cs.RO（2024-09-18）

📊 共 30 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (17 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗2) 支柱三：空间感知与语义 (Perception & Semantics) (4 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱四：生成式动作 (Generative Motion) (1 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (17 篇)

#题目一句话要点标签🔗⭐
1 Bootstrapping Object-level Planning with Large Language Models 利用大型语言模型引导物体级别规划，提升任务与运动规划性能 motion planning large language model task and motion planning
2 Representing Positional Information in Generative World Models for Object Manipulation 提出位置条件和隐变量条件策略学习，提升生成世界模型在物体操作任务中的性能 manipulation policy learning world model
3 LMMCoDrive: Cooperative Driving with Large Multimodal Model 提出LMMCoDrive，利用大模型解决按需出行系统中车辆的协同驾驶问题 motion planning spatial relationship multimodal ✅
4 Real-Time-Feasible Collision-Free Motion Planning For Ellipsoidal Objects 提出基于Minkowski和近似的椭球体实时无碰撞运动规划方法 MPC model predictive control motion planning
5 GauTOAO: Gaussian-based Task-Oriented Affordance of Objects GauTOAO：提出基于高斯模型的面向任务的物体可供性预测框架，提升机器人操作能力 manipulation dexterous hand affordance
6 Haptic-ACT: Bridging Human Intuition with Compliant Robotic Manipulation via Immersive VR 提出Haptic-ACT，通过VR遥操作和Transformer实现柔顺机器人操作 manipulation teleoperation imitation learning
7 LEMMo-Plan: LLM-Enhanced Learning from Multi-Modal Demonstration for Planning Sequential Contact-Rich Manipulation Tasks LEMMo-Plan：利用多模态示教增强LLM，规划序列化接触式操作任务 manipulation large language model
8 XP-MARL: Auxiliary Prioritization in Multi-Agent Reinforcement Learning to Address Non-Stationarity XP-MARL：通过辅助优先级排序解决多智能体强化学习中的非平稳性问题 motion planning reinforcement learning
9 A Learning-based Controller for Multi-Contact Grasps on Unknown Objects with a Dexterous Hand 提出一种基于学习的多接触抓取控制器，用于灵巧手抓取未知物体 dexterous hand
10 C-Uniform Trajectory Sampling For Fast Motion Planning 提出C-Uniform轨迹采样，加速机器人运动规划，提升MPPI控制性能。 motion planning
11 Multi-robot connective collaboration toward collective obstacle field traversal 提出一种多机器人连接协作策略，解决崎岖地形下的集体移动问题 legged robot locomotion traversability
12 Robots that Learn to Safely Influence via Prediction-Informed Reach-Avoid Dynamic Games 提出基于预测信息的Reach-Avoid动态博弈方法，实现机器人安全影响人类 manipulation reinforcement learning
13 Generalized Robot Learning Framework 提出一种低成本、可复现的通用机器人学习框架，适用于工业级机器人。 manipulation imitation learning
14 Reactive Collision Avoidance for Safe Agile Navigation 提出基于融合感知、规划与控制的反应式避障框架，实现安全敏捷导航 model predictive control
15 Human-Robot Cooperative Piano Playing with Learning-Based Real-Time Music Accompaniment 提出基于学习的实时音乐伴奏系统，实现人机协同钢琴演奏 MPC
16 RoboMorph: In-Context Meta-Learning for Robot Dynamics Modeling RoboMorph：基于Transformer的机器人动力学建模上下文元学习方法 model predictive control
17 Hook-Based Aerial Payload Grasping from a Moving Platform 提出基于钩爪的空中机械臂运动平台抓取移动目标方法 trajectory optimization

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
18 Improving Soft-Capture Phase Success in Space Debris Removal Missions: Leveraging Deep Reinforcement Learning and Tactile Feedback 利用深度强化学习和触觉反馈提升空间碎片移除任务中的软捕获成功率 reinforcement learning deep reinforcement learning
19 From Words to Wheels: Automated Style-Customized Policy Generation for Autonomous Driving 提出Words2Wheels框架，通过自然语言指令自动生成定制化自动驾驶策略 reinforcement learning inverse reinforcement learning large language model ✅
20 DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control DynaMo：用于视觉运动控制的域内动态预训练方法 imitation learning behavior cloning diffusion policy
21 IMRL: Integrating Visual, Physical, Temporal, and Geometric Representations for Enhanced Food Acquisition 提出IMRL，融合多维表征，提升机器人辅助喂食中食物获取的泛化性与鲁棒性 reinforcement learning imitation learning representation learning ✅
22 Reinforcement Learning with Lie Group Orientations for Robotics 提出基于李群的强化学习方法，提升机器人操作中姿态控制性能 reinforcement learning

🔬 支柱三：空间感知与语义 (Perception & Semantics) (4 篇)

#题目一句话要点标签🔗⭐
23 SpotLight: Robotic Scene Understanding through Interaction and Affordance Detection SpotLight：通过交互和可供性检测实现机器人场景理解，提升家务机器人操作能力 scene understanding affordance affordance detection
24 One Map to Find Them All: Real-time Open-Vocabulary Mapping for Zero-shot Multi-Object Navigation 提出一种基于可复用开放词汇特征地图的零样本多目标导航方法 semantic map open-vocabulary open vocabulary ✅
25 Towards Global Localization using Multi-Modal Object-Instance Re-Identification 提出多模态Transformer架构，用于提升复杂场景下的物体实例重识别与定位。 scene understanding multimodal
26 Discovering Conceptual Knowledge with Analytic Ontology Templates for Articulated Objects 提出基于分析本体模板的AOTNet，用于具身智能体理解和交互新类别可动对象 affordance

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#题目一句话要点标签🔗⭐
27 Fusion in Context: A Multimodal Approach to Affective State Recognition 提出基于Transformer的多模态融合方法，用于上下文感知的状态识别 multimodal
28 Hierarchical LLMs In-the-Loop Optimization for Real-Time Multi-Robot Target Tracking under Unknown Hazards 提出一种层级LLM闭环优化框架，用于未知危险下的实时多机器人目标跟踪。 large language model
29 AlignBot: Aligning VLM-powered Customized Task Planning with User Reminders Through Fine-Tuning for Household Robots AlignBot：通过微调对齐用户提醒，优化VLM驱动的家庭机器人定制任务规划。 multimodal

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
30 Hypergraph-based Motion Generation with Multi-modal Interaction Relational Reasoning 提出基于超图交互关系推理的运动生成网络RHINO，提升自动驾驶车辆运动预测精度。 motion generation ✅

⬅️ 返回 cs.RO 首页 · 🏠 返回主页