cs.RO（2025-02-27）

📊 共 19 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱一：机器人控制 (Robot Control) (12 🔗5) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱三：空间感知与语义 (Perception & Semantics) (2)

🔬 支柱一：机器人控制 (Robot Control) (12 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids	提出一种基于视觉的仿人机器人灵巧操作Sim-to-Real强化学习方法	humanoid humanoid robot manipulation
2	Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success	提出优化微调策略以提升视觉-语言-动作模型性能	bi-manual imitation learning diffusion policy	✅
3	Physics-Driven Data Generation for Contact-Rich Manipulation via Trajectory Optimization	提出基于物理的数据生成流程，用于接触丰富的机器人操作任务	manipulation bi-manual trajectory optimization	✅
4	HiFAR: Multi-Stage Curriculum Learning for High-Dynamics Humanoid Fall Recovery	HiFAR：多阶段课程学习用于高动态人形机器人跌倒恢复	humanoid humanoid robot fall recovery
5	Risk-aware Integrated Task and Motion Planning for Versatile Snake Robots under Localization Failures	提出BLISS以解决蛇形机器人定位失败问题	motion planning task and motion planning TAMP
6	Point Policy: Unifying Observations and Actions with Key Points for Robot Manipulation	Point Policy：利用关键点统一观测与动作，实现机器人操作策略学习	manipulation teleoperation policy learning	✅
7	Multi-Keypoint Affordance Representation for Functional Dexterous Grasping	提出基于多关键点可供性的灵巧抓取方法，提升视觉感知与操作的连接。	manipulation affordance	✅
8	AoECR: AI-ization of Elderly Care Robot	AoECR：面向养老护理机器人的通用AI架构，提升自主交互能力	manipulation large language model
9	Sensor-Invariant Tactile Representation	提出传感器不变触觉表征(SITR)，实现光学触觉传感器间的零样本迁移	manipulation zero-shot transfer
10	Tracailer: An Efficient Trajectory Planner for Tractor-Trailer Robots in Unstructured Environments	Tracailer：面向非结构化环境的拖拉机-拖车机器人高效轨迹规划器	trajectory optimization motion planning	✅
11	FuseGrasp: Radar-Camera Fusion for Robotic Grasping of Transparent Objects	FuseGrasp：利用雷达-相机融合技术实现透明物体机器人抓取	manipulation
12	Collaborative Object Handover in a Robot Crafting Assistant	提出基于人类协作数据的机器人协作物体递交模型，提升人机协作效率	teleoperation

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

#	题目	一句话要点	标签	🔗	⭐
13	Accelerating Model-Based Reinforcement Learning with State-Space World Models	利用状态空间世界模型加速基于模型的强化学习，提升四旋翼飞行器控制效率。	reinforcement learning world model model-based RL
14	Close-Proximity Satellite Operations through Deep Reinforcement Learning and Terrestrial Testing Environments	提出基于深度强化学习的近距离卫星自主操作方法，并进行地面环境测试。	reinforcement learning deep reinforcement learning DRL
15	Deep Reinforcement Learning based Autonomous Decision-Making for Cooperative UAVs: A Search and Rescue Real World Application	提出基于深度强化学习的无人机协同自主决策框架，用于GNSS拒止环境下的搜索与救援。	reinforcement learning deep reinforcement learning DRL
16	CarPlanner: Consistent Auto-regressive Trajectory Planning for Large-scale Reinforcement Learning in Autonomous Driving	CarPlanner：基于一致性自回归强化学习的大规模自动驾驶轨迹规划	reinforcement learning policy learning
17	ColorDynamic: Generalizable, Scalable, Real-time, End-to-end Local Planner for Unstructured and Dynamic Environments	ColorDynamic：面向非结构化动态环境的通用、可扩展、实时端到端局部规划器	reinforcement learning deep reinforcement learning DRL

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

#	题目	一句话要点	标签	🔗	⭐
18	ATLAS Navigator: Active Task-driven LAnguage-embedded Gaussian Splatting	提出ATLAS Navigator，用于在未知环境中实现基于语言指令的主动任务驱动导航	gaussian splatting splatting semantic map
19	BEV-DWPVO: BEV-based Differentiable Weighted Procrustes for Low Scale-drift Monocular Visual Odometry on Ground	提出基于BEV和可微加权Procrustes的单目视觉里程计，降低地面车辆的尺度漂移。	visual odometry

⬅️ 返回 cs.RO 首页 · 🏠 返回主页