19 BoxMap: Efficient Structural Mapping and Navigation 提出BoxMap，一种基于检测-Transformer的结构化地图构建与导航方法 scene understanding

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

#题目一句话要点标签🔗⭐
20 Context-Aware Command Understanding for Tabletop Scenarios 提出一种上下文感知混合算法，用于理解桌面场景中的自然语言指令。 multimodal visual grounding
21 Hibikino-Musashi@Home 2024 Team Description Paper Hibikino-Musashi@Home团队为家庭服务机器人开发数据集生成器和任务规划器 large language model

⬅️ 返回 cs.RO 首页 · 🏠 返回主页