cs.RO（2024-10-25）

📊 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) (12 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (3 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (3 🔗1)

🔬 支柱一：机器人控制 (Robot Control) (12 篇)

#题目一句话要点标签🔗⭐
1 DA-VIL: Adaptive Dual-Arm Manipulation with Reinforcement Learning and Variable Impedance Control DA-VIL：基于强化学习和变阻抗控制的自适应双臂操作 manipulation dual-arm reinforcement learning
2 On-Robot Reinforcement Learning with Goal-Contrastive Rewards 提出基于目标对比奖励的机器人强化学习方法，提升样本效率。 quadruped manipulation reinforcement learning ✅
3 Learning Diffusion Policies from Demonstrations For Compliant Contact-rich Manipulation 提出DIPCOM框架，通过扩散策略学习柔顺操作，解决接触力控制难题 manipulation diffusion policy multimodal
4 Image-Based Visual Servoing for Enhanced Cooperation of Dual-Arm Manipulation 提出基于图像的视觉伺服方法，增强双臂协作操作的同步性和稳定性 manipulation dual-arm
5 Visual Imitation Learning of Non-Prehensile Manipulation Tasks with Dynamics-Supervised Models 提出动力学监督的视觉模仿学习方法，提升非抓取操作任务的泛化性。 manipulation imitation learning world model
6 MILES: Making Imitation Learning Easy with Self-Supervision MILES：通过自监督简化模仿学习，仅需单次演示即可完成策略学习 manipulation reinforcement learning policy learning
7 Perception, Control and Hardware for In-Hand Slip-Aware Object Manipulation with Parallel Grippers 提出一种基于力觉和滑移感知的灵巧手内操作方法，用于平行爪夹持器 manipulation in-hand manipulation
8 Motion Planning for Robotics: A Review for Sampling-based Planners 综述：基于采样的机器人运动规划算法研究进展与挑战 motion planning
9 Non-rigid Relative Placement through 3D Dense Diffusion 提出基于3D密集扩散的非刚性相对位姿方法，用于机器人操作 manipulation multimodal
10 Equilibrium Adaptation-Based Control for Track Stand of Single-Track Two-Wheeled Robots 提出基于平衡适应的控制方案，解决两轮机器人的原地平衡难题。 MPC model predictive control
11 Soft Finger Grasp Force and Contact State Estimation from Tactile Sensors 提出基于触觉传感器的软手指抓取力与接触状态估计方法，无需物体特定训练。 manipulation
12 Beyond the Cascade: Juggling Vanilla Siteswap Patterns 提出基于序列规划和轨迹约束的机器人抛掷杂耍方法，实现复杂花式抛掷 manipulation

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

#题目一句话要点标签🔗⭐
13 APRICOT: Active Preference Learning and Constraint-Aware Task Planning with LLMs APRICOT：结合LLM、主动偏好学习与约束感知规划，实现个性化家庭机器人任务 preference learning affordance large language model ✅
14 Robotic Learning in your Backyard: A Neural Simulator from Open Source Components SplatGym：开源神经模拟器，利用3D高斯溅射加速机器人强化学习 reinforcement learning 3D gaussian splatting gaussian splatting
15 An Enhanced Hierarchical Planning Framework for Multi-Robot Autonomous Exploration 提出一种增强型分层规划框架，用于多机器人自主探索。 reinforcement learning deep reinforcement learning DRL

🔬 支柱三：空间感知与语义 (Perception & Semantics) (3 篇)

#题目一句话要点标签🔗⭐
16 IPPON: Common Sense Guided Informative Path Planning for Object Goal Navigation IPPON：常识引导的物体目标导航信息路径规划 semantic mapping semantic map large language model
17 A Robust and Efficient Visual-Inertial Initialization with Probabilistic Normal Epipolar Constraint 提出一种基于概率Normal Epipolar约束的鲁棒高效视觉惯性初始化方法，适用于快速运动和退化场景。 VIO ✅
18 Semantics in Robotics: Environmental Data Can't Yield Conventions of Human Behaviour 探讨机器人语义理解困境：环境数据无法直接推导人类行为规范 affordance

⬅️ 返回 cs.RO 首页 · 🏠 返回主页