cs.RO（2025-02-17）

📊 共 16 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (10 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱四：生成式动作 (Generative Motion) (1) 支柱八：物理动画 (Physics-based Animation) (1 🔗1) 支柱七：动作重定向 (Motion Retargeting) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱一：机器人控制 (Robot Control) (10 篇)

#题目一句话要点标签🔗⭐
1 Robot Deformable Object Manipulation via NMPC-generated Demonstrations in Deep Reinforcement Learning 提出HGCR-DDPG算法，结合NMPC生成演示数据，提升机器人对可变形物体的操作能力。 manipulation model predictive control reinforcement learning
2 Learning Getting-Up Policies for Real-World Humanoid Robots 提出一种两阶段学习框架，解决人形机器人在复杂地形下的跌倒恢复问题 humanoid humanoid robot humanoid locomotion
3 PrivilegedDreamer: Explicit Imagination of Privileged Information for Rapid Adaptation of Learned Policies PrivilegedDreamer：利用特权信息的显式想象实现策略的快速适应 manipulation sim-to-real domain randomization
4 IMLE Policy: Fast and Sample Efficient Visuomotor Policy Learning via Implicit Maximum Likelihood Estimation 提出IMLE Policy，通过隐式最大似然估计实现快速且高效的视觉运动策略学习。 manipulation policy learning imitation learning ✅
5 FUNCTO: Function-Centric One-Shot Imitation Learning for Tool Manipulation FUNCTO：面向工具操作的函数中心单样本模仿学习 manipulation imitation learning
6 Learning Dexterous Bimanual Catch Skills through Adversarial-Cooperative Heterogeneous-Agent Reinforcement Learning 提出对抗-合作异构智能体强化学习框架，提升灵巧双臂抓取能力 bi-manual reinforcement learning
7 HI-GVF: Shared Control based on Human-Influenced Guiding Vector Fields for Human-multi-robot Cooperation 提出基于人影响导引向量场的共享控制方法，用于人-多机器人协作 teleoperation shared control
8 Towards Fusing Point Cloud and Visual Representations for Imitation Learning 提出FPV-Net，融合点云与视觉表征，提升模仿学习操作任务性能 manipulation imitation learning
9 Soft Robotics for Search and Rescue: Advancements, Challenges, and Future Directions 软体机器人助力搜寻与救援：综述现有技术并展望未来方向 locomotion
10 Improving Grip Stability Using Passive Compliant Microspine Arrays for Soft Robots in Unstructured Terrain 提出被动柔顺微刺阵列，提升软体机器人在非结构化地形中的抓地稳定性 locomotion

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

#题目一句话要点标签🔗⭐
11 Hovering Flight of Soft-Actuated Insect-Scale Micro Aerial Vehicles using Deep Reinforcement Learning 提出基于深度强化学习的软驱动昆虫级微型飞行器悬停控制方案，解决系统延迟和不确定性问题。 reinforcement learning deep reinforcement learning PPO
12 X-IL: Exploring the Design Space of Imitation Learning Policies X-IL：探索模仿学习策略设计空间，发现更优策略配置 imitation learning flow matching Mamba

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
13 Leader and Follower: Interactive Motion Generation under Trajectory Constraints 提出基于Leader-Follower动态的交互式运动生成框架，解决轨迹约束下的运动生成问题 motion generation

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
14 Bandwidth-Adaptive Spatiotemporal Correspondence Identification for Collaborative Perception 提出带宽自适应时空对应识别方法，解决协作感知中通信受限问题 spatiotemporal ✅

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
15 Early Detection of Human Handover Intentions in Human-Robot Collaboration: Comparing EEG, Gaze, and Hand Motion 对比脑电、眼动和手部运动，实现人机协作中人类意图的早期检测 human-to-robot multimodal

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
16 pySLAM: An Open-Source, Modular, and Extensible Framework for SLAM pySLAM：一个开源、模块化和可扩展的SLAM框架，支持多种相机输入。 visual odometry visual SLAM

⬅️ 返回 cs.RO 首页 · 🏠 返回主页