cs.RO（2025-04-06）

📊 共 9 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (5 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱八：物理动画 (Physics-based Animation) (1 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱一：机器人控制 (Robot Control) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Diffusion-Based Approximate MPC: Fast and Consistent Imitation of Multi-Modal Action Distributions	提出基于扩散模型的近似MPC，解决多模态动作分布学习难题，实现快速稳定的机器人控制。	MPC model predictive control imitation learning
2	Tool-as-Interface: Learning Robot Policies from Observing Human Tool Use	提出Tool-as-Interface框架，通过观察人类工具使用视频学习机器人策略。	teleoperation policy learning diffusion policy
3	DexSinGrasp: Learning a Unified Policy for Dexterous Object Singulation and Grasping in Densely Cluttered Environments	DexSinGrasp：学习灵巧手在密集杂乱环境中进行物体分离和抓取的统一策略	manipulation dexterous hand curriculum learning	✅
4	B4P: Simultaneous Grasp and Motion Planning for Object Placement via Parallelized Bidirectional Forests and Path Repair	提出B4P框架，通过并行双向森林和路径修复实现物体放置的同步抓取与运动规划	motion planning
5	DexTOG: Learning Task-Oriented Dexterous Grasp with Language	DexTOG：提出基于语言引导的灵巧手任务导向抓取学习框架	manipulation dexterous hand dexterous manipulation

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

#	题目	一句话要点	标签	🔗	⭐
6	Planning Safety Trajectories with Dual-Phase, Physics-Informed, and Transportation Knowledge-Driven Large Language Models	提出LetsPi框架，融合物理信息与知识驱动LLM，实现安全轨迹规划	scene understanding large language model foundation model

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

#	题目	一句话要点	标签	🔗	⭐
7	eKalibr-Stereo: Continuous-Time Spatiotemporal Calibration for Event-Based Stereo Visual Systems	提出eKalibr-Stereo，用于事件相机双目视觉系统的连续时空标定	spatiotemporal	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
8	Deliberate Planning of 3D Bin Packing on Packing Configuration Trees	提出基于Packing Configuration Tree的3D装箱规划方法，提升工业自动化应用性。	reinforcement learning deep reinforcement learning DRL

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
9	SELC: Self-Supervised Efficient Local Correspondence Learning for Low Quality Images	提出SELC：一种自监督高效局部对应学习方法，用于低质量图像特征匹配。	feature matching spatiotemporal

⬅️ 返回 cs.RO 首页 · 🏠 返回主页